Intelligent management method and system for rubber production based on Internet of Things technology

Abstract

The invention relates to the technical field of Internet of Things, in particular to a rubber production intelligent management method and system based on the Internet of Things technology. Comprising the steps of collecting key data; processing the key data based on GIS software, and generating a soil fertility distribution map; carrying out planting planning optimization, and outputting an optimal planting scheme; when the optimal planting scheme is output, a rubber tapping point and the initial position of a rubber tapping machine are output based on the GPS; based on a Dijkstra algorithm, calculating a shortest path from the initial position to each rubber tapping point, and outputting an optimal path; historical yield data and related environment data are collected, an ARIMA model is established for data differential processing, model parameters are determined, fitted and predicted, and health indexes of the rubber tree are output; defining a fuzzy set, and outputting a rubber tapping period; based on the rubber tapping period, an operation schedule is arranged, and rubber tapping operation is executed by arriving at the rubber tapping point along the optimal path; and generating a feedback report. The device has the effect of improving the production efficiency.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things technology, and in particular to the design of an intelligent management method and system for rubber production based on Internet of Things technology. Background Art

[0002] In the traditional rubber production management system, a key flaw is the system's over-reliance on manual operation. This reliance brings two major problems: First, the low efficiency. Due to the limited speed and reliability of manual operation, the production process is slow and cannot respond quickly to market demand. Therefore, in order to improve production efficiency, it is urgent to improve this current situation of over-reliance on manual operation. Summary of the invention

[0003] In order to improve production efficiency, the present application provides an intelligent management method and system for rubber production based on Internet of Things technology.

[0004] The first object of the invention of this application is achieved through the following technical solutions: An intelligent management method for rubber production based on Internet of Things technology comprises the following steps: Collect key data, including soil moisture, pH value, and nutrient content; Process key data based on GIS software to generate soil fertility distribution maps; Based on genetic algorithms and soil fertility distribution maps, we optimize planting planning and output the optimal planting plan; When outputting the optimal planting plan, the tapping point and the starting position of the tapping machine are output based on GPS; Based on the Dijkstra algorithm, the shortest path from the starting position to each tapping point is calculated and the optimal path is output; Collect historical production data and related environmental data, establish ARIMA model for data difference processing, model parameter determination, fitting and prediction, and output rubber tree health indicators; Based on the preset fuzzy rules and the health indicators, a fuzzy set is defined and a tapping cycle is output; Arrange the operation schedule based on the tapping cycle and reach the tapping point along the optimal path to perform the tapping operation; Generate a feedback report, which includes the optimal planting plan, optimal path, health indicators, and rubber tapping cycle.

[0005] In a preferred embodiment, the step of optimizing the planting plan based on the genetic algorithm and the soil fertility distribution map and outputting the optimal planting plan includes the following steps: Planting plan Use vector express, It is a planting plan Total number of plots; Select a set of planting schemes as the initial population , ; Based on preset formula , It is a planting plan No. The potential yield of a plot of land, It is a planting plan No. Planting density of each plot, calculate planting plan Expected output ; Based on preset formula , It is a planting plan No. Planting cost per plot, calculate planting plan Cost ; Based on the preset fitness formula , is the weight of expected output, is the weight of the cost, calculating the fitness ; when , When the fitness threshold is reached, select the planting plan that meets the above conditions to enter the selection population ; Crossover initial population , select population , generate a new crossover population ; Crossover population Perform several planting scheme variations to generate variant populations ; Based on the roulette wheel selection algorithm, from the mutant population Select several planting plans to enter the final population ; Repeat crossover, mutation, and selection until the final population of , When it is the preset fitness target value, output the final population As the best planting plan.

[0006] In a preferred embodiment, when outputting the optimal planting plan, the step of outputting the tapping point and the starting position of the tapping machine based on GPS includes the following steps: Based on GPS, locate each tapping point and the starting position of the tapping machine; Based on the preset GPS coordinate library, the tapping points and the starting positions of the tapping machines are associated with the corresponding GPS coordinates, and the GPS coordinates of each tapping point and the starting position of the tapping machine are output.

[0007] In a preferred embodiment, the step of calculating the shortest path from the starting position to each tapping point based on the Dijkstra algorithm and outputting the optimal path includes the following steps: Build a graph model, where each tapping point and the starting position of the tapping machine are nodes; Based on the GPS coordinates, a weight is assigned to each edge in the graph model, wherein the weight represents the distance between two nodes; Set the starting position of the rubber tapping machine as the starting node; Set the distance of the starting node to 0 and the distance of all other nodes to infinity; Based on the priority queue, the current shortest distance of all unvisited nodes is stored; Select the node with the shortest distance from the priority queue and mark it as the current node; Calculate the distance from the current node to the neighboring node; When the calculated distance is less than the preset shortest distance, update the shortest distance of the neighbor node and the predecessor node; Mark the current node as visited; Repeat the above steps until the final node is marked as visited; When the final node is marked as visited, trace back from the final node to the starting node based on the predecessor node information to reconstruct the shortest path; Output the node sequence and related GPS coordinates of the optimal path.

[0008] In a preferred embodiment, the steps of collecting historical production data, establishing an ARIMA model for data differential processing, model parameter determination, fitting and prediction, and outputting health indicators of rubber trees include the following steps: Collect historical rubber tree production data within a preset time period and perform differential processing on the historical rubber tree production data; Based on the autocorrelation function ACF and the partial autocorrelation function PACF, the output parameters p, d, q are obtained, where p is the order of the autoregressive term, d is the number of differences, and q is the order of the moving average term. Based on the parameters p, d, q, fit the output ARIMA model; Based on the ARIMA model, forecast production; Compare the difference between the predicted output and the actual output and calculate the relative error; When the relative error is less than 5% and the predicted yield shows an upward trend, the health score is high; When the relative error is between 5% and 10% and the yield is stable, the health score is medium; When the relative error is greater than 10% and the yield shows a decreasing trend, the health score is low.

[0009] In a preferred embodiment, the step of defining a fuzzy set based on the preset fuzzy rules and the health indicators and outputting the tapping cycle comprises the following steps: The health scores were divided into three fuzzy sets: high, medium, and low; Based on the membership function, the membership of the fuzzy set is calculated; When the health score is high, calculate its membership to the high fuzzy set. When the membership is the highest, set the membership of the high fuzzy set to 1, and the membership of the other two fuzzy sets to 0. When the health score is medium, calculate its membership to the medium fuzzy set. When the membership is the highest, set the membership of the medium fuzzy set to 1, and the membership of the other two fuzzy sets to 0. When the health score is low, calculate its membership to the low fuzzy set. When the membership is the highest, set the membership of the low fuzzy set to 1, and the membership of the other two fuzzy sets to 0. The preset fuzzy rules are as follows: Rule 1: When the health score belongs to the high fuzzy set, the tapping cycle is short; Rule 2: When the health score belongs to the medium fuzzy set, the tapping cycle is medium; Rule 3: When the health score belongs to the low fuzzy set, the tapping cycle is long; Based on the membership degree and fuzzy rules, the tapping cycle of each tapping point is output.

[0010] The second object of the invention is achieved by the following technical solutions: An intelligent management system for rubber production based on Internet of Things technology, including: Collection module: collect key data, including soil moisture, pH value, and nutrient content; Processing module: Process key data based on GIS software to generate soil fertility distribution map; The first output module: optimizes the planting plan based on genetic algorithms and soil fertility distribution maps, and outputs the optimal planting plan; The second output module: when outputting the optimal planting plan, output the tapping point and the starting position of the tapping machine based on GPS; The third output module: Based on the Dijkstra algorithm, calculate the shortest path from the starting position to each tapping point and output the optimal path; The fourth output module: collects historical production data and related environmental data, establishes an ARIMA model for data differential processing, model parameter determination, fitting and prediction, and outputs health indicators of rubber trees; The fifth output module: based on the preset fuzzy rules and the health indicators, defines the fuzzy set and outputs the tapping cycle; Execution module: arranges the operation schedule based on the tapping cycle and reaches the tapping point along the optimal path to perform the tapping operation; Feedback module: Generates feedback report, which includes optimal planting plan, optimal path, health indicators, and rubber tapping cycle.

[0011] The third object of the invention is achieved by the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned intelligent management method for rubber production based on Internet of Things technology are implemented.

[0012] The fourth object of the invention of this application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent management method for rubber production based on the Internet of Things technology are implemented.

[0013] In summary, the present application includes at least one of the following beneficial technical effects: Through a series of carefully designed steps, the automation and optimization of rubber plantation management is achieved. First, key data such as soil moisture, pH value and nutrient content are collected, and then these data are analyzed using GIS software to draw soil fertility distribution maps. Genetic algorithms are used in combination with fertility distribution maps to optimize planting plans, determine the optimal planting plan, and locate the starting position of tapping points and tapping machines through GPS. Next, the Dijkstra algorithm is used to find the shortest path from the starting position to each tapping point. At the same time, historical production and environmental data are collected, and the ARIMA model is used for data analysis to predict the health indicators of rubber trees. Based on these indicators and preset fuzzy rules, the tapping cycle is determined, and the operation schedule is arranged accordingly to ensure that the tapping operation is completed efficiently along the optimal path. Finally, a comprehensive feedback report is generated, including the optimal planting plan, path, health indicators and tapping cycle, providing comprehensive data support and decision-making basis for the management of rubber plantations. This process reflects the coherence and logic from data collection to decision-making, aiming to improve the overall operational efficiency and production benefits of rubber plantations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1This is a flowchart of an implementation of an embodiment of an intelligent management method for rubber production based on Internet of Things technology in the present application; Figure 2 This is a flowchart for implementing step S30 in an embodiment of a rubber production intelligent management method based on Internet of Things technology of the present application; Figure 3 This is a flowchart for implementing step S40 in an embodiment of a rubber production intelligent management method based on Internet of Things technology of the present application; Figure 4 This is a flowchart for implementing step S50 in an embodiment of a rubber production intelligent management method based on Internet of Things technology of the present application; Figure 5 This is a flowchart for implementing step S60 in an embodiment of a rubber production intelligent management method based on Internet of Things technology of the present application; Figure 6 This is a flowchart for implementing step S70 in an embodiment of a rubber production intelligent management method based on Internet of Things technology of the present application; Figure 7 This is a principle block diagram of a computer device of the present application. DETAILED DESCRIPTION

[0015] The following is combined with Figure 1-7 This application is described in further detail.

[0016] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent management method for rubber production based on Internet of Things technology, which specifically includes the following steps: S10: Collect key data, including soil moisture, pH value, and nutrient content; S20: Process key data based on GIS software to generate soil fertility distribution map; S30: Optimize the planting plan based on the genetic algorithm and the soil fertility distribution map, and output the optimal planting plan; S40: When the optimal planting plan is output, the tapping point and the starting position of the tapping machine are output based on the GPS; S50: Based on the Dijkstra algorithm, the shortest path from the starting position to each tapping point is calculated, and the optimal path is output; S60: Collect historical production data and related environmental data, establish an ARIMA model to perform data differential processing, model parameter determination, fitting and prediction, and output health indicators of rubber trees; S70: Based on the preset fuzzy rules and the health indicators, define fuzzy sets and output the tapping cycle; S80: Arrange the operation schedule based on the tapping cycle, and reach the tapping point along the optimal path to perform the tapping operation; S90: Generate a feedback report, wherein the feedback report includes an optimal planting plan, an optimal path, health indicators, and a rubber tapping cycle.

[0017] In this embodiment, the automation and optimization management of rubber plantations are realized through a series of well-designed steps. First, key data such as soil moisture, pH value and nutrient content are collected, and then GIS software is used to analyze these data to draw a soil fertility distribution map. Genetic algorithm is used in combination with fertility distribution map to optimize planting planning, determine the optimal planting plan, and locate the starting position of tapping points and tapping machines by GPS. Then, Dijkstra algorithm is applied to find the shortest path from the starting position to each tapping point. At the same time, historical production and environmental data are collected, and data analysis is performed using ARIMA model to predict the health indicators of rubber trees. According to these indicators and preset fuzzy rules, the tapping cycle is determined, and the operation schedule is arranged accordingly to ensure that the tapping operation is completed efficiently along the optimal path. Finally, a comprehensive feedback report is generated, including the optimal planting plan, path, health indicators and tapping cycle, which provides comprehensive data support and decision-making basis for the management of rubber plantations. This process embodies the coherence and logic from data collection to decision-making, aiming to improve the overall operating efficiency and production efficiency of rubber plantations.

[0018] Figure 2 , step S30, comprising the steps of: S301: Planting plan Use vector express, It is a planting plan Total number of plots; S302: Select a group of planting schemes as the initial population , ; S303: Based on the preset formula , It is a planting plan No. The potential yield of a plot of land, It is a planting plan No. Planting density of each plot, calculate planting plan Expected output ; S304: Based on the preset formula , It is a planting plan No. Planting cost per plot, calculate planting plan Cost ; S305: Based on the preset fitness formula , is the weight of expected output, is the weight of the cost, calculating the fitness ; S306: When , When the fitness threshold is reached, select the planting plan that meets the above conditions to enter the selection population ; S307: Crossover initial population , select population , generate a new crossover population ; S308: Crossover population Perform several planting scheme variations to generate variant populations ; S309: Based on the roulette wheel selection algorithm, from the mutant population Select several planting plans to enter the final population ; S310: Repeat crossover, mutation, and selection. When the final population of , When it is the preset fitness target value, output the final population As the best planting plan.

[0019] In this embodiment, the planting plan is optimized by a genetic algorithm to find the optimal planting configuration. Vector In the form of Indicates the total number of plots. Based on a preset formula , , calculate the initial population Expected output and cost , where the expected output Potential yield based on plot and planting density ,cost Based on the planting cost of the plot Then, according to the preset fitness formula , combining the weights of output and cost , , calculate the fitness of each solution Only when fitness Greater than the preset fitness threshold When Then, through crossover and mutation operations, combined with the roulette wheel selection algorithm, the mutant population Select the scheme to enter the final population This process is repeated until the final population Fitness Reach the preset fitness target value , the final population output at this time is This process reflects the application of genetic algorithms in optimizing planting plans, ensuring the optimal balance between yield and cost.

[0020] Figure 3 , step S40, comprising the steps of: S401: Based on GPS, locate each tapping point and the starting position of the tapping machine; S402: Based on the preset GPS coordinate library, the tapping points and the starting positions of the tapping machines are associated with the corresponding GPS coordinates, and the GPS coordinates of each tapping point and the starting position of the tapping machine are output.

[0021] In this embodiment, the GPS technology is used to accurately locate the starting position of the rubber tapping point and the rubber tapping machine. First, the actual geographical location of each rubber tapping point is obtained through the GPS device, and then the location information is matched with the preset GPS coordinate library, the corresponding GPS coordinates are associated, and finally the precise GPS coordinates of each rubber tapping point and the starting position of the rubber tapping machine are output. This process ensures the accuracy and efficiency of the rubber tapping operation and provides the necessary location data for subsequent path planning and operation scheduling.

[0022] Figure 4 , step S50, comprising the steps of: S501: Establish a graph model, in which each tapping point and the starting position of the tapping machine are nodes; S502: Based on the GPS coordinates, assign a weight to each edge in the graph model, where the weight represents the distance between two nodes; S503: Setting the starting position of the rubber tapping machine as the starting node; S504: Set the distance of the starting node to 0, and the distances of all other nodes to infinity; S505: Based on the priority queue, store the current shortest distances of all unvisited nodes; S506: Select the node with the shortest distance from the priority queue and mark it as the current node; S507: Calculate the distance from the current node to the neighboring node; S508: When the calculated distance is less than the preset shortest distance, update the shortest distance of the neighbor node and the predecessor node; S509: Mark the current node as visited; S510: Repeat the above steps until the final node is marked as visited; S511: When the final node is marked as visited, trace back from the final node to the starting node based on the predecessor node information to rebuild the shortest path; S512: Output the node sequence and related GPS coordinates of the optimal path.

[0023] In the present embodiment, the operation path of the rubber tapping machine is optimized by establishing a graph model, wherein each rubber tapping point and the starting position of the rubber tapping machine are regarded as nodes in the graph, and the distance between the two points calculated based on the GPS coordinates is used as the weight of the edge connecting the nodes. The starting position of the rubber tapping machine is set as the starting node, and its distance is initialized to 0, and the distance of other nodes is infinite. Then, the priority queue is used to store and update the current shortest distance of all unvisited nodes, and the shortest distance of its neighbor nodes is calculated and updated by continuously selecting the node with the smallest distance to visit. This process continues until the shortest path to the final node is found. Finally, by backtracking the predecessor node information, the shortest path to the starting node is rebuilt from the final node, and the node sequence of this optimal path and its corresponding GPS coordinates are output to guide the rubber tapping machine to efficiently perform the rubber tapping operation.

[0024] Figure 5 , step S60, comprising the steps of: S601: Collect historical rubber tree production data within a preset time period, and perform differential processing on the historical rubber tree production data; S602: Based on the autocorrelation function ACF and the partial autocorrelation function PACF, output parameters p, d, q, where p is the order of the autoregressive term, d is the number of differences, and q is the order of the moving average term; S603: Based on the parameters p, d, q, fit and output the ARIMA model; S604: forecasting output based on the ARIMA model; S605: Compare the difference between the predicted output and the actual output, and calculate the relative error; S606: When the relative error is less than 5% and the predicted yield is on an upward trend, the health score is high; S607: When the relative error is between 5% and 10% and the yield is stable, the health score is medium; S608: When the relative error is greater than 10% and the yield is on a downward trend, the health score is low.

[0025] In the present embodiment, by differential processing and analysis of historical rubber tree production data, autocorrelation function ACF and partial autocorrelation function PACF are utilized to determine the parameters p, d, q of the ARIMA model, and then a time series model is fitted to predict future production. By comparing the difference between the predicted production and the actual production and calculating the relative error, the prediction accuracy of the model and the health status of rubber trees can be evaluated. According to the size of the relative error and the trend of the production, the health score is divided into high, medium and low three grades, wherein the relative error is less than 5% and the health score of the rubber tree with the rising trend of the predicted production is the highest, the relative error is between 5%-10% and the health score of the stable production is second, and the relative error is greater than 10% and the health score of the decline in production is the lowest. This process provides a scientific health assessment means for the management of rubber plantations.

[0026] Figure 6 , step S70, comprising the steps of: S701: Divide the health score into three fuzzy sets: high, medium, and low; S702: Calculate the membership of the fuzzy set based on the membership function; S703: When the health score is high, calculate its membership to the high fuzzy set. When the membership is the highest, set the membership of the high fuzzy set to 1, and set the membership of the other two fuzzy sets to 0; S704: When the health score is medium, calculate its membership to the medium fuzzy set. When the membership is the highest, set the membership of the medium fuzzy set to 1, and set the membership of the other two fuzzy sets to 0; S705: When the health score is low, calculate its membership to the low fuzzy set. When the membership is the highest, set the membership of the low fuzzy set to 1, and set the membership of the other two fuzzy sets to 0; S706: The preset fuzzy rules are as follows: Rule 1: When the health score belongs to the high fuzzy set, the tapping cycle is short; Rule 2: When the health score belongs to the medium fuzzy set, the tapping cycle is medium; Rule 3: When the health score belongs to the low fuzzy set, the tapping cycle is long; S707: Based on the membership degree and fuzzy rules, output the tapping cycle of each tapping point.

[0027] In this embodiment, in order to determine the tapping cycle of each tapping point, the health score is first divided into three fuzzy sets: high, medium, and low. Then, the degree to which each health score belongs to the corresponding fuzzy set is calculated by the membership function. When the health score is rated as high, its membership to the high fuzzy set is set to 1, and the membership of the other two fuzzy sets is set to 0; similarly, the same treatment is applied to the medium and low health scores. Subsequently, according to the preset fuzzy rules, if the health score belongs to the high fuzzy set, the tapping cycle is short, if it belongs to the medium fuzzy set, the tapping cycle is medium, and if it belongs to the low fuzzy set, the tapping cycle is long. Finally, the tapping cycle of each tapping point is output based on the membership and these fuzzy rules. This method converts qualitative health scores into quantitative tapping cycles through fuzzy logic theory, providing flexible and adaptable decision support for tapping operations in rubber plantations.

[0028] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0029] In one embodiment, a rubber production intelligent management system based on the Internet of Things technology is provided, and the rubber production intelligent management system based on the Internet of Things technology corresponds to the rubber production intelligent management method based on the Internet of Things technology in the above embodiment. The rubber production intelligent management system based on the Internet of Things technology includes: Collection module: collect key data, including soil moisture, pH value, and nutrient content; Processing module: Process key data based on GIS software to generate soil fertility distribution map; The first output module: optimizes the planting plan based on genetic algorithms and soil fertility distribution maps, and outputs the optimal planting plan; The second output module: when outputting the optimal planting plan, output the tapping point and the starting position of the tapping machine based on GPS; The third output module: Based on the Dijkstra algorithm, calculate the shortest path from the starting position to each tapping point and output the optimal path; The fourth output module: collects historical production data and related environmental data, establishes an ARIMA model for data differential processing, model parameter determination, fitting and prediction, and outputs health indicators of rubber trees; The fifth output module: based on the preset fuzzy rules and the health indicators, defines the fuzzy set and outputs the tapping cycle; Execution module: arranges the operation schedule based on the tapping cycle and reaches the tapping point along the optimal path to perform the tapping operation; Feedback module: Generates feedback report, which includes optimal planting plan, optimal path, health indicators, and rubber tapping cycle.

[0030] Optionally, also include: Vector Module: Planting Plan Use vector express, It is a planting plan Total number of plots; Initial population module: select a set of planting schemes as the initial population , ; The first calculation module: based on the preset formula , It is a planting plan No. The potential yield of a plot of land, It is a planting plan No. Planting density of each plot, calculate planting plan Expected output ; Second calculation module: based on preset formula , It is a planting plan No. Planting cost per plot, calculate planting plan Cost ; The third calculation module: based on the preset fitness formula , is the weight of expected output, is the weight of the cost, calculating the fitness ; Select the population module: , When the fitness threshold is reached, select the planting plan that meets the above conditions to enter the selection population ; Cross population module: cross initial population , select population , generate a new crossover population ; Mutation population module: for crossover population Perform several planting scheme variations to generate variant populations ; Final population module: Based on the roulette wheel selection algorithm, from the mutant population Select several planting plans to enter the final population ; The sixth output module: Repeatedly perform crossover, mutation, and selection. When the final population of , When it is the preset fitness target value, output the final population As the best planting plan.

[0031] Optionally, also include: Positioning module: Based on GPS, locate each tapping point and the starting position of the tapping machine; The seventh output module: Based on the preset GPS coordinate library, the tapping points and the starting positions of the tapping machines are associated with the corresponding GPS coordinates, and the GPS coordinates of each tapping point and the starting position of the tapping machine are output.

[0032] Optionally, also include: Node module: Establish a graph model, in which each tapping point and the starting position of the tapping machine are nodes; Weight Assignment Module: Based on GPS coordinates, a weight is assigned to each edge in the graph model, and the weight represents the distance between two nodes; Starting node module: sets the starting position of the rubber tapping machine as the starting node; Setting module: Set the distance of the starting node to 0 and the distance of all other nodes to infinity; Storage module: Based on the priority queue, it stores the current shortest distances of all unvisited nodes; Current node module: select the node with the smallest distance from the priority queue and mark it as the current node; The fourth calculation module: calculates the distance from the current node to the neighboring node; Update module: When the calculated distance is less than the preset shortest distance, update the shortest distance of the neighbor node and the predecessor node; The first marking module: marks the current node as visited; Second marking module: repeat the above steps until the final node is marked as visited; Shortest path module: When the final node is marked as visited, the shortest path is reconstructed by tracing back from the final node to the starting node based on the predecessor node information; The eighth output module: outputs the node sequence of the optimal path and the related GPS coordinates.

[0033] Optionally, also include: Collection and processing module: collects historical rubber tree production data within a preset time period and performs differential processing on the historical rubber tree production data; S602: Based on the autocorrelation function ACF and the partial autocorrelation function PACF, output parameters p, d, q, where p is the order of the autoregressive term, d is the number of differences, and q is the order of the moving average term; The ninth output module: based on the parameters p, d, q, fit and output the ARIMA model; Output forecasting module: forecast output based on ARIMA model; The fifth calculation module: compares the difference between the predicted output and the actual output and calculates the relative error; First comparison module: when the relative error is less than 5% and the predicted yield shows an upward trend, the health score is high; Second comparison module: when the relative error is between 5% and 10% and the yield is stable, the health score is medium; The third comparison module: When the relative error is greater than 10% and the yield shows a downward trend, the health score is low.

[0034] Optionally, also include: Division module: divides the health score into three fuzzy sets: high, medium, and low; The sixth calculation module: based on the membership function, calculates the membership of the fuzzy set; The first module: when the health score is high, calculate its membership to the high fuzzy set. When the membership is the highest, set the membership of the high fuzzy set to 1, and the membership of the other two fuzzy sets to 0. The second module: when the health score is medium, calculate its membership to the medium fuzzy set. When the membership is the highest, set the membership of the medium fuzzy set to 1, and the membership of the other two fuzzy sets to 0. The third module: when the health score is low, calculate its membership to the low fuzzy set. When the membership is the highest, set the membership of the low fuzzy set to 1, and the membership of the other two fuzzy sets to 0. Preset rule module: The preset fuzzy rules are as follows: Rule 1: When the health score belongs to the high fuzzy set, the tapping cycle is short; Rule 2: When the health score belongs to the medium fuzzy set, the tapping cycle is medium; Rule 3: When the health score belongs to the low fuzzy set, the tapping cycle is long; The tenth output module: Based on the membership degree and fuzzy rules, output the tapping cycle of each tapping point.

[0035] The specific definition of an intelligent management system for rubber production based on the Internet of Things technology can be found in the above definition of an intelligent management method for rubber production based on the Internet of Things technology, which will not be repeated here. Each module in the above-mentioned intelligent management system for rubber production based on the Internet of Things technology can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0036] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store planting plans. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent management method for rubber production based on Internet of Things technology is realized.

[0037] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an intelligent management method for rubber production based on Internet of Things technology is implemented.

[0038] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, an intelligent management method for rubber production based on Internet of Things technology is implemented.

[0039] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0040] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. An intelligent management method for rubber production based on Internet of Things technology, characterized in that: Includes steps: Collect key data, including soil moisture, pH value, and nutrient content; Process key data based on GIS software to generate soil fertility distribution maps; Based on genetic algorithms and soil fertility distribution maps, we optimize planting planning and output the optimal planting plan; When outputting the optimal planting plan, the tapping point and the starting position of the tapping machine are output based on GPS; Based on the Dijkstra algorithm, the shortest path from the starting position to each tapping point is calculated and the optimal path is output; Collect historical production data and related environmental data, establish ARIMA model for data difference processing, model parameter determination, fitting and prediction, and output rubber tree health indicators; Based on the preset fuzzy rules and the health indicators, a fuzzy set is defined and a tapping cycle is output; Arrange the operation schedule based on the tapping cycle and reach the tapping point along the optimal path to perform the tapping operation; Generate a feedback report, which includes the optimal planting plan, optimal path, health indicators, and rubber tapping cycle.

2. The intelligent management method for rubber production based on Internet of Things technology according to claim 1, characterized in that: The step of optimizing the planting plan based on the genetic algorithm and the soil fertility distribution map and outputting the optimal planting plan comprises the following steps: Planting plan Use vector express, It is a planting plan Total number of plots; Select a set of planting schemes as the initial population , ; Based on preset formula , It is a planting plan No. The potential yield of a plot of land, It is a planting plan No. Planting density of each plot, calculate planting plan Expected output ; Based on preset formula , It is a planting plan No. Planting cost per plot, calculate planting plan Cost ; Based on the preset fitness formula , is the weight of expected output, is the weight of the cost, calculating the fitness ; when , When the fitness threshold is reached, select the planting plan that meets the above conditions to enter the selection population ; Crossover initial population , select population , generate a new crossover population ; Crossover population Perform several planting scheme variations to generate variant populations ; Based on the roulette wheel selection algorithm, from the mutant population Select several planting plans to enter the final population ; Repeat crossover, mutation, and selection until the final population of , When it is the preset fitness target value, output the final population As the best planting plan.

3. The intelligent management method for rubber production based on Internet of Things technology according to claim 1 is characterized in that: The step of outputting the tapping point and the starting position of the tapping machine based on GPS when outputting the optimal planting plan comprises the following steps: Based on GPS, locate each tapping point and the starting position of the tapping machine; Based on the preset GPS coordinate library, the tapping points and the starting positions of the tapping machines are associated with the corresponding GPS coordinates, and the GPS coordinates of each tapping point and the starting position of the tapping machine are output.

4. The intelligent management method for rubber production based on Internet of Things technology according to claim 1 is characterized in that: The step of calculating the shortest path from the starting position to each tapping point based on the Dijkstra algorithm and outputting the optimal path includes the following steps: Build a graph model, where each tapping point and the starting position of the tapping machine are nodes; Based on the GPS coordinates, a weight is assigned to each edge in the graph model, wherein the weight represents the distance between two nodes; Set the starting position of the rubber tapping machine as the starting node; Set the distance of the starting node to 0 and the distance of all other nodes to infinity; Based on the priority queue, the current shortest distance of all unvisited nodes is stored; Select the node with the shortest distance from the priority queue and mark it as the current node; Calculate the distance from the current node to the neighboring node; When the calculated distance is less than the preset shortest distance, update the shortest distance of the neighbor node and the predecessor node; Mark the current node as visited; Repeat the above steps until the final node is marked as visited; When the final node is marked as visited, trace back from the final node to the starting node based on the predecessor node information to reconstruct the shortest path; Output the node sequence and related GPS coordinates of the optimal path.

5. The intelligent management method for rubber production based on Internet of Things technology according to claim 1 is characterized in that: The steps of collecting historical production data, establishing an ARIMA model for data differential processing, model parameter determination, fitting and prediction, and outputting health indicators of rubber trees include the following steps: Collect historical rubber tree production data within a preset time period and perform differential processing on the historical rubber tree production data; Based on the autocorrelation function ACF and the partial autocorrelation function PACF, the output parameters p, d, q are obtained, where p is the order of the autoregressive term, d is the number of differences, and q is the order of the moving average term. Based on the parameters p, d, q, fit the output ARIMA model; Based on the ARIMA model, forecast production; Compare the difference between the predicted output and the actual output and calculate the relative error; When the relative error is less than 5% and the predicted yield shows an upward trend, the health score is high; When the relative error is between 5% and 10% and the yield is stable, the health score is medium; When the relative error is greater than 10% and the yield shows a decreasing trend, the health score is low.

6. The intelligent management method for rubber production based on Internet of Things technology according to claim 1 is characterized in that: The step of defining a fuzzy set based on the preset fuzzy rules and the health indicators and outputting the tapping cycle comprises the following steps: The health scores were divided into three fuzzy sets: high, medium, and low; Based on the membership function, the membership of the fuzzy set is calculated; When the health score is high, calculate its membership to the high fuzzy set. When the membership is the highest, set the membership of the high fuzzy set to 1, and the membership of the other two fuzzy sets to 0. When the health score is medium, calculate its membership to the medium fuzzy set. When the membership is the highest, set the membership of the medium fuzzy set to 1, and the membership of the other two fuzzy sets to 0. When the health score is low, calculate its membership to the low fuzzy set. When the membership is the highest, set the membership of the low fuzzy set to 1, and the membership of the other two fuzzy sets to 0. The preset fuzzy rules are as follows: Rule 1: When the health score belongs to the high fuzzy set, the tapping cycle is short; Rule 2: When the health score belongs to the medium fuzzy set, the tapping cycle is medium; Rule 3: When the health score belongs to the low fuzzy set, the tapping cycle is long; Based on the membership degree and fuzzy rules, the tapping cycle of each tapping point is output.

7. An intelligent management system for rubber production based on Internet of Things technology, characterized in that: include: Collection module: collect key data, including soil moisture, pH value, and nutrient content; Processing module: Process key data based on GIS software to generate soil fertility distribution map; The first output module: optimizes the planting plan based on genetic algorithms and soil fertility distribution maps, and outputs the optimal planting plan; The second output module: when outputting the optimal planting plan, output the tapping point and the starting position of the tapping machine based on GPS; The third output module: Based on the Dijkstra algorithm, calculate the shortest path from the starting position to each tapping point and output the optimal path; The fourth output module: collects historical production data and related environmental data, establishes an ARIMA model for data differential processing, model parameter determination, fitting and prediction, and outputs health indicators of rubber trees; The fifth output module: based on the preset fuzzy rules and the health indicators, defines the fuzzy set and outputs the tapping cycle; Execution module: arranges the operation schedule based on the tapping cycle and reaches the tapping point along the optimal path to perform the tapping operation; Feedback module: Generates feedback report, which includes optimal planting plan, optimal path, health indicators, and rubber tapping cycle.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the intelligent management method for rubber production based on Internet of Things technology as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the intelligent management method for rubber production based on Internet of Things technology as claimed in any one of claims 1 to 6.

Images