A risk early warning method, device and medium based on grain depot big data

Abstract

The application discloses a risk early warning method and device based on granary big data and a medium, and belongs to the technical field of grain storage management and data analysis. The method comprises the following steps: connecting a grain planting base database to obtain external data and internal data of a granary; cleaning and arranging the external data and the internal data of the granary based on an association relationship to generate a monitoring data set; processing the monitoring data based on a preset risk prediction model library to generate an early warning report and send the early warning report to relevant personnel; wherein the model database comprises a transportation monitoring model, a grain condition monitoring model, a grain price monitoring model and a facility operation monitoring model; and comparing the early warning report with a preset risk disposal process to generate a risk decision. The application realizes the effect of improving the efficiency and safety of grain storage management through the above method.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of grain storage management and data analysis, and in particular to a risk early warning method based on grain depot big data, a device and a medium. BACKGROUND

[0002] With the rapid development of the grain storage industry, the scale of grain storage is increasing, and higher requirements are put forward for the efficiency, safety and transparency of grain storage management. However, the traditional manual supervision method has gradually shown its limitations and is difficult to cope with the increasingly complex grain management needs. At present, although some grain depots have introduced risk early warning systems based on data analysis, these systems generally have problems such as insufficient data integration, single early warning model and non-intuitive risk display.

[0003] The data integration in the existing system is mostly limited to the simple aggregation of internal data of the grain depot, and cannot realize the deep integration of multi-source data such as external market data and planting data, which limits the accuracy and comprehensiveness of risk early warning. In addition, the early warning model is mostly based on simple statistical analysis methods, lacking deep mining and intelligent analysis of complex data relationships, making it difficult to effectively identify potential risk hazards. At the same time, the risk display method is mostly in the form of text or table, lacking intuitive and vivid visualization means, making it difficult for management personnel to quickly and accurately grasp the running state and potential risks of the grain depot.

[0004] Therefore, how to improve the efficiency and safety of grain storage management has become a technical problem to be solved. SUMMARY

[0005] The embodiments of the present application provide a risk early warning method based on grain depot big data, a device and a medium, to solve the technical problem of how to improve the efficiency and safety of grain storage management.

[0006] In a first aspect, the embodiments of the present application provide a risk early warning method based on grain depot big data, which comprises: connecting a grain field planting base database to obtain external data and obtain internal data of the grain depot; wherein the internal data of the grain depot at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and storage facility operation data, and the external data at least includes one of the following: market grain price, planting cost, planting area, planting type and network information related to grain; cleaning and arranging the external data and the internal data of the grain depot based on the association relationship to generate a monitoring data set; processing the monitoring data based on a preset risk prediction model library to generate an early warning report and send it to relevant personnel; wherein the model database includes a transportation monitoring model, a grain condition monitoring model, a grain price monitoring model and a facility operation monitoring model; comparing the early warning report with a preset risk disposal process to generate a risk decision.

[0007] In an implementation form of the present application, the external data and the internal data of the grain depot are cleaned and arranged based on the association relationship to generate a monitoring data set, specifically comprising: processing the external data and the internal data of the grain depot based on a preset data cleaning algorithm to remove repeated, invalid and abnormal data in the external data and the internal data of the grain depot to generate first monitoring data; annotating the external data and the internal data of the grain depot based on data categories to generate second monitoring data; processing the second monitoring data based on time relationship and process relationship to generate monitoring data.

[0008] In an implementation form of the present application, the monitoring data is processed based on a preset risk prediction model library to generate an early warning report and send it to relevant personnel, specifically comprising: processing the grain type, inventory, warehouse record, planting area, planting type based on the transportation monitoring model, comparing the change of the planting area and the planting type with the inventory to generate a transportation early warning report; processing the temperature, humidity, mold, insect pests and network information related to grain based on the grain condition monitoring model, and generating a grain condition early warning report through the change of temperature and humidity and the generation of mold and insect pests; processing the planting cost, network information related to grain and market grain price based on the grain price monitoring model to generate a grain price early warning report; processing the temperature, humidity and storage facility operation data based on the facility operation monitoring model, and generating a facility operation early warning report through the change of temperature, humidity and storage facility operation data; integrating the transportation early warning report, the grain price early warning report and the facility operation early warning report to generate an early warning report and send it to relevant personnel.

[0009] In an implementation form of the present application, the transportation monitoring model is used to process the grain type, inventory, warehouse record, planting area and planting type, and the change of the planting area and the planting type is compared with the inventory to generate a transportation early warning report, specifically comprising: determining the planting type, planting area and freight vehicle of the grain field planting base; determining the unit yield based on the planting type, and generating the grain yield based on the unit yield and the planting area; obtaining the driving record of the freight vehicle; wherein the driving record includes the driving path and the weighbridge detection data; determining the storage warehouse based on the grain type and the freight vehicle, and obtaining the change of the inventory of the storage warehouse; comparing the grain yield, the weighbridge monitoring data and the change of the inventory, and generating a transportation early warning report when the error between the grain yield, the weighbridge monitoring data and the change of the inventory exceeds a preset error threshold.

[0010] In an implementation form of the present application, the temperature, humidity, mildew, insect damage and network information related to grain are processed based on the grain condition monitoring model, and the grain condition early warning report is generated through the change of temperature and humidity and the generation of mildew and insect damage. Specifically, the temperature and humidity in the grain depot are acquired in real time, and compared with the preset safe range. When the temperature and humidity exceed the safe range, the grain condition early warning report is generated. The mildew historical data and insect damage historical data are acquired, and the correlation between the mildew historical data, the insect damage historical data and the temperature change and the humidity change is constructed to generate a disease analysis model. When the temperature and humidity change conforms to the disease analysis model, the grain condition early warning report is generated. The data related to diseases and insect pests and weather in the network information related to grain are monitored, and the data related to diseases and insect pests and weather are processed according to the grain condition monitoring model to generate the grain condition early warning report.

[0011] In an implementation form of the present application, the planting cost, network information related to grain and market grain price are processed based on the grain price monitoring model to generate a grain price early warning report. Specifically, the historical planting cost data and historical market grain price data are collected, and the grain price monitoring model is established according to the historical planting cost data and the historical market grain price data. The change of the planting cost is monitored in real time. The planting cost includes seeds, fertilizers, pesticides and transportation. The grain supply and demand data and policy adjustment data in the network information related to grain are acquired. The grain supply and demand data and the policy adjustment data are processed based on the grain price monitoring model to generate a predicted price. When the predicted price fluctuates beyond a preset grain price threshold, the grain price early warning report is generated based on the comparison between the predicted price and the market grain price.

[0012] In an implementation form of the present application, the temperature, humidity and warehouse facility operation data are processed based on the facility operation monitoring model, and the facility operation early warning report is generated through the change of temperature and humidity and the change of warehouse facility operation data. Specifically, the warehouse facility operation data is monitored in real time to generate real-time data. The warehouse facility operation data includes a cooling system, a ventilation system and a dehumidification system. The real-time data is compared with a preset operation early warning range. When the real-time data exceeds the operation early warning range, the facility operation early warning report is generated. The correlation between the temperature, humidity and warehouse facility operation data is analyzed to generate an abnormal operation mode model. The baseline of the operation efficiency and energy consumption of the warehouse facility is set, and the real-time data is compared with the baseline to generate an energy efficiency deviation. When the energy efficiency deviation is greater than a preset energy efficiency threshold, the facility operation early warning report is generated.

[0013] In an implementation form of the present application, the method further comprises: constructing a visualization platform and associating the monitoring data; and displaying the monitoring data and the early warning report related to the monitoring data based on the visualization platform.

[0014] In a second aspect, the embodiments of the present application also provide a risk early warning device based on granary big data, which comprises at least one processor, and a memory in communication connection with 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 to enable the at least one processor to: connect a grain field planting base database to obtain external data and obtain internal data of the granary; wherein the internal data of the granary at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and warehouse facility operation data, and the external data at least includes one of the following: market grain price, planting cost, planting area, planting type, and network information related to grain; clean and arrange the external data and the internal data of the granary based on an association relationship to generate a monitoring data set; process the monitoring data based on a preset risk prediction model library to generate an early warning report and send the early warning report to relevant personnel; wherein the model database includes a transportation monitoring model, a grain condition monitoring model, a grain price monitoring model, and a facility operation monitoring model; compare the early warning report with a preset risk disposal process to generate a risk decision.

[0015] In a third aspect, the embodiments of the present application also provide a nonvolatile computer storage medium for risk early warning based on granary big data, which stores computer executable instructions, and the computer executable instructions are configured to: connect a grain field planting base database to obtain external data and obtain internal data of the granary; wherein the internal data of the granary at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and warehouse facility operation data, and the external data at least includes one of the following: market grain price, planting cost, planting area, planting type, and network information related to grain; clean and arrange the external data and the internal data of the granary based on an association relationship to generate a monitoring data set; process the monitoring data based on a preset risk prediction model library to generate an early warning report and send the early warning report to relevant personnel; wherein the model database includes a transportation monitoring model, a grain condition monitoring model, a grain price monitoring model, and a facility operation monitoring model; compare the early warning report with a preset risk disposal process to generate a risk decision.

[0016] The risk early warning method, device and medium based on granary big data provided by the embodiments of the present application at least have the following technical effects:

[0017] By automatically connecting the grain field planting base database and the internal system of the grain depot, real-time diversified data is obtained and integrated, significantly reducing the time for manual data collection and processing, and improving the overall efficiency of grain storage management; using the method of correlation relationship cleaning and data arrangement, effectively removing repeated, invalid and redundant data, ensuring the accuracy and reliability of the monitoring data set. Based on the preset risk prediction model library, the monitoring data is comprehensively processed, which can automatically identify and warn various potential risks, including transportation risk, grain condition risk, grain price fluctuation risk and facility operation risk, realizing the monitoring of the risk of the grain depot; comparing the early warning report with the preset risk disposal process, generating risk decision-making, providing scientific and reasonable decision-making basis for the management personnel, which helps to quickly respond and effectively dispose of risk events and reduce losses. By building a visual platform, real-time and intuitive display of the business data and risk warning information of the grain depot is realized, so that the management personnel can quickly master the running state and potential risks of the grain depot, and improve the transparency and scientificity of management decision-making. In summary, not only the efficiency and safety of grain storage management are improved, but also intelligent and visual means are provided for the management personnel to provide comprehensive and accurate data support and decision-making basis. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application, and do not limit the application in any way. In the drawings:

[0019] Figure 1 A risk early warning method based on grain depot big data provided by the embodiments of the application is shown in the flow chart;

[0020] Figure 2 An internal structure schematic diagram of a risk early warning device based on grain depot big data provided by the embodiments of the application is shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the application clearer, the technical scheme of the application will be described in detail below with reference to the specific embodiments of the application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0022] The embodiments of the application provide a risk early warning method, device and medium based on grain depot big data, to solve the technical problem of how to improve the efficiency and safety of grain storage management.

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

[0024] Figure 1 A risk early warning process diagram based on grain depot big data is provided for the embodiments of the present application. As shown in Figure 1 The risk early warning method based on grain depot big data provided by the embodiments of the present application specifically includes the following steps:

[0025] Step 1, connect the grain field planting base database to obtain external data and obtain internal data of the grain depot; wherein the internal data of the grain depot at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and warehouse facility operation data; the external data at least includes one of the following: market grain price, planting cost, planting area, planting type and network information related to grain.

[0026] In order to ensure the accuracy and comprehensiveness of the risk early warning based on the grain depot big data to a certain extent, the internal data and external data of the grain depot need to be obtained at the same time.

[0027] The internal data of the grain depot is the basis of the early warning system, and the internal data of the grain directly reflects the actual operation of the grain depot. Including but not limited to:

[0028] Grain type: records the types of grains stored in the grain depot.

[0029] Inventory: real-time update of the inventory of various grains in the grain depot.

[0030] Warehouse entry and exit record: the entry and exit of grain, including time, quantity, type, etc.

[0031] Temperature and humidity: real-time acquisition of temperature and humidity data in the grain depot.

[0032] Mold and insect damage: regular detection and recording of mold and insect damage of grain.

[0033] Warehouse facility operation data: including the running status of warehouse equipment, maintenance record, etc.

[0034] External data is also important for grain depot management. External data can help grain depot managers understand market dynamics, planting conditions and various information related to grain. Specifically, external data includes but is not limited to:

[0035] Market grain price: by connecting the grain field planting base database or related agricultural information platform, real-time acquisition of market grain price information, which is significant for grain depot managers to formulate purchase and sale strategy and optimize inventory management.

[0036] Planting cost: understanding the planting cost of grain helps to evaluate the actual value of grain and provides basis for grain depot managers to make reasonable decisions in the process of procurement and sales.

[0037] Planting area: Changes in planting area directly affect grain production and supply, and are of great reference value for grain depot managers to predict grain market trends and adjust inventory structure.

[0038] Planting types: Understanding the planting situation of different grain types helps grain depot managers adjust the inventory structure according to market demand and meet diverse market needs.

[0039] Food-related online information: This includes food-related information from social media, forums, news websites, and other channels. This information includes market dynamics, policy changes, and consumer preferences, which can assist grain depot managers in making decisions.

[0040] Taking a large grain depot as an example, firstly, it connects to the local grain planting base database and agricultural information platform via API interface to obtain external data such as market grain prices, planting costs, planting area, and planting types in real time. At the same time, the grain depot has deployed a grain condition monitoring system to collect internal data such as grain types, inventory, inbound and outbound records, temperature, humidity, mold, pests, and storage facility operation data in real time.

[0041] Step 2: Clean and organize external data and internal grain depot data based on the relationships to generate a monitoring dataset.

[0042] First, external and grain depot internal data are processed using a pre-defined data cleaning algorithm to remove duplicate, invalid, and abnormal data, generating the first set of monitoring data. A series of pre-defined data cleaning algorithms are applied to comprehensively scan the collected external and grain depot internal data to identify and remove duplicate, invalid, and abnormal data, which may have been generated due to errors, redundancy, or data conflicts during the data acquisition process.

[0043] The data that remains after cleaning is the first monitoring data.

[0044] Furthermore, external data and grain depot internal data are labeled based on data type to generate secondary monitoring data. The cleaned data is classified and labeled, with external data and grain depot internal data labeled into different categories according to their nature and purpose.

[0045] For example, market grain prices and planting costs are labeled as external data; grain types, inventory levels, and inbound / outbound records are labeled as internal operational data.

[0046] The labeled data is the second monitoring data. The second monitoring data has not only been cleaned and verified, but has also been clearly classified and labeled according to type.

[0047] Further, the second monitoring data is processed based on time relationship and process relationship to generate monitoring data. Considering the time sequence of the data, the second monitoring data needs to be sorted and calibrated in time.

[0048] All data is arranged according to a unified time standard, so that the time change trend of the data can be accurately reflected in subsequent analysis.

[0049] According to the actual process of grain depot operation, the second monitoring data is sorted and integrated in the process.

[0050] For example, the data of the links such as grain storage, storage, and delivery are associated to identify the logical relationship and potential risk points between the links. Through process relationship processing, the internal relationship and interaction between the data can be better understood.

[0051] The second monitoring data processed through time relationship and process relationship is the monitoring data. The monitoring data is comprehensively cleaned, labeled and arranged, and sorted and associated according to time sequence and process logic.

[0052] Step 3, processing the monitoring data based on the preset risk prediction model library to generate an early warning report and send it to relevant personnel; wherein the model database includes a transportation monitoring model, a transportation monitoring model, a grain price monitoring model and a facility operation monitoring model. After data cleaning and arrangement, the monitoring data can be processed based on the preset risk prediction model library to generate various early warning reports and send them to relevant personnel. This step includes four sub-steps of transportation monitoring, grain monitoring, grain price monitoring and facility operation monitoring.

[0053] Step 31, processing the grain type, inventory, in-out warehouse records, planting area and planting type based on the transportation monitoring model, and comparing the change of inventory based on planting area and planting type to generate a transportation early warning report.

[0054] First, determine the planting type, planting area and freight vehicle of the grain field planting base.

[0055] Determine the planting type and planting area of the grain field planting base, which is the basis for evaluating grain yield.

[0056] Identify and register the freight vehicle information involved in grain transportation, including vehicle model, carrying capacity, license plate number, etc. The above will be used to track the driving path of the vehicle and the weight detector data.

[0057] Further, based on the planting type, determine the unit yield, and based on the unit yield and planting area, generate the grain yield.

[0058] Based on the planting species and local historical data or expert evaluation, the unit yield of each crop (i.e. the grain yield per unit area) is determined. Multiply the unit yield by the planting area to calculate the theoretical total grain yield. This yield will be used as a benchmark for subsequent comparative analysis.

[0059] Further, the driving record of the freight vehicle is obtained; wherein the driving record includes the driving path and the weighbridge detection data.

[0060] The driving record of the freight vehicle is obtained in real time, including the driving path, the stop site, the weighbridge detection data, etc., wherein the weighbridge detection data is used to verify the actual transportation of grain weight.

[0061] Further, based on the grain type and the freight vehicle, the storage warehouse is determined, and the change of the inventory of the storage warehouse is obtained. The grain storage warehouse is determined, and the change of the inventory is monitored in real time.

[0062] Further, the grain yield, the weighbridge monitoring data and the change of the inventory are compared, and when the error between the grain yield, the weighbridge monitoring data and the change of the inventory exceeds the preset error threshold, a transportation warning report is generated.

[0063] The calculated grain yield is compared with the weighbridge detection data (i.e. the actual transportation of grain weight), and the change of the inventory of the storage warehouse is analyzed.

[0064] It should be noted that the correspondence between the grain type and the transportation vehicle, the storage warehouse should be paid attention to, to ensure the consistency and accuracy of the data (i.e. the data arrangement in step 2 through the association relationship).

[0065] An error threshold is set to determine whether the error between the grain yield, the weighbridge monitoring data and the change of the inventory is within an acceptable range. When the error exceeds the preset threshold, it is considered that there is an abnormal situation, which needs to be further investigated. Once an abnormal situation is found, a transportation warning report is immediately generated. The report should record the time, place, grain type and quantity involved, transportation vehicle information and inventory change in detail. For example, the difference between the weighbridge monitoring data of truck A passing through toll station B and toll station C exceeds the error threshold, then a transportation warning report is generated, which at least includes all the data of truck A passing through toll station B and toll station C.

[0066] The generated transportation warning report is sent to the grain depot managers, the superior supervisory departments and the relevant personnel in time. At the same time, the transportation warning report can be sent through system interface, WeChat public number, short message, email and other ways to improve the efficiency and coverage of information transmission.

[0067] Step 32, based on the grain condition monitoring model, process temperature, humidity, mold, insect damage and grain related network information, and generate a grain condition warning report through the change of temperature and humidity and the generation of mold and insect damage.

[0068] Firstly, the temperature and humidity in the grain depot are acquired in real time and compared with the preset safety range. When the safety range is exceeded, a grain condition warning report is generated.

[0069] Through the temperature sensor and humidity sensor in the grain depot, the temperature and humidity data in the grain depot are collected in real time. The collected temperature data and humidity data are compared with the preset safety range (determined according to the type of grain, storage conditions, etc.). Once it is found that the temperature or humidity exceeds the safety range, the warning mechanism is started immediately, and a grain condition warning report is generated.

[0070] Further, the mold history data and insect damage history data are acquired, and the mold history data and insect damage history data are associated with the temperature change and humidity change to construct a disease analysis model.

[0071] Collect historical mold and insect damage data, including occurrence time, environmental conditions (temperature, humidity), grain type, etc. Analyze the above data to find out the correlation between mold and insect damage and temperature and humidity changes. Based on the above analysis, use statistical analysis or machine learning algorithms to construct a disease analysis model. The disease analysis model can predict the occurrence probability of mold and insect damage based on the current temperature and humidity data.

[0072] Further, when the temperature and humidity change conforms to the disease analysis model, a grain condition warning report is generated.

[0073] Compare the real-time collected temperature and humidity data with the disease analysis model. When the temperature and humidity change conforms to the model prediction of mold or insect damage occurrence, automatically generate a grain condition warning report, and record the warning time, place, involved grain type and quantity, current temperature and humidity data, predicted mold or insect damage risk, etc.

[0074] Further, monitor the data related to pests and weather in the network information related to grain, and process the data related to pests and weather according to the grain condition monitoring model to generate a grain condition warning report.

[0075] Monitor the network information related to grain, especially the information related to pests and weather changes that may have potential impact on grain storage. Combine the collected network information (such as pest forecast, extreme weather warning, etc.) with the grain condition monitoring model to evaluate the potential impact of external factors on the storage state of grain in the grain depot. According to the analysis result, if there is a factor that significantly affects the safety of grain, the corresponding content is added to the grain condition warning report.

[0076] The generated grain situation early warning report is sent to the grain depot managers, the superior supervisory departments and the relevant personnel in a timely manner through various ways such as a system interface, a WeChat public number, a short message and an email.

[0077] Step 33, processing the planting cost, the network information related to grain and the market grain price based on the grain price monitoring model to generate a grain price early warning report.

[0078] Firstly, historical planting cost data and historical market grain price data are collected, and a grain price monitoring model is established according to the historical planting cost data and the historical market grain price data.

[0079] The historical planting cost data (including seed, fertilizer, pesticide, transportation and other costs) and the historical market grain price data are collected and sorted out, and a grain price monitoring model is established based on the historical planting cost data and the historical market grain price data through statistical analysis or machine learning algorithm.

[0080] Further, the changes of the planting cost are monitored in real time; wherein the planting cost includes seed, fertilizer, pesticide and transportation. The changes of the planting cost such as seed, fertilizer, pesticide and transportation are monitored in real time.

[0081] Further, the grain supply and demand data and the policy adjustment data in the network information related to grain are obtained. The network information related to grain is obtained, especially the grain supply and demand data and the policy adjustment data, the collected network information is sorted out and analyzed, and the factors potentially affecting the grain price are extracted.

[0082] Further, the grain supply and demand data and the policy adjustment data are processed based on the grain price monitoring model to generate a predicted price. The planting cost data monitored in real time and the grain supply and demand data and the policy adjustment data extracted from the network information are input into the grain price monitoring model, and the grain price monitoring model is used for prediction processing to generate a predicted price in a future period of time.

[0083] Further, based on the comparison between the predicted price and the market grain price, when the predicted price fluctuates beyond a preset grain price threshold, a grain price early warning report is generated. The predicted price is compared and analyzed with the current market grain price. A preset grain price threshold (such as fluctuation range, price interval, etc.) is set to determine whether a grain price early warning report needs to be generated.

[0084] When the predicted price fluctuates beyond the preset grain price threshold, a grain price early warning report is generated, and the report content includes the early warning time, the grain types involved, the comparison between the predicted price and the market price, the fluctuation reason analysis and the recommended measures, etc.

[0085] Step 34, processing the temperature, humidity and warehouse facility operation data based on a facility operation monitoring model to generate a facility operation early warning report through the change conditions of the temperature, humidity and the change conditions of the warehouse facility operation data.

[0086] First, real-time monitoring of warehouse operation data to generate real-time data; wherein the warehouse operation data includes cooling system, ventilation system, dehumidification system. Real-time monitoring of the operation data of the cooling system, ventilation system, dehumidification system and other key warehouse facilities in the grain depot.

[0087] Further, compare the real-time data with the preset operation warning range, and generate a facility operation warning report when the real-time data exceeds the operation warning range. According to the design standards and actual operation conditions of the warehouse facility, the operation warning range of various facilities (such as temperature range, humidity range, equipment operation parameters, etc.) is preset. Compare and analyze the real-time collected warehouse facility operation data with the preset operation warning range, and automatically generate a facility operation warning report when any real-time data is found to exceed the preset warning range.

[0088] Further, analyze the correlation between temperature, humidity and warehouse facility operation data to generate an abnormal operation mode model. Analyze the correlation between temperature, humidity and warehouse facility operation data to obtain the mutual influence, mechanism and correlation between temperature, humidity and warehouse facility operation data. Based on the above correlation analysis, an abnormal operation mode model is established. This model can identify the abnormal operation mode of the warehouse facility under different temperature and humidity conditions.

[0089] Further, set a baseline for the operation efficiency and energy consumption of the warehouse facility, and compare the real-time data with the baseline to generate an energy efficiency deviation.

[0090] Set a baseline for the operation efficiency and energy consumption of the warehouse facility. It can be set based on historical operation data, industry standards or data provided by equipment manufacturers. Compare and analyze the real-time collected warehouse facility operation data (such as energy consumption, operation efficiency, etc.) with the baseline. Calculate the deviation value between the real-time data and the baseline, which is the energy efficiency deviation.

[0091] Further, when the energy efficiency deviation is greater than the preset energy efficiency threshold, a facility operation warning report is generated. When the energy efficiency deviation is greater than the preset energy efficiency threshold, it indicates that the operation efficiency of the warehouse facility has decreased or the energy consumption has increased significantly, and a facility operation warning report is generated. The report should include warning time, facility type involved, energy efficiency deviation value, cause analysis and recommended measures, etc.

[0092] The generated facility operation warning report is sent to the grain depot managers, maintenance personnel and superior supervisory departments in a timely manner through system interface, WeChat public number, short message, email and other ways.

[0093] Step 35, integrate the transportation warning report, grain price warning report and facility operation warning report to generate a warning report and send it to the relevant personnel.

[0094] Collect early warning reports from different modules, including transportation early warning reports, grain condition early warning reports, grain price early warning reports, and facility operation early warning reports. Summarize and send the key data in each early warning report to the relevant personnel.

[0095] Step 4, compare the early warning report with the preset risk disposal process to generate a risk decision.

[0096] Identify specific risk points from the early warning report, such as transportation delays, grain price fluctuations, facility failures, etc. Consult the preset risk disposal process document or system to understand the standard processing steps and measures for different risk points. Match the risk points in the early warning report with the preset risk disposal process to find the corresponding processing process and steps.

[0097] According to the content of the early warning report and the preset risk disposal process, make a preliminary risk decision. The preliminary risk decision includes the processing target, specific measures, responsible department, responsible person, and completion time limit, etc.

[0098] Send the preliminary risk decision to the preset audit section, responsible department, and responsible person for audit to generate a risk decision.

[0099] Finally, assign specific tasks in the risk decision to the corresponding responsible department and responsible person, and clearly define the task requirements and completion time limit. In order to facilitate the relevant personnel to check and monitor, the embodiments of the present application also include the following methods.

[0100] In order to facilitate the relevant personnel to check and monitor, the embodiments of the present application also include the following methods:

[0101] First, build a visualization platform and associate the monitoring data. Design a visualization platform to real-time access monitoring data (including transportation data, grain price data, facility operation data, etc.) to the visualization platform,

[0102] Further, based on the visualization platform, display the monitoring data and the early warning report related to the monitoring data. Integrate the early warning report generation and display function, so that the platform can directly display the early warning report related to the monitoring data.

[0103] Establish data mapping relationship in the visualization platform, associate various monitoring data with corresponding visualization elements (such as charts, maps, dashboards, etc.), and realize intuitive display of data.

[0104] The above is the method embodiment of the present application. Based on the same inventive concept, the embodiments of the present application also provide a risk early warning device based on grain depot big data, the structure of which is as Figure 2 shown.

[0105] Figure 2A kind of risk early warning equipment based on grain depot big data provided for the embodiment of the application internal structure schematic view.As shown in Figure 2 The equipment includes:

[0106] At least one processor 201;

[0107] And the memory 202 connected in communication with the at least one processor;

[0108] 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:

[0109] Connect the grain field planting base database to obtain external data, and obtain the internal data of grain depot;Wherein, the internal data of grain depot at least includes the following one: grain type, inventory, warehouse record, temperature, humidity, mold, insect pests, warehousing facility operation data, external data at least includes the following one: market grain price, planting cost, planting area, planting species and network information related to grain;Based on the correlation relationship, external data and internal data of grain depot are cleaned and arranged to generate monitoring data set;Based on the preset risk prediction model database, monitoring data is processed to generate early warning report and send to relevant personnel;Wherein, the model database includes transport monitoring model, grain condition monitoring model, grain price monitoring model and facility operation monitoring model;Based on early warning report, preset risk disposal process is compared to generate risk decision.

[0110] Some embodiments of the application provide a non-volatile computer storage medium based on the risk early warning of grain depot big data corresponding to Figure 1 The computer executable instructions are set to:

[0111] Connect the grain field planting base database to obtain external data, and obtain the internal data of grain depot;Wherein, the internal data of grain depot at least includes the following one: grain type, inventory, warehouse record, temperature, humidity, mold, insect pests, warehousing facility operation data, external data at least includes the following one: market grain price, planting cost, planting area, planting species and network information related to grain;Based on the correlation relationship, external data and internal data of grain depot are cleaned and arranged to generate monitoring data set;Based on the preset risk prediction model database, monitoring data is processed to generate early warning report and send to relevant personnel;Wherein, the model database includes transport monitoring model, grain condition monitoring model, grain price monitoring model and facility operation monitoring model;Based on early warning report, preset risk disposal process is compared to generate risk decision.

[0112] The various embodiments in the present application are described in a progressive manner, and the same or similar parts among the various embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, the IoT device and medium embodiments are described simply because they are basically similar to the method embodiments.

[0113] The system and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the system and medium also have similar beneficial technical effects to the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be described here.

[0114] Those skilled in the art should understand that the embodiments of the present application can provide a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present 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 storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device implemented in the flowcharts and / or block diagrams. Figure 1 The device that implements the function specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the function specified in one flow or multiple flows and / or blocks.

[0116] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The device that implements the function specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the function specified in one flow or multiple flows and / or blocks.

[0117] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0118] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0119] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory is an example of computer readable storage media.

[0120] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as 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 programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0122] ​​The above merely provides an example of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A risk early warning method based on granary big data, characterized in that, The method comprises: connecting a grain field planting base database to obtain external data and internal data of a grain depot, wherein the internal data of the grain depot at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and warehouse facility operation data, and the external data at least includes one of the following: market grain price, planting cost, planting area, planting type, and network information related to grain; cleaning and sorting the external data and the internal data of the grain depot based on an association relationship to generate a monitoring data set, wherein the association relationship includes a time relationship and a process relationship; processing the grain type, inventory, warehouse entry and exit record, planting area, and planting type based on a transportation monitoring model, comparing the change of the inventory with each weighbridge monitoring data generated by the grain yield and each weighbridge passed by a grain-carrying truck driving path to generate a transportation early warning report, wherein the grain yield is calculated based on the unit yield of the planting type and the planting area; processing the temperature, humidity, mold, insect damage, and network information related to grain based on a grain condition monitoring model, generating a grain condition early warning report through the change of the temperature and humidity, the association relationship between the change of the temperature and humidity and the generation of mold and insect damage, and weather changes; processing the planting cost and network information related to grain based on a grain price monitoring model to generate a predicted price in a future period of time, comparing and analyzing the predicted price with a preset grain price threshold to generate a grain price early warning report; processing the temperature, humidity, and warehouse facility operation data based on a facility operation monitoring model, generating a facility operation early warning report through the change of the temperature and humidity, the change of the warehouse facility operation data, and the association relationship between the change of the temperature and humidity and the change of the warehouse facility operation data; integrating the transportation early warning report, the grain price early warning report, and the facility operation early warning report to generate an early warning report and send it to relevant personnel; comparing a preset risk disposal process based on the early warning report to generate a risk decision. 2.The risk early warning method based on granary big data according to claim 1, characterized in that, cleaning and sorting the external data and the internal data of the grain depot based on an association relationship to generate a monitoring data set, specifically comprising: processing the external data and the internal data of the grain depot based on a preset data cleaning algorithm to remove repeated, invalid, and abnormal data in the external data and the internal data of the grain depot to generate first monitoring data; annotating the external data and the internal data of the grain depot based on data type to generate second monitoring data; processing the second monitoring data based on a time relationship and a process relationship to generate monitoring data. 3.The risk early warning method based on granary big data according to claim 1, characterized in that, processing the grain type, inventory, warehouse entry and exit record, planting area, and planting type based on a transportation monitoring model, comparing the change of the inventory with each weighbridge monitoring data generated by the grain yield and each weighbridge passed by a grain-carrying truck driving path to generate a transportation early warning report, specifically comprising: determining the planting type, planting area, and freight vehicle of the grain field planting base; determining the unit yield based on the planting type, and generating the grain yield based on the unit yield and the planting area; Obtaining the driving record of the freight vehicle; wherein the driving record comprises driving path and weighbridge detection data; Based on the grain category and freight vehicle, determine the storage warehouse, and obtain the change of inventory of the storage warehouse; Compare the grain yield, the weighbridge monitoring data and the change of inventory, and when the error between the grain yield, the weighbridge monitoring data and the change of inventory exceeds the preset error threshold, generate a transportation warning report. 4.The risk early warning method based on granary big data according to claim 1, characterized in that, Based on the grain condition monitoring model, process the temperature, humidity, mold, insect damage and network information related to grain, generate a grain condition warning report through the change of temperature and humidity, the correlation between the change of temperature and humidity and the occurrence of mold and insect damage, and weather changes, specifically including: Real-time acquisition of temperature and humidity in the grain depot, and comparison with the preset safety range, when exceeding the safety range, generate a grain condition warning report; Obtain mold history data and insect damage history data, and construct a correlation between the mold history data and insect damage history data and temperature change and humidity change to generate a disease analysis model; When the change of temperature and humidity conforms to the disease analysis model, generate a grain condition warning report; Monitoring data related to pests and weather in network information related to grain, and processing the data related to pests and weather according to the grain condition monitoring model to generate a grain condition warning report.

5. The risk early warning method based on granary big data according to claim 1, characterized in that, Based on the grain price monitoring model, process the planting cost, network information related to grain, to generate a predicted price in a future period of time, and by comparing and analyzing the predicted price with the preset grain price threshold, generate a grain price warning report, specifically including: Collecting historical planting cost data and historical market grain price data, and establishing a grain price monitoring model according to the historical planting cost data and historical market grain price data; Real-time monitoring of the change of the planting cost; wherein the planting cost includes seeds, fertilizers, pesticides and transportation; Obtaining grain supply and demand data and policy adjustment data in network information related to grain; Based on the grain price monitoring model, predict and process the grain supply and demand data and policy adjustment data to generate a predicted price; Based on the comparison between the predicted price and the market grain price, when the fluctuation of the predicted price exceeds the preset grain price threshold, generate a grain price warning report.

6. The risk early warning method based on granary big data according to claim 1, characterized in that, Based on the facility operation monitoring model, process the temperature, humidity and warehouse facility operation data, generate a facility operation warning report through the change of temperature and humidity, the change of warehouse facility operation data, and the correlation between the change of temperature and humidity and the change of warehouse facility operation data, specifically including: Real-time monitoring of warehouse facility operation data to generate real-time data; wherein the warehouse facility operation data includes cooling system, ventilation system, dehumidification system; Comparing the real-time data with the preset operation warning range, when the real-time data exceeds the operation warning range, generating a facility operation warning report; Analyzing the correlation between the temperature, the humidity and the warehouse facility operation data to generate an abnormal operation mode model; setting a baseline of operation efficiency and energy consumption of a storage facility, and comparing real-time data with the baseline to generate an energy efficiency deviation; generating a facility operation warning report when the energy efficiency deviation is greater than a preset energy efficiency threshold.

7. The risk early warning method based on granary big data according to claim 1, characterized in that, The method further comprises: building a visualization platform and associating the monitoring data; displaying the monitoring data and the warning report related to the monitoring data based on the visualization platform.

8. A risk early warning device based on grain depot big data, characterized in that, The device comprises: at least one processor; and a memory connected in communication with 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 to enable the at least one processor to: connect a grain field planting base database to obtain external data and obtain internal data of a grain depot; wherein the internal data of the grain depot at least includes one of the following: grain type, inventory, warehouse entry and exit record, temperature, humidity, mold, insect damage, and storage facility operation data, and the external data at least includes one of the following: market grain price, planting cost, planting area, planting type, and network information related to grain; cleaning and organizing the external data and the internal data of the grain depot based on an association relationship to generate a monitoring data set, the association relationship including a time relationship and a process relationship; processing the grain type, inventory, warehouse entry and exit record, planting area, and planting type based on a transportation monitoring model, and generating a transportation warning report by comparing the change of inventory with each load cell monitoring data generated by the grain yield and the driving path of the load carrying vehicle passing through each load cell, the grain yield being calculated based on the planting area and the unit yield of the planting type; processing the temperature, humidity, mold, insect damage, and network information related to grain based on a grain condition monitoring model, and generating a grain condition warning report by the change of temperature and humidity, the association relationship between the change of temperature and humidity and the generation of mold and insect damage, and weather changes; processing the planting cost and network information related to grain based on a grain price monitoring model to generate a predicted price in a future period of time, and generating a grain price warning report by comparing and analyzing the predicted price with a preset grain price threshold; processing the temperature, humidity, and storage facility operation data based on a facility operation monitoring model, and generating a facility operation warning report by the change of temperature and humidity, the change of storage facility operation data, and the association relationship between the change of temperature and humidity and the change of storage facility operation data; integrating the transportation warning report, the grain price warning report, and the facility operation warning report to generate a warning report and send it to relevant personnel; comparing a preset risk disposal process based on the warning report to generate a risk decision. 9.A non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are executed by a processor to implement a risk early warning method based on granary big data, and the method comprises the steps of: The computer executable instructions are configured to: Connect the grain field planting base database to obtain external data and obtain internal data of the grain depot; wherein the internal data of the grain depot at least includes one of the following: grain type, inventory, warehouse record, temperature, humidity, mold, insect pests, storage facility operation data, the external data at least includes one of the following: market grain price, planting cost, planting area, planting type and network information related to grain; Based on the association relationship, the external data and the internal data of the grain depot are cleaned and arranged to generate a monitoring data set, the association relationship includes time relationship and process relationship; Based on the transportation monitoring model, the grain type, inventory, warehouse record, planting area and planting type are processed, by comparing the change of inventory with each load wagon monitoring data generated by the grain production and the driving path of the load wagon, a transportation early warning report is generated, the grain production is calculated based on the planting area and the unit yield of the planting type; Based on the grain condition monitoring model, the temperature, humidity, mold, insect pests and network information related to grain are processed, through the change of temperature and humidity, the association relationship between the change of temperature and humidity and the generation of mold and insect pests, and the weather change, a grain condition early warning report is generated; Based on the grain price monitoring model, the planting cost and network information related to grain are processed to generate the predicted price in a period of time in the future, by comparing and analyzing the predicted price with the preset grain price threshold, a grain price early warning report is generated; Based on the facility operation monitoring model, the temperature, humidity and storage facility operation data are processed, through the change of temperature and humidity, the change of storage facility operation data, and the association relationship between the change of temperature and humidity and the change of storage facility operation data, a facility operation early warning report is generated; Integrate the transportation early warning report, the grain price early warning report and the facility operation early warning report to generate an early warning report and send it to relevant personnel; Based on the early warning report, compare the preset risk disposal process to generate a risk decision.

Images