Intelligent field farming guidance system based on data visualization

Abstract

The invention belongs to the technical field of farming guidance, and particularly discloses and provides an intelligent field farming guidance system based on data visualization, which comprises a knowledge base generation module, a relation judgment module, a mutual exclusion analysis module, a collaborative analysis module and a scheme generation module. The agricultural operation execution effect is improved by constructing the agricultural knowledge base, quantitatively judging the cooperation and mutual exclusion relation between agricultural works, synchronously executing the cooperation agricultural works according to the optimal proportion and setting the safety interval duration for the mutual exclusion agricultural works, the urgency degree is analyzed and calculated based on the deviation of the actually measured parameters and the reference parameters, the urgency degree is ranked, and the agricultural operation efficiency is improved. According to the method, the emergency degree of each mutually exclusive farming is quantified, the priority execution of high-urgency farming is ensured, the overall gain ratio is obtained through the crop growth indexes based on each ratio of the collaborative combination, each collaborative gain ratio is calculated and weighted fusion is carried out, and the first ratio is selected according to the gain ratio sequence, so that the subjectivity of experience selection is avoided, and the overall effect of collaborative operation is improved.

Description

Technical Field

[0001] This invention belongs to the field of agricultural guidance technology and relates to a smart field agricultural guidance system based on data visualization. Background Technology

[0002] With the acceleration of agricultural modernization and the continuous expansion of field planting scale, the complexity and precision requirements of agricultural operations have significantly increased. Traditional field agricultural management mainly relies on farmers' experience or simple time-series arrangements, lacking quantitative analysis and precise judgment of agricultural relationships, thus requiring guidance for agricultural operations.

[0003] For example, Chinese invention patent CN104376426B discloses a calendar-based agricultural guidance method and system. Its core is to divide the calendar into 12 nodes and sub-nodes, assign farmers to corresponding sub-nodes based on crop planting parameters, and then mark and push agricultural guidance operations for each growth node starting from the last day of the sub-node. This technology achieves preliminary personalization of agricultural guidance through calendar node division, meeting farmers' needs for time-sequential operations to a certain extent.

[0004] The existing technologies mentioned above have the following shortcomings: 1. Currently, they only push fixed agricultural guidance operations based on calendar nodes, ignoring the cooperative and mutually exclusive relationships between agricultural operations. This makes it impossible to avoid the problems of conflict between mutually exclusive agricultural operations or loss of cooperative gains. At the same time, the use of fixed intervals cannot adapt to changes in crop status, reducing the adaptability of agricultural operations.

[0005] 2. Currently, only single agricultural operations are pushed out in the order of calendar nodes, lacking the ability to dynamically sort multiple agricultural needs. As a result, it cannot cope with conflicts in agricultural needs, leading to delays in operation timing. At the same time, it ignores the dependencies between agricultural tasks, disrupting the continuity of operations. Summary of the Invention

[0006] In view of this, in order to solve the problems mentioned in the background technology, a smart field farming guidance system based on data visualization is proposed.

[0007] The objective of this invention can be achieved through the following technical solution: This invention provides a smart field farming guidance system based on data visualization, including: a knowledge base generation module, which determines the synergistic and mutually exclusive relationships of various farming activities based on the spatiotemporal execution parameters of various farming activities and crop response data in historical farmland data, and generates a farming knowledge base.

[0008] The relationship determination module receives various agricultural needs from farmland in real time, inputs them into the agricultural knowledge base, and determines the cooperative and mutually exclusive relationships of each agricultural need.

[0009] The mutual exclusion analysis module sorts agricultural needs based on their operational urgency and measured parameters when they are mutually exclusive. It also determines the safe operating interval and dosage for each mutually exclusive agricultural need by combining historical farmland data.

[0010] The collaborative analysis module determines the collaborative ratio and dosage of each collaborative agricultural demand when there is collaboration in agricultural demand. This is based on the collaborative gain rate of each collaborative agricultural demand group in historical farmland data and the measured parameters of agricultural demand.

[0011] The scheme generation module generates agricultural guidance schemes based on the order of agricultural needs for each mutually exclusive agricultural activity, the safe operation interval, the dosage, and the coordination ratio and dosage of each collaborative agricultural activity.

[0012] The solution output terminal outputs agricultural guidance solutions through a visual terminal.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention constructs an agricultural knowledge base, quantifies and determines the synergistic and mutually exclusive relationships between agricultural activities, executes synergistic agricultural activities synchronously in the optimal proportion, and sets a safe interval for mutually exclusive agricultural activities, thereby avoiding the cancellation of the effects of agricultural operations and significantly improving the execution effect of agricultural operations.

[0014] (2) This invention uses a pairwise combination retrieval mechanism for agricultural needs to accurately locate mutually exclusive agricultural needs groups. At the same time, it calculates the urgency and sorts the data based on the deviation analysis between measured parameters and benchmark parameters, quantifies the urgency of each mutually exclusive agricultural task, ensures that high-urgency agricultural tasks are executed first, and avoids delays in urgent operations due to disordered sorting.

[0015] (3) The present invention determines the safe interval time by screening the shortest interval time when both the previous and subsequent operations meet the standard. Under the premise of ensuring that mutually exclusive operations do not interfere with each other, it reduces time waste and improves the efficiency of agricultural operations. At the same time, it calculates the amount of usage by multiplying the parameter difference and the unit scale conversion factor, avoiding the impact of insufficient or excessive usage on the final income, and realizing the precise input of usage.

[0016] (4) This invention extracts crop growth indicators of each ratio of the collaborative agricultural demand group from historical farmland data, calculates the collaborative gain rate of each ratio and weights and fuses them to obtain the overall gain rate, quantifies the effect of different ratios, and selects the first ratio as the collaborative ratio by sorting by gain rate, thereby avoiding the subjectivity of relying on experience to select and improving the overall effect of collaborative operation.

[0017] (5) By subdividing and analyzing various growth indicators, this invention ensures that the synergistic operation can play a promoting role in multiple dimensions, avoiding the situation where a single indicator is excellent while other indicators are damaged. At the same time, the dosage is dynamically adjusted in combination with real-time measured parameters, thereby improving the actual feasibility and stability of the synergistic operation. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0020] Figure 2 This is a schematic diagram showing the connection steps of the agricultural knowledge base generation process of this invention.

[0021] Figure 3 This is a schematic diagram showing the connection steps of the analysis of the synergistic gain rate of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Please see Figure 1 As shown, the present invention provides a smart field agricultural guidance system based on data visualization. The system includes: a knowledge base generation module, a relationship determination module, a mutual exclusion analysis module, a collaborative analysis module, a solution generation module, and a solution output terminal.

[0024] In the above, the relationship determination module is connected to the knowledge base generation module, the mutual exclusion analysis module, and the collaborative analysis module, respectively, and the solution generation module is also connected to the mutual exclusion analysis module, the collaborative analysis module, and the solution output terminal, respectively.

[0025] The knowledge base generation module determines the collaborative and mutually exclusive relationships of various agricultural activities based on the spatiotemporal execution parameters of various agricultural activities and crop response data in historical farmland data, and generates an agricultural activity knowledge base.

[0026] It should be added that the spatiotemporal execution parameters are core data used to define the correlation of agricultural operations, including the execution date, specific time period, and duration of the agricultural operation.

[0027] Please see Figure 2 As shown, exemplarily, the generation of the agricultural knowledge base includes: dividing agricultural activities within the same time period into related agricultural activity groups based on the spatiotemporal execution parameters.

[0028] It should be added that the same time period refers to a continuous 24 hours within the same growth stage of the crop.

[0029] The combined execution effect of each growth promotion effect index in each associated agricultural activity group is obtained from the crop response data, and compared with the sum of the execution effects of each growth promotion effect index when each agricultural activity in the corresponding associated agricultural activity group is executed individually.

[0030] It should be added that the growth promotion effect indicators are quantitative parameters that reflect the crop growth status, yield and quality, including but not limited to: physiological growth indicators, yield formation indicators and quality improvement indicators.

[0031] It should be added that the sum of the effects of each growth promotion effect index is as follows: if the growth promotion effect index is affected by multiple agricultural activities within the combination, such as nutrient absorption efficiency being affected by fertilization and irrigation, then the sum of the effects of the index when each agricultural activity is performed independently is the nutrient absorption efficiency when fertilization is performed independently and the nutrient absorption efficiency when irrigation is performed independently.

[0032] If the growth promotion effect index is only affected by a single agricultural activity within the combination, such as the pest and disease control effect being determined solely by pesticide application and unrelated to fertilization, then the sum of the effects of this index when each agricultural activity is implemented independently is the pest and disease control effect when pesticide application is implemented independently.

[0033] When all growth-promoting effect indicators meet the condition that the combined effect of the actions is greater than the sum of the combined effects, the related agricultural groups are determined to be in a synergistic relationship.

[0034] In one specific embodiment, an example of determining the collaborative relationship is as follows: After the associated agricultural group performs fertilization and irrigation, the crop height increases by 15cm and the number of fruits per plant is 10.

[0035] Fertilizer alone increases plant height by 8cm and produces 5 fruits per plant, while irrigation alone increases plant height by 5cm and produces 4 fruits per plant.

[0036] If the combined execution effect is 15cm, 10 of which are greater than the sum of the execution effects (13cm), and 9 of which are greater than the sum of the execution effects, then it is determined to be a collaborative relationship.

[0037] When all growth-promoting effect indicators meet the condition that the combined effect is less than the sum of the effects, the related agricultural groups are determined to be mutually exclusive.

[0038] In one specific embodiment, an example of mutual exclusion relationship determination is as follows: After the associated agricultural group performs pesticide application and fertilization, the weed control effect is a weed mortality rate of 60% and a crop height increase of 3cm.

[0039] The herbicidal effect of applying pesticides alone is 90%, and the plant height increase of applying fertilizer alone is 10cm.

[0040] The combined execution effect is 60%, and 3cm is less than 90% and 10cm of the sum of the execution effects, respectively, so they are determined to be mutually exclusive.

[0041] When some indicators in a related agricultural group satisfy synergy and some satisfy mutual exclusion, the related agricultural group is determined to be neutral.

[0042] In one specific embodiment, an example of neutral relationship determination is as follows: After the associated agricultural group performs fertilization and pesticide application, the fertilization effect is a plant height increase of 10cm, and the pesticide application effect is a weed mortality rate of 85%. When fertilization is performed alone, the plant height increase is 9cm, and when pesticide application is performed alone, the weed mortality rate is 88%.

[0043] The combined effect of fertilization and pesticide application on increasing plant height is greater than the sum of the effects, but the combined effect on weed mortality is less than the sum of the effects. Since not all indicators meet the conditions for synergy or mutual exclusion, the relationship is judged to be neutral.

[0044] An agricultural knowledge base is constructed based on the relationships between various related agricultural groups.

[0045] This invention constructs an agricultural knowledge base, quantifies and determines the synergistic and mutually exclusive relationships between agricultural activities, executes synergistic agricultural activities synchronously at the optimal ratio, and sets safe intervals for mutually exclusive agricultural activities, thereby avoiding the cancellation of the effects of agricultural operations and significantly improving the execution effect of agricultural operations.

[0046] The relationship determination module receives various agricultural needs from the farmland in real time, inputs them into the agricultural knowledge base, and determines the cooperative and mutually exclusive relationships of each agricultural need.

[0047] It should be added that the agricultural needs mentioned include, but are not limited to, fertilization, pesticide application, and irrigation.

[0048] For example, determining the cooperative and mutually exclusive relationship of each agricultural demand includes: combining each agricultural demand in pairs to form groups of agricultural demands.

[0049] Input each agricultural demand group into the agricultural knowledge base and retrieve the collaborative and mutually exclusive relationships between each agricultural demand group.

[0050] Agricultural demand groups that have a collaborative relationship in the knowledge base are identified as collaborative groups and marked as collaborative agricultural demand groups.

[0051] The agricultural demand groups that are mutually exclusive in the knowledge base are identified as mutually exclusive and marked as mutually exclusive agricultural demand groups, thereby obtaining the cooperative mutually exclusive relationships of each agricultural demand.

[0052] The mutual exclusion analysis module, when there are mutually exclusive agricultural needs, sorts the agricultural needs based on the urgency of the agricultural needs and measured parameters, and at the same time determines the safe operation interval and dosage for each mutually exclusive agricultural need by combining historical farmland data.

[0053] For example, the process of prioritizing agricultural needs includes: calculating the relative deviation between the measured parameters corresponding to each agricultural need and the benchmark parameters corresponding to the current production stage of the crop, to obtain the operational urgency of each agricultural need.

[0054] The urgency of the operations is sorted from highest to lowest to obtain the agricultural needs ranking.

[0055] This invention employs a pairwise combination retrieval mechanism for agricultural needs to accurately identify mutually exclusive agricultural need groups. Simultaneously, it calculates and sorts the urgency based on the deviation analysis between measured parameters and benchmark parameters, quantifying the urgency of each mutually exclusive agricultural need. This ensures that high-urgency agricultural needs are prioritized and avoids delays in urgent operations due to disordered sorting.

[0056] For example, determining the safe operating interval and dosage for each mutually exclusive agricultural task includes: obtaining the actual and target effects of agricultural activities before and after each interval from historical farmland data.

[0057] Determine whether the actual effects of the agricultural work before and after the event exceed the target effect.

[0058] It should be added that the specific determination process for whether the actual effect of the agricultural work before and after is greater than the target effect is as follows: if the actual effect of the agricultural work before is greater than the target effect, it is determined to meet the target; otherwise, it is determined to fail to meet the target.

[0059] It should be added that the pre-application compliance refers to the actual effect meeting the preset target. For example, if the actual weed mortality rate after herbicide application is 90%, which is greater than the target weed mortality rate of 80%, it is judged as compliance, ensuring that the previous operations have achieved the expected effect.

[0060] If the actual effect of subsequent agricultural activities exceeds the target effect, it is judged as meeting the target; otherwise, it is judged as failing to meet the target.

[0061] It should be added that post-farm operation meeting the target means that after a specific interval, the actual effect of subsequent operations still meets the target. For example, if organic fertilizer is applied after an interval of 3 days and the actual increase in plant height is 6cm, which is greater than the target increase in plant height of 5cm, it is judged as meeting the target, indicating that the interval time has not interfered with subsequent operations.

[0062] The intervals in which both preceding and following agricultural activities meet the standards are selected, sorted from largest to smallest, and the last interval in the sort is chosen as the safe operating interval.

[0063] It should be added that the selection criteria for the last interval in the sorting are as follows: Intervals where both preceding and following operations meet the requirements, such as 3 days and 5 days, are selected and sorted from largest to smallest as [5 days, 3 days]. The last 3 days is chosen as the safe operating interval. Under the premise of ensuring the desired effect, the shortest time interval is selected. This avoids delays in agricultural work due to excessively long intervals and ensures safety through verification using historical farmland data. For example, if a 3-day interval is sufficient to meet the desired effect before and after agricultural work, there is no need to wait redundantly for 5 days.

[0064] Calculate the deviation between the baseline parameter and the measured parameter corresponding to the current production stage of the crop for mutually exclusive agricultural demands, and take the absolute value as the parameter difference.

[0065] It should be added that the baseline parameters corresponding to the current crop production stage refer to the ideal indicators for the current crop growth stage. For example, the baseline value for soil nitrogen content during the jointing stage of wheat is 40 mg / kg, which is preset based on crop variety characteristics, soil type, and agricultural technical specifications. Measured parameters are real-time data obtained through sensors or sampling, such as the current measured value of soil nitrogen content being 25 mg / kg.

[0066] The parameters are multiplied by their preset unit scale conversion factor to obtain the amount of mutually exclusive agricultural needs.

[0067] It should be added that the preset unit scale conversion factor is a conversion coefficient that transforms the difference in crop growth parameters into the specific agricultural operation dosage. Its physical meaning is the scale of agricultural operation corresponding to a unit parameter difference, such as how many kilograms of fertilizer are needed for a 1 mg / kg deviation in soil nitrogen content, or how many milliliters of pesticide are needed for a 1% deviation in pest and disease incidence. The core function of this factor is to establish a quantitative bridge between parameter deviation and actual dosage, ensuring that the dosage calculation not only meets the needs of crop growth but also adapts to the actual operational scale of field production, such as dosage per acre or hectare, avoiding distortion of calculation results due to mismatched units of parameters and dosages.

[0068] The unit scale conversion factor is obtained by fitting historical farmland data. The specific steps are as follows: records consistent with the current farming type, crop variety, and growth stage are selected from the historical farmland data, and the correspondence between parameter differences and actual application rates is obtained. For example, for nitrogen fertilizer application during the wheat jointing stage, paired data of soil nitrogen content parameter differences and actual nitrogen application rates from the past three years are extracted, such as a parameter difference of 10 mg / kg corresponding to a nitrogen application rate of 2 kg / mu, and a parameter difference of 20 mg / kg corresponding to a nitrogen application rate of 4 kg / mu, etc.

[0069] Perform linear regression or curve fitting on the extracted parameter difference-dosage data to calculate the average dosage corresponding to a unit parameter difference. For example, in the above example, 10 mg / kg corresponds to 2 kg / mu, and the unit scale conversion factor is 0.2 kg / mu・mg / kg, thus obtaining the unit scale conversion factor.

[0070] This invention determines the safe interval by selecting the shortest interval between operations that meet the standards before and after. This reduces wasted time and improves the efficiency of agricultural operations while ensuring that mutually exclusive operations do not interfere with each other. At the same time, it calculates the dosage by multiplying the parameter difference and the unit scale conversion factor to avoid the final income being affected by insufficient or excessive dosage, thus achieving precise input of dosage.

[0071] The collaborative analysis module, when there is collaboration in agricultural needs, determines the collaboration ratio and dosage of each collaborative agricultural need based on the collaboration gain rate of each collaborative agricultural need group in the historical farmland data and the measured parameters of agricultural needs.

[0072] It should be added that the synergistic gain rate is an indicator that quantifies the synergistic effect of synergistic agricultural demand groups, such as fertilization + irrigation or pesticide application + fertilization under different ratios. Its core function is to determine the synergistic ratio that maximizes crop growth benefits by comparing the difference between the combined execution effect and the sum of the individual execution effects, such as the ratio of fertilizer to irrigation dosage.

[0073] Please see Figure 3 As shown, exemplarily, the analysis of the synergistic gain rate includes: obtaining the combined execution effect of each growth promotion effect index of each synergistic agricultural demand group under each ratio from the combined execution effect and the sum of execution effects, as well as the sum of execution effects of each growth promotion effect index when each agricultural activity is executed independently within each synergistic agricultural demand group.

[0074] The difference between the combined execution effect and the sum of its execution effects is used as the synergistic gain rate of each synergistic agricultural demand group for each growth promotion effect index under each ratio.

[0075] The synergistic gain rate is calculated by weighting and integrating the results according to preset weights to obtain the synergistic gain rate of each synergistic agricultural demand group under each ratio.

[0076] It should be added that the synergistic gain rate is calculated by multiplying the synergistic gain rates of each growth-promoting effect indicator by their preset weights and then summing the results. The preset weights are values ​​set according to the importance of each growth-promoting effect indicator to crop growth; the core logic is that the indicator with the greater impact on the current growth stage of the crop has, the higher its weight.

[0077] The synergistic gain rate is quantified using a weighted summation method. Firstly, the weights reflect the priority differences of various growth-promoting indicators at the current growth stage, ensuring that core indicators that play a decisive role in crop growth have a higher weight in the overall synergistic effect assessment. This avoids secondary indicators having an excessive impact on the results, ensuring that the final synergistic gain rate accurately reflects the actual value to production goals. Secondly, by multiplying and then adding the results separately, the gain rates of multiple dispersed indicators are integrated into a single quantitative result. This resolves the contradiction of some indicators having high gains while others have low gains in multi-indicator evaluations, making the comparison of effects between different synergistic agricultural demand groups and different ratios more intuitive and providing a clear basis for subsequent selection of the optimal synergistic ratio.

[0078] The preset weights can be set based on industry experience or obtained through a limited number of experimental data. For example, first collect historical data of farmland, statistically analyze the historical correlation between various growth promotion effect indicators and the final growth results of crops, use multiple linear regression or Pearson correlation coefficient analysis to determine the contribution of each indicator to the final result, and finally convert the contribution into preset weights through normalization, with the sum of the weights being 1.

[0079] This invention extracts crop growth indicators of each ratio in the collaborative agricultural demand group from historical farmland data, calculates the collaborative gain rate of each ratio, and weights and fuses them to obtain the overall gain rate. This quantifies the effects of different ratios and selects the first ratio as the collaborative ratio by sorting by gain rate, thus avoiding the subjectivity of relying on experience for selection and improving the overall effect of collaborative operation.

[0080] For example, determining the synergistic ratio of agricultural demand includes obtaining the synergistic gain rate of each synergistic agricultural demand group under each ratio from the synergistic gain rate of each synergistic agricultural demand group under each ratio.

[0081] The synergistic gain rates of the collaborative agricultural demand groups under each ratio are sorted from largest to smallest, and the ratio with the highest ranking is selected as the synergistic ratio of agricultural demand.

[0082] It should be added that if multiple ratios have the same and highest synergistic gain rate, the agricultural operation cost corresponding to each ratio with synergistic gain rate should be calculated, and the ratio with the lowest cost should be selected to optimize production input while ensuring synergistic effect.

[0083] For example, determining the amount of each collaborative farming requirement includes: Q1, calculating the relative deviation between the measured parameters corresponding to each collaborative farming requirement and the benchmark parameters corresponding to the current production stage of the crop to obtain the operational urgency of each collaborative farming requirement.

[0084] Q2. Compare the operational urgency of each collaborative farming task within the collaborative farming group, and select the collaborative farming task with the highest operational urgency as the benchmark farming task.

[0085] Q3. Based on the deviation between the measured parameters of the benchmark agricultural activity and its benchmark parameters, determine the dosage of the benchmark agricultural activity, and then combine it with the coordination ratio of the collaborative agricultural activity demand group to obtain the dosage of each collaborative agricultural activity demand.

[0086] It should be added that by prioritizing urgency, using benchmark dosage, and converting proportions, we can ensure that the dosage calculations are aligned with the real-time needs of the crops, and also ensure the operational compatibility of multiple agricultural tasks through coordinated proportions, ultimately achieving the goal of on-demand allocation and synergistic efficiency.

[0087] For example, if the synergistic agricultural needs group is pesticide application + fertilizer application, and the urgency of fertilizer application is higher, then the amount of pesticide application should be calculated based on the amount of topdressing fertilizer and the synergistic ratio, so as to avoid weakening the synergistic effect due to insufficient or excessive application of a certain agricultural activity.

[0088] Furthermore, determining the dosage of the benchmark agricultural practice includes: calculating the deviation between the benchmark parameters corresponding to the current crop production stage and the measured parameters, and using the absolute value of the difference as the parameter difference of the benchmark agricultural practice.

[0089] The dosage required for baseline agricultural operations is obtained by multiplying the parameter difference with its preset unit scale conversion factor.

[0090] This invention, through detailed analysis of various growth indicators, ensures that synergistic operation can play a promoting role in multiple dimensions, avoiding the situation where one indicator is excellent while other indicators are damaged. At the same time, by combining real-time measured parameters to dynamically adjust the dosage, the actual feasibility and effect stability of synergistic operation are improved.

[0091] The scheme generation module generates agricultural guidance schemes based on the order of agricultural needs for each mutually exclusive agricultural activity, the safe operation interval, the dosage, and the coordination ratio and dosage of each collaborative agricultural activity.

[0092] For example, the method for generating agricultural guidance includes: when there are only mutually exclusive agricultural activities, sorting them from highest to lowest urgency, arranging each agricultural activity and its dosage on the timeline according to the sorting results, while ensuring that the interval between adjacent mutually exclusive agricultural activities is its safe operating interval.

[0093] When only collaborative farming exists, farming activities within the same collaborative farming demand group are executed within the same time window based on the usage plan for each activity.

[0094] If there are multiple independent and coordinated farming activities, they are sorted according to the preset priority of crop growth stages and executed in conjunction with the usage plan for each farming activity.

[0095] It should be added that the preset crop growth stage priority is for synergistic farming activities that have mutual promoting or restrictive relationships, and is ordered according to the logic of prioritizing basic operations before efficiency enhancement and prioritizing protection before utilization, so as to avoid mutual interference between farming activities. For example, during the fruit expansion stage of fruit trees: irrigation is required after fertilization to promote nutrient dissolution and absorption, and pesticide application should be avoided at the same time as irrigation to prevent dilution and loss of pesticides. Therefore, the priority is fertilization > irrigation > pesticide application. During the seedling stage of vegetables: irrigation is required first to ensure soil moisture, then fertilization is applied to avoid burning the seedlings during drought, and finally pesticide application is applied to prevent seedling diseases. Therefore, the priority is irrigation > fertilization > pesticide application, thereby ensuring that farming activities at key stages are executed in a priority manner.

[0096] When mutually exclusive and synergistic farming activities coexist, a mutually exclusive timeline is first generated based on the urgency of the mutually exclusive farming activities and the safe interval duration.

[0097] When scheduling collaborative agricultural task groups within a safe window on a mutually exclusive timeline, it is simultaneously verified whether there is a mutually exclusive relationship between the collaborative agricultural task groups and the planned agricultural tasks on the mutually exclusive timeline. If so, the collaborative execution time is split, and the interval after splitting does not exceed the preset collaborative critical interval duration.

[0098] It should be added that the safety window refers to the time period in the mutually exclusive agricultural timeline that is not occupied by mutually exclusive operations and meets the safety interval. For example, if the mutually exclusive operations are on day 1 and day 5, then day 2-4 is the safety window.

[0099] It should be added that the synchronous verification of whether the collaborative farming demand group contains mutually exclusive farming activities is based on the farming knowledge base to determine whether there are mutually exclusive farming activities between the collaborative farming demand groups.

[0100] It should be added that the critical interval of collaboration refers to the maximum allowable interval when collaborative farming tasks are split and executed. If this interval is exceeded, the collaborative effect will be completely lost. It is set through historical farmland data and is based on the maximum interval when the collaborative gain rate drops to a preset threshold in the historical data. For example, if the collaborative gain rate drops to the preset threshold after the split interval of a certain collaborative farming task demand group is greater than 3 days, then the critical interval of collaboration is set to 3 days.

[0101] If it does not exist, it will be executed within the same time window according to the usage plan of the collaborative farming within the safety window.

[0102] By planning mutually exclusive and synergistic agricultural activities along the timeline as described above, an agricultural guidance scheme is formed that includes the execution time window, dosage, and execution sequence for each agricultural activity.

[0103] It should be added that the core of generating agricultural guidance plans is to rationally plan the sequence, time window and dosage of agricultural operations on the time axis based on the mutually exclusive or synergistic relationships of agricultural needs, combined with parameters such as operational urgency, safety interval, and synergistic ratio, so as to ensure that the plan not only meets the needs of crop growth, but also maximizes the agricultural effect, while avoiding mutual interference and maximizing synergistic benefits.

[0104] The solution output terminal outputs agricultural guidance solutions through a visual terminal.

[0105] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0106] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0107] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0108] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0109] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0110] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart field farming guidance system based on data visualization, characterized in that: The system includes: The knowledge base generation module determines the synergistic and mutually exclusive relationships of various agricultural activities based on the spatiotemporal execution parameters of various agricultural activities and crop response data in historical farmland data, and generates an agricultural knowledge base. The relationship determination module receives various agricultural needs from farmland in real time, inputs them into the agricultural knowledge base, and determines the cooperative and mutually exclusive relationships of each agricultural need. The mutual exclusion analysis module sorts agricultural needs based on their operational urgency and measured parameters when they are mutually exclusive. It also determines the safe operation interval and dosage for each mutually exclusive agricultural need by combining historical farmland data. The collaborative analysis module determines the collaborative ratio and dosage of each collaborative agricultural demand when there is collaboration in agricultural demand. This is based on the collaborative gain rate of each collaborative agricultural demand group in the historical farmland data and the measured parameters of agricultural demand. The scheme generation module generates agricultural guidance schemes based on the order of agricultural needs of mutually exclusive agricultural activities, the safe operation interval, the dosage, and the coordination ratio and dosage of each collaborative agricultural activity. The solution output terminal outputs agricultural guidance solutions through a visual terminal.

2. The intelligent field farming guidance system based on data visualization according to claim 1, characterized in that: The generated agricultural knowledge base includes: Based on the spatiotemporal execution parameters, agricultural activities within the same time period are divided into related agricultural activity groups; The combined execution effect of each growth promotion effect index in each associated agricultural activity group is obtained from the crop response data, and compared with the sum of the execution effects of each growth promotion effect index when each agricultural activity in the corresponding associated agricultural activity group is executed alone. When all growth-promoting effect indicators meet the condition that the combined effect of the actions is greater than the sum of the effects, the related agricultural groups are determined to be in a synergistic relationship. When all growth promotion effect indicators meet the condition that the combined effect is less than the sum of the effects, the related agricultural groups are determined to be mutually exclusive. When some indicators in an associated agricultural group satisfy synergy and some satisfy mutual exclusion, the associated agricultural group is determined to be neutral. An agricultural knowledge base is constructed based on the relationships between various related agricultural groups.

3. The intelligent field farming guidance system based on data visualization according to claim 1, characterized in that: The determination of the cooperative and mutually exclusive relationships of various agricultural needs includes: Each agricultural need is paired up to form an agricultural need group; Input each agricultural demand group into the agricultural knowledge base and retrieve the collaborative and mutually exclusive relationships of each agricultural demand group; Agricultural demand groups with collaborative relationships in the knowledge base are identified as collaborative relationships and marked as collaborative agricultural demand groups; The agricultural demand groups that are mutually exclusive in the knowledge base are identified as mutually exclusive and marked as mutually exclusive agricultural demand groups, thereby obtaining the cooperative mutually exclusive relationships of each agricultural demand.

4. The intelligent field farming guidance system based on data visualization according to claim 1, characterized in that: The process of prioritizing agricultural needs includes: The relative deviation between the measured parameters corresponding to each agricultural demand and the benchmark parameters corresponding to the current production stage of the crop is calculated to obtain the operational urgency of each agricultural demand. The urgency of the operations is sorted from highest to lowest to obtain the agricultural needs ranking.

5. The intelligent field farming guidance system based on data visualization according to claim 1, characterized in that: The determination of the safe operating interval and dosage for each mutually exclusive agricultural need includes: Obtain the actual and target effects of agricultural activities before and after mutually exclusive agricultural demand groups at various time intervals from historical farmland data; Determine whether the actual effects of the agricultural activities before and after the event exceed the target effects; The intervals in which both preceding and following agricultural activities meet the standards are selected, sorted from largest to smallest, and the interval at the bottom of the sort is selected as the safe operating interval. Calculate the deviation between the baseline parameters and measured parameters corresponding to mutually exclusive agricultural demands at the crop production stage, and take the absolute value as the parameter difference; The parameters are multiplied by their preset unit scale conversion factor to obtain the amount of mutually exclusive agricultural needs.

6. The intelligent field farming guidance system based on data visualization according to claim 2, characterized in that: The analysis of the synergistic gain rate includes: From the combined execution effect and the sum of execution effects, obtain the combined execution effect of each growth promotion effect index of each collaborative agricultural demand group under each ratio, and the sum of the execution effects of each growth promotion effect index when each agricultural activity is executed independently within each collaborative agricultural demand group; The difference between the combined execution effect and the sum of its execution effects is used as the synergistic gain rate of each synergistic agricultural demand group for each growth promotion effect index under each ratio. The synergistic gain rate is calculated by weighting and integrating the results according to preset weights to obtain the synergistic gain rate of each synergistic agricultural demand group under each ratio.

7. The intelligent field farming guidance system based on data visualization according to claim 6, characterized in that: The coordination ratio for determining agricultural needs includes: The synergistic gain rate of each synergistic farming demand group under each ratio is obtained from the synergistic gain rate of each synergistic farming demand group under each ratio. The synergistic gain rates of the collaborative agricultural demand groups under each ratio are sorted from largest to smallest, and the ratio with the highest ranking is selected as the synergistic ratio of agricultural demand.

8. The intelligent field farming guidance system based on data visualization according to claim 1, characterized in that: The determination of the dosage required for each collaborative agricultural activity includes: Q1. Calculate the relative deviation between the measured parameters corresponding to each collaborative farming requirement and the benchmark parameters corresponding to the current production stage of the crop to obtain the operational urgency of each collaborative farming requirement. Q2. Compare the operational urgency of each collaborative farming task within the collaborative farming group, and select the collaborative farming task with the highest operational urgency as the benchmark farming task. Q3. Based on the deviation between the measured parameters of the benchmark agricultural activity and its benchmark parameters, determine the dosage of the benchmark agricultural activity, and then combine it with the coordination ratio of the collaborative agricultural activity demand group to obtain the dosage of each collaborative agricultural activity demand.

9. A smart field farming guidance system based on data visualization according to claim 8, characterized in that: The determination of the baseline agricultural usage includes: The deviation between the baseline parameters corresponding to the benchmark agricultural practices at the crop production stage and the measured parameters is calculated, and the absolute value of the difference is taken as the parameter difference of the benchmark agricultural practices. The dosage required for baseline agricultural operations is obtained by multiplying the parameter difference with its preset unit scale conversion factor.

10. A smart field farming guidance system based on data visualization according to claim 1, characterized in that: The generated agricultural guidance plan includes: When there are only mutually exclusive farming activities, sort them from highest to lowest urgency. Arrange each farming activity and its usage on the timeline according to the sorting results, while ensuring that the interval between adjacent mutually exclusive farming activities is its safe operating interval. When only collaborative farming exists, the same time window is used to plan the usage of each farming activity within the same collaborative group. If there are multiple independent and coordinated farming activities, they are sorted according to the preset priority of crop growth stages and executed in combination with the usage plan of each farming activity. When mutually exclusive farming activities and synergistic farming activities exist simultaneously, a mutually exclusive timeline is first generated based on the urgency of the mutually exclusive farming activities and the safety interval duration. When scheduling collaborative agricultural task groups into a safe window on a mutually exclusive timeline, it is simultaneously verified whether there is a mutually exclusive relationship between the collaborative agricultural task groups and the planned agricultural tasks on the mutually exclusive timeline. If so, the collaborative execution time is split, and the interval after splitting does not exceed the preset collaborative critical interval duration. If it does not exist, then within the safety window, the usage of the coordinated farming plan will be executed in the same time window. By planning mutually exclusive and synergistic agricultural activities along the timeline as described above, an agricultural guidance scheme is formed that includes the execution time window, dosage, and execution sequence for each agricultural activity.

Images