Intelligent management system based on sugarcane hybridization data
By using the intelligent management system for sugarcane hybrid data, combined with the Internet of Things and genotype data, accurate prediction and dynamic control of sugarcane flowering period have been achieved, solving the problem of mismatched flowering periods and improving the efficiency and success rate of sugarcane hybrid breeding.
Patent Information
- Application Number
- CN202511649413.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-12
- Publication Date
- 2026-02-06
AI Technical Summary
Current sugarcane hybrid breeding technologies face the problem of inconsistent flowering periods, resulting in poor predictability, extensive regulation, and rigid planning, making it impossible to achieve precise, automated flowering period regulation and dynamic adjustment.
An intelligent management system based on sugarcane hybridization data is adopted. Environmental data is collected through an Internet of Things sensor network, combined with flowering period genotype data, and precise prediction and regulation are achieved using flowering period prediction and regulation modules. The hybridization planning engine dynamically adjusts the hybridization plan to form an adaptive intelligent system.
It enables the quantitative and forward-looking judgment of the flowering period of sugarcane hybrid parents, accurately calculates and predicts the peak flowering period, dynamically optimizes the hybridization plan, improves the success rate of hybrid combinations and breeding efficiency, and ensures optimal resource utilization.
Smart Images
Figure CN121483372A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of agricultural information technology, specifically to an intelligent management system based on sugarcane hybridization data. Background Technology
[0002] Sugarcane is an important sugar and energy crop, and its variety improvement relies heavily on hybridization breeding. However, sugarcane hybridization breeding has long faced a severe technical bottleneck: the flowering periods of different parent materials often have natural differences, that is, the flowering periods do not coincide. This causes many theoretically excellent hybrid combinations to fail because the parent materials cannot flower at the same time.
[0003] In existing technologies, solving the problem of asynchronous flowering mainly relies on the personal experience of breeding experts to make predictions and to make rough adjustments through rudimentary light and temperature control. This method has significant drawbacks:
[0004] Poor predictability: It relies on experience and cannot make accurate and quantitative predictions about weather changes or parental specific differences.
[0005] Extensive regulation: Lacking refined and automated control strategies based on predictive models, the regulation effect is unstable.
[0006] Rigid planning: Once a hybridization plan is formulated, it is difficult to make dynamic adjustments based on the actual progress of flowering period regulation, resulting in wasted resources and lost opportunities.
[0007] Therefore, there is an urgent need in this field for an intelligent solution that can deeply integrate flowering prediction, precise regulation and hybridization planning in order to overcome the core problem of untimely flowering. Summary of the Invention
[0008] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an intelligent management system based on sugarcane hybridization data. This system transforms breeding experience from qualitative descriptions into dynamic predictions based on the interaction between genetics and the environment, enabling the quantification and forward-looking judgment of the flowering period of sugarcane hybrid parents. The flowering period prediction module retrieves the flowering period genotypes of the parents from the germplasm resource bank and analyzes the gene loci related to photoperiod sensitivity. Simultaneously, the data acquisition module continuously captures real-time environmental data from the field. By analyzing the nonlinear relationship between cumulative growth days and the photoperiod function, it simulates the intrinsic physiological process of sugarcane transitioning from vegetative growth to reproductive growth, accurately calculating the predicted peak flowering period. This fundamentally overcomes the lag and uncertainty of traditional methods relying on manual observation and experience-based estimation, providing a reliable, data-driven decision-making basis for subsequent precise regulation, enabling hybridization programs to be established on a predictable data foundation.
[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent management system based on sugarcane hybridization data, the system comprising: a data acquisition module, a flowering period prediction module, a flowering period control module, a hybridization planning engine, and a central database module;
[0010] The data acquisition module is used to collect real-time environmental data through an Internet of Things sensor network and obtain flowering period genotype data from an external database through an interface.
[0011] The flowering period prediction module is communicatively connected to the central database module and the data acquisition module. It is used to receive the flowering period genotype data of the parents and real-time environmental data, and output the predicted peak flowering period.
[0012] The flowering period regulation module is communicatively connected to the flowering period prediction module. It is used to receive the predicted full bloom period, compare it with the preset target hybridization time window to generate an environmental regulation command, and send the command to the environmental control equipment.
[0013] The hybridization planning engine is connected to the flowering period prediction module and the flowering period regulation module. It is used to dynamically adjust the hybridization plan and output a list of executable hybridization combinations based on the regulated flowering period status of the parents.
[0014] The central database module is used to store and manage flowering period genotypes, real-time environmental data, predicted peak flowering period, target hybridization time windows, environmental control instructions, and a list of executable hybridization combinations, and provides data support for each functional module.
[0015] Furthermore, the data acquisition module continuously collects real-time environmental data, including light duration, light intensity, ambient temperature, and air humidity, through the Internet of Things sensor network deployed in the parent plant planting area;
[0016] The flowering genotype data is retrieved and verified from an external germplasm resource database using a standardized data interface. The flowering genotype data includes gene locus information related to photoperiod sensitivity and vernalization.
[0017] Furthermore, the flowering period prediction module calculates the predicted peak flowering period through the following steps:
[0018] The system receives flowering period genotype data of specific parents from the central database module and extracts photoperiod sensitivity coefficients from it. ;
[0019] Receive the daily average temperature sequence from the data acquisition module and calculate the cumulative growth days from the reference date. Where GDD represents cumulative growth days, The daily average temperature The preset biological zero degree for sugarcane growth, This represents the cumulative sum of daily values from the growth reference date to the calculation date;
[0020] Integrating genetic and environmental factors to calculate the flowering induction index ;
[0021] When the flowering induction index Greater than the flowering threshold ,Right now When the time comes, the system will determine that the day is predicted to be in full bloom.
[0022] Furthermore, the flowering induction index ,in, This represents the cumulative growth days required for this parental line from the baseline date to flowering. It is a function that takes the currently measured sunshine duration as input. , The data acquisition module represents the daily measured sunshine duration. The photoperiod of the parent's ecological type is defined in the central database module. The photoperiod deviation penalty coefficient, ranging from 0.5 to 1.0, is used to adjust the degree of inhibition on flowering induction when the actual sunshine duration deviates from the optimal photoperiod.
[0023] Furthermore, the specific steps for the flowering period control module to generate the environmental control command are as follows:
[0024] Read the preset target hybridization time window from the central database module;
[0025] The predicted full bloom period output by the flowering period prediction module is compared with the target hybridization time window to calculate the difference in flowering period for each parent.
[0026] Based on the aforementioned differences in flowering period, commands are used to control the switching on and off of supplemental lighting and the light cycle, to control the start and stop of the greenhouse heating and cooling systems, and to control the operation of the shading net.
[0027] The generated environmental control instructions are sent to the corresponding environmental control devices, and the instructions are simultaneously stored in the central database module.
[0028] Furthermore, the hybridization planning engine obtains the predicted full bloom dates of all parents updated by the flowering period control module from the flowering period prediction module, and applies this information to each candidate hybridization combination. ,in Represents the parent plant, Representing the paternal parent, calculate the flowering overlap fitness score for this combination. ,in, and Representing the parent and father Predicted peak bloom period The total length of the target hybridization time window. The absolute difference in flowering period between the parents is expressed in days. and Parent and father The breeding value weight, and These are the weighting coefficients for flowering period matching and parental value, respectively, and they satisfy the following conditions: All Hybrid combinations are included in the candidate set, and within the candidate set, according to The scores are sorted from highest to lowest to generate a final list of executable hybridization combinations. An overlap domain determination is then performed on the hybridization combination list. This is the fitness threshold.
[0029] Furthermore, the overlap region determination rule in the hybridization planning engine is as follows:
[0030] Match the predicted flowering period of each pair of planned hybridization parents to determine whether their flowering periods overlap within the target hybridization time window;
[0031] If valid overlap exists, the hybridization combination is retained and added to the list of executable hybridization combinations;
[0032] If there is no effective overlap and matching cannot be achieved through the flowering period control module, then the hybridization combination is removed from the list of executable hybridization combinations.
[0033] Furthermore, the central database module includes:
[0034] A flowering period genotype database is used to store and manage the flowering period genotype data of all parental materials;
[0035] An environmental time-series database is used to store historical and real-time environmental data uploaded by the data acquisition module;
[0036] A prediction and decision database is used to store the predicted full bloom period, the target hybridization time window, the environmental control instructions, and the list of executable hybridization combinations.
[0037] The data service interface provides unified data read, write, and query services for the flowering period prediction module, flowering period regulation module, and hybridization planning engine.
[0038] Compared with existing technologies, this intelligent management system based on sugarcane hybridization data has the following advantages:
[0039] I. This invention transforms breeding experience from qualitative description to dynamic prediction based on the interaction between heredity and environment, enabling quantitative and forward-looking judgment of the flowering period of sugarcane hybrid parents. The flowering period prediction module retrieves the flowering period genotypes of the parents from the germplasm resource bank and analyzes the gene loci related to photoperiod sensitivity. At the same time, the data acquisition module continuously captures real-time environmental data in the field. By analyzing the nonlinear relationship between cumulative growth days and the photoperiod function, it simulates the intrinsic physiological process of sugarcane transitioning from vegetative growth to reproductive growth and accurately calculates the predicted peak flowering period. This fundamentally overcomes the lag and uncertainty of traditional methods that rely on manual observation and experience estimation, providing a reliable, data-driven decision-making basis for subsequent precise regulation, and enabling hybridization programs to be established on a predictable data foundation.
[0040] Second, this invention achieves adaptive dynamic optimization of hybridization combination execution strategies by establishing a control logic of prediction, regulation, and planning. It integrates isolated operational links into an intelligent system capable of real-time feedback and autonomous decision-making. After receiving the predicted full bloom period, the flowering period regulation module compares it with the target hybridization time window in the global breeding plan to calculate the precise flowering period difference value. Based on this difference, the module generates customized environmental regulation instructions and drives the corresponding environmental control equipment to execute. The hybridization planning engine continuously monitors the changes in the flowering period status of the parents after regulation. By calculating the flowering period overlap fit score of each candidate combination, it dynamically updates the list of executable hybridization combinations and automatically discards combinations that fail due to asynchronous flowering periods. This ensures that the system's execution resources are always guided to the optimal hybridization task in the current state, forming an optimization loop that continuously self-corrects based on real-time progress. This ensures the high efficiency and success of hybridization breeding work in complex and ever-changing production environments.
[0041] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.
[0043] Figure 1 This is a flowchart illustrating the operation of an intelligent management system based on sugarcane hybridization data.
[0044] Figure 2This is a block diagram showing the modular components of an intelligent management system based on sugarcane hybridization data. Detailed Implementation
[0045] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.
[0046] Example 1
[0047] This embodiment aims to illustrate in detail the specific operation process of the intelligent management system based on sugarcane hybridization data, such as... Figure 2 As shown, this system, through the collaborative work of a data acquisition module, a flowering period prediction module, a flowering period regulation module, a hybridization planning engine, and a central database module, achieves precise data acquisition, scientific prediction of flowering period, intelligent environmental regulation, and dynamic optimization of the hybridization plan during sugarcane hybridization. The system focuses on the interaction between genetics and the environment. The data acquisition module collects real-time environmental data through an IoT sensor network and obtains flowering period genotype data from an external database via an interface. The flowering period prediction module communicates with the central database module and the data acquisition module, receiving the parental flowering period genotype data and real-time environmental data, and outputting a predicted peak flowering period. The flowering period regulation module communicates with the flowering period prediction module and receives the predicted peak flowering period. The hybridization plan engine compares the results with a preset target hybridization time window to generate environmental control instructions, which are then sent to the environmental control equipment. The hybridization planning engine communicates with the flowering prediction module and the flowering control module. Based on the regulated flowering status of the parents, it dynamically adjusts the hybridization plan and outputs a list of executable hybridization combinations. The central database module stores and manages flowering genotypes, real-time environmental data, predicted peak flowering period, target hybridization time window, environmental control instructions, and the list of executable hybridization combinations, and provides data support for each functional module. This solves problems such as mismatched flowering periods, extensive control, and rigid planning in traditional sugarcane hybridization breeding, providing an efficient, precise, and intelligent solution for sugarcane hybridization breeding, and improving the success rate of hybridization combinations and breeding efficiency.
[0048] (I) Initialization and Data Preparation of the Central Database Module
[0049] Before the system starts, the central database module is the data hub of the entire system, providing data storage, management and access support for all other functional modules. It contains four core components: flowering period genotype database, environmental time series database, prediction and decision database, and data service interface.
[0050] Construction of the flowering period genotype database: Through a standardized data entry process, the flowering period genotype data of different sugarcane parent materials are imported into this database. These data come from an external germplasm resource information database and are retrieved through the system's preset standardized data interface. The flowering period genotype data is gene locus information related to sugarcane photoperiod sensitivity and vernalization. This information directly determines the response characteristics of different parents to environmental factors such as light duration and temperature, and serves as the basis for the subsequent flowering period prediction module to calculate the photoperiod sensitivity coefficient.
[0051] Environmental Time Series Database Configuration: This database is pre-configured with data storage format and update frequency to adapt to the real-time data upload requirements of the data acquisition module. The database stores two types of environmental data: first, historical environmental data, including historical records of light duration, light intensity, ambient temperature, and air humidity in sugarcane planting areas over the past few years, which are used to provide a reference benchmark for calculating cumulative growth days in the flowering prediction module; second, current planting environment data collected in real time by the subsequent data acquisition module.
[0052] Prediction and Decision Database Parameter Preset: Based on the goals of sugarcane hybridization breeding and actual production needs, the database presets target hybridization time window parameters. The target hybridization time window refers to the preset time range within which the parent sugarcane should simultaneously reach full bloom to achieve the optimal hybridization effect. Simultaneously, the database also presets the flowering threshold required by the flowering prediction module. Biological zero degree of sugarcane growth And the fitness threshold required by the hybrid planning engine. Flowering period matching degree weighting coefficient Parental value weighting coefficient These key parameters, which are preset, will serve as the initial criteria for judging the operation of each module in the system.
[0053] Data service interface debugging: Technicians debug the data service interface to ensure that it can realize bidirectional data communication between the central database module and other functional modules. The interface supports real-time data reading and writing, ensuring smooth and accurate data flow between modules.
[0054] (II) Operation of the data acquisition module
[0055] The data acquisition module, through an IoT sensor network and an external database interface, comprehensively collects data on sugarcane growth environment and parental genotypes, providing fundamental data support for subsequent module operation. In the sugarcane parent planting area, an IoT sensor network is deployed according to a uniform distribution principle. Sensor types include light sensors, temperature sensors, and humidity sensors, used to collect four key environmental data categories: light duration, light intensity, ambient temperature, and air humidity. The data acquisition module establishes a communication connection with an external germplasm resource information database through a pre-defined standardized data interface. When the system needs to obtain flowering genotype data for a specific parent, the data acquisition module sends a data request to the external germplasm resource information database. The request includes the unique identifier of the parent to be queried. After receiving the request, the external database returns the corresponding parent's flowering genotype data. The data acquisition module verifies the received data, including data integrity and accuracy. After successful verification, the data acquisition module stores the flowering genotype data in the central database's flowering genotype database through a data service interface for use by the flowering prediction module.
[0056] (III) Operation of the flowering period prediction module
[0057] The flowering period prediction module receives flowering period genotype data and real-time environmental data from the central database module and the data acquisition module, and calculates the predicted peak flowering period of the parent plants by combining preset parameters. First, the module retrieves the flowering period genotype data of the parent plants to be predicted from the central database via a data service interface. The system analyzes the genotype data, focusing on extracting gene loci information related to photoperiod sensitivity and the photoperiod sensitivity coefficient of the parent plants. The module also obtains the daily average temperature from the real-time environmental data from the data acquisition module. Simultaneously, the preset biological zero degree of sugarcane growth is retrieved from the environmental time-series database of the central database through the data service interface. Biological zero degree This refers to the minimum temperature threshold for sugarcane growth and development. Below this temperature, sugarcane growth essentially ceases. The cumulative growth days are calculated based on this temperature. The system uses a preset growth baseline day as the starting point and calculates according to... Calculate the cumulative growth days, where This represents the daily period from the growth reference date to the calculation date. The accumulation of values, when a certain day's values are added together... Then the (day) A value of 0 indicates that no growth days are accumulated on that day. Accumulated growth days reflect the effective heat accumulation of sugarcane from the baseline growth date to the calculation date, and are an important indicator for judging the growth and development stage of sugarcane. Then, the daily measured sunshine duration is obtained from the data acquisition module. Simultaneously, the photoperiod of the parent's ecological type can be retrieved from the flowering genotype database of the central database through the data service interface. Lighting cycle This refers to the amount of sunshine required for sugarcane of this ecological type to reach its optimal flowering state, based on... Calculate the periodic function of light ( ), This is the photoperiod deviation penalty coefficient, ranging from 0.5 to 1.0, used to adjust the degree of inhibition on flowering induction when the actual daylight duration deviates from the optimal photoperiod. The function value ranges from 0 to 1. hour, This indicates that the current light conditions are most favorable for the flowering of this parent; when Deviation hour, The value decreases as the deviation increases, reflecting the enhanced inhibitory effect of current light conditions on flowering induction. The flowering prediction module retrieves the cumulative growth days required from the baseline date to flowering from the environmental time-series database of the central database through the data service interface. , This is the average cumulative growth days calculated based on the parent's flowering records over many years. It reflects the average cumulative heat required for the parent to reach flowering stage, combined with the calculated cumulative growth days. Photoperiod sensitivity coefficient With the periodic function of light ,according to Calculate the flowering induction index , This comprehensively reflects the genetic factors With environmental factors , Synergistic induction of sugarcane flowering The higher the value, the closer the parent plants are to the flowering state. The system retrieves the preset flowering threshold from the prediction and decision database in the central database. The daily calculations and When comparing, At that time, the system determines that the day is the predicted peak flowering period of the parent, and stores the predicted peak flowering period in the prediction and decision database of the central database through the data service interface, and pushes it to the flowering period control module and the hybridization planning engine.
[0058] (IV) Operation of the Flowering Period Regulation Module
[0059] The flowering period control module receives the predicted peak flowering period from the flowering period prediction module and, combined with the preset target hybridization time window in the central database, generates targeted environmental control instructions to drive environmental control equipment to adjust the planting environment, ensuring that the parent lines' flowering period matches the target hybridization time window. The flowering period control module reads the preset target hybridization time window from the prediction and decision database in the central database through a data service interface, determining the start and end dates of the time window, and thus determining the total length of the target hybridization time window. Simultaneously, the module receives the predicted peak flowering period for each parent line from the flowering period prediction module, compares the predicted peak flowering period of each parent line with the target hybridization time window, and calculates the flowering period difference value. If the predicted peak flowering period is within the target hybridization time window, the difference value is 0; if the predicted peak flowering period is earlier than the start date of the target hybridization time window, the difference value is the difference in the number of days between the start date and the predicted peak flowering period; if the predicted peak flowering period is later than the end date of the target hybridization time window, the difference value is the difference in the number of days between the predicted peak flowering period and the end date. This difference value directly reflects the degree of deviation between the parent line's current predicted flowering period and the target hybridization time window, and is the core basis for generating control instructions. Based on the calculated differences in flowering time, the system combines the influence patterns of different environmental factors on sugarcane flowering time to generate corresponding environmental control instructions. The flowering time control module sends the generated environmental control instructions to the corresponding environmental control equipment via wireless communication. After receiving the instructions, the equipment executes the corresponding operations according to the instruction parameters. At the same time, the module stores the environmental control instructions in the prediction and decision database of the central database through the data service interface, realizing the traceability and management of the instructions. This facilitates the subsequent query of environmental parameters after control by the hybridization planning engine, and allows technicians to review and analyze the control process.
[0060] (v) Hybrid Planning Engine Operation
[0061] The hybridization planning engine is the core of the system for dynamically adjusting the hybridization plan. Based on the predicted full bloom date of the parents after the flowering period control module, it calculates the fitness score of candidate hybridization combinations and selects the optimal executable hybridization combination. The hybridization planning engine obtains the updated predicted full bloom date of all parents after the flowering period control module from the prediction and decision database of the central database through the data service interface. The hybridization planning engine traverses all possible candidate hybridization combinations. ,in Represents the parent plant, Representing the father, according to Calculate the flowering period overlap fit score for each combination, where, and Representing the parent and father Predicted peak bloom period The total length of the target hybridization time window. The absolute difference in flowering period between the parents is expressed in days. and Parent and father The breeding value weight, and These are the weighting coefficients for flowering period matching and parental value, respectively, and they satisfy the following conditions: All Hybrid combinations are included in the candidate set, and combinations with low fitness are filtered out to reduce invalid hybridization attempts. For hybrid combinations in the candidate set, the system further performs overlap domain judgment: the predicted full bloom period of each pair of planned hybrid parents is matched with the target hybridization time window to determine whether there is a valid overlap between the predicted full bloom periods of the two within the target hybridization time window, that is, at least one day is within the target hybridization time window. If there is a valid overlap, the hybrid combination is retained and added to the list of executable hybrid combinations; if there is no valid overlap, the system will query again whether the flowering period control module can achieve flowering period synchronization by further adjusting environmental parameters. If the matching cannot be achieved through control, the hybrid combination is removed from the candidate set to ensure that the final executable hybrid combinations are all feasible to execute. The system sorts the hybrid combinations determined by the overlap region from high to low fitness scores, generating a final list of executable hybrid combinations. The list includes key information such as the parent number, predicted flowering period, and fitness score of the hybrid combinations. The hybridization planning engine stores the list of executable hybrid combinations in the prediction and decision database of the central database through the data service interface, and pushes it to the breeding management terminal for breeders to view and execute hybridization operations.
[0062] In summary, this embodiment, through the collaborative work of various modules, forms an intelligent management process encompassing data acquisition, flowering period prediction, environmental control, and hybridization planning. This effectively solves the problem of unmatched flowering periods in sugarcane hybridization breeding, improves the accuracy and efficiency of hybridization breeding, and provides strong technical support for sugarcane variety improvement.
[0063] Example 2
[0064] Based on Example 1, such as Figure 1 As shown in the figure, this embodiment provides the specific steps of the intelligent management system based on sugarcane hybridization data in managing sugarcane hybridization data:
[0065] Environmental data collection: An IoT sensor network deployed in the parent plantation automatically and continuously collects real-time environmental data for each field, including duration of sunlight, light intensity, ambient temperature, and air humidity.
[0066] Genetic data acquisition: The system automatically retrieves the flowering period genotype data of all current hybrid parents from an external germplasm resource database through a standardized data interface.
[0067] Centralized data storage: The collected real-time environmental data and the obtained flowering period genotype data are uniformly transmitted and stored in the corresponding database of the central database module.
[0068] Flowering period modeling and prediction: The flowering period prediction module calls the genotype and environmental data of specific parents from the central database, simulates their growth and development process, and calculates the accurate predicted peak flowering period for each parent.
[0069] Flowering period difference comparison: The flowering period control module reads the pre-set target hybridization time window and compares it with the predicted full bloom period to automatically calculate the flowering period difference of each parent.
[0070] Generate control instructions: Based on the calculated differences in flowering period, the system automatically selects the optimal solution from the strategy library and generates specific environmental control instructions.
[0071] Implement precise regulation: The generated environmental regulation instructions are sent to the corresponding environmental control equipment, which executes automatically to actively adjust the growth environment of the parent plants so that their flowering period approaches the target time window.
[0072] Combination Feasibility Assessment: The hybridization planning engine obtains the updated predicted peak flowering period after adjustment. For each planned hybridization combination, the system calculates its flowering period overlap fit score, which integrates the degree of matching of the flowering periods of the parents and their breeding value.
[0073] Generate an executable list: Based on the scoring results, the system automatically filters out all feasible hybridization combinations and sorts them according to success probability and priority, ultimately generating a dynamic list of executable hybridization combinations to directly guide breeders in field operations.
[0074] The hybridization planning engine dynamically updates the list of executable hybridization combinations based on the latest predicted peak flowering period, removing combinations that still cannot be matched due to ineffective regulation, ensuring the real-time nature and feasibility of the plan.
[0075] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. An intelligent management system based on sugarcane hybridization data, characterized in that, The system consists of: a data acquisition module, a flowering period prediction module, a flowering period control module, a hybridization planning engine, and a central database module. The data acquisition module is used to collect real-time environmental data through an Internet of Things sensor network and obtain flowering period genotype data from an external database through an interface. The flowering period prediction module is communicatively connected to the central database module and the data acquisition module. It is used to receive the flowering period genotype data of the parents and real-time environmental data, and output the predicted peak flowering period. The flowering period regulation module is communicatively connected to the flowering period prediction module. It is used to receive the predicted full bloom period, compare it with the preset target hybridization time window to generate an environmental regulation command, and send the command to the environmental control equipment. The hybridization planning engine is connected to the flowering period prediction module and the flowering period regulation module. It is used to dynamically adjust the hybridization plan and output a list of executable hybridization combinations based on the regulated flowering period status of the parents. The central database module is used to store and manage flowering period genotypes, real-time environmental data, predicted peak flowering period, target hybridization time windows, environmental control instructions, and a list of executable hybridization combinations, and provides data support for each functional module.
2. The intelligent management system based on sugarcane hybridization data according to claim 1, characterized in that, The data acquisition module continuously collects real-time environmental data, including light duration, light intensity, ambient temperature, and air humidity, through the Internet of Things sensor network deployed in the parent plantation area. The flowering genotype data is retrieved and verified from an external germplasm resource database using a standardized data interface. The flowering genotype data includes gene locus information related to photoperiod sensitivity and vernalization.
3. The intelligent management system based on sugarcane hybridization data according to claim 1, characterized in that, The flowering period prediction module calculates the predicted peak flowering period through the following steps: The system receives flowering period genotype data of specific parents from the central database module and extracts photoperiod sensitivity coefficients from it. ; Receive the daily average temperature sequence from the data acquisition module and calculate the cumulative growth days from the reference date. Where GDD represents cumulative growth days, The daily average temperature The preset biological zero degree for sugarcane growth, This represents the cumulative sum of daily values from the growth reference date to the calculation date; Integrating genetic and environmental factors to calculate the flowering induction index ; When the flowering induction index Greater than the flowering threshold ,Right now When the time comes, the system will determine that day as its predicted peak blooming period.
4. The intelligent management system based on sugarcane hybridization data according to claim 3, characterized in that, The flowering induction index ,in, This represents the cumulative growth days required for this parental line from the baseline date to flowering. It is a function that takes the currently measured sunshine duration as input. , The data acquisition module represents the daily measured sunshine duration. The photoperiod of the parent's ecological type is defined in the central database module. This is the penalty coefficient for optical period deviation, with a value ranging from 0.5 to 1.
0.
5. The intelligent management system based on sugarcane hybridization data according to claim 1, characterized in that, The specific steps by which the flowering period control module generates the environmental control command are as follows: Read the preset target hybridization time window from the central database module; The predicted full bloom period output by the flowering period prediction module is compared with the target hybridization time window to calculate the difference in flowering period for each parent. Based on the aforementioned differences in flowering period, commands are used to control the switching on and off of supplemental lighting and the light cycle, to control the start and stop of the greenhouse heating and cooling systems, and to control the operation of the shading net. The generated environmental control instructions are sent to the corresponding environmental control devices, and the instructions are simultaneously stored in the central database module.
6. The intelligent management system based on sugarcane hybridization data according to claim 1, characterized in that, The hybridization planning engine obtains the predicted full bloom dates of all parents after adjustment by the flowering period control module from the flowering period prediction module, for each candidate hybridization combination. ,in Represents the parent plant, Representing the paternal parent, calculate the flowering overlap fitness score for this combination. ,in, and Representing the parent and father Predicted peak bloom period The total length of the target hybridization time window. The absolute difference in flowering period between the parents is expressed in days. and Parent and father The breeding value weight, and These are the weighting coefficients for flowering period matching and parental value, respectively, and they satisfy the following conditions: All Hybrid combinations are included in the candidate set, and within the candidate set, according to The scores are sorted from highest to lowest to generate a final list of executable hybridization combinations. An overlap domain determination is then performed on the hybridization combination list. This is the fitness threshold.
7. The intelligent management system based on sugarcane hybridization data according to claim 6, characterized in that, The overlap region determination rule in the hybridization planning engine is as follows: Match the predicted flowering period of each pair of planned hybridization parents to determine whether their flowering periods overlap within the target hybridization time window; If valid overlap exists, the hybridization combination is retained and added to the list of executable hybridization combinations; If there is no effective overlap and matching cannot be achieved through the flowering period control module, then the hybridization combination is removed from the list of executable hybridization combinations.
8. The intelligent management system based on sugarcane hybridization data according to claim 1, characterized in that, The central database module includes: A flowering period genotype database is used to store and manage the flowering period genotype data of all parental materials; An environmental time-series database is used to store historical and real-time environmental data uploaded by the data acquisition module; A prediction and decision database is used to store the predicted full bloom period, the target hybridization time window, the environmental control instructions, and the list of executable hybridization combinations. The data service interface provides unified data read, write, and query services for the flowering period prediction module, flowering period regulation module, and hybridization planning engine.