CN117350525A - Crop growth data management decision-making system based on artificial intelligence - Google Patents
Crop growth data management decision-making system based on artificial intelligence Download PDFInfo
- Publication number
- CN117350525A CN117350525A CN202311657796.3A CN202311657796A CN117350525A CN 117350525 A CN117350525 A CN 117350525A CN 202311657796 A CN202311657796 A CN 202311657796A CN 117350525 A CN117350525 A CN 117350525A
- Authority
- CN
- China
- Prior art keywords
- crop
- data
- value
- growth
- storage
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000013523 data management Methods 0.000 title claims abstract description 17
- 238000003860 storage Methods 0.000 claims abstract description 154
- 238000012544 monitoring process Methods 0.000 claims abstract description 84
- 238000007726 management method Methods 0.000 claims abstract description 63
- 238000003745 diagnosis Methods 0.000 claims abstract description 37
- 230000009546 growth abnormality Effects 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000013500 data storage Methods 0.000 claims abstract description 7
- 241000607479 Yersinia pestis Species 0.000 claims description 94
- 238000004458 analytical method Methods 0.000 claims description 74
- 238000001514 detection method Methods 0.000 claims description 67
- 230000002159 abnormal effect Effects 0.000 claims description 55
- 238000004364 calculation method Methods 0.000 claims description 42
- 239000002689 soil Substances 0.000 claims description 39
- 238000010606 normalization Methods 0.000 claims description 26
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 12
- 239000002881 soil fertilizer Substances 0.000 claims description 12
- 241000238631 Hexapoda Species 0.000 claims description 11
- 230000035558 fertility Effects 0.000 claims description 11
- 238000005286 illumination Methods 0.000 claims description 11
- 238000012797 qualification Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 239000000428 dust Substances 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000011835 investigation Methods 0.000 abstract description 4
- 206010016165 failure to thrive Diseases 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007334 memory performance Effects 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000004083 survival effect Effects 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/78—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure storage of data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Tourism & Hospitality (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Mining & Mineral Resources (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of crop supervision, and particularly relates to an artificial intelligence-based crop growth data management decision system which comprises an intelligent management platform, a crop growth period judging module, a crop growth abnormality evaluating module, a growth abnormality tracing diagnosis module and a background management and control end. According to the invention, the crop growth conditions of all monitoring points are analyzed through the crop growth abnormality assessment module, the crop growth abnormality conditions are accurately fed back, and the crop growth abnormality tracing diagnosis module is used for analyzing when a crop growth failure signal is generated, so that automatic investigation and diagnosis of the reasons of the crop growth abnormality are realized, the reasonable and rapid corresponding management and adjustment measures are facilitated, the smooth growth of crops is further ensured, and the subsequent crop yield is improved; and the risk supervision is carried out on all the storage modules through the storage decision-making module, the rapid and reasonable selection of the storage modules is realized, the safe proceeding of the data storage process is ensured, and the intelligent degree is high.
Description
Technical Field
The invention relates to the technical field of crop supervision, in particular to an artificial intelligence-based crop growth data management decision-making system.
Background
Crops refer to a wide variety of plants cultivated and harvested in agricultural production, including but not limited to food crops and cash crops. As one of the major food sources for humans, crops are critical to human survival and development. With the continuous progress of technology, the wide application of artificial intelligence technology in various fields brings new opportunities and challenges to the agricultural field.
In current agricultural production, although a large amount of crop growth data can be collected by some means, there are some management and decision-making dilemmas. In particular, there is currently no related system that can effectively monitor the crop growing area and accurately feed back abnormal conditions. This means that problems may not be found in time and corresponding adjustment measures may be taken at the time of decision management. Furthermore, when the crop grows abnormally, a technical means for automatically checking and diagnosing the reasons of the abnormality is lacking, which further increases the difficulty of crop management.
In order to solve the problems, advanced monitoring technologies such as remote sensing and image recognition can be introduced, and the real-time monitoring of the crop growing area is hopeful to be realized, so that potential problems can be found in time. However, in addition to monitoring and diagnostics, data management is also one of the challenges currently faced. The problems of storage of crop growth data and risk assessment are urgently to be solved.
Disclosure of Invention
According to the defects in the prior art, the invention provides the crop growth data management decision-making system based on artificial intelligence, which can accurately feed back the abnormal condition of crop growth, realize automatic investigation and diagnosis of the cause of abnormal crop growth, be beneficial to reasonably and quickly making corresponding management and adjustment measures, further ensure the smooth growth of crops and promote the subsequent crop yield.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the crop growth data management decision-making system based on artificial intelligence comprises an intelligent management platform, a crop growth period judging module, a crop growth abnormality evaluating module, a growth abnormality tracing diagnosis module and a background management and control end; the intelligent management platform acquires a crop growth area to be managed and marks the crop growth area as a growth area, the crop growth period judging module determines a crop growth period based on the growth characteristics and the crop appearance of crops in the growth area, and the crop growth period is sent to the crop growth abnormality evaluation module through the intelligent management platform;
the crop growth abnormality assessment module is used for arranging a plurality of monitoring points in a growth area, marking the corresponding monitoring points as t, wherein t is a natural number larger than 1; analyzing the crop growth conditions of all monitoring points, judging the abnormal crop growth conditions in a growth area, generating a crop growth disqualification signal or a crop growth qualification signal, transmitting the crop growth disqualification signal to a background management and control end and a growth abnormality traceability diagnosis module through an intelligent management platform, and displaying the signal by the background management and control end and sending out corresponding early warning;
when the growth abnormality tracing diagnosis module receives the crop growth disqualification signal, judging the crop growth abnormality reason of the growth area through analysis, generating an insect pest abnormality signal or a ring supervision abnormality signal according to the crop growth abnormality reason, and sending the insect pest abnormality signal or the ring supervision abnormality signal to a background management and control end through an intelligent management platform; and the background control receives the insect pest abnormal signal or the ring supervision abnormal signal, displays the insect pest abnormal signal or the ring supervision abnormal signal, and sends out corresponding early warning.
Further, the intelligent management platform is in communication connection with the storage decision module, and is in communication connection with a plurality of storage modules, and the storage modules store corresponding crop growth data; the storage decision module is used for acquiring all the storage modules, marking the corresponding storage modules as target storage blocks i, wherein i is a natural number larger than 1; performing safety supervision analysis on the target memory block i, generating a memory signal or a memory signal of the target memory block i according to the safety supervision analysis, and transmitting the memory signal and the corresponding target memory block i to a background management and control end through an intelligent management platform; and before data storage, all the storage modules are subjected to storage allocation decision analysis, so that the optimal storage blocks are determined, the optimal storage blocks are sent to an intelligent management platform, and the intelligent management platform sends corresponding crop growth data to the optimal storage blocks for storage.
Further, the specific analysis process of the safety supervision analysis is as follows:
acquiring the real-time temperature, the real-time humidity and the dust concentration of the environment where the target storage block i is positioned, performing difference calculation on the real-time temperature and a preset proper storage temperature value, taking an absolute value to obtain a storage temperature feedback value, acquiring a storage humidity feedback value in a similar way, and performing numerical calculation on the storage temperature feedback value, the storage humidity feedback value and the dust concentration to obtain a storage environment detection value; comparing the storage environment detection value with a preset storage environment detection threshold value, if the storage environment detection value exceeds the preset storage environment detection threshold value, judging that the target memory block i is in a negative feedback state of the ring table, and generating a risk signal of the target memory block i;
if the storage environment detection value does not exceed the preset storage environment detection threshold value, acquiring the total duration of the target memory block i in the loop table negative feedback state in the history operation process, marking the total duration as a loop negative feedback value, calculating the time difference between the current date and the date of the target memory block i when the target memory block i is put into use, and obtaining the storage duration; setting a storage detection period with a time length of L1, collecting the memory debugging efficiency data and the memory debugging non-response frequency of a target memory block i in the storage detection period, and carrying out numerical calculation on a loop negative feedback time value, the storage time length, the memory debugging efficiency data and the memory debugging non-response frequency of the target memory block i to obtain a memory block supervision decision value;
comparing the memory block supervision decision value with a preset memory block supervision decision threshold value in a numerical mode, and generating a risk signal of the target memory block i if the memory block supervision decision value exceeds the preset memory block supervision decision threshold value; and if the memory block supervision decision value does not exceed the preset memory block supervision decision threshold, generating a memory security signal of the target memory block i.
Further, the specific analysis process of the storage allocation decision analysis is as follows:
all the storage modules corresponding to the storage security signals are obtained in real time, and the corresponding storage modules are marked as storage blocks to be distributed; obtaining the memory block supervision decision values of all the memory blocks to be allocated, sequencing all the memory blocks to be allocated according to the sequence from small to large of the values of the memory block supervision decision values, and marking the first third of the memory blocks to be allocated as primary memory blocks;
collecting the residual storage space data of the corresponding primary storage block, collecting the distance between the corresponding primary storage block and the intelligent management platform, marking the distance as a storage transmission distance table value, obtaining the model of the corresponding primary storage block, presetting a group of storage values corresponding to the storage modules of each model respectively, and calling the storage value corresponding to the primary storage block based on the model of the primary storage block;
performing numerical calculation on a memory block supervision decision value, residual memory space data, a memory transmission distance table value and a memory value corresponding to the initially selected memory block, and marking a numerical calculation result as a memory allocation decision value; and sorting according to the order of the values of the memory allocation values from small to large, and marking the first selected memory block positioned at the first position as the optimal memory block.
Further, the specific operation process of the crop growth abnormality assessment module comprises the following steps:
setting a growth monitoring period with the day of T1, collecting the heights of crops at a monitoring point T on the starting date and the ending date of the growth monitoring period, marking the heights as first crop height data and last crop height data respectively, and subtracting the first crop height data from the last crop height data to obtain crop height increasing data; the leaf color deviation data of the crops at the monitoring point t are collected, and the crop heightening data, the crop last height data and the leaf color deviation data are subjected to numerical calculation to obtain crop expression data;
establishing crop expression sets from crop expression data of all monitoring points, and carrying out mean value calculation and variance calculation on the crop expression sets to obtain crop table average data and crop table difference data; respectively carrying out numerical comparison on the crop surface average data and the crop surface difference data and a preset crop surface average data threshold value and a crop surface difference data threshold value corresponding to the crop growth period, and generating a crop growth qualification signal if the crop surface average data exceeds the preset crop surface average data threshold value and the crop surface difference data does not exceed the preset crop surface difference data threshold value; if the crop surface average data does not exceed the preset crop surface average data threshold value and the crop surface difference data does not exceed the preset crop surface difference data threshold value, generating a crop growth disqualification signal; and carrying out point-by-point evaluation normalization analysis on the rest conditions.
Further, the specific analysis procedure for evaluating the normalized analysis point by point is as follows:
the crop expression data of the monitoring point t is compared with a preset crop expression data threshold value corresponding to the crop growth period, if the crop expression data does not exceed the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point, and if the crop expression data exceeds the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point;
calculating the ratio of the number of the growth abnormal points to the number of the growth non-abnormal points to obtain a growth abnormal number detection value, and marking the crop expression data with the smallest value as a low crop amplitude value; carrying out normalization calculation on the growth abnormal number detection value, the crop low amplitude value and the crop table average data to obtain a growth normalization coefficient; comparing the growth normalization coefficient with a preset growth normalization coefficient threshold value in a numerical value mode, and generating a crop growth disqualification signal if the growth normalization coefficient exceeds the preset growth normalization coefficient threshold value; and if the growth normalization coefficient does not exceed the preset growth normalization coefficient threshold value, generating a crop growth qualification signal.
Further, the specific operation process of the growth abnormality traceability diagnosis module comprises the following steps:
monitoring and pest trapping are carried out on all monitoring points to determine the types of pests in a growing area, the number of monitoring points distributed by the pests of the corresponding types in the growing area is collected and marked as pest distribution detection values, the pest distribution detection values are compared with preset pest distribution detection thresholds in numerical values, and if the pest distribution detection values exceed the preset pest distribution detection thresholds, the pests of the corresponding types are marked as high-coverage pests; if the high coverage rate pests exist in the growing area, generating a pest anomaly signal;
if the high coverage rate pests do not exist in the growing area, a group of preset damage causing values corresponding to each type of pests are preset, pest distribution detecting values of the corresponding type of pests are multiplied by the corresponding preset damage causing values, and the multiplied values are marked as pest influence evaluating values; and carrying out summation calculation on pest influence evaluation values of all pests in the growing area to obtain a pest diagnosis value, carrying out numerical comparison on the pest diagnosis value and a preset pest diagnosis threshold value, and generating a pest abnormality signal if the pest diagnosis value exceeds the preset pest diagnosis threshold value.
Further, if the pest diagnosis value does not exceed the preset pest diagnosis threshold value, the first analysis value and the second analysis value of the corresponding date are obtained through ring supervision decision analysis, the first analysis value and the second analysis value of the corresponding date are respectively compared with the preset first analysis value and the preset second analysis value, and if the first analysis value and the second analysis value exceed the corresponding preset threshold value, the corresponding date is marked as a inferior supervision date; if the first analysis value and the second analysis value do not exceed the corresponding preset threshold values, marking the corresponding date as a superior supervision day, and marking the corresponding date as a good supervision day in the other cases;
the method comprises the steps of obtaining the number of inferior supervision days, the number of good supervision days and the number of superior supervision days in a growth monitoring period, marking the numbers of inferior supervision days, the number of good supervision days and the number of superior supervision days as an inferior detection japanese table value, a good supervision japanese table value and a superior supervision japanese table value respectively, and carrying out numerical calculation on the inferior detection japanese table value, the good supervision japanese table value and the superior supervision japanese table value to obtain an environmental monitoring early warning value; and comparing the ring monitoring early warning value with a preset ring monitoring early warning threshold value, and generating a ring monitoring abnormal signal if the ring monitoring early warning value exceeds the preset ring monitoring early warning threshold value.
Further, the specific analysis process of the ring supervision decision analysis is as follows:
acquiring daily illumination time length data, illumination intensity data and temperature difference data in a growth monitoring period, carrying out difference value calculation on the temperature difference data and a median value of a preset proper temperature difference range corresponding to the crop growth period, taking an absolute value to obtain temperature difference deviation data, acquiring light intensity deviation data in a similar way, and carrying out numerical calculation on the illumination time length data, the temperature difference deviation data and the light intensity deviation data to obtain a ring analysis initial detection value corresponding to the date;
collecting soil fertility data, soil temperature data and soil humidity data of a monitoring point t, calculating a difference value between the soil fertility data and a median value of a preset proper soil fertility range corresponding to a crop growth period, taking an absolute value to obtain soil fertilizer deviation data, and obtaining the soil temperature deviation data and the soil humidity deviation data in a similar way; carrying out average value calculation on the soil fertilizer deviation data of all the monitoring points to obtain soil fertilizer deviation average data of corresponding dates, and similarly obtaining soil temperature deviation average data and soil humidity deviation average data of corresponding dates; and carrying out numerical calculation on the soil fertilizer bias average data, the soil temperature bias average data and the soil humidity bias average data to obtain a ring analysis recheck value of a corresponding date.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, a plurality of monitoring points are distributed in a growth area through the crop growth abnormality assessment module, crop growth conditions of all the monitoring points are analyzed, crop growth disqualification signals or crop growth qualification signals are generated according to the monitoring points, a manager can grasp the crop growth abnormality in detail, and corresponding management measures can be adjusted more quickly and timely, so that normal growth of crops is ensured; and when the unqualified signal of crop growth is generated, the abnormal crop growth cause of the growth area is analyzed and judged through the abnormal growth tracing diagnosis module, so that the automatic investigation and diagnosis of the abnormal crop growth cause are realized, the reasonable and rapid corresponding management and adjustment measures are facilitated, the smooth growth of crops is further ensured, and the subsequent crop yield is improved.
2. According to the invention, all storage modules for storing related crop growth data are obtained through the storage decision-making module, and are subjected to safety supervision analysis, so that a storage safety signal or a storage risk signal of the corresponding storage module is generated, the storage risk signal is sent to a background management and control end through the intelligent management platform, and management staff can check the corresponding storage modules in time to ensure the storage safety of the crop growth data; and before data storage, all the storage modules are subjected to storage allocation decision analysis to determine the optimal storage blocks, and the intelligent management platform sends corresponding crop growth data to the optimal storage blocks for storage, so that the storage modules are quickly and reasonably selected, the safe implementation of the data storage process is ensured, and the intelligent degree is high.
Drawings
FIG. 1 is a system block diagram of a first embodiment of the present invention;
fig. 2 is a system block diagram of the second and third embodiments of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Embodiment one: as shown in fig. 1, the crop growth data management decision system based on artificial intelligence provided by the invention comprises an intelligent management platform, a crop growth period judging module, a crop growth abnormality evaluating module, a growth abnormality tracing diagnosis module and a background management and control end; the intelligent management platform acquires a crop growth area to be managed and marks the crop growth area as a growth area, the crop growth period judging module determines a crop growth period based on the growth characteristics and the crop appearance of crops in the growth area, and the crop growth period is sent to the crop growth abnormality evaluation module through the intelligent management platform.
The crop growth abnormality assessment module is used for arranging a plurality of monitoring points in a growth area, marking the corresponding monitoring points as t, wherein t is a natural number larger than 1; analyzing the growth conditions of crops at all monitoring points, judging the abnormal growth conditions of crops in a growth area, generating a crop growth disqualification signal or a crop growth qualification signal, and sending the crop growth disqualification signal to a background management and control end and a growth abnormality traceability diagnosis module through an intelligent management platform, wherein the background management and control end displays the signal and sends out corresponding early warning so that management personnel can master the abnormal growth conditions of crops in the growth area in time; the specific operation process of the crop growth abnormality assessment module is as follows:
setting a growth monitoring period of T1 days, preferably, T1 is twenty-five days; the crop height of the crops at the monitoring point t on the starting date and the ending date of the growth monitoring period is collected and marked as first crop height data and last crop height data respectively, and the first crop height data is subtracted from the last crop height data to obtain crop height increasing data; the leaf color deviation data of the crops at the monitoring point t are collected, and the crop heightening data NFt, the crop last height data NGt and the leaf color deviation data NYt are subjected to numerical calculation through the formula NZt =sd1× NFt +sd2× NGt +sd3/NYt to obtain crop expression data NZt; wherein sd1, sd2, sd3 are preset proportionality coefficients, sd3 > sd1 > sd2 > 0; and, the larger the value of the crop expression data NZt, the better the crop growth condition at the monitoring point t.
Establishing crop expression sets from crop expression data of all monitoring points, and carrying out mean value calculation and variance calculation on the crop expression sets to obtain crop table average data and crop table difference data; respectively comparing the crop surface average data and the crop surface difference data with a preset crop surface average data threshold value and a crop surface difference data threshold value corresponding to the crop growth period, and generating a crop growth qualification signal if the crop surface average data exceeds the preset crop surface average data threshold value and the crop surface difference data does not exceed the preset crop surface difference data threshold value, which indicates that the overall crop growth condition of a growth area is good; if the crop surface average data does not exceed the preset crop surface average data threshold value and the crop surface difference data does not exceed the preset crop surface difference data threshold value, indicating that the overall crop growth condition of the growth area is poor, generating a crop growth disqualification signal.
The other conditions are subjected to point-by-point evaluation normalization analysis, specifically: the crop expression data of the monitoring point t is compared with a preset crop expression data threshold value corresponding to the crop growth period, if the crop expression data does not exceed the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point, and if the crop expression data exceeds the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point; and calculating the ratio of the number of the growth abnormal points to the number of the growth non-abnormal points to obtain a growth abnormal number detection value, and marking the crop expression data with the smallest numerical value in the crop expression set as a crop low-amplitude value.
The growth abnormal number detection value ZDt, the crop low amplitude value ZWt and the crop table average data ZRt are normalized by the formula ZGt = (tg 1 x ZDt +tg2)/(tg 2 x ZWt +tg3 x ZRt) to obtain a growth normalization coefficient ZGt; wherein tg1, tg2 and tg3 are preset proportional coefficients, and values of tg1, tg2 and tg3 are all larger than zero; and, the larger the value of the growth normalization coefficient ZGt, the worse the crop growth condition of the growth area as a whole.
Comparing the growth normalization coefficient ZGt with a preset growth normalization coefficient threshold value, and if the growth normalization coefficient ZGt exceeds the preset growth normalization coefficient threshold value, indicating that the overall crop growth condition of the growth area is poor, generating a crop growth disqualification signal; if the growth normalization coefficient ZGt does not exceed the preset growth normalization coefficient threshold, indicating that the crop growth condition of the growth area is overall better, generating a crop growth qualification signal.
When the growth abnormality tracing diagnosis module receives the crop growth disqualification signal, judging the crop growth abnormality reason of the growth area through analysis, generating an insect pest abnormality signal or a ring supervision abnormality signal according to the crop growth abnormality reason, and sending the insect pest abnormality signal or the ring supervision abnormality signal to a background management and control end through an intelligent management platform; the background control device displays the pest abnormal signal or the ring monitoring abnormal signal when receiving the pest abnormal signal and sends out corresponding early warning, corresponding deinsectization treatment should be carried out in time when receiving the pest abnormal signal, corresponding improvement measures should be carried out in time when receiving the ring monitoring abnormal signal, such as reasonable adjustment of the times of fertilization and irrigation, interval duration and the like, so that smooth growth of crops is guaranteed, and the subsequent crop yield is improved; the specific operation process of the growth abnormality traceability diagnosis module is as follows:
monitoring and pest trapping are carried out on all monitoring points to determine the types of pests in a growing area, the number of monitoring points distributed by the pests of the corresponding types in the growing area is collected and marked as pest distribution detection values, the pest distribution detection values are compared with preset pest distribution detection thresholds, if the pest distribution detection values exceed the preset pest distribution detection thresholds, the pests of the corresponding types are indicated to be distributed widely in the growing area, and the pests of the corresponding types are marked as high-coverage pests; if there is a high coverage pest in the growing area, a pest anomaly signal is generated.
If the high coverage rate pests do not exist in the growing area, each type of pest is preset to correspond to a group of preset damage values, wherein the values of the preset damage values are all larger than zero and preset by a manager, and the larger the adverse effect of the corresponding type of pest on crops is, the larger the value of the preset damage value matched with the corresponding type of pest is; multiplying the pest distribution detection value of the corresponding species of pests with a corresponding preset damage causing value, and marking the product value as a pest influence evaluation value; and carrying out summation calculation on pest influence evaluation values of all pests in the growing area to obtain a pest diagnosis value, carrying out numerical comparison on the pest diagnosis value and a preset pest diagnosis threshold value, and generating a pest abnormality signal if the pest diagnosis value exceeds the preset pest diagnosis threshold value, which indicates that the possibility of abnormal crop growth caused by pests is high.
Further, if the pest diagnosis value does not exceed the preset pest diagnosis threshold, the preliminary analysis value and the recheck value of the ring analysis on the corresponding date are obtained through ring monitoring decision analysis, specifically: collecting illumination time length data, illumination intensity data and temperature difference data of each day in a growth monitoring period, wherein the illumination intensity data is a data value representing the average illumination intensity of the same day, and the temperature difference data is a data value representing the difference value of the highest temperature and the lowest temperature of the same day; and calculating the difference value between the temperature difference data and the median value of the preset proper temperature difference range corresponding to the growth period of the crops, taking the absolute value to obtain temperature difference deviation data, and obtaining light intensity deviation data in a similar way.
Numerical calculation is carried out on the illumination duration data GS, the temperature difference deviation data GK and the light intensity deviation data GY through a formula RG= (fp2+fp3+GY)/(fp1+GS+0.637) to obtain a ring analysis initial detection value RG of a corresponding date; wherein fp1, fp2 and fp3 are preset proportionality coefficients, and the values of fp1, fp2 and fp3 are all larger than zero; and, the larger the value of the preliminary analysis value RG, the worse the environmental performance of the growing area of the crops on the corresponding date, the more unfavorable the growth of the crops.
Soil fertility data, soil temperature data and soil humidity data of a monitoring point t are collected, wherein the soil fertility data are data magnitude values representing the content and the value of nitrogen, phosphorus and potassium elements in soil; calculating the difference value between the soil fertility data and the median value of the preset suitable soil fertility range corresponding to the crop growth period, and taking the absolute value to obtain soil fertility deviation data, and obtaining soil temperature deviation data and soil humidity deviation data in a similar way; and carrying out average calculation on the soil fertilizer deviation data of all the monitoring points to obtain soil fertilizer deviation average data of corresponding dates, and similarly obtaining soil temperature deviation average data and soil humidity deviation average data of corresponding dates.
Numerical calculation is carried out on the soil fertilizer bias average data GT, the soil temperature bias average data GD and the soil moisture bias average data GW through the formula RZ=eq1, GT+eq2, GD+eq3, so as to obtain a ring analysis recheck value RZ of a corresponding date; wherein, eq1, eq2, eq3 are preset weight coefficients, eq1 > eq2 > eq3 > 1; and the numerical value of the ring analysis re-detection value RZ is in a direct proportion relation with soil fertilizer bias average data GT, soil temperature bias average data GD and soil humidity bias average data GW, and the larger the numerical value of the ring analysis re-detection value RZ is, the worse the soil performance condition of a corresponding date growing area is, and the normal growth of crops is not facilitated.
Respectively carrying out numerical comparison on a ring analysis initial detection value RG and a ring analysis re-detection value RZ of corresponding dates, a preset ring analysis initial detection threshold value and a preset ring analysis re-detection threshold value, and marking the corresponding dates as inferior supervision days if the ring analysis initial detection value RG and the ring analysis re-detection value RZ exceed the corresponding preset threshold values; if the ring analysis initial detection value RG and the ring analysis re-detection value RZ do not exceed the corresponding preset threshold values, marking the corresponding date as a good-level supervision day, and marking the corresponding date as a good-level supervision day under the other conditions; the number of inferior supervision days, the number of good supervision days and the number of superior supervision days in the growth monitoring period are obtained and marked as an inferior detection daily value, a good supervision daily value and a superior supervision daily value respectively.
Carrying out numerical calculation on the inferior detection Japanese table value HR1, the good supervision Japanese table value HR2 and the good supervision Japanese table value HR3 through a formula HY= (kw1+kw2)/(kw3+kw1+kw2) to obtain an environmental supervision early warning value HY; wherein, kw1 > kw2 > kw3 > 0; moreover, the larger the numerical value of the ring monitoring early warning value HY is, the worse the condition of the crop growth environment in the growth monitoring period is indicated; and comparing the ring monitoring early warning value HY with a preset ring monitoring early warning threshold value, and generating a ring monitoring abnormal signal if the ring monitoring early warning value HY exceeds the preset ring monitoring early warning threshold value, which indicates that the possibility of abnormal crop growth caused by environmental reasons is high.
Embodiment two: as shown in fig. 2, the difference between the present embodiment and embodiment 1 is that the intelligent management platform is communicatively connected to the storage decision module, and the intelligent management platform is communicatively connected to a plurality of storage modules, which store the corresponding crop growth data; the storage decision module acquires all the storage modules, marks the corresponding storage module as a target storage block i, and i is a natural number larger than 1; performing safety supervision analysis on the target memory block i to generate a memory signal or a memory signal of the target memory block i, sending the memory signal and the corresponding target memory block i to a background management and control end through an intelligent management platform, sending out corresponding early warning when the background management and control end receives the memory signal, checking the corresponding memory module in time by a manager, and taking corresponding improvement measures, so that the storage safety of the related crop growth data is guaranteed; the specific analysis process of the safety supervision analysis is as follows:
acquiring the real-time temperature, the real-time humidity and the dust concentration of the environment where the target storage block i is positioned, performing difference calculation on the real-time temperature and a preset proper storage temperature value, taking an absolute value to obtain a storage temperature feedback value, acquiring a storage humidity feedback value in a similar way, and performing numerical calculation on the storage temperature feedback value XFi, the storage humidity feedback value XSi and the dust concentration XTi through a formula XKi =ed1x XFi +ed2 x XSi+ed3 x XTi to obtain a storage environment detection value XKi; wherein, ed1, ed2 and ed3 are preset weight coefficients, and the values of ed1, ed2 and ed3 are all larger than zero; and, the larger the value of the storage environment detection value XKi, the larger the current running risk of the target memory block i is indicated.
Comparing the storage environment detection value XKi with a preset storage environment detection threshold value, if the storage environment detection value XKi exceeds the preset storage environment detection threshold value, judging that the target memory block i is in a loop table negative feedback state, generating a risk signal of the target memory block i, and checking the target memory block i in time and performing corresponding regulation and control operation to reduce the storage risk; if the storage environment detection value XKi does not exceed the preset storage environment detection threshold, acquiring the total duration of the target memory block i in the loop table negative feedback state in the history operation process, marking the total duration as a loop negative feedback value, calculating the time difference between the current date and the date of the target memory block i when the target memory block i is in use, and obtaining the storage duration.
Setting a storage detection period with a duration of L1, wherein L1 is preferably fifteen days; the method comprises the steps of collecting memory debugging efficiency data and memory debugging non-response frequency of a target memory block i in a memory detection period, wherein the memory debugging efficiency data is a data magnitude indicating the average speed of data memory debugging in the memory detection period, and the memory debugging non-response frequency is a data magnitude indicating the number of times of data memory failure and data memory debugging in the memory detection period; the larger the value of the memory modulation efficiency data and the smaller the value of the memory modulation non-response frequency, the better the memory performance condition of the corresponding target memory block i is indicated.
By the formulaPerforming numerical calculation on a loop negative feedback value HFi, a storage time length HSi, memory modulation efficiency data HXi and memory modulation non-response frequency HWi of a target memory block i to obtain a memory block supervision decision value CYi; wherein tf1, tf2, tf3, tf4 are preset proportionality coefficients, tf3 > tf4 > tf1 > tf2 > 0; and, the larger the value of the memory block supervision decision value CYi, the larger the storage risk of the corresponding target memory block i.
Comparing the memory block supervision decision value CYi with a preset memory block supervision decision threshold value, and if the memory block supervision decision value CYi exceeds the preset memory block supervision decision threshold value, indicating that the storage risk of the corresponding target memory block i is large, and timely carrying out data backup and checking optimization or elimination replacement are needed, generating a risk storage signal of the target memory block i; if the memory block supervision decision value CYi does not exceed the preset memory block supervision decision threshold, which indicates that the memory risk of the corresponding target memory block i is smaller, generating a memory security signal of the target memory block i.
Embodiment III: as shown in fig. 2, the difference between the present embodiment and embodiments 1 and 2 is that the storage decision module is further configured to perform storage allocation decision analysis on all storage modules before performing data storage, so as to determine an optimal storage block, and send the optimal storage block to the intelligent management platform, where the intelligent management platform sends corresponding crop growth data to the optimal storage block for storage, so that quick and reasonable selection of the storage modules is achieved, which is helpful for ensuring safe performance of the data storage process, and has high intelligent degree; the specific analysis process of the storage allocation decision analysis is as follows:
all the storage modules corresponding to the storage security signals are obtained in real time, and the corresponding storage modules are marked as storage blocks to be distributed; obtaining the memory block supervision decision values of all the memory blocks to be allocated, sequencing all the memory blocks to be allocated according to the sequence from small to large of the values of the memory block supervision decision values, and marking the first third of the memory blocks to be allocated as primary memory blocks; and collecting the residual storage space data corresponding to the primary storage block, and collecting the distance between the corresponding primary storage block and the intelligent management platform and marking the distance as a storage transmission distance table value.
The method comprises the steps of obtaining the model corresponding to a primary selected memory block, and presetting a group of memory values corresponding to each type of memory module, wherein the memory values are larger than zero and preset by a manager, and the memory performance of the memory module corresponding to the model is better, the value of the memory value matched with the memory module is larger; and calling the memory value corresponding to the model of the initially selected memory block.
By the formulaPerforming numerical calculation on a memory block supervision decision value CYi, remaining memory space data CKi, a memory transmission distance table value CJi and a memory value CWi of the corresponding primary selected memory block, and marking a numerical calculation result as a memory allocation decision value CPi; wherein a1, a2, a3 and a4 are preset proportionality coefficients, and the values of a1, a2, a3 and a4 are all larger than zero; and, the smaller the value of the allocation decision value CPi, the more the storage risk of the corresponding primary selection storage block is indicatedThe smaller the more suitable the current storage operation is to be performed; and sequencing all the primary selected memory blocks according to the sequence of the values of the memory allocation values from small to large, and marking the primary selected memory block positioned at the first position as the optimal memory block.
The working principle of the invention is as follows: when the crop growth abnormal assessment system is used, a plurality of monitoring points are distributed in a growth area through the crop growth abnormal assessment module, crop growth conditions of all the monitoring points are analyzed, abnormal crop growth conditions in the growth area are judged, and crop growth disqualification signals or crop growth qualification signals are generated, so that management staff can master the abnormal crop growth conditions in the growth area in detail, corresponding management measures can be adjusted more quickly and timely, and normal growth of crops is guaranteed; and when the unqualified signal of crop growth is generated, the abnormal cause of crop growth in the growth area is analyzed and judged through the abnormal trace of growth diagnostic module, so that the abnormal signal of insect damage or abnormal signal of ring supervision is generated, the automatic investigation and diagnosis of the abnormal cause of crop growth is realized, the corresponding management and adjustment measures are reasonably and quickly made, the smooth growth of crops is ensured, the subsequent crop yield is improved, and the intelligent degree is high.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
Claims (9)
1. The crop growth data management decision-making system based on artificial intelligence is characterized by comprising an intelligent management platform, a crop growth period judging module, a crop growth abnormality assessment module, a growth abnormality tracing diagnosis module and a background management and control end; the intelligent management platform acquires a crop growth area to be managed and marks the crop growth area as a growth area, the crop growth period judging module determines a crop growth period based on the growth characteristics and the crop appearance of crops in the growth area, and the crop growth period is sent to the crop growth abnormality evaluation module through the intelligent management platform;
the crop growth abnormality assessment module is used for arranging a plurality of monitoring points in a growth area, marking the corresponding monitoring points as t, wherein t is a natural number larger than 1; analyzing the crop growth conditions of all monitoring points, judging the abnormal crop growth conditions in a growth area, generating a crop growth disqualification signal or a crop growth qualification signal, transmitting the crop growth disqualification signal to a background management and control end and a growth abnormality traceability diagnosis module through an intelligent management platform, and displaying the signal by the background management and control end and sending out corresponding early warning;
when the growth abnormality tracing diagnosis module receives the crop growth disqualification signal, judging the crop growth abnormality reason of the growth area through analysis, generating an insect pest abnormality signal or a ring supervision abnormality signal according to the crop growth abnormality reason, and sending the insect pest abnormality signal or the ring supervision abnormality signal to a background management and control end through an intelligent management platform; and the background control receives the insect pest abnormal signal or the ring supervision abnormal signal, displays the insect pest abnormal signal or the ring supervision abnormal signal, and sends out corresponding early warning.
2. The artificial intelligence-based crop growth data management decision system according to claim 1, wherein the intelligent management platform is in communication connection with the storage decision module, and the intelligent management platform is in communication connection with a plurality of storage modules, and the storage modules store corresponding crop growth data; the storage decision module is used for acquiring all the storage modules, marking the corresponding storage modules as target storage blocks i, wherein i is a natural number larger than 1;
performing safety supervision analysis on the target memory block i, generating a memory signal or a memory signal of the target memory block i according to the safety supervision analysis, and transmitting the memory signal and the corresponding target memory block i to a background management and control end through an intelligent management platform; and before data storage, all the storage modules are subjected to storage allocation decision analysis, so that the optimal storage blocks are determined, the optimal storage blocks are sent to an intelligent management platform, and the intelligent management platform sends corresponding crop growth data to the optimal storage blocks for storage.
3. The artificial intelligence based crop growth data management decision system of claim 2, wherein the specific analysis process of the safety supervision analysis is as follows:
acquiring the real-time temperature, the real-time humidity and the dust concentration of the environment where the target storage block i is positioned, performing difference calculation on the real-time temperature and a preset proper storage temperature value, taking an absolute value to obtain a storage temperature feedback value, acquiring a storage humidity feedback value in a similar way, and performing numerical calculation on the storage temperature feedback value, the storage humidity feedback value and the dust concentration to obtain a storage environment detection value; if the storage environment detection value exceeds a preset storage environment detection threshold value, judging that the target memory block i is in a loop table negative feedback state, and generating a risk signal of the target memory block i;
if the storage environment detection value does not exceed the preset storage environment detection threshold value, acquiring the total duration of the target memory block i in the loop table negative feedback state in the history operation process, marking the total duration as a loop negative feedback value, calculating the time difference between the current date and the date of the target memory block i when the target memory block i is put into use, and obtaining the storage duration; setting a storage detection period with a time length of L1, collecting the memory debugging efficiency data and the memory debugging non-response frequency of a target memory block i in the storage detection period, and carrying out numerical calculation on a loop negative feedback time value, the storage time length, the memory debugging efficiency data and the memory debugging non-response frequency of the target memory block i to obtain a memory block supervision decision value;
if the memory block supervision decision value exceeds a preset memory block supervision decision threshold, generating a memory risk signal of the target memory block i; and if the memory block supervision decision value does not exceed the preset memory block supervision decision threshold, generating a memory security signal of the target memory block i.
4. The artificial intelligence based crop growth data management decision system of claim 2, wherein the specific analysis process of the storage allocation decision analysis is as follows:
all the storage modules corresponding to the storage security signals are obtained in real time, and the corresponding storage modules are marked as storage blocks to be distributed; obtaining the memory block supervision decision values of all the memory blocks to be allocated, sequencing all the memory blocks to be allocated according to the sequence from small to large of the values of the memory block supervision decision values, and marking the first third of the memory blocks to be allocated as primary memory blocks;
collecting the residual storage space data of the corresponding primary storage block, collecting the distance between the corresponding primary storage block and the intelligent management platform, marking the distance as a storage transmission distance table value, obtaining the model of the corresponding primary storage block, presetting a group of storage values corresponding to the storage modules of each model respectively, and calling the storage value corresponding to the primary storage block based on the model of the primary storage block;
performing numerical calculation on a memory block supervision decision value, residual memory space data, a memory transmission distance table value and a memory value corresponding to the initially selected memory block, and marking a numerical calculation result as a memory allocation decision value; and sorting according to the order of the values of the memory allocation values from small to large, and marking the first selected memory block positioned at the first position as the optimal memory block.
5. The artificial intelligence based crop growth data management decision system of claim 1, wherein the specific operation of the crop growth anomaly evaluation module comprises:
setting a growth monitoring period with the day of T1, collecting the heights of crops at a monitoring point T on the starting date and the ending date of the growth monitoring period, marking the heights as first crop height data and last crop height data respectively, and subtracting the first crop height data from the last crop height data to obtain crop height increasing data; the leaf color deviation data of the crops at the monitoring point t are collected, and the crop heightening data, the crop last height data and the leaf color deviation data are subjected to numerical calculation to obtain crop expression data;
establishing crop expression sets from crop expression data of all monitoring points, and carrying out mean value calculation and variance calculation on the crop expression sets to obtain crop table average data and crop table difference data; if the crop surface average data exceeds a preset crop surface average data threshold value and the crop surface difference data does not exceed a preset crop surface difference data threshold value, generating a crop growth qualification signal; if the crop surface average data does not exceed the preset crop surface average data threshold value and the crop surface difference data does not exceed the preset crop surface difference data threshold value, generating a crop growth disqualification signal; and carrying out point-by-point evaluation normalization analysis on the rest conditions.
6. The artificial intelligence based crop growth data management decision system of claim 5, wherein the specific analysis process of the point-wise evaluation normalization analysis is as follows:
the crop expression data of the monitoring point t is compared with a preset crop expression data threshold value corresponding to the crop growth period, if the crop expression data does not exceed the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point, and if the crop expression data exceeds the preset crop expression data threshold value, the monitoring point t is marked as a growth abnormal point;
calculating the ratio of the number of the growth abnormal points to the number of the growth non-abnormal points to obtain a growth abnormal number detection value, and marking the crop expression data with the smallest value as a low crop amplitude value; carrying out normalization calculation on the growth abnormal number detection value, the crop low amplitude value and the crop table average data to obtain a growth normalization coefficient; if the growth normalization coefficient exceeds a preset growth normalization coefficient threshold value, generating a crop growth disqualification signal; and if the growth normalization coefficient does not exceed the preset growth normalization coefficient threshold value, generating a crop growth qualification signal.
7. The artificial intelligence based crop growth data management decision system of claim 1, wherein the specific operation process of the growth anomaly traceability diagnostic module comprises:
monitoring and pest trapping are carried out on all monitoring points to determine the types of pests in a growing area, the number of monitoring points distributed by the pests of the corresponding types in the growing area is collected and marked as pest distribution detection values, and if the pest distribution detection values exceed a preset pest distribution detection threshold, the pests of the corresponding types are marked as high-coverage pests; if the high coverage rate pests exist in the growing area, generating a pest anomaly signal;
if the high coverage rate pests do not exist in the growing area, a group of preset damage causing values corresponding to each type of pests are preset, pest distribution detecting values of the corresponding type of pests are multiplied by the corresponding preset damage causing values, and the multiplied values are marked as pest influence evaluating values; and summing pest influence evaluation values of all pests in the growing area to obtain a pest diagnosis value, and generating a pest abnormality signal if the pest diagnosis value exceeds a preset pest diagnosis threshold.
8. The artificial intelligence-based crop growth data management decision system according to claim 7, wherein if the pest diagnosis value does not exceed the preset pest diagnosis threshold value, the first analysis value and the second analysis value of the corresponding date are obtained through ring supervision decision analysis, and if the first analysis value and the second analysis value of the corresponding date exceed the corresponding preset threshold value, the corresponding date is marked as a inferior supervision day; if the first analysis value and the second analysis value do not exceed the corresponding preset threshold values, marking the corresponding date as a superior supervision day, and marking the corresponding date as a good supervision day in the other cases;
the method comprises the steps of obtaining the number of inferior supervision days, the number of good supervision days and the number of superior supervision days in a growth monitoring period, marking the numbers of inferior supervision days, the number of good supervision days and the number of superior supervision days as an inferior detection japanese table value, a good supervision japanese table value and a superior supervision japanese table value respectively, and carrying out numerical calculation on the inferior detection japanese table value, the good supervision japanese table value and the superior supervision japanese table value to obtain an environmental monitoring early warning value; if the ring monitoring early warning value exceeds a preset ring monitoring early warning threshold value, generating a ring monitoring abnormal signal.
9. The artificial intelligence based crop growth data management decision system of claim 8, wherein the specific analysis process of the ring supervision decision analysis is as follows:
acquiring daily illumination time length data, illumination intensity data and temperature difference data in a growth monitoring period, carrying out difference value calculation on the temperature difference data and a median value of a preset proper temperature difference range corresponding to the crop growth period, taking an absolute value to obtain temperature difference deviation data, acquiring light intensity deviation data in a similar way, and carrying out numerical calculation on the illumination time length data, the temperature difference deviation data and the light intensity deviation data to obtain a ring analysis initial detection value corresponding to the date;
collecting soil fertility data, soil temperature data and soil humidity data of a monitoring point t, calculating a difference value between the soil fertility data and a median value of a preset proper soil fertility range corresponding to a crop growth period, taking an absolute value to obtain soil fertilizer deviation data, and obtaining the soil temperature deviation data and the soil humidity deviation data in a similar way; carrying out average value calculation on the soil fertilizer deviation data of all the monitoring points to obtain soil fertilizer deviation average data of corresponding dates, and similarly obtaining soil temperature deviation average data and soil humidity deviation average data of corresponding dates; and carrying out numerical calculation on the soil fertilizer bias average data, the soil temperature bias average data and the soil humidity bias average data to obtain a ring analysis recheck value of a corresponding date.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657796.3A CN117350525A (en) | 2023-12-06 | 2023-12-06 | Crop growth data management decision-making system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657796.3A CN117350525A (en) | 2023-12-06 | 2023-12-06 | Crop growth data management decision-making system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117350525A true CN117350525A (en) | 2024-01-05 |
Family
ID=89365368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311657796.3A Pending CN117350525A (en) | 2023-12-06 | 2023-12-06 | Crop growth data management decision-making system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117350525A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540934A (en) * | 2024-01-08 | 2024-02-09 | 山东科翔智能科技有限公司 | Intelligent monitoring system for wheat growth period based on data analysis |
| CN118169338A (en) * | 2024-05-11 | 2024-06-11 | 四川长虹云数信息技术有限公司 | Crop growth monitoring method and system based on cloud service |
| CN118410923A (en) * | 2024-07-01 | 2024-07-30 | 江苏煤炭地质物测队 | Digital agricultural intelligent management platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118323A (en) * | 2020-11-18 | 2020-12-22 | 北京滕华软件有限公司 | Data encryption modularization cloud storage system based on artificial intelligence |
| CN112636974A (en) * | 2020-12-22 | 2021-04-09 | 安徽飞凯电子技术有限公司 | Communication equipment intelligent supervision system based on big data |
| CN115984028A (en) * | 2023-03-21 | 2023-04-18 | 山东科翔智能科技有限公司 | AI technology-based intelligent agricultural production data decision management system |
| CN117150576A (en) * | 2023-10-30 | 2023-12-01 | 易签链(深圳)科技有限公司 | Intelligent verification system and method for block chain electronic seal |
| CN117172952A (en) * | 2023-08-04 | 2023-12-05 | 福建省霞浦海润农业科技发展有限公司 | Agricultural disaster monitoring system based on Internet of things and remote sensing technology |
-
2023
- 2023-12-06 CN CN202311657796.3A patent/CN117350525A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118323A (en) * | 2020-11-18 | 2020-12-22 | 北京滕华软件有限公司 | Data encryption modularization cloud storage system based on artificial intelligence |
| CN112636974A (en) * | 2020-12-22 | 2021-04-09 | 安徽飞凯电子技术有限公司 | Communication equipment intelligent supervision system based on big data |
| CN115984028A (en) * | 2023-03-21 | 2023-04-18 | 山东科翔智能科技有限公司 | AI technology-based intelligent agricultural production data decision management system |
| CN117172952A (en) * | 2023-08-04 | 2023-12-05 | 福建省霞浦海润农业科技发展有限公司 | Agricultural disaster monitoring system based on Internet of things and remote sensing technology |
| CN117150576A (en) * | 2023-10-30 | 2023-12-01 | 易签链(深圳)科技有限公司 | Intelligent verification system and method for block chain electronic seal |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540934A (en) * | 2024-01-08 | 2024-02-09 | 山东科翔智能科技有限公司 | Intelligent monitoring system for wheat growth period based on data analysis |
| CN117540934B (en) * | 2024-01-08 | 2024-04-05 | 山东科翔智能科技有限公司 | Intelligent monitoring system for wheat growth period based on data analysis |
| CN118169338A (en) * | 2024-05-11 | 2024-06-11 | 四川长虹云数信息技术有限公司 | Crop growth monitoring method and system based on cloud service |
| CN118410923A (en) * | 2024-07-01 | 2024-07-30 | 江苏煤炭地质物测队 | Digital agricultural intelligent management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117350525A (en) | Crop growth data management decision-making system based on artificial intelligence | |
| CN115185220B (en) | Agriculture and forestry disease and pest monitoring system based on thing networking | |
| CN115938083B (en) | Agricultural monitoring and early warning method and system based on mobile terminal | |
| CN117575169A (en) | Intelligent agriculture management system based on data processing | |
| CN116579874A (en) | Edible fungus planting environment intelligent management and control system based on artificial intelligence | |
| CN112116206A (en) | Intelligent agricultural system based on big data | |
| CN116627082A (en) | Intelligent management system for live pig breeding suitable for stock quantity checking | |
| CN117391427A (en) | Medical instrument production intelligent supervision system based on artificial intelligence | |
| CN116295662B (en) | Crop growth state monitoring method and device, electronic equipment and medium | |
| KR20220011878A (en) | Method for monitoring damages by blight and harmful insects and growth based on artificial intelligence | |
| CN117172952A (en) | Agricultural disaster monitoring system based on Internet of things and remote sensing technology | |
| CN114460080A (en) | Rice disease and pest intelligent monitoring system | |
| CN118395386A (en) | Plant growth monitoring method for intelligent plant factory | |
| CN112003948A (en) | Wisdom agricultural thing networking systems | |
| CN115685862A (en) | Intelligent agricultural detection system based on edge calculation | |
| CN114967801A (en) | Intelligent production regulation curve and big data platform | |
| CN117854006B (en) | Tobacco growth state monitoring system based on image processing | |
| CN114543869A (en) | Agricultural braced system based on internet of things | |
| CN117968757A (en) | Autonomous navigation inspection field crop growth management system and method | |
| CN112001343A (en) | Gardening pest control management system | |
| CN118426493B (en) | Unmanned aerial vehicle inspection system and method based on cloud platform | |
| CN112450177A (en) | Big data-based greenhouse intelligent management system | |
| CN118155144B (en) | Vegetable planting pesticide input supervision system and method based on AI vision | |
| CN115239513B (en) | Sharing farm intelligent operation system applied to village happy service | |
| CN118733696B (en) | Land information mapping system based on Internet of things |
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 |