A facility agriculture prevention and control delivery method and system based on disease expansion precursor isolation

Abstract

This application discloses a method and system for disease prevention and control in facility agriculture based on the isolation of disease precursors. By acquiring disease precursor migration characterization data and propagation and inheritance relationship data from each production unit within the target facility, precursor migration fragment data is generated. Evolutionary correlation is performed on the precursor migration fragment data to form disease precursor evolution chain data, and combined with propagation and inheritance relationship data to construct precursor propagation and inheritance diagram data, which is then mapped to generate precursor expansion potential energy data. Based on the precursor expansion potential energy data, isolation control zoning data, inheritance and blocking configuration sequences, and blocking constraint deployment sequences are generated. Furthermore, the precursor expansion potential energy data is corrected by writing back based on the inhibition response characterization data, and the prevention and control deployment configuration is updated hierarchically, thereby improving the processing efficiency of disease expansion precursor identification, cross-production unit inheritance and blocking, and dynamic matching of prevention and control deployment.

Description

Technical Field

[0001] This application relates to the field of intelligent prevention and control technology in facility agriculture, and in particular to a method and system for prevention and control in facility agriculture based on the isolation of early signs of disease expansion. Background Technology

[0002] In facility agriculture production environments, crops are typically situated in relatively enclosed or semi-enclosed spaces such as greenhouses, polytunnels, and plant factories. Temperature, humidity, airflow exchange, irrigation conditions, operational pathways, and crop canopy distribution are strongly correlated. When diseases spread in such environments, they often do not begin to propagate only after obvious lesions appear. Instead, they gradually develop precursors through localized heat and humidity retention, airflow recirculation, canopy shading, operational contact, and changes in the conditions of adjacent production units. Therefore, disease control in facility agriculture requires identifying the evolutionary trends of disease precursors before symptoms appear and implementing isolation, blocking, and control measures in advance based on the transmission relationships between production units.

[0003] Disease control methods in facility agriculture typically rely on identifying visible lesions in crop images, environmental parameter threshold alarms, manual inspection records, or fixed-cycle spraying, ventilation, dehumidification, and operational management. Some control systems determine the areas requiring treatment based on greenhouse temperature and humidity data, image recognition results, or disease risk scores, and then perform spraying, activate control equipment, or adjust the environment in the corresponding areas according to preset rules. These methods often focus on areas with existing abnormalities, lesion areas, or preset management zones, with control boundaries usually determined by the current monitoring area, greenhouse zones, or fixed operational areas.

[0004] The above methods still have shortcomings in the treatment of disease precursors in facility agriculture: disease control in facility agriculture relies on the identification of symptomatic lesions or fixed-cycle application, making it difficult to identify the continuous evolution of disease precursors within production units in a timely manner, to determine isolation boundaries and targets for blocking based on the driving intensity, direction of absorption, and priority of absorption of precursors to adjacent production units, and to update the control application sequence in stages based on the changes in precursors after application. Summary of the Invention

[0005] In view of the above-mentioned actual situation, this application proposes a method and system for disease control and prevention in facility agriculture based on the isolation of disease precursors, in order to solve the problems in the existing technology that rely on the identification of symptomatic lesions or fixed-cycle application for disease control in facility agriculture, which makes it difficult to identify the continuous evolution process of disease precursors in production units in a timely manner, makes it difficult to determine the isolation boundary and the target of interception based on the driving intensity, direction of reception and priority of the precursors migrating to adjacent production units, and makes it difficult to update the control and prevention application sequence in a hierarchical manner based on the changes in precursors after application.

[0006] A method for disease control and prevention in facility agriculture based on isolating disease precursors includes: Acquire disease precursor migration characterization data of each production unit within the target facility and data on the propagation and inheritance relationship between the production units. Perform fragment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data. Evolutionary correlation processing is performed on the precursor migration fragment data to determine the target production unit and generate the precursor evolution chain data corresponding to the target production unit; precursor propagation and acceptance map data is constructed based on the precursor evolution chain data and the propagation and acceptance relationship data, and the precursor propagation and acceptance map data is subjected to extended potential energy mapping processing to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving strength, acceptance direction, and acceptance priority relationship of the precursor migration to adjacent production units along the precursor propagation and acceptance map data; Based on the disease precursor evolution chain data, precursor aggregation contour data is determined. The directional distribution of the precursor expansion potential energy data in the precursor propagation and transfer diagram data is subjected to boundary projection processing to generate transfer extrapolation contour data. Based on the precursor aggregation contour data, a core isolation zone is determined. Based on the transfer extrapolation contour data, an extensional blocking zone is determined. Isolation control partition data is generated from the core isolation zone and the extensional blocking zone. Based on the distribution of the precursor propagation potential energy data in the precursor propagation and acceptance map data, the accepting production unit is determined from the adjacent production units that have a propagation and acceptance relationship with the target production unit, and acceptance hierarchical sequence data is generated; the acceptance hierarchical sequence data is subjected to blocking configuration processing to generate an acceptance blocking configuration sequence. A primary suppression deployment sequence is generated based on the isolation control partition data. This primary suppression deployment sequence is then subjected to hierarchical constraint processing based on the receiving blocking configuration sequence to generate a blocking constraint deployment sequence. Prevention and control deployment processing is performed according to the blocking constraint deployment sequence to obtain suppression response characterization data. The precursor expansion potential energy data is then written back and corrected based on the suppression response characterization data to generate corrected expansion potential energy data. Finally, the blocking constraint deployment sequence is sequentially updated based on the corrected expansion potential energy data to generate a hierarchical prevention and control deployment configuration sequence.

[0007] Furthermore, the process of merging and grouping the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data includes: Acquire unit time-series acquisition data of each production unit within the target facility, extract precursor migration characterization from the unit time-series acquisition data, and generate the disease precursor migration characterization data. The disease precursor migration characterization data is used to characterize the migration and changes of disease precursors within the production unit during the acquisition period. The disease precursor migration characterization data are divided into candidate windows to obtain candidate precursor window data; Based on the continuity relationship and unit location attribution relationship between adjacent acquisition periods of the candidate precursor window data, the candidate precursor window data is subjected to segment merging processing to generate the precursor migration segment data. The precursor migration segment data is used to characterize the local continuous anomaly range of disease precursors within a single production unit.

[0008] Furthermore, the step of performing evolutionary correlation processing on the precursor migration fragment data to determine the target production unit and generate the precursor evolution chain data corresponding to the target production unit includes: The segments in the precursor migration fragment data are identified as precursor evolution nodes; The basic evolutionary connection relationship is formed based on the temporal succession relationship between adjacent precursor evolutionary nodes; Based on the precursor intensity variation relationship and spatial migration relationship corresponding to the basic evolutionary connectivity relationship, a corrected evolutionary connectivity relationship is generated; The precursor evolution nodes are connected according to the corrected evolution connection relationship, and precursor stage markers are configured for the precursor evolution nodes to generate the disease precursor evolution chain data. The disease precursor evolution chain data is used to characterize the serialized association results of the disease precursor evolution from initial abnormality, continuous abnormality to intensified abnormality or outward expansion abnormality. The target production unit is determined based on the precursor evolution nodes in the disease precursor evolution chain data that are configured with precursor stage markers corresponding to the expansion stage.

[0009] Furthermore, the feature is that constructing the precursor propagation and succession diagram data based on the disease precursor evolution chain data and the propagation and succession relationship data includes: Obtain the unit-bearing structure data of the target facility, perform propagation and acceptance analysis on the unit-bearing structure data, and generate the propagation and acceptance relationship data. The propagation and acceptance relationship data is used to characterize the pathway and directional relationships between adjacent production units that can be used for the migration and acceptance of disease precursors. The production unit is mapped to the receiving node in the precursor propagation receiving diagram data, and the receiving node corresponding to the target production unit is determined as the starting receiving node; Map the directed inheritance relationship between adjacent production units that have a propagation inheritance relationship as connecting edges; Configure the bearing direction parameters and bearing strength parameters for the connecting edge based on the propagation bearing relationship data; The precursor propagation and acceptance map data is constructed from the acceptance node, the starting acceptance node, the connecting edge, the acceptance direction parameter, and the acceptance strength parameter. The precursor propagation and acceptance map data is used to characterize the graphical acceptance structure of disease precursors being transmitted from the target production unit to adjacent production units.

[0010] Furthermore, the step of performing extended potential energy mapping processing on the precursor propagation transition map data to generate precursor extended potential energy data includes: The precursor evolution node located at the outer end is obtained from the disease precursor evolution chain data and used as the outer end node; The outer end node is mapped to the starting receiving node in the precursor propagation receiving map data, and an initial potential energy value is generated based on the precursor intensity of the outer end node. The initial potential energy value is transmitted along the connecting edge corresponding to the starting receiving node, and the edge transmission value is generated according to the receiving strength parameter of the connecting edge. The edge transmission values ​​at different propagation levels are subjected to hierarchical attenuation processing to obtain the potential energy transmission values ​​corresponding to the candidate receiving nodes; The driving intensity and the receiving direction are determined based on the potential energy transfer value and the receiving direction parameter, and the receiving priority relationship is determined according to the magnitude relationship of the potential energy transfer value. The precursor expansion potential energy data is generated from the driving intensity, the receiving direction, and the receiving priority relationship. The precursor expansion potential energy data is used to characterize the potential energy distribution results of the disease precursor spreading to adjacent production units along the precursor propagation receiving map data.

[0011] Furthermore, the step of determining precursor aggregation contour data based on the precursor evolution chain data, performing boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation transition map data to generate transition extrapolation contour data; determining a core isolation zone based on the precursor aggregation contour data, determining an extensional blocking zone based on the extensional blocking zone data, and generating isolation control partition data from the core isolation zone and the extensional blocking zone, includes: Based on the unit location and segment coverage of the precursor evolution node located within the target production unit in the disease precursor evolution chain data, the precursor cluster contour data is generated. The precursor cluster contour data is used to characterize the bounded range of continuous precursor clusters that have formed within the target production unit. The boundary projection direction is determined based on the receiving direction in the precursor extended potential energy data, and the boundary extrapolation amplitude is determined based on the driving intensity in the precursor extended potential energy data. According to the boundary projection direction and the boundary extrapolation magnitude, the boundary of adjacent production units is subjected to boundary projection processing to generate candidate data for the extrapolation contour. The candidate data for the extrapolation of the bearing contour are sorted according to the bearing priority relationship in the precursor extended potential energy data to generate the extrapolation of the bearing contour data. The extrapolation of the bearing contour data is used to characterize the peripheral blocking range formed by extrapolation along the propagation bearing direction. The core isolation zone is defined based on the precursor aggregation contour data, the extended blocking zone is defined based on the receiving extrapolation contour data, and the direction-strengthened isolation sub-region is determined within the extended blocking zone according to the receiving priority relationship; The isolation control partition data is generated from the core isolation zone, the extended blocking zone, and the directional reinforcement isolation sub-zone. The isolation control partition data is used to characterize the partition control range for disease precursor isolation and outward expansion blocking.

[0012] Furthermore, based on the distribution of the precursor propagation potential energy data in the precursor propagation succession map data, the succession production unit is determined from adjacent production units that have a propagation succession relationship with the target production unit, and succession hierarchical sequence data is generated; the succession hierarchical sequence data is then subjected to blocking configuration processing to generate a succession blocking configuration sequence, including: Based on the potential energy transfer value of the precursor extended potential energy data at each receiving node, candidate receiving production units are determined from the adjacent production units that have a propagation receiving relationship with the target production unit. According to the threshold range of the acceptance level where the potential energy transfer value is located, the candidate acceptance production units are divided into acceptance levels. The candidate acceptance production units that have completed the acceptance level division are determined as the acceptance production units. The acceptance production units are arranged according to the acceptance level to generate the acceptance level sequence data. The acceptance level sequence data is used to characterize the order and acceptance level relationship of the acceptance production units to the outward spread of disease precursors. According to the acceptance level, the corresponding acceptance control items are configured for the acceptance production unit, and the acceptance control items include blocking control items, prevention control items, or observation control items; The acceptance blocking configuration sequence is generated based on the acceptance control item. The acceptance blocking configuration sequence is used to characterize the acceptance control method corresponding to the acceptance production unit of different acceptance levels.

[0013] Furthermore, the step of generating a primary suppression deployment sequence based on the isolation control partition data, and performing hierarchical constraint processing on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence, includes: Based on the isolation control zone data, the primary suppression action corresponding to each control zone is determined. The primary suppression action refers to the action taken to weaken the conditions for the spread and transmission of disease precursors within the control zone. The primary suppression actions are arranged according to the control priority of the core isolation zone, the directional enhanced isolation sub-zone, and the extended blocking zone to generate the primary suppression deployment sequence. The primary suppression deployment sequence is used to characterize the combination of suppression actions configured for different control zones in the initial prevention and control phase. Based on the aforementioned blocking configuration sequence, the intensity of the actions in the primary inhibition delivery sequence is subject to level constraints to obtain an intensity-constrained delivery sequence. Based on the accepted control item, the scope of application and execution order of the strength constraint deployment sequence are updated to generate the blocking constraint deployment sequence. The blocking constraint deployment sequence is used to characterize the prevention and control execution sequence after accepting the blocking configuration constraints.

[0014] Further, the execution of the blocking constraint deployment sequence yields suppression response characterization data; the suppression response characterization data is used to write back and correct the precursor extended potential energy data to generate corrected extended potential energy data; and the blocking constraint deployment sequence is then sequentially updated based on the corrected extended potential energy data to generate a sequential prevention and control deployment configuration sequence, including: After performing the prevention and control deployment process according to the blocking constraint deployment sequence, the inhibition response characterization data corresponding to the target production unit and the receiving production unit are obtained. The inhibition response characterization data is used to characterize the precursor changes after the execution of the blocking constraint deployment sequence. Based on the suppression response characterization data, determine the precursor fall-off result, precursor maintenance result, or precursor enhancement result; Based on the precursor fallback result, the precursor maintenance result, or the precursor strengthening result, the driving intensity, receiving direction, and receiving priority relationship in the precursor extended potential energy data are written back and corrected to generate the corrected extended potential energy data. When the corrected extended potential energy data indicates an increased risk, the blocking constraint deployment sequence is upgraded and updated to generate an upgraded suppression deployment sequence; when the corrected extended potential energy data indicates that the risk remains the same, the blocking constraint deployment sequence is maintained and updated to generate a maintained suppression deployment sequence; when the corrected extended potential energy data indicates that the risk decreases, the blocking constraint deployment sequence is recovered and updated to generate a deployment and recovery sequence. The hierarchical prevention and control deployment configuration sequence is generated based on the upgraded suppression deployment sequence, the maintained suppression deployment sequence, or the deployment and recovery sequence. The hierarchical prevention and control deployment configuration sequence is used to characterize the prevention and control deployment execution configuration updated as the risk of disease precursor expansion changes.

[0015] Furthermore, this application also discloses a facility agriculture control and application system based on the isolation of disease pre-spreading signs, the system comprising: The precursor fragment generation unit is used to acquire the disease precursor migration characterization data of each production unit in the target facility and the propagation and inheritance relationship data between the production units, and to perform fragment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data. An extended potential energy mapping unit is used to perform evolutionary correlation processing on the precursor migration fragment data, determine the target production unit, and generate the disease precursor evolution chain data corresponding to the target production unit; construct precursor propagation and acceptance diagram data based on the disease precursor evolution chain data and the propagation and acceptance relationship data, and perform extended potential energy mapping processing on the precursor propagation and acceptance diagram data to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving strength, acceptance direction, and acceptance priority relationship of the disease precursor migrating to adjacent production units along the precursor propagation and acceptance diagram data. The isolation zone generation unit is used to determine precursor aggregation contour data based on the disease precursor evolution chain data, perform boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation transition map data, and generate transition extrapolation contour data; determine the core isolation zone based on the precursor aggregation contour data, determine the extensional blocking zone based on the transitional extrapolation contour data, and generate isolation control zone data from the core isolation zone and the extensional blocking zone; The receiving and blocking configuration unit is used to determine the receiving production unit from the adjacent production units that have a propagation receiving relationship with the target production unit based on the distribution result of the precursor propagation potential energy data in the precursor propagation receiving map data, and generate receiving hierarchical sequence data; and to perform blocking configuration processing on the receiving hierarchical sequence data to generate a receiving and blocking configuration sequence. The hierarchical deployment and update unit is used to generate a primary suppression deployment sequence based on the isolation control partition data, and to perform hierarchical constraint processing on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence; to perform prevention and control deployment processing according to the blocking constraint deployment sequence to obtain suppression response characterization data; to perform write-back correction on the precursor extended potential energy data based on the suppression response characterization data to generate corrected extended potential energy data; and to perform hierarchical update processing on the blocking constraint deployment sequence based on the corrected extended potential energy data to generate a hierarchical prevention and control deployment configuration sequence.

[0016] The proposed method and system for disease prevention and control in facility agriculture based on the isolation of disease precursors achieve the following: merging and identifying the migration fragments of disease precursors before the onset of symptoms in facility agriculture; constructing the disease precursor evolution chain and precursor propagation succession diagram; mapping and generating precursor expansion potential energy data; and continuously generating isolation control zones, succession blocking configurations, and blocking constraint deployment sequences. Furthermore, by writing back and correcting the precursor expansion potential energy data using suppression response characterization data, the prevention and control deployment configuration can be upgraded, maintained, or updated according to changes in the risk of disease precursor expansion, thereby improving the processing effectiveness of disease precursor identification, cross-production unit succession blocking, and dynamic matching of prevention and control deployment. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for disease control and prevention in facility agriculture based on isolating early signs of disease spread. Figure 2 A schematic diagram illustrating the data logic relationship between the evolution, transmission, and hierarchical delivery of disease precursors; Figure 3 A schematic diagram of the pre-emergence aggregation, transduction, and isolation control zones within the target facility; Figure 4 A schematic diagram of a function model for the transfer of precursory extended potential energy along the propagation hierarchy; Figure 5 A schematic diagram of the function model for suppressing response write-back and hierarchical prevention and control of update deployment; Figure 6 This is a schematic diagram illustrating the transmission, reception, and isolation control scenario of a multi-span tomato greenhouse production unit in this application embodiment; Figure 7 This is a schematic diagram of a facility agriculture prevention and control system based on the isolation of early signs of disease expansion, provided as an embodiment of this application. Detailed Implementation

[0018] To make the purpose, technical solution, and beneficial effects of this application clearer, the implementation methods of this application will be further described in detail below, combining the division of facility agriculture production units, the collection of precursor data, the analysis of propagation and transmission relationships, and the implementation process of prevention and control measures. It should be understood that the following implementation methods are used to illustrate the technical solution of this application and are not intended to limit the scope of protection of this application.

[0019] It should be noted that before and during the collection of production operation data, crop image data, environmental monitoring data, work record data, and equipment execution feedback data within the target facility, this application collects, stores, and processes data in accordance with the configuration of the target facility owner, manager, or authorized user. In scenarios involving image acquisition, work record acquisition, or facility operation data acquisition, the activation of acquisition equipment, acquisition scope, acquisition time period, and data usage method are all implemented in accordance with facility management configuration and relevant laws and regulations. Data without the corresponding authorized configuration will not be included in the disease precursor identification, transmission and analysis, and control and prevention application processing flow described in the implementation method of this application.

[0020] The target facility described in this application refers to a closed or semi-closed production space used for facility agriculture production. The target facility includes one of the following: greenhouse, multi-span greenhouse, plant factory, facility-based seedling area, or elevated cultivation facility. Several production units are set up within the target facility. These production units are the basic objects for precursor data collection, transmission relationship analysis, isolation zoning, and control deployment in this application. Production units are determined according to management areas defined by planting beds, cultivation troughs, crop rows, seedling trays, irrigation zones, greenhouse zones, or facility control systems. Multiple production units within the same target facility have spatial adjacency, environmental exchange, operational access, or control zone linkage relationships. These relationships provide the basis for subsequent formation and dissemination of transmission relationship data.

[0021] The method described in this application is executed by one of the following: a facility agriculture management server, an edge computing device, a greenhouse controller, and a cloud-based prevention and control scheduling platform, or by a combination of the above devices. The acquisition end is used to acquire unit time-series acquisition data of each production unit within the target facility. The acquisition end includes environmental acquisition equipment, image acquisition equipment, operation recording equipment, and an equipment operation record acquisition module. The computing end is used to extract precursor migration characteristics from the unit time-series acquisition data and further form precursor migration fragment data, disease precursor evolution chain data, precursor propagation and transfer diagram data, precursor expansion potential energy data, and prevention and control deployment-related sequences. The execution end is used to execute environmental adjustments, prevention and control treatments, and operational restrictions based on the prevention and control deployment-related sequences. The storage end is used to store historical operation data, production unit structure data, threshold ranges, parameter configurations, deployment execution records, and suppression response records.

[0022] In this application's embodiments, unit time-series data refers to a data set aggregated to the corresponding production unit according to the collection period. This data set reflects environmental changes, crop phenotypic changes, operational activity changes, and equipment execution changes within the production unit during the continuous collection period. Unit-based structural data refers to structured data formed by the spatial structural relationships, environmental exchange relationships, operational access relationships, and management zoning relationships between production units within the target facility. Disease precursor migration characterization data is the time-series characterization result extracted based on unit time-series data, used to characterize the occurrence, maintenance, enhancement, or migration changes of disease precursors within the production unit during the collection period. Transmission and transmission relationship data is the relationship data obtained based on the parsing of unit-based structural data, used to characterize the pathway and directional relationships between adjacent production units for the transmission and transmission of disease precursors.

[0023] The specific hardware structure and underlying driver methods of the aforementioned environmental acquisition equipment, image acquisition equipment, communication equipment, database, environmental control equipment, prevention and control equipment, and operation scheduling equipment are implementation methods well-known to those skilled in the art in the field of facility agriculture control. The timestamp alignment, outlier removal, format conversion, and normalization processing of the unit time-series acquisition data are also conventional techniques in data preprocessing and will not be elaborated upon in this application's embodiments. The above implementation details do not affect the understanding and implementation of the embodiments of this application.

[0024] In the prevention and control of diseases in facility agriculture, control measures typically rely on the identification of symptomatic lesions, fixed-cycle spraying, or regionalized unified treatment. These methods struggle to promptly identify the process by which disease precursors spread from localized anomalies within a production unit to adjacent units, and also find it difficult to determine the extent of outreach based on the direction and intensity of the spread. The implementation method in this application utilizes disease precursor evolution chain data, precursor propagation and transmission map data, and precursor expansion potential energy data to form a continuous control process from precursor identification, isolation zoning, transmission blocking, to hierarchical application updates. This transforms the control application from post-symptom treatment to pre-symptom isolation and transmission blocking.

[0025] To facilitate understanding of the data processing procedures in the embodiments of this application, the core data objects, data structures, and parameter sources involved in this application are described below. Each data object is used in different processing stages. The data object formed in the previous stage serves as the input or constraint object for the processing in the next stage, thereby forming a processing chain of precursor migration identification, propagation and acceptance analysis, extended potential energy mapping, isolation partitioning, acceptance blocking, and hierarchical deployment.

[0026] The disease precursor migration characterization data is not an instantaneous reading from a single sensor at a single moment, but rather a time-series characterization result obtained from multi-source data collected within a production unit through time period attribution, unit attribution, and precursor migration characterization. This disease precursor migration characterization data is used to represent the occurrence, maintenance, enhancement, or migration changes of disease precursors within a production unit over a continuous collection period. The propagation and inheritance relationship data is not simply an adjacency relationship, but rather a pathway and directional relationship parsed from the unit inheritance structure data, used to represent the structural conditions under which disease precursors migrate and inherit from one production unit to adjacent production units.

[0027] Candidate precursor window data are candidate time period objects formed by windowing the precursor migration characterization data. They are used to represent local abnormal changes that meet the precursor triggering conditions within a certain collection period. Precursor migration fragment data are data objects obtained by merging fragments when there are continuous succession relationships and unit location affiliation relationships between candidate precursor window data. They are used to represent the range of local continuous anomalies within a single production unit. Precursor evolution nodes are node objects converted from precursor migration fragment data, carrying fragment location, fragment coverage, fragment intensity, and collection period information.

[0028] The basic evolutionary connection relationship is formed based on the temporal sequence between adjacent precursor evolutionary nodes. The corrected evolutionary connection relationship is formed by combining the precursor intensity variation relationship and spatial migration relationship with the basic evolutionary connection relationship. Precursor stage markers are stage identifiers configured on precursor evolutionary nodes to indicate whether the corresponding precursor evolutionary node is in the initial stage, continuous stage, intensification stage, or expansion stage. Expansion end nodes are the end nodes in the disease precursor evolution chain data that represent the outward expansion of the precursor from the target production unit. Disease precursor evolution chain data is a serialized association result formed by precursor evolutionary nodes and corrected evolutionary connection relationships, used to represent the process of disease precursors evolving from initial anomalies and continuous anomalies to intensified anomalies or expansion anomalies.

[0029] The precursor disease propagation and inheritance diagram data is a graph-based association data constructed based on precursor disease evolution chain data and propagation and inheritance relationship data. In this graph-based association data, production units are mapped as inheritance nodes, the inheritance node corresponding to the target production unit is determined as the starting inheritance node, and the directed inheritance relationship between adjacent production units with propagation and inheritance relationships is mapped as connecting edges. The connecting edges carry inheritance direction parameters and inheritance strength parameters. The inheritance direction parameter is used to represent the directional relationship of precursor disease propagation along the connecting edge, and the inheritance strength parameter is used to represent the inheritance capacity corresponding to the connecting edge.

[0030] The initial potential energy value is the initial potential energy value formed after the outward expansion node is mapped to the initial receiving node. The edge transfer value is the transfer amount formed after the initial potential energy value is transferred along the connecting edge and affected by the connecting edge receiving strength. Hierarchical attenuation processing refers to the process of attenuating and correcting the edge transfer values ​​at different propagation levels. The potential energy transfer value is the potential energy result formed on the candidate receiving node after connecting edge transfer and hierarchical attenuation processing. The precursor expansion potential energy data is formed by driving strength, receiving direction, and receiving priority relationship, and is used to represent the potential energy distribution result of the disease precursor expanding to adjacent production units along the precursor propagation receiving map data. Among them, driving strength is used to characterize the strength of the disease precursor migration to the receiving production unit, receiving direction is used to characterize the direction of the disease precursor migration, and receiving priority relationship is used to characterize the receiving order relationship between multiple candidate receiving nodes.

[0031] Precursor aggregation contour data is boundary data generated based on the cell location and segment coverage of precursor evolution nodes within the target production unit. It is used to represent the range within the target production unit where continuous precursor aggregation has formed. Outward extrapolation contour data is contour data formed after boundary projection processing based on the directional distribution of precursor extension potential energy data in the precursor propagation outward projection map data. It is used to represent the peripheral blocking range formed by outward projection along the propagation outward projection direction. Boundary projection processing refers to the process of determining the outward projection direction based on the outward projection direction, determining the outward projection amplitude based on the driving intensity, and sorting or discarding the outward projection contours according to the outward projection priority.

[0032] The isolation control zoning data consists of a core isolation zone, an outer blocking zone, and a directional reinforcement isolation sub-zone. The core isolation zone corresponds to the precursor aggregation range bounded by the precursor aggregation contour data; the outer blocking zone corresponds to the outer blocking range bounded by the receiving extrapolated contour data; and the directional reinforcement isolation sub-zone corresponds to the outward expansion direction with a higher receiving priority. The receiving grade sequence data is a sequence of data formed based on the potential energy transfer values ​​of the precursor expansion potential energy data at each receiving node and the receiving grade threshold range. It is used to represent the receiving production unit's receiving sequence and receiving grade relationship for the outward expansion of the precursor.

[0033] Acceptance control items are control configuration objects corresponding to acceptance levels, including blocking control items, preventive control items, and observation control items. Blocking control items are used for production units with high acceptance risk, preventive control items are used for production units with intermediate risk levels, and observation control items are used for production units with low risk but still requiring continuous monitoring. The acceptance blocking configuration sequence is a configuration sequence formed based on acceptance level sequence data and acceptance control items, used to represent the acceptance control methods corresponding to production units at different acceptance levels.

[0034] The primary suppression deployment sequence is an initial execution sequence formed based on isolation control zone data, used to represent the combination of suppression actions configured for different control zones in the initial prevention and control phase. The blocking constraint deployment sequence is a prevention and control execution sequence formed after updating the action intensity, scope of effect, and execution order of the primary suppression deployment sequence based on the receiving blocking configuration sequence. Suppression response characterization data is a data object formed by a new round of data collection and deployment execution records from the target production unit and the receiving production unit after executing the blocking constraint deployment sequence, used to represent the precursor change results after deployment execution. The precursor change results include precursor decline results, precursor maintenance results, and precursor strengthening results.

[0035] Corrected extended potential energy data is a data object formed by writing back and correcting the driving intensity, direction of absorption, and priority of absorption in the precursor extended potential energy data based on the suppression response characterization data. An upgraded suppression deployment sequence is a deployment sequence formed when the corrected extended potential energy data indicates an increased absorption risk; a maintained suppression deployment sequence is a deployment sequence formed when the corrected extended potential energy data indicates that the absorption risk is maintained; and a deployment recovery sequence is a deployment sequence formed when the corrected extended potential energy data indicates that the absorption risk has decreased. A tiered control deployment configuration sequence is an execution configuration generated based on the upgraded suppression deployment sequence, the maintained suppression deployment sequence, or the deployment recovery sequence, used to represent the control deployment execution configuration updated as the risk of precursor disease expansion changes.

[0036] In some implementations, the production unit data structure includes a production unit identifier, a unit location, adjacent unit identifiers, a control zone attribute, a data acquisition device identifier, and an execution device identifier. The production unit identifier distinguishes different production units within the target facility; the unit location indicates the spatial position of the production unit within the target facility; the adjacent unit identifier indicates production units that are adjacent to this production unit; the control zone attribute indicates the production unit's affiliation within the isolation control zone; and the data acquisition device identifier and the execution device identifier are used to associate the data acquisition end and the prevention and control execution end, respectively.

[0037] In some implementations, the precursor propagation and acceptance map data structure includes acceptance nodes, initial acceptance nodes, connecting edges, acceptance direction parameters, acceptance strength parameters, and propagation levels. Acceptance nodes correspond to production units within the target facility; initial acceptance nodes correspond to target production units determined by the precursor evolution chain data; connecting edges correspond to the directed acceptance relationships between adjacent production units; acceptance direction parameters indicate the direction of the connecting edges; acceptance strength parameters indicate the acceptance capacity of the connecting edges; and propagation levels indicate the hierarchical distance between candidate acceptance nodes and the initial acceptance node.

[0038] In some implementations, the deployment configuration sequence data structure includes a control area identifier, acceptance level, action type, action intensity, scope of effect, execution order, and update type. The control area identifier indicates the core isolation zone, extended blocking zone, or directional reinforcement isolation sub-zone corresponding to the action; the acceptance level indicates the blocking, prevention, or observation level of the receiving production unit; the action type indicates environmental adjustment, prevention and control measures, or operational restrictions; the action intensity indicates the strength of the action; the scope of effect indicates the production unit or control area covered by the action; the execution order indicates the sequential relationship between multiple actions; and the update type indicates upgrade update, maintenance update, or recycling update.

[0039] The fragment trigger threshold, fragment duration threshold, acceptance level threshold range, acceptance strength parameter, propagation level attenuation parameter, acceptance inhibition degree, potential energy upper limit, and deployment execution deviation are all determined by statistical analysis of historical operational data of the target facility, historical disease data of similar crops, facility layout data, production management configuration, and rolling correction results during continuous operation. These parameters have corresponding value ranges for different target facilities, different crop types, different growth stages, or different management models; the specific values ​​are determined based on the target facility's operational data and prevention and control management configuration, and do not rely on a single manual experience rule.

[0040] After completing the above descriptions of data objects, data structures, and parameter sources, refer to... Figure 2 , Figure 2 This diagram illustrates the data logic relationships between disease precursor evolution, propagation and succession, and hierarchical deployment in embodiments of this application. This diagram is not intended to represent a single linear processing step, but rather to illustrate the connection relationships between the intra-unit precursor evolution chain, the inter-unit propagation and succession chain, and the deployment feedback update chain. Figure 2 In this context, the unit-based time-series acquisition data corresponds to the continuous acquisition results within the production unit. This data, after being extracted by precursor migration characterization and fragment merging, enters the precursor migration fragment data formation process. The unit-based connection structure data corresponds to the spatial structure, environmental exchange, and operational communication relationships between production units. This data, after being analyzed by propagation and connection, enters the propagation and connection relationship data formation process. Therefore, Figure 2 The upper part forms two basic input links: the precursor state change within the unit and the structural change between units.

[0041] Figure 2In this process, the precursor migration fragment data further enters the formation process of the disease precursor evolution chain data, used to represent the process of disease precursors progressing from initial aberrations and continuous aberrations to intensified aberrations or outward expansion aberrations. After the target production unit is determined, the disease precursor evolution chain data, together with the propagation and inheritance relationship data, enters the construction process of the precursor propagation and inheritance diagram data. This precursor propagation and inheritance diagram data organizes the target production unit, adjacent production units, and their directed inheritance relationships into a graphical inheritance structure, transforming the disease precursor from an intra-unit evolution object to an inter-unit propagation and inheritance object.

[0042] Figure 2 In this model, the precursor extension potential energy data follows the precursor propagation and transfer diagram data, serving as an intermediate control object for subsequent control generation. The driving intensity, transfer direction, and transfer priority relationships within the precursor extension potential energy data are used to control the boundary extrapolation amplitude, boundary projection direction, and transfer processing sequence, respectively. Based on this precursor extension potential energy data, on the one hand, isolation control zoning data is formed to define the spatial control range of the core isolation zone, the extended blocking zone, and the directional reinforcement isolation sub-zone; on the other hand, a transfer blocking configuration sequence is formed to define the transfer level and transfer control method for different transfer production units. The isolation control zoning data and the transfer blocking configuration sequence are... Figure 2 The downward flow of the blocking constraint deployment sequence indicates that spatial partition constraints and acceptance level constraints work together in the prevention and control execution sequence.

[0043] Figure 2 The hierarchical control deployment configuration sequence shown at the bottom has an execution update relationship with the blocking constraint deployment sequence. After the blocking constraint deployment sequence is executed by the execution terminal, the acquisition terminal obtains the suppression response characterization data, the calculation terminal performs write-back correction on the precursor extended potential energy data based on the suppression response characterization data, and upgrades, maintains, or retracts the deployment sequence according to the corrected potential energy state. Figure 2 The backflow guideline in the diagram is used to summarize the closed-loop relationship between deployment execution, response acquisition, potential energy correction, and sequence update. It does not mean that the hierarchical prevention and control deployment configuration sequence directly generates precursor extended potential energy data. The data involved in writing back and correcting the precursor extended potential energy data is the suppression response characterization data after deployment execution, and the hierarchical prevention and control deployment configuration sequence is the next round of execution configuration formed based on the corrected extended potential energy data.

[0044] based on Figure 2 The data object connection relationships shown below will be further combined with... Figure 1 This application describes the overall process of the facility agriculture control and prevention method based on the isolation of disease expansion precursors in the embodiments of this application.

[0045] In some implementations, refer to Figure 1 , Figure 1This paper illustrates the overall process of a facility agriculture disease control and prevention method based on the isolation of disease precursors, as provided in an embodiment of this application. The method continuously processes the migration of disease precursors within production units of the target facility, the transmission and inheritance relationships between production units, the potential energy of precursor expansion, and the feedback from disease control and prevention deployment. This transforms the disease control process from post-symptom regional treatment to pre-symptom isolation, inheritance blocking, and tiered deployment. The method includes the following steps.

[0046] S101, acquire the disease precursor migration characterization data of each production unit in the target facility and the propagation and inheritance relationship data between the production units, and perform segment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration segment data.

[0047] In this step, the disease precursor migration characterization data is used to reflect the changes in disease precursor migration within a production unit during a continuous collection period, and its processing object is the change in precursor state within the production unit; the propagation and inheritance relationship data is used to reflect the pathway and directional relationships between adjacent production units, and its processing object is the precursor inheritance conditions between production units. These two data correspond to the state within the unit and the relationship between units, respectively, and together participate in the formation of the precursor evolution chain and the precursor propagation and inheritance map in subsequent processing.

[0048] In some implementations, the computing end performs time-series aggregation of disease precursor migration characterization data according to the collection period, and maps the aggregated data to the corresponding production unit according to the production unit location. When the precursor changes corresponding to multiple adjacent collection periods within the same production unit have a continuous succession relationship, and the corresponding locations belong to the same local anomaly range, the data corresponding to the above collection periods are processed by segment merging to form precursor migration fragment data. The precursor migration fragment data obtained in this way is not a single abnormal sampling point, but a local continuous anomaly range formed within a certain time and space range within the production unit.

[0049] After the precursor migration fragment data is formed, subsequent steps no longer directly use single acquisition values ​​as the judgment object, but use the continuous anomaly range after fragment merging as the basis for precursor evolution analysis. Therefore, instantaneous noise, local mis-acquisition, or short-term disturbances will not directly enter the process of determining the outward spread of disease precursors. Precursor evolution analysis uses fragment objects with temporal continuity and location attribution as input.

[0050] S102, perform evolutionary correlation processing on the precursor migration fragment data to determine the target production unit and generate the disease precursor evolution chain data corresponding to the target production unit; construct precursor propagation and inheritance diagram data based on the disease precursor evolution chain data and the propagation and inheritance relationship data, and perform extended potential energy mapping processing on the precursor propagation and inheritance diagram data to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving intensity, inheritance direction, and inheritance priority relationship of the disease precursor migrating to adjacent production units along the precursor propagation and inheritance diagram data.

[0051] In this step, the evolutionary correlation processing of precursor migration fragment data refers to connecting multiple precursor migration fragments according to temporal succession, intensity changes, and spatial migration relationships, so that the originally scattered precursor fragments form a chain of data with an evolutionary direction. The precursor evolution chain data is used to reflect the process of precursors progressing from initial anomalous activity and continuous anomalous activity to intensified or outward-expanding anomalous activity. The target production unit is determined by the outward-expanding end node in the precursor evolution chain data; this outward-expanding end node corresponds to the end node of the precursor that has the tendency to inherit and expand to adjacent production units.

[0052] After generating the disease precursor evolution chain data, the computing end constructs a precursor propagation and inheritance graph based on the target production unit and the propagation and inheritance relationships between production units. This graph data carries the path relationships of disease precursors transmitted from the target production unit to adjacent production units, where the target production unit corresponds to the initial inheritance node, adjacent production units correspond to candidate inheritance nodes, and the propagation and inheritance relationships between production units correspond to connecting edges. This graph structure serves as the path carrier for subsequent extended potential energy mapping.

[0053] When performing extended potential energy mapping on the precursor propagation and reception map data, the computing end maps the outward expansion node in the precursor evolution chain data to the starting reception node in the precursor propagation and reception map data, and transmits the precursor extended potential energy along the connecting edges to the candidate reception nodes. After extended potential energy mapping processing, precursor extended potential energy data is formed. The driving strength in the precursor extended potential energy data is used to represent the strength of the migration of the precursor to the candidate reception production unit, the reception direction is used to represent the direction of migration, and the reception priority relationship is used to represent the reception sequence among multiple candidate reception production units. This precursor extended potential energy data participates in the formation of the reception extrapolation profile, the classification of reception production units, and the hierarchical update of the control and prevention deployment sequence in subsequent steps.

[0054] S103, determine precursor aggregation contour data based on the disease precursor evolution chain data, perform boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation and transfer map data to generate transfer extrapolation contour data; determine the core isolation zone based on the precursor aggregation contour data, determine the extensional blocking zone based on the transferal extrapolation contour data, and generate isolation control partition data from the core isolation zone and the extensional blocking zone.

[0055] In this step, the precursor cluster contour data is determined by the range within the target production unit where continuous precursor clusters have already formed. The computational unit, based on the precursor evolution nodes located within the target production unit in the disease precursor evolution chain data, and combining the unit location and segment coverage range corresponding to those precursor evolution nodes, forms the precursor cluster contour data. This precursor cluster contour data is used to define the core boundary range where continuous precursor anomalies have occurred.

[0056] The receptivity extrapolation contour data is formed by the directional distribution of precursor propagation potential energy data in the precursor propagation receptivity diagram data. The computational unit determines the boundary projection direction based on the receptivity direction in the precursor propagation potential energy data, determines the boundary extrapolation amplitude based on the driving intensity, and determines the processing order among multiple extrapolation directions based on the receptivity priority relationship. This process is then used to perform boundary projection processing on the cell boundaries of adjacent production units, generating the receptivity extrapolation contour data. The receptivity extrapolation contour data is used to represent the peripheral blocking range formed by extrapolation along the propagation receptivity direction.

[0057] After generating precursor clustering contour data and extrapolated contour data, the computation unit determines the core isolation zone based on the precursor clustering contour data and the extended blocking zone based on the extrapolated contour data. The core isolation zone corresponds to the area within the target production unit where continuous precursor clusters have formed, while the extended blocking zone corresponds to the peripheral areas that need to be blocked in advance as the precursors migrate outward along the propagation direction. The core isolation zone and the extended blocking zone together form the isolation control zoning data. This isolation control zoning data is used in subsequent steps to determine the effective range and control priority of the primary suppression deployment sequence.

[0058] S104, based on the distribution results of the precursor propagation potential energy data in the precursor propagation and acceptance map data, determine the accepting production unit from the adjacent production units that have a propagation and acceptance relationship with the target production unit, and generate acceptance hierarchical sequence data; perform blocking configuration processing on the acceptance hierarchical sequence data to generate an acceptance blocking configuration sequence.

[0059] In this step, the receiving production unit is not all adjacent production units surrounding the target production unit, but rather determined by the distribution of precursor expansion potential energy data in the precursor propagation and receiving map data. The calculation unit determines the receiving production unit from among the adjacent production units that have a propagation and receiving relationship with the target production unit based on the potential energy transfer results at the candidate receiving nodes. The receiving production unit represents a production unit capable of receiving the outward expansion trend of the precursor disease.

[0060] After identifying the production units to be assigned, the computing unit classifies and ranks these units according to the driving strength and priority relationship in the precursor expansion potential energy data, generating a graded assignment sequence data. This graded assignment sequence data represents the order and grade of assignment of production units to the outward spread of disease precursors. Higher-graded production units correspond to greater assignment risk, while lower-graded production units correspond to less risk or require monitoring.

[0061] When configuring blocking for the hierarchical sequence data, the computing end configures corresponding control items for the receiving production units according to the receiving level, and the receiving control items form the receiving blocking configuration sequence. The receiving blocking configuration sequence is not directly equivalent to the final prevention and control deployment action, but serves as the configuration object for subsequent constraint primary suppression deployment sequences, used to limit the control requirements of production units of different receiving levels in terms of action intensity, scope of action, and execution order.

[0062] S105, a primary suppression deployment sequence is generated based on the isolation control partition data, and a hierarchical constraint processing is performed on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence; prevention and control deployment processing is performed according to the blocking constraint deployment sequence to obtain suppression response characterization data; the precursor extended potential energy data is written back and corrected based on the suppression response characterization data to generate corrected extended potential energy data; the blocking constraint deployment sequence is sequentially updated based on the corrected extended potential energy data to generate a sequential prevention and control deployment configuration sequence.

[0063] In this step, the computing unit determines the primary suppression actions corresponding to each control zone based on the isolation control zone data, and generates a primary suppression deployment sequence according to the control relationship between the core isolation zone and the extended blocking zone. The primary suppression deployment sequence is used to represent the combination of suppression actions configured for different control zones in the initial prevention and control phase, and its formation is based on the isolation control zone data, not the level of control itself.

[0064] Subsequently, the computational end performs hierarchical constraint processing on the primary suppression delivery sequence based on the acceptance blocking configuration sequence. This hierarchical constraint processing includes updating the action strength, scope of effect, and execution order within the primary suppression delivery sequence, ensuring that the same primary suppression delivery sequence forms different execution boundaries in production units at different acceptance levels. After hierarchical constraint processing, a blocking constraint delivery sequence is generated.

[0065] After the execution end performs the prevention and control deployment process according to the blocking constraint deployment sequence, the acquisition end re-acquires the precursor change data corresponding to the target production unit and the receiving production unit, and combines it with the deployment execution record to form suppression response characterization data. Suppression response characterization data is used to represent the precursor change results after the execution of the blocking constraint deployment sequence. This data is not simply a record of the execution result, but serves as the basis for writing back and correcting the precursor extended potential energy data.

[0066] The computational end performs a write-back correction on the precursor extended potential energy data based on the suppression response characterization data, generating corrected extended potential energy data. This write-back correction process updates the driving strength, receiving direction, and receiving priority relationships in the precursor extended potential energy data, ensuring that the next round of deployment adjustments no longer depends on the initial potential energy state, but rather on the changes in the precursors after deployment. Based on the corrected extended potential energy data, the computational end performs a hierarchical update process on the blocking constraint deployment sequence, generating a hierarchical prevention and control deployment configuration sequence. The hierarchical prevention and control deployment configuration sequence is used by the execution end to upgrade, maintain, or reclaim the updated prevention and control deployment configuration in subsequent prevention and control rounds.

[0067] In some implementations, disease precursor migration fragments, disease precursor evolution chains, precursor propagation connection diagrams, and precursor expansion potential energy data are formed according to a continuously sequential processing chain. This processing chain starts with the unit-time acquisition data of each production unit within the target facility. It extracts disease precursor migration characterization data through precursor migration characterization, then divides the data into candidate windows and merges fragments to form precursor migration fragment data. Subsequently, the fragments in the precursor migration fragment data are converted into precursor evolution nodes, and disease precursor evolution chain data is formed based on temporal connection relationships, precursor intensity change relationships, and spatial migration relationships. After determining the target production unit, the propagation connection relationship data between production units is analyzed based on the unit connection structure data of the target facility, and precursor propagation connection diagram data is constructed accordingly. Then, the outward expansion node in the disease precursor evolution chain data is mapped to the initial connection node in the precursor propagation connection diagram data, and precursor expansion potential energy data is formed through initial potential energy values, edge transfer values, hierarchical attenuation processing, and potential energy transfer values. Thus, the precursor evolution process within the production unit and the propagation and acceptance process between production units are connected in the same processing chain, and subsequent isolation extrapolation, acceptance grading, and deployment updates all use precursor expansion potential energy data as the control object.

[0068] In some implementations, the process of forming disease precursor migration fragment data includes: acquiring unit time-series acquisition data of each production unit within the target facility; extracting precursor migration characteristics from the unit time-series acquisition data to generate disease precursor migration characteristic data; dividing the disease precursor migration characteristic data into candidate windows to obtain candidate precursor window data; and performing fragment merging processing on the candidate precursor window data based on the continuity relationship and unit location affiliation relationship between adjacent acquisition periods to generate precursor migration fragment data. The disease precursor migration characteristic data is used to characterize the migration changes of disease precursors within a production unit during the acquisition period, and the precursor migration fragment data is used to characterize the local continuous anomaly range of disease precursors within a single production unit.

[0069] In some implementations, the process of forming disease precursor evolution chain data includes: identifying segments in the precursor migration fragment data as precursor evolution nodes; forming basic evolutionary connections based on the temporal continuity between adjacent precursor evolution nodes; generating corrected evolutionary connections based on the precursor intensity change relationship and spatial migration relationship corresponding to the basic evolutionary connections; connecting the precursor evolution nodes according to the corrected evolutionary connections and configuring precursor stage markers for the precursor evolution nodes to generate disease precursor evolution chain data; and determining the target production unit based on the precursor evolution nodes in the disease precursor evolution chain data that are configured with precursor stage markers corresponding to the outward expansion stage. The disease precursor evolution chain data is used to characterize the serialized association results of disease precursor evolution from initial anomalous movement and continuous anomalous movement to intensified anomalous movement or outward expansion anomalous movement.

[0070] In some implementations, the process of constructing the precursor propagation and reception map data includes: acquiring unit reception structure data of the target facility; performing propagation and reception parsing processing on the unit reception structure data to generate propagation and reception relationship data; mapping the production unit as a reception node in the precursor propagation and reception map data, and determining the reception node corresponding to the target production unit as the starting reception node; mapping the directed reception relationship between adjacent production units with propagation and reception relationships as connecting edges; configuring reception direction parameters and reception strength parameters for the connecting edges according to the propagation and reception relationship data; and constructing the precursor propagation and reception map data using the reception nodes, the starting reception node, the connecting edges, the reception direction parameters, and the reception strength parameters. The propagation and reception relationship data is used to characterize the pathway and directional relationships between adjacent production units for the reception of precursor migration, and the precursor propagation and reception map data is used to characterize the graphical reception structure of precursor transmission from the target production unit to adjacent production units.

[0071] In some implementations, the process of generating precursor expansion potential energy data includes: obtaining precursor evolution nodes located at the outward expansion end from the disease precursor evolution chain data, as outward expansion end nodes; mapping the outward expansion end nodes to the starting receiving nodes in the precursor propagation receiving diagram data, and generating initial potential energy values ​​based on the precursor intensity of the outward expansion end nodes; transmitting the initial potential energy values ​​along the connecting edges corresponding to the starting receiving nodes, and generating edge transmission values ​​based on the receiving strength parameters of the connecting edges; performing hierarchical attenuation processing on the edge transmission values ​​at different propagation levels to obtain potential energy transmission values ​​corresponding to candidate receiving nodes; determining the driving strength and receiving direction based on the potential energy transmission values ​​and the receiving direction parameters, and determining the receiving priority relationship according to the magnitude relationship of the potential energy transmission values; and generating precursor expansion potential energy data from the driving strength, the receiving direction, and the receiving priority relationship. The precursor expansion potential energy data is used to characterize the potential energy distribution results of disease precursors expanding to adjacent production units along the precursor propagation receiving diagram data.

[0072] In some implementations, the acquisition terminal obtains unit-time-series data from each production unit within the target facility according to a preset acquisition period. This unit-time-series data is aggregated according to production unit identifier, acquisition period, and acquisition source, and is used to reflect environmental changes, crop phenotypic changes, operational activity changes, and equipment operation changes in different production units within the target facility during continuous acquisition periods. Timestamp alignment, outlier removal, data normalization, and format conversion in the unit-time-series data are implemented using data preprocessing methods well-known to those skilled in the art in the field of facility agriculture data processing, and will not be elaborated upon further here.

[0073] The computing unit extracts precursor migration characteristics from the time-series data collected by the unit, generating precursor migration characteristic data for disease. This precursor migration characteristic extraction does not involve thresholding a single collected value; instead, it analyzes the changing trends, persistence, and local location attribution of the same production unit within continuous collection periods. This allows the precursor migration characteristic data to reflect the occurrence, maintenance, enhancement, or migration of disease precursors during the collection period. In this process, short-term disturbances, single abnormal samplings, or instantaneous equipment fluctuations within the production unit are not directly treated as precursor migration fragment data; instead, they are included in the candidate window segmentation process for time period continuation judgment.

[0074] In some implementations, the computing end divides the disease precursor migration characterization data into candidate windows to obtain candidate precursor window data. Candidate window division is based on the data collection period, and the window length is determined by the crop growth stage, collection frequency, and target facility management granularity. When adjacent candidate windows are set as overlapping or non-overlapping windows, the establishment of a candidate window is based on whether the precursor characterization intensity and duration within the window meet the corresponding thresholds. When the precursor characterization intensity meets the segment trigger threshold, and the duration of the corresponding window meets the segment duration threshold, the window is determined as candidate precursor window data. The segment trigger threshold and segment duration threshold are derived from historical operational data statistics of the target facility, historical disease data of similar crops, production management configuration, and rolling correction results during operation, and are updated according to crop growth stage, facility zoning, and seasonal conditions.

[0075] In some implementations, the computing unit performs segment merging on the candidate precursor window data based on the continuity relationship and unit location attribution relationship between adjacent acquisition periods, generating precursor migration segment data. The continuity relationship indicates that candidate precursor windows in adjacent acquisition periods have continuity in precursor intensity, duration, and direction of change; the unit location attribution relationship indicates that the local locations corresponding to adjacent candidate precursor windows belong to a continuous range of anomalies within the same production unit. When consecutive candidate precursor windows simultaneously satisfy both the continuity relationship and the unit location attribution relationship, the computing unit merges them into the same precursor migration segment; when candidate precursor windows are discontinuous in time or do not belong to the same continuous range of anomalies in unit location, the computing unit assigns them to different precursor migration segments.

[0076] The resulting precursor migration fragment data is used to characterize the local continuous variation range of disease precursors within a single production unit. This data object retains the start and end times of the fragment, the fragment coverage location, the fragment characterization intensity, and the production unit to which the fragment belongs, and serves as the basic source of precursor evolution nodes.

[0077] In some implementations, the computing end identifies each segment in the precursor migration fragment data as a precursor evolution node. Each precursor evolution node carries the acquisition time range, unit location range, fragment representation intensity, and production unit identifier of the corresponding precursor migration fragment. This precursor evolution node is used to carry the staged representation of the disease precursor within a local continuous anomaly range.

[0078] The computing unit establishes a basic evolutionary connection relationship based on the temporal continuity between adjacent precursor evolutionary nodes. This temporal continuity relationship indicates that two precursor evolutionary nodes are sequentially connected during the acquisition period, and that the start time of the later precursor evolutionary node and the end time of the earlier precursor evolutionary node satisfy a preset continuity interval. After the basic evolutionary connection relationship is established, the computing unit continues to generate a corrected evolutionary connection relationship based on the precursor intensity variation and spatial migration relationships corresponding to this basic evolutionary connection relationship.

[0079] The precursor intensity variation relationship is used to indicate whether the segment representation intensity between adjacent precursor evolution nodes is maintaining, increasing, or decreasing. The spatial migration relationship is used to indicate that the segment coverage position of adjacent precursor evolution nodes moves from a local area within the production unit to an adjacent location, a boundary direction, or a receiving direction. The computational end applies the precursor intensity variation relationship and the spatial migration relationship to the basic evolutionary connection relationship; for basic evolutionary connection relationships that only satisfy the temporal receiving relationship but not the precursor intensity variation constraint or the spatial migration constraint, their connection effectiveness is reduced or their transmission as an evolutionary connection relationship is terminated; for basic evolutionary connection relationships that simultaneously satisfy the temporal receiving relationship, the precursor intensity variation constraint, and the spatial migration constraint, they are identified as corrected evolutionary connection relationships.

[0080] In some implementations, the computing terminal connects precursor evolution nodes according to the corrected evolutionary connection relationship and configures precursor evolution nodes with precursor stage markers to generate disease precursor evolution chain data. Precursor stage markers include the initial stage, the continuous stage, the intensification stage, and the expansion stage. The initial stage corresponds to the precursor evolution node in which the disease precursor first forms a local continuous change within the production unit; the continuous stage corresponds to the precursor evolution node in which the precursor remains continuously present in adjacent collection periods; the intensification stage corresponds to the precursor evolution node in which the precursor characterization intensity increases or the coverage area expands; and the expansion stage corresponds to the precursor evolution node in which the precursor migration direction points to the boundary of the production unit or to the direction of acceptance of the adjacent production unit.

[0081] Disease precursor evolution chain data is used to characterize the sequential correlation results of disease precursors evolving from initial aberrations and continuous aberrations to intensified aberrations or outward expansion aberrations. If an end node in this disease precursor evolution chain data is configured with a precursor stage marker corresponding to the outward expansion stage, then that end node is identified as an outward expansion end node. The computation unit determines the target production unit based on the production unit to which the outward expansion end node belongs. Therefore, the target production unit is not an arbitrary production unit specified manually, but rather determined by nodes in the disease precursor evolution chain data that exhibit an outward expansion trend.

[0082] In some implementations, the computing terminal acquires the unit-based structural data of the target facility. This unit-based structural data originates from the production unit layout, environmental exchange channels, work paths, and management zoning relationships of the target facility. The production unit layout represents the spatial adjacency between production units; the environmental exchange channels represent the exchange paths of airflow, water vapor, temperature, or humidity between production units; the work paths represent the direction of movement of personnel, equipment, or materials between production units; and the management zoning relationships represent the zoning relationships within the target facility defined by the control system or production management rules.

[0083] The computing unit performs propagation and acceptance analysis on the unit receiving structure data to generate propagation and acceptance relationship data. This propagation and acceptance analysis is used to extract the pathway and directional relationships between adjacent production units for the migration and acceptance of disease precursors from the unit receiving structure data. The propagation and acceptance relationship data does not simply indicate whether production units are adjacent, but also indicates whether there is a precursor migration and acceptance pathway between adjacent production units, the direction of the pathway, and the pathway's capacity to accept the outward spread of disease precursors.

[0084] In some implementations, the computing terminal maps production units within the target facility to receiving nodes in the precursor propagation receiving diagram data, and determines the receiving node corresponding to the target production unit as the starting receiving node. Adjacent production units with propagation receiving relationships form directed receiving relationships, and the computing terminal maps these directed receiving relationships to connecting edges in the precursor propagation receiving diagram data. Each connecting edge is configured with receiving direction parameters and receiving strength parameters.

[0085] The direction parameter indicates the direction in which disease precursors propagate along the connecting edge. The strength parameter is obtained by analyzing the openness of the pathway, the continuous state of environmental exchange, and the operational access state in the unit's connecting structure data. When there is a management partition or equipment control barrier between preceding and following production units, this barrier relationship serves as the source of the degree of resistance to potential energy transfer in subsequent processing. Thus, the strength parameter describes the connecting edge's capacity, and the degree of resistance describes the barrier effect of the connecting edge on potential energy transfer; both are then processed in subsequent extended potential energy mapping.

[0086] The precursor propagation and transmission map data is constructed from the receiving node, the initial receiving node, the connecting edge, the receiving direction parameter, and the receiving strength parameter. This precursor propagation and transmission map data is used to characterize the graphical transmission structure of disease precursors from the target production unit to adjacent production units, providing a path carrier for subsequent extended potential energy mapping processing.

[0087] In some implementations, the computing terminal obtains the precursor evolution nodes located at the outer expansion end from the disease precursor evolution chain data, and uses them as outer expansion end nodes. The precursor intensity corresponding to the outer expansion end node is used to form the initial potential energy value. The computing terminal maps the outer expansion end node to the starting receiving node in the precursor propagation receiving diagram data, so that the inner and outer expansion states of the units in the disease precursor evolution chain data enter the graphical receiving structure between production units.

[0088] In some implementations, the initial potential energy value is determined by the following relationship: ,in represents the initial potential energy value after the outward expansion node is mapped to the initial receiving node; s represents the initial receiving node; This represents the precursor representation vector corresponding to the outer expansion node; This represents the baseline representation vector of the same production unit during the baseline stable period. This represents the precursor sensitivity matrix corresponding to production unit u; This represents the deviation distance obtained under the constraint of the precursor sensitivity matrix; This represents the increment in duration of the outermost node relative to the previous precursor evolution node; This indicates a compression mapping that limits the deviation distance; This represents the adjustment term after saturation mapping of the duration increment.

[0089] The above relationship is used to characterize the degree of deviation of the extended end node from the stable reference state, and this deviation is saturated and adjusted by the duration increment. The precursor characterization vector... The baseline representation vector is extracted from the disease precursor migration characterization data corresponding to the outer expansion node. The precursor sensitivity matrix is ​​obtained by statistically analyzing historical data collected from the same production unit during periods of stable or no precursor operation. It is determined by historical precursor samples of the production unit, crop growth stage, and facility zoning attributes. The resulting initial potential energy value is not the anomalous intensity corresponding to a single sample value, but rather the potential energy starting value formed after the outward-expanding end node continuously deviates from the steady state in the precursor evolution chain.

[0090] After generating the initial potential energy value, the computational terminal transmits it along the connecting edges corresponding to the initial receiving node and generates edge transmission values ​​based on the receiving strength parameters of the connecting edges. The edge transmission values ​​at different propagation levels are then attenuated to form the potential energy transmission values ​​corresponding to the candidate receiving nodes. For a candidate receiving node v, its potential energy transmission value at propagation level r is determined by the following relationship: in This represents the potential energy transfer value of the candidate receiving node v at propagation level r; This represents the set of acceptance paths from the initial accepting node s to the candidate accepting node v, with a propagation level not exceeding r. This represents a single path within the set of receiving paths. This indicates the number of connecting edges in the path p; This represents the valid path gate value for the receiving path p; m represents the propagation order of the connecting edge in the receiving path. Indicates connecting edges Consistency parameters of the acceptance direction; Indicates connecting edges The bearing strength parameters; Indicates connecting edges The degree of obstruction in the acceptance process; Indicates the hysteresis control parameter; Indicates the propagation level attenuation parameter; This represents the hierarchical attenuation term as potential energy is transferred step by step along the receiving path.

[0091] The inner product in the above relationship represents the continuous transmission of the initial potential energy value by multiple connecting edges on the same receiving path. The receiving direction consistency parameter of the connecting edges is used to weaken the transmission relationship with inconsistent directions, the receiving strength parameter is used to characterize the receiving capacity of the connecting edges, the receiving obstruction degree is used to suppress the contribution of connecting edges with large obstruction to the potential energy transmission, and the hierarchical attenuation term is used to characterize the attenuation of potential energy as the propagation order increases when it is transmitted step by step along the receiving path. The outer chain multiplication structure is used to handle the parallel receiving accumulation when multiple receiving paths point to the same candidate receiving node at the same time, so that the potential energy transmission of the candidate receiving node by multiple effective receiving paths forms a synthetic effect, rather than simply adding the path potential energies.

[0092] In some implementations, the valid path threshold is determined by the following relationship: in Indicates an indicator function; Indicates the lower limit of the bearing capacity; Indicates the upper limit of path obstruction; This represents the lower limit of directional consistency. The above effective path gate value is used to exclude connection paths with insufficient bearing strength, excessive overall obstruction, or overall direction deviating from the outward expansion direction. If a connection path contains connecting edges below the lower limit of bearing strength, or if the total obstruction of the connection path exceeds the upper limit of path obstruction, or if the average directional consistency of the connection path is lower than the lower limit of directional consistency, the connection path will not participate in potential energy transfer processing; if the connection path simultaneously satisfies the constraints of bearing strength, obstruction, and directional consistency, it will participate in potential energy transfer processing.

[0093] Consistency parameters of acceptance direction Determined by the degree of consistency between the direction of the connecting edge and the migration direction of the outward-expanding end node; bearing strength parameter The degree of connection obstruction is obtained by analyzing the open state of the pathway, the continuous state of environmental exchange, and the operational access status in the unit connection structure data. The minimum bearing capacity is determined by physical barriers, management partitions, equipment control partitions, or operational restrictions within the corresponding pathway of the connecting edge; Path blockage limit Lower limit of directional consistency and propagation level attenuation parameters It is derived from historical facility operation data, records of disease expansion in similar crops, facility layout data, or production management configuration.

[0094] When there is no valid gating path between the initial receiving node and a candidate receiving node, the candidate receiving node will not participate in the generation of precursor expansion potential energy data in the current round, or its potential energy transfer value will be set to zero. When subsequent data collection indicates that the candidate receiving node has formed a new precursor migration fragment data, the new precursor evolution chain data will then enter the next round of processing.

[0095] After the above processing, the computing end obtains the potential energy transfer value corresponding to the candidate receiving nodes. Then, the computing end determines the driving strength and receiving direction based on the potential energy transfer value and the receiving direction parameter, and determines the receiving priority relationship according to the magnitude of the potential energy transfer value. When multiple candidate receiving nodes obtain potential energy transfer values, the computing end generates the receiving priority relationship according to the potential energy transfer value from high to low; when the potential energy transfer values ​​of two candidate receiving nodes are in the same threshold range, the relative order is determined based on the propagation level, the consistency of the receiving direction, and the degree of receiving obstruction between the candidate receiving nodes and the starting receiving node.

[0096] Precursor propagation potential energy data is generated from the driving intensity, receiving direction, and receiving priority relationship. This precursor propagation potential energy data is used to characterize the potential energy distribution results of the disease precursor propagation receiving map data extending to adjacent production units. In subsequent boundary projection processing, the receiving direction is used to determine the extrapolation direction, the driving intensity is used to determine the extrapolation amplitude, and the receiving priority relationship is used to determine the extrapolation contour and the processing order of receiving production units; in subsequent hierarchical deployment updates, the precursor propagation potential energy data also serves as the control object for write-back correction and deployment sequence updates.

[0097] The relationship between the initial potential energy value, the potential energy transfer value, and the effective path gate value mentioned above is as follows: Figure 4 The diagram is illustrated using a function model. (Refer to...) Figure 4 The horizontal axis represents the propagation level or the sequence of the receiving path, the left vertical axis represents the potential energy value, and the right vertical axis represents the gating coefficient or the receiving strength. Figure 4The potential energy transfer curve in the diagram corresponds to the potential energy transfer value formed after the precursor spreading potential energy is transferred from the initial receiving node to the candidate receiving node along the connecting edges in the precursor propagation receiving diagram data. This curve generally decreases with increasing propagation level, corresponding to the weakening relationship of the edge transfer value in the corresponding level attenuation processing. Local plateaus or slight fluctuations in the curve correspond to situations where the connecting edge receiving strength is high, the receiving direction is highly consistent, or multiple effective receiving paths converge into the same candidate receiving node, resulting in a phased maintenance or local increase in the potential energy transfer value at the corresponding propagation level.

[0098] Figure 4 The hierarchical attenuation curve corresponds to the effect of the propagation hierarchical attenuation parameter on the potential energy transfer process. This curve gradually decreases with increasing propagation level, indicating that when the precursor disease spreads outward from the initial receiving node, its potential energy does not extend indefinitely, but is attenuated hierarchically as the propagation path sequence increases. This curve, together with the potential energy transfer curve, illustrates that the potential energy transfer value of a candidate receiving node is not solely determined by spatial adjacency, but is formed by the combined effects of the initial potential energy value, the strength of the connecting edge, the consistency of the receiving direction, the degree of receiving obstruction, and the propagation level.

[0099] Figure 4 The path gating curve corresponds to the effective gating value of the path and its filtering relationship with the receiving path. When the path gating curve is in a higher range, it indicates that the corresponding receiving path simultaneously meets the lower limit of receiving strength, the upper limit of path obstruction, and the lower limit of directional consistency. When the path gating curve reaches a trough, it indicates that the corresponding receiving path has insufficient receiving strength, excessive overall obstruction, or insufficient directional consistency, and the potential energy transfer contribution of this receiving path in the current round is weakened or excluded. Therefore... Figure 4 The path gating curve in the embodiment is used to illustrate that the existence of an adjacent relationship in the embodiments of this application is not directly equivalent to the formation of a valid receiving path.

[0100] Figure 4 The acceptance threshold is used to indicate the discrimination boundary for accepting paths to enter the effective potential energy transfer processing. When the acceptance strength, directional consistency, or comprehensive gating result of the accepting path does not reach the acceptance threshold, the path will not enter the precursor extended potential energy data generation process of the current round, or the potential energy transfer value of the corresponding candidate accepting node will be set to zero. Figure 4 The key level in the middle is used to represent the position of the propagation level in the propagation path that has an impact on the acceptance level, boundary extrapolation or delivery constraints; near this level, changes in potential energy transfer value, path gating results or acceptance strength will further affect the acceptance level and acceptance priority of candidate acceptance production units.

[0101] therefore Figure 4The three types of curves—potential energy transfer, hierarchical attenuation, and path gating—correspond to the potential energy transfer relationship, hierarchical attenuation relationship, and path selection relationship in the formation process of precursor extended potential energy data, respectively. Combining the aforementioned formulas, Figure 4 This is used to illustrate the process by which the precursor extended potential energy data is generated from the initial potential energy value of the extended end node, which is then transferred through the connection edge, processed by hierarchical attenuation, and processed by effective path gating. This process then forms the potential energy transfer value on the candidate receiving node, and further establishes the driving strength, receiving direction, and receiving priority relationship.

[0102] In some implementations, isolation control zones, interception and blocking configuration sequences, and blocking constraint deployment sequences are formed hierarchically according to the directional distribution of precursor expansion potential energy data. This processing chain uses precursor evolution chain data and precursor expansion potential energy data as input. It identifies the area within the target production unit where continuous precursor aggregation has formed as the core isolation object, and the outer perimeter formed by extrapolation along the propagation and acceptance direction as the interception and blocking object. Subsequently, based on the distribution of precursor expansion potential energy data in the precursor propagation and acceptance map data, the receiving production units are determined, and these units are configured hierarchically. Then, a primary suppression deployment sequence is generated based on the isolation control zone data, and the interception and blocking configuration sequence is used to update the primary suppression deployment sequence in terms of action intensity, scope of action, and execution order, forming a blocking constraint deployment sequence. Thus, the precursor expansion potential energy data is not only used to identify the outward expansion direction but also further participates in the delineation of isolation zones, the determination of acceptance levels, and the constraint of deployment sequences.

[0103] In some implementations, the process of forming isolation control zoning data includes: generating precursor aggregation contour data based on the cell location and segment coverage of precursor evolution nodes located within the target production unit in the precursor evolution chain data; determining the boundary projection direction based on the receiving direction in the precursor expansion potential energy data, and determining the boundary extrapolation amplitude based on the driving intensity in the precursor expansion potential energy data; performing boundary projection processing on the cell boundaries of adjacent production units according to the boundary projection direction and boundary extrapolation amplitude to generate receiving extrapolation contour candidate data; sorting the receiving extrapolation contour candidate data according to the receiving priority relationship in the precursor expansion potential energy data to generate receiving extrapolation contour data; delineating the core isolation zone based on the precursor aggregation contour data, delineating the extension blocking zone based on the receiving extrapolation contour data, and determining the directional reinforcement isolation sub-region within the extension blocking zone according to the receiving priority relationship; and generating isolation control zoning data from the core isolation zone, the extension blocking zone, and the directional reinforcement isolation sub-region. The precursor aggregation contour data is used to characterize the enclosure range of continuous precursor aggregation that has formed within the target production unit. The receiving extrapolation contour data is used to characterize the peripheral blocking range formed by extrapolation along the propagation receiving direction. The isolation control zoning data is used to characterize the zoning control range for disease precursor isolation and outward expansion blocking.

[0104] In some implementations, the process of forming the interception and blocking configuration sequence includes: determining candidate receiving production units from adjacent production units that have a propagation and receiving relationship with the target production unit based on the potential energy transfer value of the precursor expansion potential energy data at each receiving node; classifying the candidate receiving production units into receiving levels according to the receiving level threshold range of the potential energy transfer value; determining the candidate receiving production units that have completed the receiving level classification as receiving production units; arranging the receiving production units according to the receiving level to generate receiving level classification sequence data; configuring corresponding receiving control items for the receiving production units according to the receiving level; and generating the interception and blocking configuration sequence based on the receiving control items. The receiving level classification sequence data is used to characterize the receiving sequence relationship and receiving level relationship of the receiving production units to the outward spread of disease precursors, and the interception and blocking configuration sequence is used to characterize the receiving control methods corresponding to receiving production units of different receiving levels.

[0105] In some implementations, the process of forming the blocking constraint deployment sequence includes: determining the primary suppression actions corresponding to each control zone based on isolation control zoning data; arranging the primary suppression actions according to the control priority of the core isolation zone, the directional reinforcement isolation sub-zone, and the extended blocking zone to generate a primary suppression deployment sequence; applying level constraints to the action intensity in the primary suppression deployment sequence based on the receiving blocking configuration sequence to obtain an intensity constraint deployment sequence; and updating the scope of action and execution order of the intensity constraint deployment sequence according to the receiving control item to generate a blocking constraint deployment sequence. The primary suppression actions refer to the actions used to weaken the conditions for the spread and transmission of disease precursors within the control zone. The primary suppression deployment sequence characterizes the combination of suppression actions configured for different control zones in the initial control phase, and the blocking constraint deployment sequence characterizes the control execution sequence after being constrained by the receiving blocking configuration.

[0106] In some implementations, the computing unit generates precursor cluster contour data based on the unit location and segment coverage of precursor evolution nodes within the target production unit in the precursor evolution chain data. The formation of the precursor cluster contour data is confined to areas within the target production unit where continuous precursor clusters have already formed, not to single anomalous sampling points. When precursor evolution nodes within the same production unit have continuous sampling periods, adjacent location coverage, and a relationship of maintained or enhanced precursor intensity, the computing unit performs contour closure processing on the segment coverage corresponding to the aforementioned precursor evolution nodes to form precursor cluster contour data.

[0107] After the precursor aggregation contour data is formed, the computing end further determines the extrapolation contour data based on the directional distribution of the precursor extension potential energy data in the precursor propagation and reception map data. This process does not directly use the original boundary of the target production unit as the extrapolation blocking boundary; instead, it incorporates the reception direction, driving strength, and reception priority relationship from the precursor extension potential energy data into the boundary projection process. The reception direction is used to determine the boundary projection direction, the driving strength is used to determine the boundary extrapolation amplitude, and the reception priority relationship is used to determine the ranking among multiple extrapolation contour candidates.

[0108] In some implementations, the boundary projection process determines the receiving extrapolation profile through the following relationship: ,in This represents the acceptance extrapolation contour corresponding to the candidate acceptance node v; This represents the precursor aggregation profile corresponding to the target production unit u; This represents the precursory extended potential value corresponding to the candidate receiving node v; This indicates the sorting number of the candidate accepting node v in the accepting priority relationship; This represents the acceptance direction vector from the target production unit u to the candidate accepting node v; This represents the spatial constraint domain that allows the production unit containing the candidate receiving node v to form an extended blocking range; This indicates that the extrapolated profile is restricted to a spatially constrained domain. Projection operator within.

[0109] In the above relationship, This is used to convert the precursor extended potential energy value into the boundary extrapolation amplitude, so as to prevent the extrapolation amplitude from expanding unbounded as the potential energy increases; The ranking of candidate receiving nodes is used to reflect the impact of priority on the extrapolation profile. The higher the ranking of the candidate receiving nodes, the higher the extrapolation response under the same potential energy conditions. Used to keep the extrapolated contour unfolding along the propagation direction; This is used to constrain the extrapolated profile to the spatial constraints of the candidate receiving production unit, preventing the extrapolation blockade from exceeding the production unit boundary, management zone boundary, or equipment control boundary set within the facility.

[0110] In some implementations, spatial constraint domain The boundaries of the candidate production unit are jointly defined by the unit boundaries, management zone boundaries, equipment control range, and operational access boundaries. When the extrapolated range pointed to by the current mega-expansion potential energy data exceeds this spatial constraint domain, the projection operator projects the excess portion back into the spatial constraint domain. Thus, the extrapolated contour data, while reflecting the expansion trend, remains consistent with the actual production unit boundaries and management boundaries within the target facility.

[0111] After the precursor extended potential energy data enters the boundary projection processing, its zoning control relationship in the target facility plane is referenced. Figure 3 Please provide an explanation. Figure 3 The spatial correspondence between the precursor aggregation, receiving extrapolation, and isolation control zones in the target facility is shown. Figure 3 In the process, the target facility is divided into multiple production units, each of which corresponds to a spatial unit in the aforementioned unit-bearing structure data; the irregular enclosed area within the target production unit corresponds to precursor clustering contour data, which is formed by the unit position and segment coverage of the precursor evolution node located within the target production unit in the disease precursor evolution chain data.

[0112] Figure 3 In this context, the control zone surrounding the precursor cluster outline corresponds to the core isolation zone. The core isolation zone covers the area within the target production unit where continuous precursor clusters have already formed. Its formation is based on the precursor cluster outline data, not the risk of adjacent production units inheriting the clusters. Therefore, the core isolation zone primarily serves to initially isolate and suppress existing precursor clusters.

[0113] Figure 3 In the diagram, the arrows pointing from the target production unit to adjacent production units correspond to the receiving direction in the precursor expansion potential energy data. The direction of the arrow indicates the direction in which the precursor disease spreads along the precursor propagation receiving map data towards adjacent production units. The strength of the arrow corresponds to the differences in receiving priority relationships among different candidate receiving production units. Directions with higher receiving priority relationships... Figure 3 The middle corresponds to a more prominent direction of acceptance, and further enters the process of forming a direction-strengthened isolation sub-region.

[0114] Figure 3 In this context, the outer contour formed by extending outwards along the receiving direction to adjacent production units corresponds to the receiving outward contour data. This receiving outward contour data is formed by the combined effects of the receiving direction, driving strength, and receiving priority relationship in the precursor expansion potential energy data. The receiving direction controls the outward direction, the driving strength controls the outward amplitude, and the receiving priority relationship controls the sorting and selection among multiple outward contour candidate data. The receiving outward contour data encloses an extensional blocking zone, which is used to cover the outer perimeter that needs to be blocked in advance when the precursor of the disease migrates outwards along the propagation receiving direction.

[0115] Figure 3In this context, the locally reinforced region located on the high-priority receiving direction corresponds to the directional reinforced isolation sub-region. The directional reinforced isolation sub-region is not an independent region generated separately from the epitaxial blocking region, but rather a locally reinforced control region determined within the epitaxial blocking region based on the receiving direction with higher receiving priority. This directional reinforced isolation sub-region has a higher control priority than the general epitaxial blocking region in subsequent primary suppression delivery sequences, and further enters the generation process of the blocking constraint delivery sequence under the action of the receiving blocking configuration sequence.

[0116] Depend on Figure 3 As shown in the spatial relationship, the isolation control zoning data is not simply formed by expanding outward from the boundary of the target production unit, but is jointly defined by the precursor aggregation contour data and the receiving extrapolation contour data. Specifically, the precursor aggregation contour data determines the core isolation zone, the receiving extrapolation contour data determines the extended blocking zone, and the receiving priority relationship further determines the directional reinforcement isolation sub-regions within the extended blocking zone. This spatial zoning relationship corresponds to the aforementioned boundary projection processing and spatial constraint domain projection relationship, and serves as the basis for the subsequent arrangement of primary suppression actions and the constraint of their effective range.

[0117] In some implementations, the computing unit performs boundary projection processing on the cell boundaries of adjacent production cells according to the boundary projection direction and boundary extrapolation magnitude, generating candidate data for receiving extrapolation contours. Subsequently, the computing unit sorts the candidate data for receiving extrapolation contours based on the receiving priority relationship in the precursor extended potential energy data, generating receiving extrapolation contour data. When multiple candidate data for receiving extrapolation contours overlap within the same production cell, the computing unit determines the merging order based on the receiving priority relationship and potential energy transfer value; contours that still belong to the same extrapolation blocking range after merging are merged into the same extrapolation blocking region, and contours corresponding to the direction with high receiving priority relationship after merging are determined as directional reinforcement isolation sub-regions.

[0118] In some implementations, the core isolation zone is defined by precursor aggregation contour data, corresponding to the area within the target production unit where continuous precursor aggregation has formed. The extensional blocking zone is defined by receiving extrapolation contour data, corresponding to the outer area that needs to be blocked in advance when the precursor spreads to adjacent production units along the transmission direction. The directional reinforcement isolation sub-zone is located within the extensional blocking zone and corresponds to the outward expansion direction with a higher transmission priority. The core isolation zone, extensional blocking zone, and directional reinforcement isolation sub-zone form isolation control partition data. This isolation control partition data serves as the spatial constraint object and control priority source for subsequent primary suppression deployment sequences.

[0119] In some implementations, the computing unit determines candidate receiving production units from adjacent production units that have a propagation receiving relationship with the target production unit based on the potential energy transfer values ​​of the precursor propagation potential energy data at each receiving node. The determination of candidate receiving production units is not solely based on the adjacent relationship itself, but rather on whether the candidate receiving node obtains a valid potential energy transfer value, whether that potential energy transfer value falls within the receiving level threshold range, and whether the candidate receiving node exists on a valid receiving path in the precursor propagation receiving map data. Adjacent production units whose potential energy transfer values ​​do not reach the lower limit of the tracking level are not included in the receiving level sequence data of the current round; their data is retained in the regular monitoring records of the target facility.

[0120] In some implementations, the acceptance level threshold range is determined by historical operational data of the target facility, historical disease expansion records of similar crops, facility layout data, and production management configuration, and is updated in conjunction with suppression response records during the operation of the target facility. The acceptance level threshold range includes blocking level ranges, prevention level ranges, and tracking level ranges. When the potential energy transfer value corresponding to a candidate accepting production unit falls within the blocking level range, the candidate accepting production unit is designated as a blocking level; when the potential energy transfer value falls within the prevention level range, the candidate accepting production unit is designated as a prevention level; when the potential energy transfer value falls within the tracking level range, the candidate accepting production unit is designated as a tracking level.

[0121] After completing the classification of acceptance levels, the computing unit identifies candidate acceptance production units as acceptance production units and arranges them according to acceptance levels, generating acceptance level sequence data. Within the acceptance level sequence data, the relative order of acceptance production units within the same acceptance level is determined by potential energy transfer value, propagation level, consistency of acceptance direction, and degree of acceptance obstruction. Acceptance production units with higher potential energy transfer values, closer propagation levels, higher consistency of acceptance direction, and lower degree of acceptance obstruction are arranged at the beginning of the same acceptance level.

[0122] In some implementations, the computing end configures corresponding acceptance control items for the accepting production unit based on the acceptance level. These acceptance control items include a control type identifier, an associated production unit identifier, an action intensity boundary, an effective scope boundary, an execution order priority, a duration of operation, and feedback sampling requirements. The control type identifier distinguishes between blocking, prevention, and observation control items; the associated production unit identifier determines which accepting production unit the control item applies to; the action intensity boundary limits the strength of subsequent actions; the effective scope boundary limits the control area or production unit covered by subsequent actions; the execution order priority limits the ordering impact of the control item in the blocking constraint deployment sequence; the duration of operation limits the duration of the control item in the current prevention and control round; and the feedback sampling requirements limit the range of suppression response characterization data to be collected after execution.

[0123] When the acceptance level is the blocking level, the computing terminal configures blocking control items for the corresponding accepting production unit. Blocking control items limit the spread of disease precursors along the corresponding acceptance path, and their control content includes limiting higher action intensity boundaries, larger effective range boundaries, and earlier execution priority. When the acceptance level is the prevention level, the computing terminal configures prevention control items for the corresponding accepting production unit. Prevention control items are used to lightly suppress production units with acceptance trends but not yet reaching the blocking level, and their control content includes limiting intermediate action intensity boundaries, moderate effective range boundaries, and execution priority following the blocking control items. When the acceptance level is the tracking level, the computing terminal configures observation control items for the corresponding accepting production unit. Observation control items are used to maintain monitoring of production units with low acceptance risk but still requiring continuous tracking, and their control content includes limiting low action intensity boundaries, tracking sampling range, and delayed execution priority.

[0124] Based on the aforementioned acceptance control items, the computing end generates an acceptance blocking configuration sequence. This sequence characterizes the acceptance control methods corresponding to different acceptance levels of the production unit. It does not directly constitute a prevention and control deployment action, but rather serves as the basis for configuring subsequent hierarchical constraints on the primary suppression deployment sequence. Thus, the acceptance level, acceptance control items, and blocking configuration relationships of the production unit are retained in the same sequence, allowing subsequent deployment sequences to form different execution boundaries based on differences in acceptance risk.

[0125] In some implementations, the computing unit determines the primary suppression actions corresponding to each control zone based on the isolation control zone data. These primary suppression actions refer to actions taken to weaken the conditions for the spread and transmission of disease precursors within the control zone. Primary suppression actions include precursor aggregation suppression actions targeting the core isolation zone, transmission direction blocking actions targeting directional strengthening isolation sub-zones, and weakening actions targeting the peripheral conditions of the extensional blocking zones. When these actions involve environmental regulation, control treatment, and operational restrictions at the specific equipment level, the underlying equipment driving methods are implemented in a manner well-known to those skilled in the art in the field of facility agriculture control, and will not be elaborated upon further here.

[0126] In some implementations, the computing unit prioritizes primary suppression actions according to the control priorities of the core isolation zone, the directional reinforcement isolation sub-region, and the extended blocking zone, generating a primary suppression deployment sequence. The core isolation zone corresponds to the area where continuous precursor aggregation has formed, and its primary suppression actions have a fundamental control position in the sequence; the directional reinforcement isolation sub-region corresponds to the outward expansion direction with higher priority, and its primary suppression actions play an outward expansion blocking role in the sequence; the extended blocking zone corresponds to the outer blocking range, and its primary suppression actions play an expansion buffer role in the sequence. The generated primary suppression deployment sequence is used to characterize the combination of suppression actions configured for different control zones in the initial control phase.

[0127] After the primary suppression deployment sequence is formed, the computing end performs hierarchical constraint processing on the primary suppression deployment sequence based on the accepting blocking configuration sequence. The hierarchical constraint processing includes action strength constraints, scope constraints, and execution order constraints. Action strength constraints are used to adjust the execution strength of the corresponding control area according to the accepting level; scope constraints are used to limit the production unit or control area covered by the execution action according to the accepting control item; execution order constraints are used to determine the order of multiple execution actions according to the accepting priority and control area priority.

[0128] In some implementations, the computing end applies level constraints to the action intensity in the primary suppression delivery sequence based on the receiving and blocking configuration sequence, resulting in an intensity-constrained delivery sequence. For receiving production units at the blocking level, the corresponding action intensity enters the blocking execution range according to the action intensity boundary corresponding to the blocking control item; for receiving production units at the prevention level, the corresponding action intensity enters the prevention execution range according to the action intensity boundary corresponding to the prevention control item; for receiving production units at the tracking level, the corresponding action intensity enters the tracking acquisition or light intervention range according to the action intensity boundary corresponding to the observation control item.

[0129] After forming the strength constraint deployment sequence, the computing end updates the scope and execution order of the strength constraint deployment sequence based on the accepting control terms, generating the blocking constraint deployment sequence. Scope constraints ensure that the same primary suppression action has different coverage boundaries within production units of different accepting levels; execution order constraints ensure that production units with higher accepting priority, such as those in directional reinforcement isolation sub-regions or blocking levels, obtain a higher execution position in the execution sequence. If the same production unit falls into both the extended blocking region and the directional reinforcement isolation sub-region, the computing end determines its deployment constraints according to the control priority corresponding to the directional reinforcement isolation sub-region; if the same execution action is constrained by multiple accepting control terms, the computing end determines the action strength boundary and execution order priority according to the accepting control term corresponding to the higher accepting level.

[0130] The blocking constraint deployment sequence retains the control area identifier, the receiving production unit identifier, the action type, the action intensity boundary, the scope boundary, the execution order priority, the retention period, and the feedback sampling requirements. The execution end performs prevention and control deployment processing based on this blocking constraint deployment sequence, and the subsequent acquisition end obtains the suppression response characterization data based on the feedback sampling requirements. The resulting blocking constraint deployment sequence characterizes the prevention and control execution sequence after accepting the blocking configuration constraints and serves as the basis for subsequent feedback write-back and hierarchical updates.

[0131] In some implementations, the suppression response write-back, correction of extended potential energy data, and hierarchical prevention and control deployment configuration sequence are formed step-by-step according to the results of precursor changes after deployment execution. This processing chain starts with the execution result of the blocking constraint deployment sequence. After executing the prevention and control deployment process, it acquires the suppression response characterization data corresponding to the target production unit and the receiving production unit; based on the suppression response characterization data, it determines the precursor decline result, precursor maintenance result, or precursor strengthening result; then, based on the above results, it writes back and corrects the driving intensity, receiving direction, and receiving priority relationship in the precursor extended potential energy data to generate corrected extended potential energy data; subsequently, based on the corrected extended potential energy data, it performs hierarchical update processing on the blocking constraint deployment sequence to form an upgraded suppression deployment sequence, a maintained suppression deployment sequence, or a deployment recovery sequence, respectively; finally, it generates a hierarchical prevention and control deployment configuration sequence based on the updated deployment sequence. Therefore, the prevention and control deployment process does not stop at a single execution record, but reintroduces the precursor changes after deployment into the extended potential energy and deployment sequence update process, allowing subsequent prevention and control rounds to be adjusted according to changes in the risk of precursor expansion.

[0132] In some implementations, the process of forming a hierarchical prevention and control deployment configuration sequence includes: after executing prevention and control deployment processing according to the blocking constraint deployment sequence, obtaining suppression response characterization data corresponding to the target production unit and the receiving production unit, wherein the suppression response characterization data is used to characterize the precursor change results after the execution of the blocking constraint deployment sequence; determining the precursor fall-off result, precursor maintenance result, or precursor strengthening result based on the suppression response characterization data; performing write-back correction on the driving intensity, receiving direction, and receiving priority relationship in the precursor extended potential energy data based on the precursor fall-off result, the precursor maintenance result, or the precursor strengthening result, to generate corrected extended potential energy data; when the corrected extended potential energy data indicates an increased receiving risk, upgrading and updating the blocking constraint deployment sequence to generate an upgraded suppression deployment sequence; when the corrected extended potential energy data indicates that the receiving risk is maintained, maintaining and updating the blocking constraint deployment sequence to generate a maintained suppression deployment sequence; when the corrected extended potential energy data indicates a fall in receiving risk, retrieving and updating the blocking constraint deployment sequence to generate a deployment retrieval sequence; and generating a hierarchical prevention and control deployment configuration sequence based on the upgraded suppression deployment sequence, the maintained suppression deployment sequence, or the deployment retrieval sequence. The hierarchical prevention and control deployment configuration sequence is used to characterize the updated prevention and control deployment execution configuration as the risk of disease precursor expansion changes.

[0133] In some implementations, after the execution end performs the prevention and control deployment process according to the blocking constraint deployment sequence, the acquisition end re-acquires the precursor change data corresponding to the target production unit and the receiving production unit based on the feedback sampling requirements in the blocking constraint deployment sequence, and associates the precursor change data with the deployment execution record to form suppression response characterization data. The feedback sampling requirements include sampling object, sampling period, sampling area, and sampling frequency. The sampling object corresponds to the control area identifier, receiving production unit identifier, execution action type, action intensity boundary, scope boundary, and execution order priority in the blocking constraint deployment sequence.

[0134] In some implementations, the precursor change data includes changes in the range of precursor migration segments within the target production unit, changes in segment characterization intensity, changes in precursor stage markers, and changes in the potential energy transfer value, receiving direction, and receiving priority relationship corresponding to the receiving production unit. The deployment execution record includes the type of execution action, action intensity, scope of action, execution time period, execution sequence, execution equipment status, and deployment execution deviation. The calculation unit maps the precursor change data to the deployment execution record according to the production unit identifier, control area identifier, and execution time period, forming suppression response characterization data that matches the blocking constraint deployment sequence item.

[0135] In some implementations, the suppression response characterization data is not based on a single execution record as an independent criterion. Instead, it maps the changes in precursory data after execution to the action intensity boundaries, scope boundaries, execution order priorities, and feedback sampling requirements in the blocking constraint deployment sequence. When the range of precursory migration segments within the target production unit shrinks, the segment characterization intensity decreases, the number of outward expansion nodes decreases, or the potential energy transfer value decreases, a precursory decline tendency is formed in the suppression response characterization data. When the range of precursory migration segments, potential energy transfer values, and acceptance priority relationships corresponding to the target production unit and the receiving production unit change within a preset maintenance range, a precursory maintenance tendency is formed in the suppression response characterization data. When a new precursory migration segment appears in the receiving production unit, the potential energy transfer value increases, the acceptance priority relationship moves forward, or a new outward expansion node is formed, a precursor strengthening tendency is formed in the suppression response characterization data.

[0136] In some implementations, the computing unit determines the precursor decline result, precursor maintenance result, or precursor strengthening result based on the suppression response characterization data. The precursor decline result indicates that the precursor expansion risk in the target production unit or the receiving production unit decreases after the execution of the blocking constraint deployment sequence; the precursor maintenance result indicates that the precursor expansion risk does not substantially increase or decrease after execution; the precursor strengthening result indicates that the precursor expansion risk increases or a new receiving expansion trend emerges after execution. These results are obtained by comparing the precursor change data after execution with the precursor expansion potential energy data before execution, and are corrected based on the deployment execution deviation.

[0137] The deployment execution deviation is used to characterize the discrepancy between the set action and the actual action in the blocking constraint deployment sequence. The deployment execution deviation increases when the actual action intensity is lower than the set action intensity, the actual range of effect is smaller than the set range of effect, or the actual execution order deviates from the set execution order. The deployment execution deviation is incorporated into the subsequent correction and expansion potential energy data formation process to prevent misjudging a precursory decline as a genuine risk reduction when deployment execution is incomplete. When the deployment execution deviation exceeds the preset execution deviation upper limit, the precursory decline result of the current round is not directly used as the basis for risk reduction; the calculation end will place the corresponding production unit into the maintenance update path or the resampling processing path.

[0138] In some implementations, suppression response characterization data is used to perform write-back correction on precursor extended potential energy data. This write-back correction does not regenerate a set of independent risk data, but rather modifies the driving strength, receiving direction, and receiving priority relationships within the original precursor extended potential energy data, ensuring that the precursor changes following the previous round of deployment are incorporated into the next round of extended potential energy calculation and deployment sequence update process.

[0139] In some implementations, when the suppression response characterization data corresponds to a precursor decline result, the computing end reduces the driving intensity of the corresponding receiving production unit and adjusts its receiving priority relationship according to the decrease in potential energy transfer value; when the suppression response characterization data corresponds to a precursor maintenance result, the computing end keeps the driving intensity and receiving priority relationship of the corresponding receiving production unit in the current level range and continues the corresponding maintenance update process; when the suppression response characterization data corresponds to a precursor strengthening result, the computing end increases the driving intensity of the corresponding receiving production unit and improves its receiving priority relationship if the receiving direction remains unchanged, and synchronously corrects the receiving direction if the receiving direction changes.

[0140] In some implementations, the corrected extended potential energy value corresponding to the candidate receiving node is determined by the following relationship: ,in This represents the corrected extended potential energy value corresponding to the candidate receiving node v; This represents the precursory extended potential energy value before correction; This represents the precursor fallback response of candidate node v after the execution of the blocking constraint delivery sequence; This represents the precursor reinforcement response of candidate receiving node v after the execution of the blocking constraint delivery sequence; This represents the execution deviation corresponding to the candidate receiving node v; This represents the upper limit of the potential energy of the candidate receiving node v.

[0141] In the above relationship, Used to represent the weakening effect of the precursor fallback response on the original precursor extended potential energy value. Deployment execution deviation. The larger the value, the greater the precursor pullback response. The weaker the weakening effect on the original precursor potential value, the better to avoid incorrectly reducing the risk of acceptance when the deployment is not executed properly. It is used to represent the enhancement effect of the precursor enhancement response on the corrected extended potential energy value, and the range of enhanced potential energy is limited by the upper limit of the potential energy value.

[0142] In some implementations, the precursor fallback response quantity The magnitude of the decrease in potential energy transfer value after execution, the magnitude of the reduction in the range of the precursor migration fragment, the magnitude of the decrease in fragment characterization intensity, and the reduction in the number of outward-expanding nodes are all determined by this factor. Precursor enhancement response quantity. The deviation is determined by the increase in potential energy transfer value after execution, the addition of new precursor migration segments, the shift in priority relationships, the appearance of new outward expansion nodes, and changes in the direction of reception. It is formed by the deviation between the set action intensity and the actual action intensity, the deviation between the set range of action and the actual range of action, and the deviation between the set execution order and the actual execution order.

[0143] Based on the corrected extended potential energy value, the computational end further updates the driving strength, acceptance direction, and acceptance priority in the precursor extended potential energy data. For candidate acceptance nodes whose corrected extended potential energy value decreases and falls into a lower acceptance level threshold range, their driving strength is reduced or their acceptance priority is shifted backward; for candidate acceptance nodes whose corrected extended potential energy value remains within the original acceptance level threshold range, their driving strength and acceptance priority are maintained; for candidate acceptance nodes whose corrected extended potential energy value increases and falls into a higher acceptance level threshold range, their driving strength is increased or their acceptance priority is shifted forward. If a newly appearing precursor migration fragment changes the original acceptance direction after execution, the computational end synchronously updates the corresponding acceptance direction.

[0144] The corrected extended potential energy data generated by the above-mentioned write-back correction process not only retains the graphical propagation relationship in the precursor extended potential energy data, but also introduces the response results after the execution of the blocking constraint deployment sequence, which serves as the basis for the formation of the hierarchical prevention and control deployment configuration sequence.

[0145] In some implementations, the computing unit determines changes in the risk of acceptance based on the corrected extended potential energy data and performs hierarchical update processing on the blocking constraint deployment sequence accordingly. Hierarchical update processing includes upgrade updates, maintenance updates, and recovery updates. Instead of performing uniform adjustments on all production units, hierarchical update processing focuses on the sequence items in the blocking constraint deployment sequence, determining whether the sequence item should enter the upgrade, maintenance, or recovery path based on the corrected extended potential energy data of the corresponding production unit.

[0146] When the corrected extended potential energy data indicates an increased risk of acceptance, the computational end upgrades and updates the blocking constraint deployment sequence to generate an upgraded suppression deployment sequence. Increased risk of acceptance includes the corrected extended potential energy value rising to a higher acceptance level threshold range, a shift in acceptance priority, an acceptance direction pointing to a new adjacent production unit, or the appearance of a new outward expansion node within the accepting production unit. The upgraded suppression deployment sequence increases the action intensity boundary, expands the scope of action boundary, or shifts the execution order priority based on the original blocking constraint deployment sequence to enhance the suppression strength for high-risk production units.

[0147] When the corrected extended potential energy data characterizes the sustained risk of acceptance, the computational end updates the blocking constraint deployment sequence to maintain and generate a sustained suppression deployment sequence. Sustained risk of acceptance includes the corrected extended potential energy value remaining within the original acceptance level threshold range, and no substantial change in the acceptance direction and priority relationship. The sustained suppression deployment sequence maintains the original action intensity boundaries, scope boundaries, and execution order priorities, and continues the next round of suppression response characterization data collection according to feedback sampling requirements.

[0148] When the corrected extended potential energy data indicates a decline in the risk of acceptance, the computational end updates the blocking constraint deployment sequence to generate a deployment-recovery sequence. A decline in risk of acceptance includes a decrease in the corrected extended potential energy value to a lower acceptance level threshold range, a shift in acceptance priority, the disappearance of the outer expansion node, or a continuous shrinking of the precursor migration fragment range. The deployment-recovery sequence reduces the action intensity boundary, shrinks the scope of action boundary, or delays the execution priority based on the original blocking constraint deployment sequence, in order to reduce unnecessary control disturbances and resource consumption.

[0149] In some implementations, the computing end generates a hierarchical prevention and control deployment configuration sequence based on the upgrade suppression deployment sequence, the maintenance suppression deployment sequence, or the deployment and recovery sequence. The hierarchical prevention and control deployment configuration sequence retains the update type, target control area, receiving production unit, execution action type, action intensity boundary, scope boundary, execution order priority, maintenance period, and feedback sampling requirements. The execution end executes the next prevention and control round according to the hierarchical prevention and control deployment configuration sequence, and the acquisition end acquires new suppression response characterization data according to the feedback sampling requirements, thus creating continuous feedback between the precursor expansion potential energy data, the blocking constraint deployment sequence, and the hierarchical prevention and control deployment configuration sequence.

[0150] After the blocking constraint deployment sequence is executed at the execution end and suppression response characterization data is generated, the update relationship between the corrected extended potential energy data and the hierarchical control deployment configuration sequence is referenced. Figure 5 Please provide an explanation. Figure 5 The functional model relationship between suppression response write-back and hierarchical prevention and control deployment update is shown. Figure 5 The horizontal axis represents the prevention and control round or execution period, the left vertical axis represents the corrected extended potential energy, and the right vertical axis represents the deployment level. The corrected extended potential energy curve corresponds to the potential energy change process obtained after the calculation end corrects the precursor extended potential energy data by writing back based on the suppression response characterization data; the deployment level curve corresponds to the step-by-step update process of the execution level in the hierarchical prevention and control deployment configuration sequence as the corrected extended potential energy changes.

[0151] Figure 5 The corrected extended potential energy curve shows a decrease, maintenance, or increase in different rounds of prevention and control, with the corresponding relationships derived from the precursor decline results, precursor maintenance results, and precursor strengthening results, respectively. When the range of the precursor migration segment shrinks, the potential energy transfer value decreases, or the number of outward expansion nodes decreases after execution, the corrected extended potential energy curve moves towards the decline zone; when the potential energy transfer value after execution is still within the original acceptance level threshold range, and the acceptance direction and acceptance priority relationship have not changed substantially, the corrected extended potential energy curve remains in the maintenance zone; when a new precursor migration segment appears after execution, the potential energy transfer value increases, or the acceptance priority relationship moves forward, the corrected extended potential energy curve moves towards the strengthening zone.

[0152] Figure 5The strengthening zone, maintenance zone, and decline zone in the calculation represent the risk status intervals corresponding to the corrected extended potential energy data. When the corrected extended potential energy curve migrates from the maintenance zone or decline zone to the strengthening zone, it indicates that the risk of the corresponding production unit increases, and the calculation terminal upgrades and updates the corresponding sequence item in the blocking constraint deployment sequence. When the corrected extended potential energy curve remains within the maintenance zone or fluctuates slightly, it indicates that the risk of the corresponding production unit remains, and the calculation terminal maintains the action intensity boundary, scope boundary, and execution order priority of the corresponding sequence item. When the corrected extended potential energy curve migrates from the strengthening zone or maintenance zone to the decline zone, it indicates that the risk of the corresponding production unit decreases, and the calculation terminal reclaims and updates the corresponding sequence item. Therefore, Figure 5 The risk status zone in the data does not directly represent the action itself, but rather the update path that the corresponding sequence item enters when the corrected extended potential energy data is in or migrates to the corresponding interval in different rounds of prevention and control.

[0153] Figure 5 The deployment level curve in the diagram represents the update relationship of the execution level in the hierarchical prevention and control deployment configuration sequence in a step-like manner. When the corrected expansion potential energy curve migrates to the enhanced zone, the deployment level curve jumps upward in the corresponding prevention and control round; when the corrected expansion potential energy curve remains in the maintenance zone, the deployment level curve maintains its current level; when the corrected expansion potential energy curve migrates to the decline zone, the deployment level curve decreases in the corresponding prevention and control round. Therefore, Figure 5 The changes in the deployment level shown are not a direct mapping of the potential energy value at a single moment, but rather a hierarchical response to the correction of the potential energy change trend after the suppression response is written back.

[0154] Figure 5 This also illustrates that the mapping relationship between the corrected extended potential energy data and the hierarchical control deployment configuration sequence is not a one-time mapping. In each round of control, the execution of the blocking constraint deployment sequence generates corresponding suppression response characterization data; after the suppression response characterization data enters the write-back correction process, new corrected extended potential energy data is generated; the new corrected extended potential energy data then determines whether the corresponding sequence item enters the upgrade update, maintenance update, or recycling update path. Thus, the deployment level curve changes stepwise with each round of control, while the corrected extended potential energy curve changes continuously with the suppression response result. Together, they represent the closed-loop correspondence between the risk of disease precursor expansion and the control deployment execution configuration.

[0155] based on Figure 5 As illustrated, in subsequent implementation scenarios, different production units within the same target facility will enter the upgrade, maintenance, or recovery path respectively after the same round of prevention and control, depending on the range and trend of their respective corrected extended potential energy data. This diagram provides a graphical basis for understanding why A5 enters the recovery and renewal path and A8 enters the upgrade and renewal path in the following multi-span greenhouse scenario.

[0156] In a specific implementation scenario, refer to Figure 6 , Figure 6 This illustration shows the division of production units, the direction of transmission, and the relationship between isolation and control areas within a multi-span tomato greenhouse. The target facility is a multi-span tomato greenhouse, which is divided into twelve production units, A1 to A12, according to planting rows, ventilation zones, and work passages. A4 is located in the central ventilation recirculation zone, A5 is located in the adjacent area downwind of A4, and A8 is located in the adjacent management area sharing a work passage with A4. Figure 6 The direction from A4 to A5 is used to indicate the propagation and transmission relationship in the ventilation direction, the direction from A4 to A8 is used to indicate the propagation and transmission relationship in the operation and passage direction, the local enclosure area formed around A4 is used to indicate the precursor accumulation area and its corresponding core isolation area within the target production unit, and the reinforcement area formed by pushing outward along the A5 direction is used to indicate the directional reinforcement isolation sub-area in the high priority transmission direction.

[0157] Within three consecutive acquisition periods, the time-series acquisition data corresponding to unit A4 is extracted using precursor migration characterization to form disease precursor migration characterization data. The computing unit performs candidate window partitioning and segment merging on this disease precursor migration characterization data to generate precursor migration segment data corresponding to A4. This precursor migration segment data remains continuous within adjacent acquisition periods, and its segment coverage position moves from the interior of A4 towards the boundary between A4 and A5, thus forming an expansion end node configured with a precursor stage marker corresponding to the expansion stage. The computing unit determines A4 as the target production unit based on this expansion end node.

[0158] The computing unit constructs a precursor propagation and connection map based on the unit connection structure data of the target facility. In this precursor propagation and connection map, A4 corresponds to the initial connection node, and A5 and A8 correspond to candidate connection nodes, respectively; the connecting edge from A4 to A5 corresponds to the ventilation connection direction, and the connecting edge from A4 to A8 corresponds to the work passage connection direction. After extended potential energy mapping processing, the potential energy transfer value corresponding to A5 falls into the blocking level range, and the potential energy transfer value corresponding to A8 falls into the prevention level range. Based on this, the computing unit generates connection classification sequence data, in which A5 is arranged before A8. Figure 6 In the diagram, A5 has a higher priority than A8, and its corresponding direction is indicated as the high priority direction.

[0159] Then, the computational unit generates precursor aggregation contour data based on the cell positions and fragment coverage of precursor evolution nodes within A4, and delineates the core isolation zone based on this precursor aggregation contour data; it generates reception extrapolation contour data based on the reception direction, driving strength, and reception priority relationship corresponding to A5 and A8, and delineates the extensional blocking zone based on this reception extrapolation contour data. Since the reception priority relationship of A5 is higher than that of A8, the extrapolation direction corresponding to A5 is determined as a directional reinforcement isolation sub-region within the extensional blocking zone. Figure 6 In the middle, the spatial hierarchy between the core isolation zone, the extended blocking zone, and the directional reinforcement isolation sub-zone is used to correspond to the partition control relationship formed by extrapolating from the target production unit to the adjacent receiving production unit in the isolation control partition data.

[0160] The computational unit generates a primary suppression deployment sequence based on the isolation control partition data and constrains this primary suppression deployment sequence according to the receiving blocking configuration sequence. For A5, the receiving control item is a blocking control item, corresponding to a higher action intensity boundary, a larger scope boundary, and a higher execution order priority; for A8, the receiving control item is a prevention control item, corresponding to an intermediate action intensity boundary, a moderate scope boundary, and an execution order priority following the blocking control item. After the above constraints, blocking constraint deployment sequences for A4, A5, and A8 are formed.

[0161] After the execution end performs the prevention and control deployment process according to the blocking constraint deployment sequence, the acquisition end re-acquires the precursor change data corresponding to A4, A5, and A8 in subsequent sampling periods, and combines it with the deployment execution record to form suppression response characterization data. If the potential energy transfer value corresponding to A5 drops to the prevention level range, and the outward expansion node in the direction corresponding to A5 disappears, the calculation end determines the precursor decline result corresponding to A5, and performs write-back correction on the precursor expansion potential energy data corresponding to A5, so that the sequence item corresponding to A5 enters the deployment and recovery path. If the potential energy transfer value corresponding to A8 rises to the blocking level range, and new precursor migration fragment data appears within A8, the calculation end determines the precursor enhancement result corresponding to A8, and performs write-back correction on the precursor expansion potential energy data corresponding to A8, so that the sequence item corresponding to A8 enters the upgrade and update path.

[0162] In the above scenario, after the same round of prevention and control deployment, the sequence item corresponding to A5 enters the recycling and update path, and the sequence item corresponding to A8 enters the upgrade and update path. The hierarchical prevention and control deployment configuration sequence does not perform uniform adjustments on all production units, but updates the action intensity boundary, scope boundary, and execution order priority separately based on the corrected extended potential energy data of different receiving production units. In this scenario, the disease precursor migration fragment data, disease precursor evolution chain data, precursor propagation and reception diagram data, precursor extended potential energy data, blocking constraint deployment sequence, and hierarchical prevention and control deployment configuration sequence are continuously passed on in the same control flow, forming a closed-loop processing process of pre-symptom isolation, reception blocking, and feedback hierarchical deployment.

[0163] Based on the description of the above embodiments of the method for controlling and distributing pests and diseases in facility agriculture based on the isolation of early signs of disease expansion, this application also discloses a system for controlling and distributing pests and diseases in facility agriculture based on the isolation of early signs of disease expansion. This system can be a computer program (including program code) that runs the aforementioned method for controlling and distributing pests and diseases in facility agriculture based on the isolation of early signs of disease expansion. Please see the appendix. Figure 7 As shown, the facility agriculture control and prevention system based on disease pre-expansion isolation can operate the following units: The precursor fragment generation unit 110 is used to acquire the disease precursor migration characterization data of each production unit in the target facility and the propagation and inheritance relationship data between the production units, and to perform fragment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data. The extended potential energy mapping unit 120 is used to perform evolutionary correlation processing on the precursor migration fragment data, determine the target production unit, and generate the disease precursor evolution chain data corresponding to the target production unit; construct precursor propagation and acceptance diagram data based on the disease precursor evolution chain data and the propagation and acceptance relationship data, and perform extended potential energy mapping processing on the precursor propagation and acceptance diagram data to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving strength, acceptance direction, and acceptance priority relationship of the disease precursor migrating to adjacent production units along the precursor propagation and acceptance diagram data. The isolation partition generation unit 130 is used to determine precursor aggregation contour data based on the disease precursor evolution chain data, perform boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation transition map data, and generate transition extrapolation contour data; determine the core isolation zone based on the precursor aggregation contour data, determine the extensional blocking zone based on the transitional extrapolation contour data, and generate isolation control partition data from the core isolation zone and the extensional blocking zone; The receiving and blocking configuration unit 140 is used to determine the receiving production unit from the adjacent production units that have a propagation receiving relationship with the target production unit based on the distribution result of the precursor propagation potential energy data in the precursor propagation receiving map data, and generate receiving hierarchical sequence data; and to perform blocking configuration processing on the receiving hierarchical sequence data to generate a receiving and blocking configuration sequence. The hierarchical deployment update unit 150 is used to generate a primary suppression deployment sequence based on the isolation control partition data, and to perform hierarchical constraint processing on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence; to perform prevention and control deployment processing according to the blocking constraint deployment sequence to obtain suppression response characterization data; to perform write-back correction on the precursor extended potential energy data based on the suppression response characterization data to generate corrected extended potential energy data; and to perform hierarchical update processing on the blocking constraint deployment sequence based on the corrected extended potential energy data to generate a hierarchical prevention and control deployment configuration sequence.

[0164] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A method for disease control and prevention in facility agriculture based on isolating early signs of disease spread, characterized in that, include: Acquire disease precursor migration characterization data of each production unit within the target facility and data on the propagation and inheritance relationship between the production units. Perform fragment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data. Evolutionary correlation processing is performed on the precursor migration fragment data to determine the target production unit and generate the precursor evolution chain data corresponding to the target production unit; precursor propagation and acceptance map data is constructed based on the precursor evolution chain data and the propagation and acceptance relationship data, and the precursor propagation and acceptance map data is subjected to extended potential energy mapping processing to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving strength, acceptance direction, and acceptance priority relationship of the precursor migration to adjacent production units along the precursor propagation and acceptance map data; Based on the disease precursor evolution chain data, precursor aggregation contour data is determined. The directional distribution of the precursor expansion potential energy data in the precursor propagation and transfer diagram data is subjected to boundary projection processing to generate transfer extrapolation contour data. Based on the precursor aggregation contour data, a core isolation zone is determined. Based on the transfer extrapolation contour data, an extensional blocking zone is determined. Isolation control partition data is generated from the core isolation zone and the extensional blocking zone. Based on the distribution of the precursor propagation potential energy data in the precursor propagation and acceptance map data, the accepting production unit is determined from the adjacent production units that have a propagation and acceptance relationship with the target production unit, and acceptance hierarchical sequence data is generated; the acceptance hierarchical sequence data is subjected to blocking configuration processing to generate an acceptance blocking configuration sequence. A primary suppression deployment sequence is generated based on the isolation control partition data. This primary suppression deployment sequence is then subjected to hierarchical constraint processing based on the receiving blocking configuration sequence to generate a blocking constraint deployment sequence. Prevention and control deployment processing is performed according to the blocking constraint deployment sequence to obtain suppression response characterization data. The precursor expansion potential energy data is then written back and corrected based on the suppression response characterization data to generate corrected expansion potential energy data. Finally, the blocking constraint deployment sequence is sequentially updated based on the corrected expansion potential energy data to generate a hierarchical prevention and control deployment configuration sequence.

2. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 1, characterized in that, The disease precursor migration characterization data is processed by merging segments according to the collection time period and unit location to generate precursor migration segment data, including: Acquire unit time-series acquisition data of each production unit within the target facility, extract precursor migration characterization from the unit time-series acquisition data, and generate the disease precursor migration characterization data. The disease precursor migration characterization data is used to characterize the migration and changes of disease precursors within the production unit during the acquisition period. The disease precursor migration characterization data are divided into candidate windows to obtain candidate precursor window data; Based on the continuity relationship and unit location attribution relationship between adjacent acquisition periods of the candidate precursor window data, the candidate precursor window data is subjected to segment merging processing to generate the precursor migration segment data. The precursor migration segment data is used to characterize the local continuous anomaly range of disease precursors within a single production unit.

3. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 1, characterized in that, The step of performing evolutionary correlation processing on the precursor migration fragment data to determine the target production unit and generate the precursor evolution chain data corresponding to the target production unit includes: The segments in the precursor migration fragment data are identified as precursor evolution nodes; The basic evolutionary connection relationship is formed based on the temporal succession relationship between adjacent precursor evolutionary nodes; Based on the precursor intensity variation relationship and spatial migration relationship corresponding to the basic evolutionary connectivity relationship, a corrected evolutionary connectivity relationship is generated; The precursor evolution nodes are connected according to the corrected evolution connection relationship, and precursor stage markers are configured for the precursor evolution nodes to generate the disease precursor evolution chain data. The disease precursor evolution chain data is used to characterize the serialized association results of the disease precursor evolution from initial abnormality, continuous abnormality to intensified abnormality or outward expansion abnormality. The target production unit is determined based on the precursor evolution nodes in the disease precursor evolution chain data that are configured with precursor stage markers corresponding to the expansion stage.

4. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion according to any one of claims 1-3, characterized in that, The construction of the precursor propagation succession diagram data based on the disease precursor evolution chain data and the propagation succession relationship data includes: Obtain the unit-bearing structure data of the target facility, perform propagation and acceptance analysis on the unit-bearing structure data, and generate the propagation and acceptance relationship data. The propagation and acceptance relationship data is used to characterize the pathway and directional relationships between adjacent production units that can be used for the migration and acceptance of disease precursors. The production unit is mapped to the receiving node in the precursor propagation receiving diagram data, and the receiving node corresponding to the target production unit is determined as the starting receiving node; Map the directed inheritance relationship between adjacent production units that have a propagation inheritance relationship as connecting edges; Configure the bearing direction parameters and bearing strength parameters for the connecting edge based on the propagation bearing relationship data; The precursor propagation and acceptance map data is constructed from the acceptance node, the starting acceptance node, the connecting edge, the acceptance direction parameter, and the acceptance strength parameter. The precursor propagation and acceptance map data is used to characterize the graphical acceptance structure of disease precursors being transmitted from the target production unit to adjacent production units.

5. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 4, characterized in that, The step of performing extended potential energy mapping processing on the precursor propagation transition map data to generate precursor extended potential energy data includes: The precursor evolution node located at the outer end is obtained from the disease precursor evolution chain data and used as the outer end node; The outer end node is mapped to the starting receiving node in the precursor propagation receiving diagram data, and an initial potential energy value is generated based on the precursor intensity of the outer end node. The initial potential energy value is transmitted along the connecting edge corresponding to the starting receiving node, and the edge transmission value is generated according to the receiving strength parameter of the connecting edge. The edge transmission values ​​at different propagation levels are subjected to hierarchical attenuation processing to obtain the potential energy transmission values ​​corresponding to the candidate receiving nodes; The driving intensity and the receiving direction are determined based on the potential energy transfer value and the receiving direction parameter, and the receiving priority relationship is determined according to the magnitude relationship of the potential energy transfer value. The precursor expansion potential energy data is generated from the driving intensity, the receiving direction, and the receiving priority relationship. The precursor expansion potential energy data is used to characterize the potential energy distribution results of the disease precursor spreading to adjacent production units along the precursor propagation receiving map data.

6. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 5, characterized in that, The process involves determining precursor clustering contour data based on the disease precursor evolution chain data, performing boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation transition map data to generate transition extrapolation contour data, determining a core isolation zone based on the precursor clustering contour data, determining an extensional blocking zone based on the extensional blocking contour data, and generating isolation control zoning data from the core isolation zone and the extensional blocking zone, including: Based on the unit location and segment coverage of the precursor evolution node located within the target production unit in the disease precursor evolution chain data, the precursor cluster contour data is generated. The precursor cluster contour data is used to characterize the bounded range of continuous precursor clusters that have formed within the target production unit. The boundary projection direction is determined based on the receiving direction in the precursor extended potential energy data, and the boundary extrapolation amplitude is determined based on the driving intensity in the precursor extended potential energy data. According to the boundary projection direction and the boundary extrapolation magnitude, the boundary of adjacent production units is subjected to boundary projection processing to generate candidate data for the extrapolation contour; The candidate data for the extrapolation of the bearing contour are sorted according to the bearing priority relationship in the precursor extended potential energy data to generate the extrapolation of the bearing contour data. The extrapolation of the bearing contour data is used to characterize the peripheral blocking range formed by extrapolation along the propagation bearing direction. The core isolation zone is defined based on the precursor aggregation contour data, the extended blocking zone is defined based on the receiving extrapolation contour data, and the direction-strengthened isolation sub-region is determined within the extended blocking zone according to the receiving priority relationship; The isolation control partition data is generated from the core isolation zone, the extended blocking zone, and the directional reinforcement isolation sub-zone. The isolation control partition data is used to characterize the partition control range for disease precursor isolation and outward expansion blocking.

7. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 6, characterized in that, Based on the distribution of the precursor propagation potential energy data in the precursor propagation and acceptance map data, the accepting production unit is determined from the adjacent production units that have a propagation and acceptance relationship with the target production unit, and acceptance hierarchical sequence data is generated. The receiving hierarchical sequence data is subjected to blocking configuration processing to generate a receiving blocking configuration sequence, including: Based on the potential energy transfer value of the precursor extended potential energy data at each receiving node, candidate receiving production units are determined from the adjacent production units that have a propagation receiving relationship with the target production unit. According to the threshold range of the acceptance level where the potential energy transfer value is located, the candidate acceptance production units are divided into acceptance levels. The candidate acceptance production units that have completed the acceptance level division are determined as the acceptance production units. The acceptance production units are arranged according to the acceptance level to generate the acceptance level sequence data. The acceptance level sequence data is used to characterize the order and acceptance level relationship of the acceptance production units to the outward spread of disease precursors. According to the acceptance level, the corresponding acceptance control items are configured for the acceptance production unit, and the acceptance control items include blocking control items, prevention control items, or observation control items; The acceptance blocking configuration sequence is generated based on the acceptance control item. The acceptance blocking configuration sequence is used to characterize the acceptance control method corresponding to the acceptance production unit of different acceptance levels.

8. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 7, characterized in that, The step of generating a primary suppression deployment sequence based on the isolation control partition data, and performing hierarchical constraint processing on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence includes: Based on the isolation control zone data, the primary suppression action corresponding to each control zone is determined. The primary suppression action refers to the action taken to weaken the conditions for the spread and transmission of disease precursors within the control zone. The primary suppression actions are arranged according to the control priority of the core isolation zone, the directional enhanced isolation sub-zone, and the extended blocking zone to generate the primary suppression deployment sequence. The primary suppression deployment sequence is used to characterize the combination of suppression actions configured for different control zones in the initial prevention and control phase. Based on the aforementioned blocking configuration sequence, the intensity of the actions in the primary inhibition delivery sequence is subject to level constraints to obtain an intensity-constrained delivery sequence. Based on the accepted control item, the scope of application and execution order of the strength constraint deployment sequence are updated to generate the blocking constraint deployment sequence. The blocking constraint deployment sequence is used to characterize the prevention and control execution sequence after accepting the blocking configuration constraints.

9. The method for disease control and prevention in facility agriculture based on the isolation of early signs of disease expansion as described in claim 8, characterized in that, The process involves executing the blocking constraint deployment sequence to obtain suppression response characterization data; performing write-back correction on the precursor extended potential energy data based on the suppression response characterization data to generate corrected extended potential energy data; and performing hierarchical update processing on the blocking constraint deployment sequence based on the corrected extended potential energy data to generate a hierarchical prevention and control deployment configuration sequence, including: After performing the prevention and control deployment process according to the blocking constraint deployment sequence, the inhibition response characterization data corresponding to the target production unit and the receiving production unit are obtained. The inhibition response characterization data is used to characterize the precursor changes after the execution of the blocking constraint deployment sequence. Based on the suppression response characterization data, determine the precursor fall-off result, precursor maintenance result, or precursor enhancement result; Based on the precursor fallback result, the precursor maintenance result, or the precursor strengthening result, the driving intensity, receiving direction, and receiving priority relationship in the precursor extended potential energy data are written back and corrected to generate the corrected extended potential energy data. When the corrected extended potential energy data indicates an increased risk, the blocking constraint deployment sequence is upgraded and updated to generate an upgraded suppression deployment sequence; when the corrected extended potential energy data indicates that the risk remains the same, the blocking constraint deployment sequence is maintained and updated to generate a maintained suppression deployment sequence; when the corrected extended potential energy data indicates that the risk decreases, the blocking constraint deployment sequence is recovered and updated to generate a deployment and recovery sequence. The hierarchical prevention and control deployment configuration sequence is generated based on the upgraded suppression deployment sequence, the maintained suppression deployment sequence, or the deployment and recovery sequence. The hierarchical prevention and control deployment configuration sequence is used to characterize the prevention and control deployment execution configuration updated as the risk of disease precursor expansion changes.

10. A facility agriculture control and application system based on the isolation of disease precursors, characterized in that, The system includes: The precursor fragment generation unit is used to acquire the disease precursor migration characterization data of each production unit in the target facility and the propagation and inheritance relationship data between the production units, and to perform fragment merging processing on the disease precursor migration characterization data according to the collection time period and unit location to generate precursor migration fragment data. An extended potential energy mapping unit is used to perform evolutionary correlation processing on the precursor migration fragment data, determine the target production unit, and generate the disease precursor evolution chain data corresponding to the target production unit; construct precursor propagation and acceptance diagram data based on the disease precursor evolution chain data and the propagation and acceptance relationship data, and perform extended potential energy mapping processing on the precursor propagation and acceptance diagram data to generate precursor extended potential energy data. The precursor extended potential energy data is used to characterize the driving strength, acceptance direction, and acceptance priority relationship of the disease precursor migrating to adjacent production units along the precursor propagation and acceptance diagram data. The isolation zone generation unit is used to determine precursor aggregation contour data based on the disease precursor evolution chain data, perform boundary projection processing on the directional distribution of the precursor expansion potential energy data in the precursor propagation transition map data, and generate transition extrapolation contour data; determine the core isolation zone based on the precursor aggregation contour data, determine the extensional blocking zone based on the transitional extrapolation contour data, and generate isolation control zone data from the core isolation zone and the extensional blocking zone; The receiving and blocking configuration unit is used to determine the receiving production unit from the adjacent production units that have a propagation receiving relationship with the target production unit based on the distribution result of the precursor propagation potential energy data in the precursor propagation receiving map data, and generate receiving hierarchical sequence data; and to perform blocking configuration processing on the receiving hierarchical sequence data to generate a receiving and blocking configuration sequence. The hierarchical deployment and update unit is used to generate a primary suppression deployment sequence based on the isolation control partition data, and to perform hierarchical constraint processing on the primary suppression deployment sequence according to the receiving blocking configuration sequence to generate a blocking constraint deployment sequence; to perform prevention and control deployment processing according to the blocking constraint deployment sequence to obtain suppression response characterization data; to perform write-back correction on the precursor extended potential energy data based on the suppression response characterization data to generate corrected extended potential energy data; and to perform hierarchical update processing on the blocking constraint deployment sequence based on the corrected extended potential energy data to generate a hierarchical prevention and control deployment configuration sequence.

Images