Sugarcane planting decision optimization method and system based on AI analysis

Abstract

The invention relates to the technical field of intelligent agriculture application, and discloses a sugarcane planting decision optimization method and system based on AI analysis, and the method comprises the steps: receiving a sugarcane planting decision optimization instruction, determining a sugarcane management system based on the sugarcane planting decision optimization instruction, obtaining a sugarcane planting instruction, obtaining an information collection tool set based on the sugarcane planting instruction, and carrying out the collection of the information collection tool set. Acquiring an acquisition node set based on an information acquisition tool set, acquiring an update database and a pre-processing data table set based on the acquisition node set, and acquiring a sugarcane planting decision set based on the pre-processing data table set and a pre-constructed analysis decision model, and obtaining a farming pre-execution instruction set based on the sugarcane planting decision set and a pre-constructed decision optimization model, obtaining a farming implementation instruction set based on the farming pre-execution instruction set and the update database and information exchange unit, and realizing sugarcane planting decision optimization by using the farming implementation instruction set. According to the invention, the accuracy of sugarcane planting decision optimization can be improved.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture application technology, and in particular to a method and system for optimizing sugarcane planting decisions based on AI analysis. Background Technology

[0002] In modern agricultural production, sugarcane planting decision optimization technology is crucial. With the intensification of global climate change, the environmental factors affecting sugarcane planting are becoming increasingly complex, making planting decisions more difficult to control. Highly accurate planting decisions can ensure precise control of pests and diseases during the sugarcane planting process, thereby improving sugarcane quality and yield.

[0003] Currently, traditional sugarcane planting decisions rely primarily on manual experience and static data, lacking real-time collaborative analysis of multi-source dynamic environmental factors. During the planting process, data collection on key influencing factors such as soil, weather changes, and pests and diseases is often scattered and unstructured, leading to delayed decision-making. Furthermore, traditional methods struggle to effectively integrate time-series data, resulting in low decision accuracy. Therefore, improving the accuracy of sugarcane planting decision optimization has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides an AI-based sugarcane planting decision optimization method and a computer-readable storage medium, the main purpose of which is to achieve accurate control of electric heat tracing pipelines.

[0005] To achieve the above objectives, this invention provides an AI-based method for optimizing sugarcane planting decisions, comprising:

[0006] The system receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0007] Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools;

[0008] The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables.

[0009] Based on the preprocessed data set and the pre-constructed analysis and decision model, a sugarcane planting decision set is obtained;

[0010] Based on the sugarcane planting decision set and the pre-constructed decision optimization model, obtain the agricultural pre-execution instruction set;

[0011] Based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit, an agricultural implementation instruction set is obtained, and the sugarcane planting decision is optimized using the agricultural implementation instruction set.

[0012] Optionally, the information acquisition toolset based on sugarcane planting instructions includes:

[0013] The planting target node is obtained based on the sugarcane planting instruction and the preset instruction parsing method, wherein the planting target node includes sugarcane variety, planting area and sugarcane planting plan;

[0014] The sugarcane planting influencing factor set is obtained based on the planting target node and the pre-constructed influencing factor matching model. The sugarcane planting influencing factor set includes multiple sugarcane planting influencing factors.

[0015] Sugarcane planting influencing factors were extracted sequentially from the sugarcane planting influencing factor set, and an initial information collection tool was obtained based on the sugarcane planting influencing factors;

[0016] By summarizing the aforementioned initial information collection tools, we obtain an initial information collection toolset.

[0017] The initial information collection toolset is filtered and selected to obtain the final information collection toolset.

[0018] Optionally, the step of acquiring the collection node set based on the information collection toolset includes:

[0019] Information collection tools are extracted sequentially from the set of information collection tools, and the following operations are performed on each extracted information collection tool:

[0020] An initial node set is obtained based on the extracted information collection tools and the preset collection time interval. The initial node set includes one or more initial nodes, and the initial nodes include the data collection time, the value of the sugarcane planting influencing factor, and the name of the sugarcane planting influencing factor.

[0021] Initial nodes are extracted sequentially from the initial node set, and the following operations are performed on each extracted initial node:

[0022] Data filtering methods are obtained based on information processing units, and standardized nodes are obtained based on the extracted initial nodes and data filtering methods.

[0023] Summarize the standardized nodes to obtain the standardized node set;

[0024] The standardized node sets are aggregated to obtain multiple standardized node sets, which are then used as the collection node sets.

[0025] Optionally, the step of obtaining the updated database and preprocessed data table set based on the collection node set includes:

[0026] Collecting nodes are extracted sequentially from the collection node set, and sugarcane planting influencing factor names are extracted from the collection nodes. The sugarcane planting influencing factor names are used to identify data tables with table names in a pre-constructed database, wherein the table name of the data table is the sugarcane planting influencing factor name.

[0027] The data table is updated by using the sugarcane planting influencing factor values ​​corresponding to the data collection nodes and the data collection time.

[0028] After confirming that each data collection node in the data collection node set has obtained the corresponding updated data table, the updated data tables are aggregated to obtain multiple updated data tables. The multiple updated data tables are then stored in the database to obtain the updated database.

[0029] The missing value imputation method is obtained based on the information processing unit, and the preprocessed data table is obtained based on the updated data table and the missing value imputation method, wherein the preprocessed data table corresponds one-to-one with the acquisition node;

[0030] Summarize the preprocessed data tables to obtain the preprocessed data table set.

[0031] Optionally, obtaining the preprocessed data table based on the updated data table and the missing value imputation method includes:

[0032] Sort the data collection nodes in the updated data table according to the data collection time of the collection nodes from earliest to latest to obtain the updated data sequence;

[0033] The updated data collection times are extracted sequentially from the updated data sequence to obtain the reference time;

[0034] Using the reference time, the analysis time is determined in the updated data sequence, wherein the acquisition node corresponding to the analysis time is adjacent to and lags behind the acquisition node corresponding to the reference time.

[0035] Calculate the absolute difference between the reference time and the analysis time to obtain the analysis difference;

[0036] Compare the analyzed difference with the data acquisition time interval;

[0037] If the difference is not equal to the collection time interval, a missing value sequence is obtained using a pre-constructed missing value completion formula, wherein the missing value sequence includes one or more missing values, and the missing value completion formula is as follows:

[0038]

[0039] in, Indicates the missing numerical sequence of the first... One missing value This indicates the numerical values ​​of sugarcane planting influencing factors corresponding to the reference time. This represents the numerical values ​​of sugarcane planting influencing factors corresponding to the analysis time. Indicates the missing numerical sequence of the first... The missing time corresponding to each missing value. Indicates reference time. Indicates the analysis time. This indicates the difference in analysis. Indicates the time interval for data collection;

[0040] By associating missing values ​​with the corresponding missing times, we can obtain missing nodes.

[0041] Summarize the missing nodes to obtain the missing node set, and add the missing node set to the updated data table to obtain the preprocessed data table.

[0042] Optionally, obtaining the sugarcane planting decision set based on the preprocessed data set and the pre-built analysis and decision model includes:

[0043] The preprocessed data tables are extracted sequentially from the preprocessed data table set, and the following operations are performed on the extracted preprocessed data tables:

[0044] The preprocessed data in the preprocessed data table is sorted according to the time sequence corresponding to the preprocessed data to obtain the preprocessed data sequence.

[0045] Using a preset fixed window, a sequence of feature nodes is extracted from the preprocessed data sequence, wherein the window length value of the preset fixed window is set.

[0046] The number of feature nodes in the feature node sequence is counted to obtain the number of discriminations.

[0047] The sugarcane planting status is obtained based on the discrimination quantity and window length value, wherein the sugarcane planting status is either normal or abnormal.

[0048] If the number of samples is less than the window length, the sugarcane planting status is confirmed to be normal.

[0049] Otherwise, anomaly discrimination values ​​are obtained based on the feature node sequence and the pre-built anomaly alarm model;

[0050] If the abnormal discrimination value is outside the preset normal value range, the sugarcane planting status is confirmed to be abnormal; otherwise, the sugarcane planting status is confirmed to be normal.

[0051] When the sugarcane planting status is abnormal, an analysis and decision-making model is obtained based on the AI ​​analysis unit, and a sugarcane planting decision is obtained based on the feature node sequence and the analysis and decision-making model.

[0052] By summarizing sugarcane planting decisions, a sugarcane planting decision set is obtained.

[0053] Optionally, the step of obtaining the agricultural pre-execution instruction set based on the sugarcane planting decision set and the pre-constructed decision optimization model includes:

[0054] Sugarcane planting decisions are extracted sequentially from the sugarcane planting decision set, and pre-execution planting decisions are obtained based on the sugarcane planting decisions and the preset sugarcane planting decision specification set.

[0055] The pre-implementation planting decisions are summarized to obtain the pre-implementation planting decision set;

[0056] The agricultural pre-execution instruction set is obtained based on the pre-execution planting decision set and the decision optimization unit.

[0057] Optionally, the step of obtaining the agricultural pre-execution instruction set based on the pre-execution planting decision set and the decision optimization unit includes:

[0058] Based on each sugarcane planting influencing factor in the sugarcane planting influencing factor set, multiple pre-planting decision value sets are extracted from the pre-implementation planting decision set, wherein the sugarcane planting influencing factors correspond one-to-one with the pre-planting decision value sets.

[0059] For each of the multiple pre-planting decision data sets, perform the following operation:

[0060] The decision clustering method is obtained based on the decision optimization unit. The decision clustering method is used to cluster the pre-planting decision numerical set to obtain multiple clustered decision numerical sets.

[0061] The number of pre-planting decision values ​​in the statistical pre-planting decision value set is used to obtain the statistical decision quantity;

[0062] Calculate the product of the number of statistical decisions and the preset confidence ratio to obtain the number of screenings. Count the number of cluster decision values ​​corresponding to each cluster decision value set in the multiple cluster decision value sets to obtain the number of multiple cluster statistical decisions.

[0063] By using the number of screenings and the number of multiple cluster statistical decisions, multiple target decision value sets are identified from multiple cluster decision value sets, and the number of cluster statistical decisions corresponding to the target decision value sets is greater than or equal to the number of screenings.

[0064] Extract the target decision value set with the largest number of clustered statistical decisions from multiple target decision value sets to obtain the reference decision value set;

[0065] Calculate the mean of the reference decision values ​​in the reference decision value set to obtain the mean of the reference decision values;

[0066] The pre-execution agricultural command values ​​are calculated based on the average reference decision values ​​and multiple target decision value sets, as shown below:

[0067]

[0068] in, This represents the value of the pre-executed agricultural instructions. This indicates that the set of decision values ​​for multiple objectives is shared. A set of numerical values ​​for a single objective decision. Represents the first value in a set of multiple objective decision values. The number of clustered statistical decisions corresponding to a set of target decision values. Represents the first value in a set of multiple objective decision values. The number of clustered statistical decisions corresponding to a set of target decision values. Indicates the first value in the target decision numerical set. A target decision value, This represents the mean of the reference decision values. Indicates the first value in the target decision numerical set. A target decision value, The total number of target decision values ​​in the set is A set of numerical values ​​for a single objective decision. Indicates a non-zero positive coefficient;

[0069] The agricultural pre-execution instructions are obtained based on the numerical values ​​of the pre-executed agricultural instructions, and the agricultural pre-execution instructions are summarized to obtain the agricultural pre-execution instruction set.

[0070] Optionally, obtaining the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the update database, and the information exchange unit includes:

[0071] The agricultural pre-execution instructions are extracted sequentially from the set of agricultural pre-execution instructions, and the following operations are performed on the extracted agricultural pre-execution instructions:

[0072] Based on the agricultural pre-execution instructions and the updated database, an effective impact factor data table is obtained. The effective impact factor data table contains one or more effective impact factor nodes, and each effective impact factor node includes the effective impact factor collection time and the effective impact factor value.

[0073] Obtain a line graph of effective impact factors based on the effective impact factor data table;

[0074] The method for obtaining instruction confirmation based on information exchange unit is used to obtain agricultural implementation instructions based on agricultural pre-execution instructions, effective influencing factor line charts, and the instruction confirmation method.

[0075] By compiling agricultural implementation instructions, a set of agricultural implementation instructions is obtained.

[0076] To achieve the above objectives, the present invention also provides an AI-based sugarcane planting decision optimization system, comprising:

[0077] The data acquisition and processing module is used to receive sugarcane planting decision optimization instructions, and to confirm the sugarcane management system based on the sugarcane planting decision optimization instructions. The sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0078] Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools;

[0079] The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables.

[0080] The AI ​​analysis and decision-making module is used to obtain a sugarcane planting decision set based on the preprocessed data table set and the pre-built analysis and decision-making model.

[0081] The planting decision optimization module is used to obtain a set of agricultural pre-execution instructions based on the sugarcane planting decision set and the pre-constructed decision optimization model.

[0082] The planting instruction confirmation module is used to obtain the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the update database, and the information exchange unit, and to optimize sugarcane planting decisions using the agricultural implementation instruction set.

[0083] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0084] A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the aforementioned AI-based sugarcane planting decision optimization method.

[0085] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned AI-based sugarcane planting decision optimization method.

[0086] To address the problems described in the background art, this invention receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit. It acquires sugarcane planting instructions and, based on these instructions, obtains an information collection toolset. This toolset includes multiple information collection tools, demonstrating that by integrating and optimizing the information collection tools used, this invention improves data acquisition efficiency. Based on the information collection toolset, it acquires a collection node set, and based on the collection node set, it acquires an updated database and a preprocessed data table set. The preprocessed data table set includes multiple preprocessed data tables. This invention improves data integrity and reliability by performing real-time filtering, dynamic storage, and missing data filling operations on the sugarcane planting influencing factor values, thereby enhancing the accuracy of AI analysis and decision-making. Based on the preprocessed data table set and a pre-built analysis and decision-making model, it acquires a sugarcane planting decision set. This invention uses a dynamic window detection method to promptly determine the status of sugarcane planting influence shadows, achieving real-time monitoring of the sugarcane planting status and enabling timely decision-making for abnormal states. Based on the sugarcane planting decision set and the pre-constructed decision optimization model, a set of pre-execution agricultural instructions is obtained. This invention uses a clustering algorithm to remove outliers from the pre-execution decision set, takes the reference decision mean as the core, and employs a dynamic weighting method to ensure that the pre-execution agricultural instructions closely approximate the optimal planting parameters, thereby improving the rationality of the decisions and the scientific and executable nature of the agricultural instructions. Based on the pre-execution agricultural instructions set, the updated database, and the information exchange unit, a set of implementation agricultural instructions is obtained. This implementation agricultural instructions set is then used to optimize sugarcane planting decisions. This invention combines pre-execution agricultural instructions with the updated database and the information exchange unit to generate a visualized implementation agricultural instruction set, enabling dynamic adjustment of sugarcane planting decisions and improving the accuracy and executability of sugarcane planting instructions. Therefore, this invention can improve the accuracy of sugarcane planting decision optimization. Attached Figure Description

[0087] Figure 1 A flowchart illustrating an AI-based sugarcane planting decision optimization method according to an embodiment of the present invention;

[0088] Figure 2 This is a functional module diagram of an AI-based sugarcane planting decision optimization system provided in an embodiment of the present invention;

[0089] Figure 3 A schematic diagram of the structure of an electronic device for implementing the AI-based sugarcane planting decision optimization method according to an embodiment of the present invention;

[0090] Figure 4A sugarcane management system APP interface diagram of an AI-based sugarcane planting decision optimization system provided in an embodiment of the present invention;

[0091] Explanation of reference numerals in the attached figures:

[0092] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0093] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0094] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0095] This application provides a method for optimizing sugarcane planting decisions based on AI analysis. The executing entity of this AI-based sugarcane planting decision optimization method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the AI-based sugarcane planting decision optimization method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0096] Reference Figure 1 The diagram shown is a flowchart illustrating an AI-based sugarcane planting decision optimization method according to an embodiment of the present invention. In this embodiment, the AI-based sugarcane planting decision optimization method includes:

[0097] S1. Receive sugarcane planting decision optimization instructions, confirm the sugarcane management system based on the sugarcane planting decision optimization instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0098] It should be explained that the sugarcane planting decision optimization instruction is issued by personnel who want to optimize sugarcane planting decisions. The sugarcane management system is an app used to achieve sugarcane planting decision optimization. The sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit. For the specific application of these units, please refer to the following embodiments. The main purpose of this invention is to improve the accuracy of sugarcane planting decisions. For details, please refer to... Figure 4 As shown, Figure 4 This is a screenshot of the sugarcane management system app interface.

[0099] For example, Xiao Zhang, as the manager of sugarcane planting, in order to realize the automatic decision-making of agricultural work in the process of sugarcane planting from cultivation to harvest, and to avoid the problem of inaccurate execution of agricultural work at each stage of sugarcane growth, which would lead to a decrease in sugarcane yield, Xiao Zhang issues sugarcane planting decision optimization instructions and confirms the sugarcane management system.

[0100] S2. Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools.

[0101] It should be explained that the toolset for acquiring information based on sugarcane planting instructions includes:

[0102] The planting target node is obtained based on the sugarcane planting instruction and the preset instruction parsing method, wherein the planting target node includes sugarcane variety, planting area and sugarcane planting plan;

[0103] The sugarcane planting influencing factor set is obtained based on the planting target node and the pre-constructed influencing factor matching model. The sugarcane planting influencing factor set includes multiple sugarcane planting influencing factors.

[0104] Sugarcane planting influencing factors were extracted sequentially from the sugarcane planting influencing factor set, and an initial information collection tool was obtained based on the sugarcane planting influencing factors;

[0105] By summarizing the aforementioned initial information collection tools, we obtain an initial information collection toolset.

[0106] The initial information collection toolset is filtered and selected to obtain the final information collection toolset.

[0107] It should be understood that a sugarcane planting instruction is a message merging multiple sugarcane planting information. It is input into the sugarcane management system in a fixed format by personnel who want to optimize sugarcane planting decisions. The instruction parsing method is the message acquisition method set by the sugarcane management system according to the instruction format. For example, if Xiao Zhang issues a sugarcane planting instruction of 01130210378, the sugarcane management system first obtains the first three digits 011 as the sugarcane variety, then obtains the three digits 302 as the sugarcane planting area, and finally obtains the last five digits 10378 as the sugarcane planting plan.

[0108] Understandably, sugarcane planting influencing factors are a collection of environmental elements that can affect sugarcane growth throughout the entire growth cycle. The influencing factors involved will vary depending on the sugarcane variety, the planting area, and the planting scheme. Optionally, sugarcane planting influencing factors include, but are not limited to, temperature, humidity, rainfall, and soil pH.

[0109] It should be explained that the aforementioned influencing factor matching model is an algorithm-based sugarcane planting influencing factor mapping system. It can match sugarcane planting influencing factors based on sugarcane variety, planting region, and planting plan. For example, assuming the sugarcane variety is sugarcane, the planting region is Guangdong, and the planting plan is summer planting, considering that Guangdong experiences high temperatures and is susceptible to typhoons and rainfall, and the planting season is summer, the matched influencing factors for sugarcane planting are wind force, temperature, humidity, and rainfall. Assuming the sugarcane variety is fruit sugarcane, the planting region is Shanxi, and the planting plan is spring planting, considering that Shanxi is susceptible to sandstorms and the planting season is spring, the matched influencing factors for sugarcane planting are PM2.5, humidity, and rainfall. Generally, the actual sugarcane planting influencing factors matched for each planting target node will include multiple environmental factors; this example only lists some of these environmental factors.

[0110] It should be explained that the initial information acquisition tool is a numerical acquisition device used to collect values ​​of sugarcane planting influencing factors. Each sugarcane planting influencing factor corresponds one-to-one with an initial information acquisition tool. Generally, in practice, multiple initial information acquisition tools may correspond to the same numerical acquisition device. Therefore, by filtering and selecting, identical initial information acquisition tools in the initial information acquisition tool set are merged to obtain an information acquisition tool set. For example, assuming that obtaining soil pH, soil nitrogen content, and soil conductivity requires three initial information acquisition tools, but all three are soil sensors, then the soil sensor obtained after filtering and selecting the three initial information acquisition tools will be used as the information acquisition tool. This embodiment of the invention improves data acquisition efficiency by integrating and optimizing the information acquisition tool resources used.

[0111] S3. Obtain a set of collection nodes based on the information collection toolset, and obtain an updated database and a set of preprocessed data tables based on the set of collection nodes, wherein the set of preprocessed data tables contains multiple preprocessed data tables.

[0112] In detail, the acquisition of the collection node set based on the information collection toolset includes:

[0113] Information collection tools are extracted sequentially from the set of information collection tools, and the following operations are performed on each extracted information collection tool:

[0114] An initial node set is obtained based on the extracted information collection tools and the preset collection time interval. The initial node set includes one or more initial nodes, and the initial nodes include the data collection time, the value of the sugarcane planting influencing factor, and the name of the sugarcane planting influencing factor.

[0115] Initial nodes are extracted sequentially from the initial node set, and the following operations are performed on each extracted initial node:

[0116] Data filtering methods are obtained based on information processing units, and standardized nodes are obtained based on the extracted initial nodes and data filtering methods.

[0117] Summarize the standardized nodes to obtain the standardized node set;

[0118] The standardized node sets are aggregated to obtain multiple standardized node sets, which are then used as the collection node sets.

[0119] It should be understood that the initial node set is a collection of multiple initial nodes collected using the same information collection tool. For example, if the soil sensor obtains at 9:00 that the soil pH value is 6.8, the soil nitrogen content is 0.3%, and the soil moisture is 82%, then the three initial nodes collected are (9:00, soil pH value, 6.8), (9:00, soil nitrogen content, 0.3%), and (9:00, soil moisture, 0.3%).

[0120] Understandably, information collection tools may experience periodic operational anomalies. Therefore, the sugarcane planting influencing factor values ​​corresponding to the initial nodes may contain anomalies. To ensure the accuracy of decision-making, data filtering methods are needed to filter the initial nodes. The process of obtaining standardized nodes based on the extracted initial nodes and the data filtering method is as follows: For example, the normal range for sugarcane planting influencing factor values ​​is set to 0 to 100. When the sugarcane planting influencing factor value corresponding to the initial node (e.g., 65535) exceeds the range of 0 to 100, the sugarcane planting influencing factor value 65535 is removed.

[0121] It should be explained that the process of obtaining the updated database and preprocessed data table set based on the collection node set includes:

[0122] Collecting nodes are extracted sequentially from the collection node set, and sugarcane planting influencing factor names are extracted from the collection nodes. The sugarcane planting influencing factor names are used to identify data tables with table names in a pre-constructed database, wherein the table name of the data table is the sugarcane planting influencing factor name.

[0123] The data table is updated by using the sugarcane planting influencing factor values ​​corresponding to the data collection nodes and the data collection time.

[0124] After confirming that each data collection node in the data collection node set has obtained the corresponding updated data table, the updated data tables are aggregated to obtain multiple updated data tables. The multiple updated data tables are then stored in the database to obtain the updated database.

[0125] The missing value imputation method is obtained based on the information processing unit, and the preprocessed data table is obtained based on the updated data table and the missing value imputation method, wherein the preprocessed data table corresponds one-to-one with the acquisition node;

[0126] Summarize the preprocessed data tables to obtain the preprocessed data table set.

[0127] It is understood that the data table is a storage area that uses the name of the sugarcane planting influencing factor as the table name and can store multiple collection nodes with the same name (sugarcane planting influencing factor name). The database is a storage space that can store multiple data tables. The process of identifying the data table from the database using the sugarcane planting influencing factor name and the process of updating the sugarcane planting influencing factor value and data collection time to the data table are both achievable with existing technology and will not be elaborated here. For example, if the information collection tool collects a weather temperature-related collection node as (9:00, temperature, 27℃), then the temperature is used as the query keyword to find the data table named "temperature" in the database, and the temperature collection time 9:00 is used as the data collection time, and the temperature value 27℃ is used as the sugarcane planting influencing factor value to update the temperature data table. The updated database is a storage space that stores multiple updated data tables.

[0128] It should be understood that the information processing unit is a functional module used to detect and fill missing values ​​in sugarcane planting data. It intelligently fills in randomly or consecutively missing nodes using a preset algorithm, ensuring the integrity and reliability of the sugarcane planting influencing factor values. The missing value filling method involves replacing missing nodes in the updated data table with specific nodes. When the information collection tool malfunctions, the collected sugarcane planting influencing factor values ​​may contain abnormal values. After filtering out these abnormal values, the corresponding updated data table will have missing collection nodes in time. To improve the accuracy of subsequent analysis and decision-making, it is necessary to fill in the missing collection nodes. The types of missing collection nodes include random and consecutive missing values.

[0129] It should be explained that the process of obtaining the preprocessed data table based on the updated data table and the missing value imputation method includes:

[0130] Sort the data collection nodes in the updated data table according to the data collection time of the collection nodes from earliest to latest to obtain the updated data sequence;

[0131] The updated data collection times are extracted sequentially from the updated data sequence to obtain the reference time;

[0132] Using the reference time, the analysis time is determined in the updated data sequence, wherein the acquisition node corresponding to the analysis time is adjacent to and lags behind the acquisition node corresponding to the reference time.

[0133] Calculate the absolute difference between the reference time and the analysis time to obtain the analysis difference;

[0134] Compare the analyzed difference with the data acquisition time interval;

[0135] If the difference is not equal to the collection time interval, a missing value sequence is obtained using a pre-constructed missing value completion formula, wherein the missing value sequence includes one or more missing values, and the missing value completion formula is as follows:

[0136]

[0137] in, Indicates the missing numerical sequence of the first... One missing value This indicates the numerical values ​​of sugarcane planting influencing factors corresponding to the reference time. This represents the numerical values ​​of sugarcane planting influencing factors corresponding to the analysis time. Indicates the missing numerical sequence of the first... The missing time corresponding to each missing value. Indicates reference time. Indicates the analysis time. This indicates the difference in analysis. Indicates the time interval for data collection;

[0138] By associating missing values ​​with the corresponding missing times, we can obtain missing nodes.

[0139] Summarize the missing nodes to obtain the missing node set, and add the missing node set to the updated data table to obtain the preprocessed data table.

[0140] For example, assuming the updated data table is {(Air humidity -7:40 -49%), (Air humidity -7:30 -50%), (Air humidity -7:00 -48%), (Air humidity -7:20 -52%), (Air humidity -8:10 -54%)}, the resulting updated data sequence is {(Air humidity -7:00 -48%), (Air humidity -7:20 -52%), (Air humidity -7:30 -50%), (Air humidity -7:40 -49%), (Air humidity -8:10 -54%)}. Assuming the data collection interval is 10 minutes, the reference time is 7:00, and the corresponding analysis time is 7:20, the analysis difference is 20 minutes = 2. The data collection interval is 10 minutes. At this time, the updated data sequence contains only one missing value. The missing value is obtained using the missing value completion formula. missing values ​​associated with the data The missing time corresponding to the missing value is 7:10, resulting in the missing node being (air humidity - 7:10 - 50%). Assuming the reference time is 7:40, the corresponding analysis time is 8:10, and the corresponding analysis difference is greater than 2 for 30 minutes. The data collection interval is 10 minutes. At this time, the updated data sequence contains two missing values, and the missing values ​​are used to fill in the missing values ​​in the formula. The method for obtaining missing values ​​is described below and will not be elaborated upon. The process of supplementing the missing node set into the updated data table is achievable using existing technology and will not be described further. This embodiment of the invention improves data integrity and reliability by performing real-time filtering, dynamic storage, and missing value imputation on the numerical values ​​of sugarcane planting influencing factors, thereby enhancing the accuracy of AI analysis and decision-making.

[0141] S4. Obtain a sugarcane planting decision set based on the preprocessed data table set and the pre-constructed analysis and decision model.

[0142] It should be explained that obtaining the sugarcane planting decision set based on the preprocessed data table set and the pre-built analysis and decision model includes:

[0143] The preprocessed data tables are extracted sequentially from the preprocessed data table set, and the following operations are performed on the extracted preprocessed data tables:

[0144] The preprocessed data in the preprocessed data table is sorted according to the time sequence corresponding to the preprocessed data to obtain the preprocessed data sequence.

[0145] Using a preset fixed window, a sequence of feature nodes is extracted from the preprocessed data sequence, wherein the window length value of the preset fixed window is set.

[0146] The number of feature nodes in the feature node sequence is counted to obtain the number of discriminations.

[0147] The sugarcane planting status is obtained based on the discrimination quantity and window length value, wherein the sugarcane planting status is either normal or abnormal.

[0148] If the number of samples is less than the window length, the sugarcane planting status is confirmed to be normal.

[0149] Otherwise, anomaly discrimination values ​​are obtained based on the feature node sequence and the pre-built anomaly alarm model;

[0150] If the abnormal discrimination value is outside the preset normal value range, the sugarcane planting status is confirmed to be abnormal; otherwise, the sugarcane planting status is confirmed to be normal.

[0151] When the sugarcane planting status is abnormal, an analysis and decision-making model is obtained based on the AI ​​analysis unit, and a sugarcane planting decision is obtained based on the feature node sequence and the analysis and decision-making model.

[0152] By summarizing sugarcane planting decisions, a sugarcane planting decision set is obtained.

[0153] It should be understood that the method of extracting the feature node sequence from the preprocessed data sequence using the window length value is as follows: extract the preprocessed data from the position closest to the current time in the preprocessed data sequence towards an earlier time. For example, assuming the preprocessed data sequence is {(9:00, soil pH, 6.4), (9:10, soil pH, 6.3), (9:20, soil pH, 6.1)}, and the window length value is 2, then the extracted feature node sequence is {(9:10, soil pH, 6.3), (9:20, soil pH, 6.1)}.

[0154] It should be understood that the window length value is based on the minimum data volume threshold set by the anomaly alarm model. For example, if the minimum data volume of the anomaly alarm model is 1000, it means that the anomaly alarm model can only output anomaly judgment values ​​when the input data volume is greater than or equal to 1000. The anomaly alarm model is a data dynamic detection system built based on algorithmic logic, used to detect features of feature node sequences. Optionally, the exponential smoothing method is used for the anomaly alarm model, which is existing technology and will not be elaborated here.

[0155] For example, assuming there are 500 preprocessed data in the preprocessed data sequence, if the window length is 1000, then the number of feature nodes in the obtained feature node sequence is 500, that is, the number of discriminations is 500. At this time, the number of discriminations of 500 is less than the window length of 1000. The number of feature nodes in the feature node sequence is insufficient to be calculated using the anomaly alarm model, so the sugarcane planting status is determined to be normal. If there are 1500 preprocessed data points in the preprocessed data sequence, then the number of feature nodes in the obtained feature node sequence is 1000, i.e., the number of discriminations is 1000. At this time, the number of discriminations of 1000 is equal to the window length value of 1000. Then, the anomaly alarm model is used to calculate the anomaly discrimination value for the 1000 feature nodes in the feature node sequence. Assuming that the sugarcane planting influencing factor corresponding to the preprocessed data sequence is soil moisture, if the normal value range of soil moisture required for sugarcane growth is 4 to 7, and if the anomaly discrimination value corresponding to the 1000 feature nodes is 6, then the sugarcane planting status is determined to be normal. Otherwise, the analysis and decision model generates a sugarcane planting decision based on the 1000 feature nodes. Assuming that the 1000 feature nodes show the characteristics of continuous drought, the generated sugarcane planting decision is to irrigate with 500 cubic meters of water. The AI ​​analysis unit is a sugarcane planting status analysis module based on dynamic window detection and an intelligent decision-making model. It monitors preprocessed data sequences in real time, combines this with an anomaly alarm model to determine the planting status (normal / abnormal), and triggers the analysis and decision-making model to generate precise agricultural instructions, achieving intelligent closed-loop management of sugarcane planting. The analysis and decision-making model is an AI-based intelligent decision engine capable of generating corresponding execution decisions based on the preprocessed data sequence. Optionally, an agricultural expert system can be used as the analysis and decision-making model, which is existing technology and will not be elaborated further. This embodiment of the invention uses dynamic window detection to promptly determine the impact of sugarcane planting on the planting status, achieving real-time monitoring and timely decision-making for abnormal conditions.

[0156] S5. Obtain the agricultural pre-execution instruction set based on the sugarcane planting decision set and the pre-constructed decision optimization model.

[0157] It should be explained that the process of obtaining the agricultural pre-execution instruction set based on the sugarcane planting decision set and the pre-constructed decision optimization model includes:

[0158] Sugarcane planting decisions are extracted sequentially from the sugarcane planting decision set, and pre-execution planting decisions are obtained based on the sugarcane planting decisions and the preset sugarcane planting decision specification set.

[0159] The pre-implementation planting decisions are summarized to obtain the pre-implementation planting decision set;

[0160] The agricultural pre-execution instruction set is obtained based on the pre-execution planting decision set and the decision optimization unit.

[0161] It should be understood that the decision optimization model is an algorithmic mechanism used to screen and optimize sugarcane planting decisions. Its purpose is to eliminate unreasonable sugarcane planting decisions and retain and optimize those that conform to the standards, thereby generating accurate pre-execution instructions for agricultural operations. The sugarcane planting decision set obtained using the analytical decision model may contain unreasonable decisions that could affect the accuracy of the final implementation of agricultural instructions; therefore, it is necessary to eliminate unreasonable sugarcane planting decisions. The sugarcane planting decision standard set is a collection of decision-making standards in the sugarcane planting field. Optionally, the construction methods of the sugarcane planting decision standard set include, but are not limited to: obtaining standards from expert experience and knowledge, extracting standards from historical sugarcane planting data, and accumulating standards from field experiment results. For example, suppose the sugarcane planting decision set obtained solely from expert experience is: {Irrigation should not exceed 300 cubic meters, and fertilizer application should not exceed 70 kg}. Suppose that there are three sugarcane planting decisions in the sugarcane planting decision set generated during the sugarcane growth process: irrigating 150 cubic meters, applying 50 kg of nitrogen fertilizer, and relocating the sugarcane planting area. However, there is no decision to relocate the sugarcane planting area in the sugarcane planting decision set. Therefore, the decision to relocate the sugarcane planting area is removed, and the decision to irrigate 150 cubic meters and apply 50 kg of nitrogen fertilizer is retained as the pre-execution planting decision set.

[0162] It should be explained that the process of obtaining the agricultural pre-execution instruction set based on the pre-execution planting decision set and the decision optimization unit includes:

[0163] Based on each sugarcane planting influencing factor in the sugarcane planting influencing factor set, multiple pre-planting decision value sets are extracted from the pre-implementation planting decision set, wherein the sugarcane planting influencing factors correspond one-to-one with the pre-planting decision value sets.

[0164] For each of the multiple pre-planting decision data sets, perform the following operation:

[0165] The decision clustering method is obtained based on the decision optimization unit. The decision clustering method is used to cluster the pre-planting decision numerical set to obtain multiple clustered decision numerical sets.

[0166] The number of pre-planting decision values ​​in the statistical pre-planting decision value set is used to obtain the statistical decision quantity;

[0167] Calculate the product of the number of statistical decisions and the preset confidence ratio to obtain the number of screenings. Count the number of cluster decision values ​​corresponding to each cluster decision value set in the multiple cluster decision value sets to obtain the number of multiple cluster statistical decisions.

[0168] By using the number of screenings and the number of multiple cluster statistical decisions, multiple target decision value sets are identified from multiple cluster decision value sets, and the number of cluster statistical decisions corresponding to the target decision value sets is greater than or equal to the number of screenings.

[0169] Extract the target decision value set with the largest number of clustered statistical decisions from multiple target decision value sets to obtain the reference decision value set;

[0170] Calculate the mean of the reference decision values ​​in the reference decision value set to obtain the mean of the reference decision values;

[0171] The pre-execution agricultural command values ​​are calculated based on the average reference decision values ​​and multiple target decision value sets, as shown below:

[0172]

[0173] in, This represents the value of the pre-executed agricultural instructions. This indicates that the set of decision values ​​for multiple objectives is shared. A set of numerical values ​​for a single objective decision. Represents the first value in a set of multiple objective decision values. The number of clustered statistical decisions corresponding to a set of target decision values. Represents the first value in a set of multiple objective decision values. The number of clustered statistical decisions corresponding to a set of target decision values. Indicates the first value in the target decision numerical set. A target decision value, This represents the mean of the reference decision values. Indicates the first value in the target decision numerical set. A target decision value, The total number of target decision values ​​in the set is A set of numerical values ​​for a single objective decision. Indicates a non-zero positive coefficient;

[0174] The agricultural pre-execution instructions are obtained based on the numerical values ​​of the pre-executed agricultural instructions, and the agricultural pre-execution instructions are summarized to obtain the agricultural pre-execution instruction set.

[0175] Understandably, the decision optimization unit is used to generate optimal agricultural instructions. Through cluster analysis and weighted fusion algorithms, it filters, optimizes, and integrates pre-implemented planting decisions, eliminating outliers to ensure the scientific validity and feasibility of the planting decisions. For example, assuming the pre-planting decision value set is {25 cubic meters, 26 cubic meters, 26 cubic meters, 45 cubic meters, 46 cubic meters, 43 cubic meters, 45 cubic meters, 46 cubic meters, 65 cubic meters, 110 cubic meters}, then the number of decisions is 10. Taking 25 cubic meters as an example: 25 cubic meters represents the pre-implemented planting decision: water 25 cubic meters. The resulting clustered decision value sets are {25 cubic meters, 26 cubic meters, 26 cubic meters}, {45 cubic meters, 46 cubic meters, 43 cubic meters, 45 cubic meters, 46 cubic meters}, {65 cubic meters}, and {110 cubic meters}, respectively. The number of cluster statistical decisions are 3, 5, 1, and 1 respectively. Assuming the confidence ratio is 20%, the number of selections is the product of the number of statistical decisions (10) and the confidence ratio (20%), which is 2. This results in the target decision value set corresponding to cluster statistical decision number 3 being {25 cubic meters, 26 cubic meters, 26 cubic meters}, and the target decision value set corresponding to cluster statistical decision number 5 being {45 cubic meters, 46 cubic meters, 43 cubic meters, 45 cubic meters, 46 cubic meters}. The reference decision value set is then {45 cubic meters, 46 cubic meters, 43 cubic meters, 45 cubic meters, 46 cubic meters}, with the mean of the reference decision value being 45 cubic meters. The pre-executed agricultural instruction value is a comprehensive agricultural decision value based on cluster analysis and weighted optimization, reflecting planting parameters close to the optimal mean. The non-zero positive coefficient c is used to avoid cases where the denominator is 0. Optionally, the K-Means clustering algorithm is used as the decision clustering method. This is existing technology and will not be elaborated further. For example, assuming the value of c is 0.01, based on the average reference decision value of 45 cubic meters and the calculation method, the pre-execution agricultural instruction value can be calculated to be 39.33 cubic meters. Therefore, the pre-execution agricultural instruction is 39.33 cubic meters of watering. This embodiment of the invention uses a clustering algorithm to remove outliers from the pre-execution decision set, with the average reference decision as the core, and utilizes a dynamic weighting method to ensure that the pre-execution agricultural instruction closely approximates the optimal planting parameters, thereby improving the rationality of the decision and the scientific and executable nature of the agricultural instruction implementation.

[0176] S6. Obtain the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the update database, and the information exchange unit, and use the agricultural implementation instruction set to optimize sugarcane planting decisions.

[0177] It should be explained that the step of obtaining the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit includes:

[0178] The agricultural pre-execution instructions are extracted sequentially from the set of agricultural pre-execution instructions, and the following operations are performed on the extracted agricultural pre-execution instructions:

[0179] Based on the agricultural pre-execution instructions and the updated database, an effective impact factor data table is obtained. The effective impact factor data table contains one or more effective impact factor nodes, and each effective impact factor node includes the effective impact factor collection time and the effective impact factor value.

[0180] Obtain a line graph of effective impact factors based on the effective impact factor data table;

[0181] The method for obtaining instruction confirmation based on information exchange unit is used to obtain agricultural implementation instructions based on agricultural pre-execution instructions, effective influencing factor line charts, and the instruction confirmation method.

[0182] By compiling agricultural implementation instructions, a set of agricultural implementation instructions is obtained.

[0183] It should be understood that the effective impact factor data table is a data table corresponding to the names of sugarcane planting impact factors used to generate agricultural pre-execution instructions. The method of obtaining the effective impact factor data table from the updated database is existing technology and will not be described in detail here.

[0184] Understandably, the aforementioned pre-implementation agricultural instructions are agricultural operation suggestions generated based on sugarcane planting influencing factors and analytical decision-making models, and have not yet been finalized for implementation. They require manual review and system verification to ensure their rationality and applicability before being converted into actual agricultural implementation instructions. The effective influencing factor line graph is a coordinate graph plotted from the effective influencing factor data table at different time points, showing the collection time of the effective influencing factors and their corresponding values. The information exchange unit is used to dynamically link the pre-implementation agricultural instructions and effective influencing factor data through a visual interface, providing interactive decision-making basis for manual review and achieving closed-loop verification between machine intelligence and expert experience. The instruction confirmation method is a visual operation interface that displays agricultural implementation instructions and corresponding effective factor line graphs. The process of obtaining agricultural implementation instructions based on pre-execution instructions, effective factor line graphs, and the instruction confirmation method is as follows: For example, if the pre-execution instruction for sugarcane planting caused by a sugarcane planting influencing factor named soil moisture is irrigating 100 cubic meters, then the 100 cubic meter irrigation and historical soil moisture data are plotted on the visual operation interface. Experienced user Xiao Zhao confirms the agricultural implementation instruction as: whether to execute the pre-execution instruction (irrigating 100 cubic meters). The agricultural implementation instructions are manually reviewed and confirmed to guide actual agricultural operations. This embodiment of the invention combines pre-execution instructions with an updated database and an information exchange unit to generate a visual agricultural implementation instruction set, enabling dynamic adjustment of sugarcane planting decisions and improving the accuracy and executability of sugarcane planting instructions.

[0185] To address the problems described in the background art, this invention receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit. It acquires sugarcane planting instructions and, based on these instructions, obtains an information collection toolset. This toolset includes multiple information collection tools, demonstrating that by integrating and optimizing the information collection tools used, this invention improves data acquisition efficiency. Based on the information collection toolset, it acquires a collection node set, and based on the collection node set, it acquires an updated database and a preprocessed data table set. The preprocessed data table set includes multiple preprocessed data tables. This invention improves data integrity and reliability by performing real-time filtering, dynamic storage, and missing data filling operations on the sugarcane planting influencing factor values, thereby enhancing the accuracy of AI analysis and decision-making. Based on the preprocessed data table set and a pre-built analysis and decision-making model, it acquires a sugarcane planting decision set. This invention uses a dynamic window detection method to promptly determine the status of sugarcane planting influence shadows, achieving real-time monitoring of the sugarcane planting status and enabling timely decision-making for abnormal states. Based on the sugarcane planting decision set and the pre-constructed decision optimization model, a set of pre-execution agricultural instructions is obtained. This invention uses a clustering algorithm to remove outliers from the pre-execution decision set, takes the reference decision mean as the core, and employs a dynamic weighting method to ensure that the pre-execution agricultural instructions closely approximate the optimal planting parameters, thereby improving the rationality of the decisions and the scientific and executable nature of the agricultural instructions. Based on the pre-execution agricultural instructions set, the updated database, and the information exchange unit, a set of implementation agricultural instructions is obtained. This implementation agricultural instructions set is then used to optimize sugarcane planting decisions. This invention combines pre-execution agricultural instructions with the updated database and the information exchange unit to generate a visualized implementation agricultural instruction set, enabling dynamic adjustment of sugarcane planting decisions and improving the accuracy and executability of sugarcane planting instructions. Therefore, this invention can improve the accuracy of sugarcane planting decision optimization.

[0186] like Figure 2 The diagram shown is a functional block diagram of a sugarcane planting decision optimization system based on AI analysis provided in an embodiment of the present invention.

[0187] The AI-based sugarcane planting decision optimization system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the AI-based sugarcane planting decision optimization system 100 may include a data acquisition and processing module 101, an AI analysis and decision module 102, a planting decision optimization module 103, and a planting instruction confirmation module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0188] The data acquisition and processing module 101 is used to receive sugarcane planting decision optimization instructions, and to confirm the sugarcane management system based on the sugarcane planting decision optimization instructions. The sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0189] Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools;

[0190] The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables.

[0191] The AI ​​analysis and decision-making module 102 is used to obtain a sugarcane planting decision set based on the preprocessed data table set and the pre-built analysis and decision-making model.

[0192] The planting decision optimization module 103 is used to obtain a set of agricultural pre-execution instructions based on the sugarcane planting decision set and the pre-constructed decision optimization model.

[0193] The planting instruction confirmation module 104 is used to obtain the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the update database and the information exchange unit, and to optimize sugarcane planting decisions using the agricultural implementation instruction set.

[0194] In detail, the modules in the sugarcane planting decision optimization system 100 based on AI analysis described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the sugarcane planting decision optimization method based on AI analysis described in the article, and can produce the same technical effect, so it will not be repeated here.

[0195] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing an AI-based sugarcane planting decision optimization method, according to an embodiment of the present invention.

[0196] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a sugarcane planting decision optimization method program based on AI analysis.

[0197] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a sugarcane planting decision optimization method program based on AI analysis, but also to temporarily store data that has been output or will be output.

[0198] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a sugarcane planting decision optimization method program based on AI analysis) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0199] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0200] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0201] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0202] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0203] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0204] The sugarcane planting decision optimization method program based on AI analysis, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0205] The system receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0206] Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools;

[0207] The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables.

[0208] Based on the preprocessed data set and the pre-constructed analysis and decision model, a sugarcane planting decision set is obtained;

[0209] Based on the sugarcane planting decision set and the pre-constructed decision optimization model, obtain the agricultural pre-execution instruction set;

[0210] Based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit, an agricultural implementation instruction set is obtained, and the sugarcane planting decision is optimized using the agricultural implementation instruction set.

[0211] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0212] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0213] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0214] The system receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit.

[0215] Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools;

[0216] The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables.

[0217] Based on the preprocessed data set and the pre-constructed analysis and decision model, a sugarcane planting decision set is obtained;

[0218] Based on the sugarcane planting decision set and the pre-constructed decision optimization model, obtain the agricultural pre-execution instruction set;

[0219] Based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit, an agricultural implementation instruction set is obtained, and the sugarcane planting decision is optimized using the agricultural implementation instruction set.

[0220] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0221] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0222] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0223] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0224] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A sugarcane planting decision optimization method based on AI analysis, characterized in that, The method includes: The system receives sugarcane planting decision optimization instructions, identifies a sugarcane management system based on these instructions, and the sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit. Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools; The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables. Based on the preprocessed data set and the pre-constructed analysis and decision model, a sugarcane planting decision set is obtained; Based on the sugarcane planting decision set and the pre-constructed decision optimization model, obtain the agricultural pre-execution instruction set; Based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit, an agricultural implementation instruction set is obtained, and the sugarcane planting decision is optimized using the agricultural implementation instruction set.

2. The sugarcane planting decision optimization method based on AI analysis as described in claim 1, characterized in that, The toolset for acquiring information based on sugarcane planting instructions includes: The planting target node is obtained based on the sugarcane planting instruction and the preset instruction parsing method, wherein the planting target node includes sugarcane variety, planting area and sugarcane planting plan; The sugarcane planting influencing factor set is obtained based on the planting target node and the pre-constructed influencing factor matching model. The sugarcane planting influencing factor set includes multiple sugarcane planting influencing factors. Sugarcane planting influencing factors were extracted sequentially from the sugarcane planting influencing factor set, and an initial information collection tool was obtained based on the sugarcane planting influencing factors; By summarizing the aforementioned initial information collection tools, we obtain an initial information collection toolset. The initial information collection toolset is filtered and selected to obtain the final information collection toolset.

3. The sugarcane planting decision optimization method based on AI analysis as described in claim 2, characterized in that, The acquisition of the collection node set based on the information collection toolset includes: Information collection tools are extracted sequentially from the set of information collection tools, and the following operations are performed on each extracted information collection tool: An initial node set is obtained based on the extracted information collection tools and the preset collection time interval. The initial node set includes one or more initial nodes, and the initial nodes include the data collection time, the value of the sugarcane planting influencing factor, and the name of the sugarcane planting influencing factor. Initial nodes are extracted sequentially from the initial node set, and the following operations are performed on each extracted initial node: Data filtering methods are obtained based on information processing units, and standardized nodes are obtained based on the extracted initial nodes and data filtering methods. Summarize the standardized nodes to obtain the standardized node set; The standardized node sets are aggregated to obtain multiple standardized node sets, which are then used as the collection node sets.

4. The sugarcane planting decision optimization method based on AI analysis as described in claim 3, characterized in that, The process of obtaining and updating the database and preprocessing data table set based on the collection node set includes: Collecting nodes are extracted sequentially from the collection node set, and sugarcane planting influencing factor names are extracted from the collection nodes. The sugarcane planting influencing factor names are used to identify data tables with table names in a pre-constructed database, wherein the table name of the data table is the sugarcane planting influencing factor name. The data table is updated by using the sugarcane planting influencing factor values ​​corresponding to the data collection nodes and the data collection time. After confirming that each data collection node in the data collection node set has obtained the corresponding updated data table, the updated data tables are aggregated to obtain multiple updated data tables. The multiple updated data tables are then stored in the database to obtain the updated database. The missing value imputation method is obtained based on the information processing unit, and the preprocessed data table is obtained based on the updated data table and the missing value imputation method, wherein the preprocessed data table corresponds one-to-one with the acquisition node; Summarize the preprocessed data tables to obtain the preprocessed data table set.

5. The sugarcane planting decision optimization method based on AI analysis as described in claim 4, characterized in that, The process of obtaining a preprocessed data table based on the updated data table and the missing value imputation method includes: Sort the data collection nodes in the updated data table according to the data collection time of the collection nodes from earliest to latest to obtain the updated data sequence; The updated data collection times are extracted sequentially from the updated data sequence to obtain the reference time; Using the reference time, the analysis time is determined in the updated data sequence, wherein the acquisition node corresponding to the analysis time is adjacent to and lags behind the acquisition node corresponding to the reference time. Calculate the absolute difference between the reference time and the analysis time to obtain the analysis difference; Compare the analyzed difference with the data acquisition time interval; If the analysis difference is not equal to the collection time interval, the missing value sequence is obtained by using the pre-constructed missing value completion formula, wherein the missing value sequence includes one or more missing values; By associating missing values ​​with the corresponding missing times, we can obtain missing nodes. Summarize the missing nodes to obtain the missing node set, and add the missing node set to the updated data table to obtain the preprocessed data table.

6. The sugarcane planting decision optimization method based on AI analysis as described in claim 5, characterized in that, The process of obtaining a sugarcane planting decision set based on the preprocessed data set and the pre-built analysis and decision model includes: The preprocessed data tables are extracted sequentially from the preprocessed data table set, and the following operations are performed on the extracted preprocessed data tables: The preprocessed data in the preprocessed data table is sorted according to the time sequence corresponding to the preprocessed data to obtain the preprocessed data sequence. Using a preset fixed window, a sequence of feature nodes is extracted from the preprocessed data sequence, wherein the window length value of the preset fixed window is set. The number of feature nodes in the feature node sequence is counted to obtain the number of discriminations. The sugarcane planting status is obtained based on the discrimination quantity and window length value, wherein the sugarcane planting status is either normal or abnormal. If the number of samples is less than the window length, the sugarcane planting status is confirmed to be normal. Otherwise, anomaly discrimination values ​​are obtained based on the feature node sequence and the pre-built anomaly alarm model; If the abnormal discrimination value is outside the preset normal value range, the sugarcane planting status is confirmed to be abnormal; otherwise, the sugarcane planting status is confirmed to be normal. When the sugarcane planting status is abnormal, an analysis and decision-making model is obtained based on the AI ​​analysis unit, and a sugarcane planting decision is obtained based on the feature node sequence and the analysis and decision-making model. By summarizing sugarcane planting decisions, a sugarcane planting decision set is obtained.

7. The sugarcane planting decision optimization method based on AI analysis as described in claim 6, characterized in that, The process of obtaining the agricultural pre-execution instruction set based on the sugarcane planting decision set and the pre-constructed decision optimization model includes: Sugarcane planting decisions are extracted sequentially from the sugarcane planting decision set, and pre-execution planting decisions are obtained based on the sugarcane planting decisions and the preset sugarcane planting decision specification set. The pre-implementation planting decisions are summarized to obtain the pre-implementation planting decision set; The agricultural pre-execution instruction set is obtained based on the pre-execution planting decision set and the decision optimization unit.

8. The sugarcane planting decision optimization method based on AI analysis as described in claim 7, characterized in that, The process of obtaining the agricultural pre-execution instruction set based on the pre-execution planting decision set and the decision optimization unit includes: Based on each sugarcane planting influencing factor in the sugarcane planting influencing factor set, multiple pre-planting decision value sets are extracted from the pre-implementation planting decision set, where each sugarcane planting influencing factor corresponds one-to-one with a pre-planting decision value set. For each of the multiple pre-planting decision data sets, perform the following operation: The decision clustering method is obtained based on the decision optimization unit. The decision clustering method is used to cluster the pre-planting decision numerical set to obtain multiple clustered decision numerical sets. The number of pre-planting decision values ​​in the statistical pre-planting decision value set is used to obtain the statistical decision quantity; Calculate the product of the number of statistical decisions and the preset confidence ratio to obtain the number of screenings. Count the number of cluster decision values ​​corresponding to each cluster decision value set in the multiple cluster decision value sets to obtain the number of multiple cluster statistical decisions. By using the number of screenings and the number of multiple cluster statistical decisions, multiple target decision value sets are identified from multiple cluster decision value sets, and the number of cluster statistical decisions corresponding to the target decision value sets is greater than or equal to the number of screenings. Extract the target decision value set with the largest number of clustered statistical decisions from multiple target decision value sets to obtain the reference decision value set; Calculate the mean of the reference decision values ​​in the reference decision value set to obtain the mean of the reference decision values; The pre-execution agricultural instructions are calculated based on the average reference decision values ​​and multiple target decision value sets. The agricultural pre-execution instructions are obtained based on the numerical values ​​of the pre-executed agricultural instructions, and the agricultural pre-execution instructions are summarized to obtain the agricultural pre-execution instruction set.

9. The sugarcane planting decision optimization method based on AI analysis as described in claim 8, characterized in that, The process of obtaining the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the updated database, and the information exchange unit includes: The agricultural pre-execution instructions are extracted sequentially from the set of agricultural pre-execution instructions, and the following operations are performed on the extracted agricultural pre-execution instructions: Based on the agricultural pre-execution instructions and the updated database, an effective impact factor data table is obtained. The effective impact factor data table contains one or more effective impact factor nodes, and each effective impact factor node includes the effective impact factor collection time and the effective impact factor value. Obtain a line graph of effective impact factors based on the effective impact factor data table; The method for obtaining instruction confirmation based on information exchange unit is used to obtain agricultural implementation instructions based on agricultural pre-execution instructions, effective influencing factor line charts, and the instruction confirmation method. By compiling agricultural implementation instructions, a set of agricultural implementation instructions is obtained.

10. A sugarcane planting decision optimization system based on AI analysis, characterized in that, The system includes: The data acquisition and processing module is used to receive sugarcane planting decision optimization instructions, and to confirm the sugarcane management system based on the sugarcane planting decision optimization instructions. The sugarcane management system includes an information processing unit, an AI analysis unit, a decision optimization unit, and an information exchange unit. Obtain sugarcane planting instructions, and obtain an information collection toolset based on the sugarcane planting instructions, wherein the information collection toolset includes a variety of information collection tools; The data collection toolset is used to obtain a data collection node set, and the data collection node set is used to obtain an update database and a preprocessed data table set, wherein the preprocessed data table set contains multiple preprocessed data tables. The AI ​​analysis and decision-making module is used to obtain a sugarcane planting decision set based on the preprocessed data table set and the pre-built analysis and decision-making model. The planting decision optimization module is used to obtain a set of agricultural pre-execution instructions based on the sugarcane planting decision set and the pre-constructed decision optimization model. The planting instruction confirmation module is used to obtain the agricultural implementation instruction set based on the agricultural pre-execution instruction set, the update database, and the information exchange unit, and to optimize sugarcane planting decisions using the agricultural implementation instruction set.

Images