CN116702987A - Grain supply chain safety monitoring and early warning system based on big data analysis - Google Patents
Grain supply chain safety monitoring and early warning system based on big data analysis Download PDFInfo
- Publication number
- CN116702987A CN116702987A CN202310703499.1A CN202310703499A CN116702987A CN 116702987 A CN116702987 A CN 116702987A CN 202310703499 A CN202310703499 A CN 202310703499A CN 116702987 A CN116702987 A CN 116702987A
- Authority
- CN
- China
- Prior art keywords
- data
- variable
- early warning
- supply chain
- grain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 238000007405 data analysis Methods 0.000 title claims abstract description 31
- 230000004044 response Effects 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 65
- 238000000034 method Methods 0.000 claims description 30
- 238000004519 manufacturing process Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 235000013305 food Nutrition 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 231100000279 safety data Toxicity 0.000 claims description 4
- 235000013339 cereals Nutrition 0.000 description 82
- 230000000875 corresponding effect Effects 0.000 description 63
- 239000003337 fertilizer Substances 0.000 description 16
- 239000000618 nitrogen fertilizer Substances 0.000 description 12
- 239000002686 phosphate fertilizer Substances 0.000 description 12
- 230000001960 triggered effect Effects 0.000 description 10
- 238000003860 storage Methods 0.000 description 9
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 8
- 229910052700 potassium Inorganic materials 0.000 description 8
- 239000011591 potassium Substances 0.000 description 8
- KWYUFKZDYYNOTN-UHFFFAOYSA-M Potassium hydroxide Chemical compound [OH-].[K+] KWYUFKZDYYNOTN-UHFFFAOYSA-M 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000004720 fertilization Effects 0.000 description 4
- 229940072033 potash Drugs 0.000 description 4
- 235000015320 potassium carbonate Nutrition 0.000 description 4
- BWHMMNNQKKPAPP-UHFFFAOYSA-L potassium carbonate Substances [K+].[K+].[O-]C([O-])=O BWHMMNNQKKPAPP-UHFFFAOYSA-L 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001632 homeopathic effect Effects 0.000 description 3
- 230000001932 seasonal effect Effects 0.000 description 3
- 240000008042 Zea mays Species 0.000 description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 238000009331 sowing Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000004718 Panda Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 239000000447 pesticide residue Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 235000020985 whole grains Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a grain supply chain safety monitoring and early warning system based on big data analysis, which comprises: the data acquisition module is configured to capture preset data of each link of a grain supply chain in a preset area; the data analysis module is configured to analyze the preset data to obtain the predicted demand of the grains; the data monitoring module is configured to screen historical data matched with the predicted demand, screen the historical data with the most variable overlapping, set the overlapped variable in the preset data as a first variable, set the residual variable as a second variable, monitor the second variable and set an early warning index according to the second variable and the historical data; the early warning issuing module is configured to issue early warning information to an early warning center; the emergency response module is configured to generate a corresponding emergency plan according to the early warning information; according to the invention, the predicted demand of the grain is compared with the historical data, and the preset data is adjusted, so that the terminal supply of the grain meets the predicted demand.
Description
Technical Field
The invention belongs to the field of grain supply chains, and particularly relates to a grain supply chain safety monitoring and early warning system based on big data analysis.
Background
The grain supply chain comprises links from grain production, processing, storage and circulation to consumption, hundreds of millions of farmers and tens of thousands of small and medium-sized agricultural enterprises exist on the grain supply chain in China, the grain supply chain is continuously prolonged along with the gradual formation of the urban development and the production and marketing pattern of North grain south transportation, key nodes are continuously increased, the links are mutually connected and influenced, the pressure of intermediate links is increased, and the whole toughness of the supply chain is extremely easily influenced.
If the data index of each link in the grain supply chain needs to be accurately controlled, great difficulty is generated.
Disclosure of Invention
The invention aims to: in order to overcome the defects, the invention aims to provide a grain supply chain safety monitoring and early warning system based on big data analysis, which can improve the toughness of the whole grain supply chain and reduce the data index of an intermediate link to be monitored.
The technical scheme is as follows: a grain supply chain safety monitoring and early warning system based on big data analysis, comprising:
the data acquisition module is configured to capture preset data of each link of a grain supply chain in a preset area, and integrate the preset data into a database, wherein the preset data is dynamic data, the preset data comprises a plurality of variables, and the preset data is updated at preset frequency;
the data analysis module is configured to process and analyze the preset data and obtain the predicted demand of future grains by carrying out trend analysis on the historical data;
the data monitoring module is configured to screen historical data matched with the predicted demand, screen the historical data with the most variable overlapping, set the overlapped variable in preset data as a first variable, set the residual variable as a second variable, monitor the second variable and set an early warning index according to the second variable and the historical data;
the early warning issuing module is configured to issue corresponding grain supply chain safety early warning information to the early warning center according to the monitoring situation and the early warning index;
the emergency response module is configured to generate a corresponding emergency plan according to the early warning information;
by comparing the historical data with the variable overlapping pairs, the second variable needing to be monitored is reduced, and the monitoring efficiency and the early warning success rate are improved.
Preferably, the preset area at least comprises a grain production area, a grain reserve area, a grain transportation area and a grain sales area, and the preset data at least comprises production data, processing data, transportation and logistics data, sales and market data, quality and security data, environment and meteorological data.
Preferably, the historical data represents a relationship between a data index and a historical grain demand, and the historical data of which the historical grain demand is matched with the predicted demand is used as the first screening standard.
Preferably, the first variable comprises an artificial control variable and an uncontrollable variable, and the second variable is an artificial control variable; the artificial control variables are used as monitoring objects, so that the second variables can be conveniently adjusted to corresponding data indexes.
Preferably, the change trend of the corresponding data index in the second variable and the historical data is monitored, if the second variable is subjected to inverse potential change, corresponding grain supply chain safety early warning information is issued to an early warning center, and the early warning information comprises the current value of the second variable and the corresponding data index; the adjusting method is to adjust the second variable to the corresponding data index, if the difference between the second variable and the corresponding data index is enlarged, the warning prompt is needed.
Preferably, if the second variable is subjected to inverse potential change, continuing to monitor the change trend of the second variable in the error interval, if the value corresponding to the end point of the second variable in the error interval is closer to the data index corresponding to the historical data than the value corresponding to the start point, regarding the inverse potential change as normal fluctuation of the second variable, and if the value corresponding to the start point of the second variable in the error interval is closer to the data index corresponding to the historical data than the value corresponding to the end point, issuing corresponding grain supply chain safety early warning information to the early warning center; the data has a normal fluctuation range, and the allowable variation range of the second variable under the normal condition is calibrated through the values of the error interval and the second variable corresponding to the starting point and the ending point of the error interval.
Preferably, if the second variable changes in inverse potential, continuously monitoring the change trend of the second change in the error interval, if the second variable changes in the error interval in direct potential and the direct potential continues to the end point of the error interval, regarding the inverse potential change as normal fluctuation of the second variable, otherwise, issuing corresponding grain supply chain safety early warning information to an early warning center; the allowable variation range of the second variable under normal conditions is calibrated through the variation trend of the error interval and the second variable in the error interval, so that the fault tolerance of the second variable is further improved, and invalid regulation and control of the second variable are reduced.
Preferably, if the starting point of the homeotropic variation of the second variable is located between the starting point of the error interval and the middle point of the interval, the inversion variation is regarded as the normal fluctuation of the second variable, otherwise, the corresponding grain supply chain safety early warning information is issued to the early warning center; the judgment of the starting point position of the homeotropic variation is added in the calibration process, the observation length of the second variable can be increased in the error interval, and more accurate analysis results can be obtained.
Preferably, the emergency plan includes an adjustment plan for the second variable to change to a corresponding data index in a homeopathic manner; and the second variable is directly regulated and controlled through the emergency plan, so that the difficulty of data regulation and control is reduced.
Preferably, a plurality of segment intervals are set, and the second variable is gradually changed to the corresponding data index through the segment intervals; aiming at a second variable with larger deviation data index, the second variable is gradually changed to the corresponding data index through a segmentation interval, so that the change trend of the second variable is wholly controllable.
The technical scheme can be seen that the invention has the following beneficial effects:
1. the invention provides a grain supply chain safety monitoring and early warning system based on big data analysis, which can establish a complete and real-time updated grain supply chain database through a data acquisition module; through the data analysis module, the change trend of the grain supply chain can be known, and the future demand can be predicted; through the data monitoring module, the system can establish a reference model or a reference data set, which is helpful for determining the most relevant and key variables for monitoring and prediction, saving the monitoring program and improving the early warning efficiency; through the early warning release module, potential safety risks can be known in time; by means of the emergency response module, a corresponding emergency plan is generated according to the early warning information, so that the system can respond to potential risks and threats rapidly, and potential losses and influences are reduced.
2. If the second variable is subjected to inverse potential change, namely the second variable deviates from the corresponding data index in the historical data, the system triggers an early warning mechanism, and the inverse potential change can help an early warning center to timely respond, so that the problem in a grain supply chain is prevented from being further expanded; the early warning information comprises the current value of the second variable and the data index corresponding to the current value of the second variable, so that the early warning center can be helped to better evaluate and cope with potential safety problems in a grain supply chain.
3. Further, if the second variable is subjected to inverse potential change, the system continuously monitors the change trend of the second variable in the error interval so as to distinguish normal fluctuation from potential problems, and accuracy is improved; and comparing the values corresponding to the starting point and the ending point of the second variable in the error interval with the data index corresponding to the historical data by the system, and if the value corresponding to the ending point is closer to the data index in the historical data than the value corresponding to the starting point, changing the visual inverse potential into the normal fluctuation of the second variable by the system, so that the safety and the stability of the grain supply chain are better protected.
4. Further, if the second variable changes in inverse potential, the system will observe the dynamic change condition of the second variable, if the second variable changes in cis-position in the error interval and continues to the end point of the error interval, the system regards the inverse potential change as the normal fluctuation of the second variable, and by carefully observing and analyzing the change of the second variable, the system can more accurately judge whether the inverse potential change belongs to the normal fluctuation, thereby providing reliable early warning information.
5. Based on the homeotropic variation, if the starting point of the homeotropic variation is located between the starting point of the error interval and the middle point of the interval, the system regards the inversion variation as the normal fluctuation of the second variable, and by further subdividing and analyzing the position of the starting point of the homeotropic variation, the system can provide more accurate judgment and early warning.
6. By means of reasonable sectional setting and gradual adjustment, the system can better control and manage the change process of the second variable so as to cope with the problems in the supply chain and ensure the safety and stability of the grain supply chain.
Drawings
FIG. 1 is a block diagram of a grain supply chain safety monitoring and early warning system based on big data analysis according to the invention;
FIG. 2 is a flow chart of a trend early warning method according to the present invention;
FIG. 3 is a flow chart of a method for distinguishing normal fluctuation of data according to the present invention;
FIG. 4 is a flowchart of another method for distinguishing normal fluctuation of data according to the present invention;
FIG. 5 is a flow chart of a method for distinguishing normal fluctuation of data based on homeopathic changes according to the present invention;
FIG. 6 is a flowchart of a method for differentiating between homeopathic origin points according to the present invention;
FIG. 7 is a flowchart of a threshold early warning method according to the present invention;
FIG. 8 is a flow chart of a working method of the grain supply chain safety monitoring and early warning system based on big data analysis.
Detailed Description
The invention is further elucidated below in connection with the drawings and the specific embodiments.
Example 1
As shown in fig. 1, the embodiment provides a grain supply chain safety monitoring and early warning system based on big data analysis, which comprises a data acquisition module 1, a data analysis module 2, a data monitoring module 3, an early warning issuing module 4 and an emergency response module 5.
Specifically, in this embodiment, the system includes a data acquisition module 1, which is configured to capture preset data of each link of the grain supply chain in a preset area, where the preset area includes at least a grain production area, a grain storage area, a grain transportation area, and a grain sales area. In whole, the coverage area of the preset area can be set according to actual requirements, such as regions, provinces, cities, counties and the like, and the grain production area, the grain storage area and the like are all located in the preset area; the preset data at least comprises production data, processing data, transportation and logistics data, sales and market data, quality and safety data, environment and meteorological data;
the production data are data related to planting, breeding and agricultural production, such as planting area, planting variety, fertilization condition, pesticide usage amount, crop yield and the like; the processing data are data in the processing and treating processes of grains, such as the production condition, processing technological parameters, product quality indexes and the like of a grain processing factory; the transportation and logistics data are data of transportation, storage and storage links of grains, such as logistics routes, running conditions of transportation means, utilization rate of storage facilities, transportation time and the like; the sales and market data are data of food sales and market demands, such as market price, sales volume, market trend, consumer demand, etc.; the quality and safety data are data related to grain quality and safety, such as agricultural product quality detection data, pesticide residue detection data, food safety monitoring data and the like; the environmental and weather data are data of influences of environmental and weather factors on grain production, such as air temperature, precipitation, soil humidity, weather disaster data and the like. It can be understood that the preset data is dynamic data and is updated at a preset frequency, wherein the preset frequency is set according to actual requirements, for example, adjustment is performed according to seasonality and day-night. Sources of the above data include, but are not limited to, sensor technology, internet of things equipment, farmer surveys, market research, government statistics. For example, the sensor equipment is arranged in links of production, processing, transportation, storage and the like of a grain supply chain, and data such as temperature, humidity, air pressure and the like are collected; the RFID tag is arranged on the goods in the grain supply chain, so that the automatic identification and tracking of the goods are realized, and the data of links such as goods transportation, storage and the like are collected; data such as transaction, inventory, sales and the like are collected through internet technologies such as a grain supply chain management system, an electronic commerce platform and the like.
The data acquisition module 1 then integrates the preset data into a database, it being understood that in the field of the grain supply chain, a data platform or database is utilized for integrating and managing data, for example: relational Database (RDBMS): mySQL, oracle, microsoft SQL Server, etc., the relational database can provide structured data storage and query functions, facilitating storage and management of various data in the grain supply chain; noSQL database: mongoDB, cassandra, redis, and the like, the NoSQL database can store unstructured or semi-structured data, and has good scalability and flexibility; data Warehouse (Data warp): amazon Redshift, google BigQuery, snodfake, etc., the data warehouse is capable of storing large-scale data sets and supporting high-performance data query and analysis; data Lake (Data Lake): apache Hadoop, amazon S3, azure Data Lake and the like, the Data Lake can store structured, semi-structured and unstructured original Data, and subsequent Data analysis and mining are facilitated.
In addition to the databases and data platforms described above, other solutions and cloud service providers are included to select an appropriate data platform or database according to particular needs, data types, and specifications.
The system further comprises a data analysis module 2, the function of which is to process and analyze preset data based on historical data, wherein,
the historical data includes the same type of preset data at the past time, for example, production data, process data, transportation and logistics data, sales and marketing data, quality and security data, environmental and weather data, and the like at the past time.
The system utilizes a big data analysis technology to clean the captured preset data and historical data, wherein the method comprises the steps of processing missing values, abnormal values and repeated values, and is helpful for ensuring the quality and accurate determination of the data so as to perform subsequent data analysis, modeling and decision. It will be appreciated that various data analysis tools and programming languages, such as the pandas library of Python, the R language, etc., may be used to support the data cleansing operation.
Further, the grain supply chain data may have missing values, such as missing production records, missing transportation data, etc. Processing the missing values can avoid biasing the data during subsequent analysis. By filling in missing values or deleting data records containing missing values, it is possible to ensure the integrity of the data set. In grain supply chain data, outliers may be caused by measurement errors, anomalies, or other factors. Handling outliers can ensure accuracy and consistency of the data. In the grain supply chain data, repeated purchasing records, repeated transaction records and the like can generate repeated values, and repeated calculation or misleading of the data in the analysis process can be avoided by processing the repeated values.
Accordingly, the historical data is processed and analyzed, including observing trends, seasonal changes, periodical changes and the like of the historical data, specifically, the historical data is time-series data, the historical data is ensured to comprise enough time span and frequency, an AR model is selected according to the properties of the historical data, for example, by plotting a line graph of the time-series data, the characteristics of overall trends, seasonality and periodicity and the like of the historical data are observed, an AR model with trend items or season items is used, the AR model is an autoregressive model based on past observations, future observations are assumed to be related to the past observations, parameter values in the AR model are estimated through maximum likelihood estimation or least square method, the parameter values reflect autocorrelation relations in the historical data, the AR model is fitted to the historical data of the historical food amount by using the parameter values, prediction is sequentially carried out forwards from a starting point of the historical data, and a recursion method is adopted, namely, the next trend is predicted each time by using the estimated value of the known observations, and the future demands are obtained. The AR autoregressive model can predict grain demands in different time periods, such as annual or quaternary grain demands, and is adjusted and optimized according to actual conditions, the trained model is used for predicting future grain demands, relevant factors include population growth rate, economic development trend and the like, the model gives corresponding prediction results, and the prediction results are the prediction demand.
The system further comprises a data monitoring module 3, which functions to monitor the change of the preset data, wherein the reference object is the history data,
the method comprises the steps of selecting a preset data at the past moment and a historical grain demand, defining the preset data at the past moment as a data index, wherein the data index comprises production data, processing data, transportation and logistics data, sales and market data, quality and safety data, environment and weather data and the like, regulating and controlling the preset data at the current moment to be compared with each data index corresponding to the historical grain demand, wherein the historical grain demand is the actual grain demand at the past moment, screening the historical data matched with the preset demand after determining the predicted demand, the matching refers to the preset demand being equal to or similar to the historical grain demand, the difference value between the matching refers to the preset demand and the similar data in a preset difference value, screening the historical data if a plurality of pieces of historical data exist, firstly, comparing the preset data at the current moment with each data index of the historical data, wherein the preset data and the data index with a numerical value overlapped, namely, the overlapped variables are equal or similar in numerical value, the overlapped variables comprise production data, processing data, the transportation and logistics data, the quality and the market and the weather data, the first and the second time are set as the rest variables, the second variables are the rest variables, the rest variables are the first and the rest variables are the second variables, the rest variables are the rest variables, and the rest variables are set and the variables, and the rest variables are the second variables.
The human control means that in the modern agricultural management technology, most data can be adjusted manually, such as weather data, soil humidity can be adjusted through a reasonable drainage system, a proper growth environment is provided, reasonable cultivation operation and pest control can also enhance the adaptability of crops to weather changes, the direct connection between the crop growth environment and external weather conditions can be partially isolated by utilizing a greenhouse or a greenhouse, the influence of the weather changes on crops is reduced, measures such as sunshade net, thermal insulation shed and the like are adopted to adjust illumination and temperature, and the method belongs to the category of human control,
for example, assuming that the predicted demand is a purchased amount of grain, the data monitoring module 3 will select data indexes equivalent to the purchased amount from the history data, including the supply amount of the supplier, the market price, seasonal factors, and the like. Wherein, assuming that the variable that overlaps most is the supply of the supplier, the seasonal factor, will be set as the first variable, while the remaining market price will be set as the second variable. The data monitoring module 3 monitors the value of the second variable and compares the value with the market price in the historical data, and the system can set an early warning index for detecting whether the market price deviates.
The system also comprises an early warning issuing module 4 which is used for issuing corresponding grain supply chain safety early warning information to an early warning center,
as shown in fig. 2, the present embodiment provides a trend early warning method, which includes the following steps:
s101: monitoring the change trend of the data index corresponding to the second variable and the historical data;
s102: judging whether the second variable has inverse potential change, wherein the inverse potential change refers to the change trend of the second variable deviating from the change trend of the corresponding data index;
s103: if yes, corresponding grain supply chain safety early warning information is issued to the early warning center, and if not, S101 is continuously executed.
The method carries out early warning by analyzing the variation trend of the second variable, the preset data is subjected to time sequence analysis or trend line fitting, the numerical variation of the second variable is observed, a corresponding trend early warning index is set, and when the trend of the second variable deviates from the early warning index, the early warning is triggered.
It is conceivable that the trend of change includes a homeotropic change and an inversion change, the homeotropic change and the inversion change need to be introduced into the data index corresponding to the second variable in the history data, no matter whether the value of the second variable increases or decreases, the system determines that the second variable is a homeotropic change when the second variable is close to the corresponding data index, the system determines that the inversion change when the second variable deviates from the corresponding data index, and in the trend early warning method, the early warning is triggered when the inversion change occurs to the second variable.
In one case, the second variable is the amount of fertilizer applied, exemplified by the amount of fertilizer applied by common crops, such as corn, at the sowing time, 20-30kg of nitrogen fertilizer, 20-30kg of phosphate fertilizer and 20-30kg of potash fertilizer per mu of land, and additional fertilizer applied during the growing period according to the crop requirements; for example, wheat, 20-30kg of nitrogen fertilizer, 20-30kg of phosphate fertilizer and 20-30kg of potash fertilizer are fertilized before sowing, and additional fertilization can be carried out in the tillering stage and the heading stage; the data gives a reference, in actual operation, the fertilizing amount at the current moment is compared with the fertilizing amount corresponding to the historical data, if the fertilizing amount at the current moment deviates from the fertilizing amount corresponding to the historical data, the early warning is triggered, for example, 20kg of nitrogen fertilizer, 20kg of phosphate fertilizer and 20kg of potash fertilizer are applied to each mu of land in the historical data, 25kg of nitrogen fertilizer, 25kg of phosphate fertilizer and 25kg of potash fertilizer are applied to each mu of land in preset data, the fertilizing amount needs to be reduced by 5kg respectively, and in the subsequent adjustment process, if the fertilizing amount is increased, the early warning is triggered as deviating from the historical data.
The early warning distribution module 4 will collect data related to the abnormal situation, such as the value of the second variable, the monitoring time, the degree of abnormality, etc. The generated early warning information includes, but is not limited to, identification of a second variable of the abnormality, time and place of occurrence of the abnormality, evaluation of the degree of abnormality. The early warning issuing module 4 can timely transmit the generated early warning information to an early warning center, and the early warning information is transmitted to related staff through a proper communication channel. The pre-warning center may take corresponding actions based on the received pre-warning information, such as adjusting a fertilization scheme, adjusting a purchase plan, coordinating suppliers, or re-assessing risk, etc.
The system further comprises an emergency response module, which is functional for generating a corresponding emergency plan,
after the early warning issuing module 4 issues the grain supply chain safety early warning information to the early warning center, the early warning center receives and analyzes the early warning information. If the early warning center or related staff confirms that a potential supply chain safety problem exists, the operation of the emergency response module 5 is triggered, the emergency response module 5 automatically generates a corresponding emergency plan according to the received early warning information, and the process can be based on predefined rules and strategies, or the emergency plan can be generated by using a machine learning algorithm and a decision model, and the generated emergency plan comprises, but is not limited to, description of emergency measures, responsibility division, resource allocation schemes, coordination and communication strategies, expected time schedules and targets.
Further, the emergency plan includes an adjustment scheme for the second variable to be changed to a corresponding data index, for example, corn, where the fertilizing amount at the current moment is: 20kg of nitrogen fertilizer, 20kg of phosphate fertilizer and 20kg of potassium fertilizer, wherein the corresponding fertilization amount in the historical data is as follows: 30kg of nitrogen fertilizer, 30kg of phosphate fertilizer and 30kg of potassium fertilizer, the emergency plan is to add 10kg of nitrogen fertilizer, 10kg of phosphate fertilizer and 10kg of potassium fertilizer.
Further, the emergency plan includes an adjustment scheme for the second variable to change to a corresponding data index, and the adjustment scheme further includes: setting a plurality of segmentation intervals, wherein the second variable gradually changes to the corresponding data index through the segmentation intervals.
Specifically, the plurality of segment intervals are used for adjusting the second variable gradually and homeotropically, and the emergency plan module can adjust the numerical value of the second variable gradually in each segment interval according to the second variable in the early warning information and the corresponding data index, so that the numerical value of the second variable gradually approaches the corresponding data index.
For example, the step of applying fertilizer is to divide the required nitrogen fertilizer, phosphate fertilizer and potassium fertilizer into a plurality of times, for example, adding a subsection interval in the emergency plan, and the first subsection: adding 5kg of nitrogen fertilizer, 5kg of phosphate fertilizer and 5kg of potassium fertilizer, and carrying out second segmentation: by adding 5kg of nitrogen fertilizer, 5kg of phosphate fertilizer and 5kg of potassium fertilizer, 20kg of nitrogen fertilizer, 20kg of phosphate fertilizer and 20kg of potassium fertilizer are added to 30kg of nitrogen fertilizer, 30kg of phosphate fertilizer and 30kg of potassium fertilizer through two segmented intervals.
Example two
As shown in fig. 3, this embodiment is substantially the same as the first embodiment, except that the inverse potential change of the second variable further includes:
if the second variable changes inversely, then:
s201: continuously monitoring the change trend of the second variable in an error interval;
s202: judging whether the value corresponding to the ending point of the error interval of the second variable is closer to the data index corresponding to the historical data than the value corresponding to the starting point of the second variable;
s203: if yes, regarding the inverse potential change as normal fluctuation of the second variable;
s204: if not, the corresponding grain supply chain safety early warning information is issued to the early warning center.
Specifically, the normal fluctuation range of the data represents the allowable variation amplitude of the data in a certain time or under a specific condition, the error interval is [ a, b ], a is the current moment, a certain time is included between a and b, and the variation trend of the second variable in the error interval [ a, b ] is detected from the moment a. In the first embodiment, if the second variable changes in inverse potential within the error interval [ a, b ], the early warning is triggered, in this embodiment, the value x of the second variable at the time a and the value y of the second variable at the time b are recorded first, in the historical data, the data index at the time a is x ', the data index at the time b is y', and if |y-y '| > |x-x' |, the early warning is triggered.
Example III
As shown in fig. 4, this embodiment is substantially the same as the first embodiment, except that the inverse potential change of the second variable further includes:
if the second variable is changed in inverse potential
S301: continuing to monitor the trend of the second change in the error interval,
s302: judging whether the second variable continuously changes in the homeotropic state or not and continuously changing the homeotropic state to the ending point of the error interval;
s303: if yes, regarding the inverse potential change as normal fluctuation of the second variable;
s304: if not, the corresponding grain supply chain safety early warning information is issued to the early warning center.
Specifically, the error interval is [ a, b ], a is the current time, a certain time is included between a and b, and a time c exists between a and b; starting from the time a, detecting the change trend of the second variable in the error interval [ a, b ]. In the first embodiment, if the second variable is in the error interval [ a, b ] and the inverse potential change occurs, the early warning is triggered, in this embodiment, if the second variable is in the interval [ a, c ] and the second variable is in the interval [ c, b ] and the second variable is in the forward potential change, the inverse potential change is regarded as the normal fluctuation of the second variable; the numerical values are as follows: in the history data, the data index at the time a is x ', the data index at the time c is z ', the data index at the time b is y ', and if |z ' | > x-x ' | and |z ' | > y-y ' | are the values at the time a, the value at the time c and the value at the time b of the second variable are z, the inverse potential change is regarded as normal fluctuation of the second variable.
By further observing whether the second variable has a homeotropic variation and continuously reaching the end point of the error interval, the system can screen the inversion variation and distinguish normal fluctuation from abnormal conditions, so that the accuracy and the reliability of early warning are improved.
Example IV
As shown in fig. 5, this embodiment is basically the same as the third embodiment, except that the homeotropic variation of the second variable within the error interval further includes:
s401: judging whether a starting point of the homeotropic variation of the second variable is positioned between the starting point of the error interval and the midpoint of the interval;
s402: if yes, regarding the inverse potential change as normal fluctuation of the second variable;
s403: if not, the corresponding grain supply chain safety early warning information is issued to the early warning center.
Specifically, the error interval is [ a, b ], a is the current time, a certain time is included between a and b, and a time c exists between a and b; starting from the time a, detecting the change trend of the second variable in the error interval [ a, b ]. In this embodiment, if the second variable is a reverse change in interval [ a, c ], a forward change in interval [ c, b ], and a < c < (a+b)/2, the reverse change is considered as a normal fluctuation of the second variable.
Therefore, the early warning accuracy can be further improved, the early warning can be triggered only when the abnormal situation really needs to be concerned, and corresponding measures can be taken in time to deal with potential risks and problems, so that the safety and stability of a grain supply chain are guaranteed.
Example five
The present embodiment is substantially the same as the first embodiment, except that the present embodiment provides a threshold early warning method that monitors the second variable based on a set threshold.
Specifically, the threshold is set based on a data index corresponding to the historical data, in one case, the second variable is a grain inventory level, and if the grain inventory level is lower than a certain threshold, the early warning of insufficient inventory is triggered.
Accordingly, the contingency plan is at least increased from the current time stock level to a threshold value.
Further, a segmentation interval is added in the emergency plan, and the first segmentation: taking the grains with the stock quantity a from a warehouse A; the second section: and B, taking the grains with the stock quantity from the warehouse B.
Specifically, as shown in fig. 6, the early warning method provided in this embodiment is as follows:
s501: setting a threshold value to obtain the grain stock quantity;
s502: judging whether the grain stock quantity is lower than the threshold value;
s503: if yes, corresponding grain supply chain safety early warning information is issued to the early warning center, and if not, S301 is continuously executed.
Example six
The embodiment is basically the same as the first embodiment, except that the artificial control variable in the first variable is monitored at the same time, and it can be understood that the first variable is an overlapped variable in preset data and history data at the current moment, that is, the first variable meets the preset demand at the current moment, but in practical application, the first variable has possibility of changing, the artificial control variable in the first variable is extracted and set as a third variable, and the third variable is monitored.
As shown in fig. 7, the early warning method provided in this embodiment is as follows:
s601: extracting an artificial control variable in the first variable, setting the artificial control variable as a third variable, monitoring the third variable, and setting an early warning index according to the third variable and historical data; it can be understood that the preset data are dynamic data, and the first variable and the second variable have the possibility of changing, and the first variable also has the possibility of deviating from the data index after being changed, so that the artificial control variable in the first variable is monitored.
S602: according to the monitoring condition and the early warning index, corresponding grain supply chain safety early warning information is issued to an early warning center;
s603: and generating a corresponding emergency plan according to the early warning information.
Example seven
As shown in fig. 8, the working method corresponding to the grain supply chain safety monitoring and early warning system based on big data analysis in the first embodiment includes the following working steps:
s701: capturing preset data of each link of a grain supply chain in a preset area, and integrating the preset data into a database;
s702: processing and analyzing the preset data, and obtaining the predicted demand of future grains through trend analysis on the historical data;
s703: screening historical data matched with the predicted demand, screening the historical data with the most variable overlapping, setting the overlapped variable in preset data as a first variable, setting the residual variable as a second variable, monitoring the second variable, and setting an early warning index according to the second variable and the historical data;
s704: according to the monitoring condition and the early warning index, corresponding grain supply chain safety early warning information is issued to an early warning center;
s705: and generating a corresponding emergency plan according to the early warning information.
The foregoing is merely a preferred embodiment of the invention, and it should be noted that modifications could be made by those skilled in the art without departing from the principles of the invention, which modifications would also be considered to be within the scope of the invention.
Claims (10)
1. A grain supply chain safety monitoring and early warning system based on big data analysis is characterized in that: comprising the following steps:
the data acquisition module is configured to capture preset data of each link of a grain supply chain in a preset area, and integrate the preset data into a database, wherein the preset data is dynamic data, the preset data comprises a plurality of variables, and the preset data is updated at preset frequency;
the data analysis module is configured to process and analyze the preset data and obtain the predicted demand of future grains by carrying out trend analysis on the historical data;
the data monitoring module is configured to screen historical data matched with the predicted demand, screen the historical data which is overlapped with the preset data variable most, set the variable overlapped with the historical data in the preset data as a first variable, set the remaining variable as a second variable, monitor the second variable and set an early warning index according to the second variable and the historical data;
the early warning issuing module is configured to issue corresponding grain supply chain safety early warning information to the early warning center according to the monitoring situation and the early warning index;
and the emergency response module is configured to generate a corresponding emergency plan according to the early warning information.
2. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 1, wherein:
the preset area at least comprises a grain production area, a grain reserve area, a grain transportation area and a grain sales area, and the preset data at least comprises production data, processing data, transportation and logistics data, sales and market data, quality and safety data, environment and meteorological data.
3. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 1, wherein: screening historical data matched with the preset requirement further comprises:
the historical data comprises a plurality of data indexes, the historical data represents the relation between the data indexes and the historical grain demand, and the historical data matched with the predicted demand is used as a first screening standard.
4. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 1, wherein:
the first variable comprises an artificial control variable and an uncontrollable variable, and the second variable is an artificial control variable.
5. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 1, wherein: the issuing of the corresponding grain supply chain safety early warning information to the early warning center further comprises:
and monitoring the change trend of the corresponding data index in the second variable and the historical data, and if the second variable is subjected to inverse potential change, issuing corresponding grain supply chain safety early warning information to an early warning center, wherein the early warning information comprises the current value of the second variable and the corresponding data index.
6. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 5, wherein: the inverse potential change of the second variable further comprises:
if the second variable is subjected to inverse potential change, continuing to monitor the change trend of the second variable in the error interval, if the value of the second variable corresponding to the ending point of the error interval is closer to the data index corresponding to the historical data than the value of the second variable corresponding to the starting point, regarding the inverse potential change as normal fluctuation of the second variable, and if the value of the second variable corresponding to the starting point of the error interval is closer to the data index corresponding to the historical data than the value of the second variable corresponding to the ending point, issuing corresponding grain supply chain safety early warning information to the early warning center.
7. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 5, wherein: the inverse potential change of the second variable further comprises:
if the second variable is subjected to inverse potential change, continuing to monitor the change trend of the second change in the error interval, and if the second variable is subjected to the orthotopic change in the error interval and the orthotopic change is continued to the end point of the error interval, regarding the inverse potential change as the normal fluctuation of the second variable, otherwise, issuing corresponding grain supply chain safety early warning information to an early warning center.
8. The big data analysis based food supply chain safety monitoring and early warning system according to claim 7, wherein: the second variable homeotropically varying within the error interval further comprises:
and if the starting point of the homeotropic variation of the second variable is positioned between the starting point of the error interval and the middle point of the interval, regarding the inversion variation as the normal fluctuation of the second variable, otherwise, issuing corresponding grain supply chain safety early warning information to an early warning center.
9. The big data analysis-based food supply chain safety monitoring and early warning system according to claim 1, wherein: the generating of the corresponding emergency plan according to the early warning information further comprises:
the emergency plan includes an adjustment plan for the second variable to change to a corresponding data index.
10. The big data analysis based food supply chain safety monitoring and early warning system according to claim 9, wherein: the adjustment scheme further includes:
setting a plurality of segmentation intervals, wherein the second variable gradually changes to the corresponding data index through the segmentation intervals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310703499.1A CN116702987A (en) | 2023-06-14 | 2023-06-14 | Grain supply chain safety monitoring and early warning system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310703499.1A CN116702987A (en) | 2023-06-14 | 2023-06-14 | Grain supply chain safety monitoring and early warning system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702987A true CN116702987A (en) | 2023-09-05 |
Family
ID=87830818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310703499.1A Pending CN116702987A (en) | 2023-06-14 | 2023-06-14 | Grain supply chain safety monitoring and early warning system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702987A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978313A (en) * | 2017-12-28 | 2019-07-05 | 航天信息股份有限公司 | A kind of method and system for the price monitoring wheat processing link |
| CN113469751A (en) * | 2021-07-21 | 2021-10-01 | 布瑞克农业大数据科技集团有限公司 | Agricultural product supply chain management method and system |
| CN116012720A (en) * | 2023-03-28 | 2023-04-25 | 航天万源云数据河北有限公司 | Crop growth condition monitoring method, device and medium based on high-resolution remote sensing image |
-
2023
- 2023-06-14 CN CN202310703499.1A patent/CN116702987A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978313A (en) * | 2017-12-28 | 2019-07-05 | 航天信息股份有限公司 | A kind of method and system for the price monitoring wheat processing link |
| CN113469751A (en) * | 2021-07-21 | 2021-10-01 | 布瑞克农业大数据科技集团有限公司 | Agricultural product supply chain management method and system |
| CN116012720A (en) * | 2023-03-28 | 2023-04-25 | 航天万源云数据河北有限公司 | Crop growth condition monitoring method, device and medium based on high-resolution remote sensing image |
Non-Patent Citations (1)
| Title |
|---|
| 吴赜书 等: "基于大数据和物联网的农产品供应链风险预警平台研究", 通信设计与应用, 31 July 2018 (2018-07-31), pages 47 - 48 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Durai et al. | Smart farming using machine learning and deep learning techniques | |
| US20210209705A1 (en) | System and Method for Managing and Operating an Agricultural-Origin-Product Manufacturing Supply Chain | |
| CN110134733B (en) | Land management system and method based on GIS system and big data analysis | |
| US11833313B2 (en) | Systems and methods for monitoring and regulating plant productivity | |
| US20180049364A1 (en) | Precision crop production-function models | |
| Lambert et al. | An expert system for predicting orchard yield and fruit quality and its impact on the Persian lime supply chain | |
| KR20150096103A (en) | Prediction Apparatus and Method for Yield of Agricultural Products | |
| Biswas | Importance of chat GPT in Agriculture: According to chat GPT | |
| CN108346069A (en) | A kind of agricultural product supply demand method for early warning and system | |
| Akulwar | A recommended system for crop disease detection and yield prediction using machine learning approach | |
| Sudduth et al. | AI down on the farm | |
| CN116361562A (en) | Knowledge recommendation method and system for agricultural industry Internet | |
| CN116702987A (en) | Grain supply chain safety monitoring and early warning system based on big data analysis | |
| US20220309595A1 (en) | System and Method for Managing and Operating an Agricultural-Origin-Product Manufacturing Supply Chain | |
| Ranjan et al. | Artificial intelligence applications in soil & crop management | |
| Gyamerah et al. | Crop yield probability density forecasting via quantile random forest and Epanechnikov Kernel function | |
| Mundada | Optimized Farming: Crop Recommendation System Using Predictive Analytics. | |
| CN113570240A (en) | Wisdom farm platform based on full life cycle management of crops | |
| Hernández-Cruz et al. | Layered decision environment for agricultural market intelligence | |
| Buklagin et al. | Digitalization of crop production: development trends | |
| CN112598533A (en) | Agricultural planting planning system based on internet | |
| Khatraty et al. | Smart Digital-Twin hub Concept for Rice yield prediction and monitoring from multivariate time series data | |
| Patki et al. | Application of Data Sampling for Crop Yield Prediction using Stochastic Gradient Descent Neural Networks | |
| CN111062554B (en) | Crop output management analysis system in output period | |
| Fondaj et al. | Proposal of Prediction Model for Smart Agriculture Based on IoT Sensor Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |