An intelligent management system and method applied to strawberry disease identification

Abstract

The application discloses an intelligent management system and method applied to strawberry disease identification, relates to the technical field of intelligent management of strawberry soil-borne disease prevention and control, and collects standardised shed body basic information and soil pathogen data; determines the shed body as a new shed, an old shed and a transition shed based on planting years and pathogen threshold values; generates a differentiated prevention and control scheme according to the shed type, wherein the scheme comprises soil treatment and above-ground prevention and control measures; then, the scheme is converted into a standardised execution guide containing pesticide calculation and is pushed, the pesticide calculation adopts corresponding formulae; finally, pathogen changes are monitored every month; and the shed type and the scheme are dynamically adjusted according to the monitoring results.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for the prevention and control of soil-borne diseases in strawberries, specifically an intelligent management system and method for identifying strawberry diseases. Background Technology

[0002] In strawberry cultivation, the prevention and control of soil-borne diseases is a key aspect of ensuring yield and quality, but existing management methods have significant shortcomings:

[0003] Firstly, the collection of basic information about greenhouses (years of continuous planting, planting patterns) and soil pathogen data lacks a standardized process, and the data is prone to logical contradictions or insufficient representativeness, resulting in a lack of reliable basis for subsequent disease analysis.

[0004] Secondly, the classification of greenhouse types relies solely on the number of years of planting without considering the actual accumulation level of pathogens, resulting in a mismatch between the classification results and the actual disease risk of the greenhouse.

[0005] Third, the prevention and control plan lacks differentiated design. New greenhouses, old greenhouses and greenhouses in the transitional stage of pathogen accumulation are all treated with the same measures, which may result in problems such as excessive use of pesticides, insufficient prevention and control, or measures that are not compatible with the planting model.

[0006] Fourth, there is a lack of regular dynamic monitoring of soil pathogens and a real-time adjustment mechanism for control plans. After the plans are implemented, they cannot be optimized in a timely manner according to changes in pathogens, resulting in disease control lagging behind actual risks.

[0007] The above problems lead to low efficiency in the prevention and control of soil-borne diseases in strawberries and serious waste of resources. To solve these problems, this invention proposes an intelligent management system and method for identifying strawberry diseases. Summary of the Invention

[0008] The purpose of this invention is to provide an intelligent management system and method for identifying strawberry diseases, in order to solve the problems raised in the prior art.

[0009] To achieve the above objectives, the present invention provides the following technical solution:

[0010] A smart management method for identifying strawberry diseases includes the following steps:

[0011] S1. Collect basic information about strawberry greenhouses and soil pathogen data. The basic information includes the number of years of continuous planting in the greenhouse and the planting pattern in the past 3 years. The soil pathogen data is obtained by quantitative detection to obtain the content of soil-borne pathogens in the root zone of the greenhouse.

[0012] S2. Based on the two dimensions of continuous planting years and soil pathogen content, the greenhouse type is determined. The threshold of soil pathogen content for the two types of soil is calibrated through preliminary field trials, corresponding to the pathogen accumulation level of new and old greenhouses respectively. The greenhouse is classified according to the preset rules to form a classification result that matches the pathogen accumulation status.

[0013] S3. Generate differentiated prevention and control plans based on the classification results of the greenhouses. The plans include two parts: soil treatment and above-ground control. Different types of greenhouses correspond to different intensities of soil treatment measures and above-ground pesticide application measures.

[0014] S4. Transform the prevention and control plan into standardized implementation guidelines. Use mobile terminals to clarify the operation steps, dosage of pesticides, concentration of pesticides for above-ground application, and spraying locations, and guide users to follow the guidelines.

[0015] S5. Regularly monitor soil pathogen content. Collect soil samples from the root zone of the greenhouse at a fixed time each month, obtain pathogen content data through quantitative detection, and track the changing trend of pathogens in the greenhouse.

[0016] S6. Adjust the greenhouse type and prevention and control plan based on the pathogen content data obtained from monitoring. Re-determine the greenhouse type based on the changes in pathogen content and switch to the corresponding prevention and control plan for the greenhouse type simultaneously.

[0017] S1 further includes the following:

[0018] S1.1: Set up an information entry interface through the greenhouse management terminal. The interface includes two mandatory data collection items: one is the continuous planting years of the greenhouse, which is filled in by the user according to the actual planting cycle; the other is the planting mode of the past 3 years, with standardized options for users to choose from, covering common modes such as strawberry continuous cropping and strawberry rotation with other crops. After the data collection is completed, the terminal automatically performs format verification on the information, removes logically contradictory data, and forms a structured greenhouse basic information dataset.

[0019] S1.2: Based on the overall area of ​​the strawberry greenhouse and the spacing between the plant rows, delineate the sampling area: Within the greenhouse, determine 5 sampling points according to the spatial distribution principle of edge-middle-center. The distance from the edge of the greenhouse to the edge of the greenhouse should be consistent with the spacing between the plant rows. The middle and center points should be evenly distributed in the remaining area, and a permanent mark should be made at each sampling point.

[0020] S1.3: At each marked sampling point, use a soil sampler to vertically collect soil samples from the strawberry root zone; after collecting an equal amount of soil at each point, mix all soil samples thoroughly, remove plant debris and stones from the samples, and form a mixed soil sample that is representative of the entire greenhouse; dispense the mixed soil sample into sterile sampling containers, and label the containers with the greenhouse number and sampling date;

[0021] S1.4: The pretreated mixed soil sample is sent to the detection module, which performs quantitative detection on common soil-borne pathogens in strawberry cultivation. After the detection is completed, the detection module outputs the content data of various pathogens. The data format is uniformly set to numerical form that can be directly used for calculation and comparison. At the same time, the detection module judges the validity of the data and removes outliers caused by detection operation errors. If outliers are found, the retesting process is automatically triggered.

[0022] S2 further includes the following:

[0023] S2.1: Based on the basic information dataset of the greenhouse and the soil pathogen content data, the two types of data are uniquely associated according to the greenhouse number to form a binary association dataset of continuous planting years and pathogen content.

[0024] S2.2: Based on the binary association dataset constructed in S2.1, the analysis is carried out using a combination of group statistics and association verification: First, the dataset is divided into ≤3 years and >3 years groups according to the continuous planting years, and the distribution range and concentration value of pathogen content in each group are statistically analyzed; then, soil pathogen detection technology is used to conduct actual disease surveys on the two groups of greenhouses to verify the correspondence between pathogen content in each group and the disease occurrence status of the greenhouse, and to clarify that when the pathogen content reaches a certain value, the occurrence of greenhouse diseases exhibits a characteristic behavior of fluctuations within a preset range. The pathogen content value that meets the characteristic behavior is used as a preliminary reference for the threshold of pathogen content in the corresponding planting year group.

[0025] S2.3: Based on the preliminary threshold reference determined in S2.2, conduct field calibration experiments: Select strawberry greenhouses that match the characteristics of the two groups of planting years, set temporary thresholds according to the preliminary threshold reference values, and use soil pathogen quantitative detection technology to regularly monitor the matching of threshold judgment results under different temporary thresholds with the actual pathogen accumulation and disease occurrence status of the greenhouse.

[0026] Then, based on the monitoring results, the temporary threshold values ​​are gradually adjusted according to the preset standards until the matching degree between the judgment result and the actual state of the greenhouse is kept within the preset range. At this time, the temporary threshold values ​​are the final calibrated threshold values ​​for two types of soil pathogen content: the first type of threshold matches the pathogen accumulation level of greenhouses with no more than 3 years of continuous planting, which is the threshold for new greenhouses; the second type of threshold matches the pathogen accumulation level of greenhouses with more than 3 years of continuous planting, which is the threshold for old greenhouses.

[0027] Based on the obtained thresholds for new and old greenhouses, and combined with the planting patterns of the past three years, the two types of basic thresholds are corrected to form four types of thresholds that are suitable for greenhouses with continuous planting years ≤ 3 years + continuous cropping, continuous planting years ≤ 3 years + crop rotation, continuous planting years > 3 years + continuous cropping, and continuous planting years > 3 years + crop rotation. The four types of thresholds are stored in the system database.

[0028] S2.4: Perform the classification operation according to the preset rules, as follows:

[0029] A greenhouse is considered new if it has been continuously planted for ≤3 years and the pathogen count is < the threshold for new greenhouses.

[0030] A greenhouse is considered an old greenhouse if it has been continuously planted for more than 3 years and the pathogen count exceeds the threshold for old greenhouses.

[0031] The rest are transitional sheds;

[0032] The transition shed is defined as a shed where the pathogen content is within the threshold range of the transition shed and meets the transition state criteria based on the planting mode; and a shed is defined as a shed where the pathogen content is within the corresponding specific threshold critical range and meets the transition state criteria based on the planting mode.

[0033] Then, a structured classification result containing greenhouse number, continuous planting years, pathogen content, and determination type is generated and stored in the system database after being associated with planting pattern information of the past 3 years.

[0034] S3 further includes the following:

[0035] S3.1: Based on the structured greenhouse classification results and considering the differences in pathogen accumulation levels among the three types of greenhouses, a control intensity benchmark is set: new greenhouses correspond to basic control intensity, suitable for their low pathogen accumulation state; old greenhouses correspond to enhanced control intensity, suitable for their high pathogen accumulation state; transitional greenhouses correspond to medium control intensity, suitable for their pathogen accumulation state between new and old greenhouses; then, the greenhouse type-control intensity relationship is stored in the system's control plan database to clarify the control intensity boundary for each type of greenhouse.

[0036] S3.2: Based on the control intensity benchmark set in S3.1, and combined with the planting patterns of the past three years, corresponding soil treatment and above-ground control measures are matched for each type of greenhouse:

[0037] The new greenhouse adopts a soil treatment method that combines root dipping with biological agents with regular fertigation of biological agents. For above-ground control, protective pesticides are used, with the application focused on the leaves of the strawberry plants.

[0038] The old greenhouse uses a soil treatment method that combines fumigation soil disinfection with biological agent mixing. For above-ground prevention and control, therapeutic pesticides are used, and the application area covers the strawberry plant leaves and the soil around the root zone.

[0039] The transition greenhouse uses a combination of fumigation soil disinfection and regular biological agent soil treatment. For above-ground pest control, pesticides with both protective and curative effects are selected, and the application area focuses on the leaves and base of the stems of strawberry plants.

[0040] All the biological agents, fumigants, and pesticides involved in the measures are screened by calling the system's built-in list of compliant agricultural inputs for the planting area;

[0041] S3.3: Integrate soil treatment measures and above-ground control measures into a structured control plan. The plan fields include greenhouse number, greenhouse type, control intensity, key points of soil treatment operation, key points of above-ground control operation, and adaptation instructions for planting patterns in the past 3 years. Then, store the structured plan in the system database.

[0042] S4 further includes the following:

[0043] S4.1: Retrieve the structured prevention and control plan from the system database, associate the basic information of the shed with the shed classification results according to the shed number, and parse out the execution information in the prevention and control plan for each type of shed: the type of agent for soil treatment, the application sequence, operation requirements and corresponding agent dosage, and the type of agent for aboveground application, the basis for concentration conversion, the spraying location and application time requirements;

[0044] S4.2: Based on the parsed execution information, a standardized execution guidance framework is constructed for the soil treatment module, the above-ground pest control module, and operational precautions: The soil treatment module is broken down into operational steps in chronological order, and the dosage of pesticides and operating tools for each step are determined based on the area of ​​the greenhouse. The pesticide dosage calculation formula is as follows:

[0045] Q = S × q;

[0046] Where Q represents the total amount of soil treatment agent used in a certain step; S represents the actual planting area of ​​the strawberry greenhouse;

[0047] q represents the recommended dosage of soil treatment agent per unit area for each step, and the data comes from the key points of soil treatment operation in the structured control scheme.

[0048] The above-ground control module specifies the exact pesticide concentration and spraying location based on the ratio of the concentrate concentration to the target application concentration; the operation precautions module indicates the requirements for compatibility with the greenhouse planting patterns of the past three years and general operational contraindications; the pesticide concentration conversion formula is as follows:

[0049] C1×V1=C2×V2;

[0050] Wherein, C1 represents the concentration of the active ingredient in the pesticide concentrate, and the data comes from the information related to the type of pesticide agent for aboveground application analyzed in S4.1; V1 represents the required volume of pesticide concentrate, which is an unknown quantity to be calculated; C2 represents the target concentration of the active ingredient for aboveground application, and the data comes from the key points of aboveground control operation in the structured control scheme; V2 represents the total volume of pesticide solution required for a single application, and the data comes from the information related to the application time period requirements analyzed in S4.1;

[0051] S4.3: The completed standardized execution guidelines will be pushed to the user accounts of the corresponding greenhouses via mobile terminals. The push content will be in the form of a combination of text and images: step instructions will be accompanied by a real-scene map of the greenhouse, including a schematic diagram of soil treatment sampling points and application sites, and then the pesticide parameters will be given based on the soil treatment results. At the same time, an execution feedback entry will be set up on the mobile terminal. After completing the operation, the user needs to fill in the actual execution steps, pesticide dosage, completion time and upload photos of the operation site. The system will automatically associate the feedback information with the corresponding greenhouse's prevention and control plan and classification results and store it in the database.

[0052] S5 further includes the following:

[0053] S5.1: Based on the monitoring needs of the greenhouse, set a fixed time each month as the monitoring node for soil pathogens, and push monitoring reminders to mobile terminals through the system. The reminder content includes the sampling time and sampling requirements for the corresponding greenhouse.

[0054] S5.2: During the set monitoring time, perform the following operations according to the sample collection procedure: At each sampling point, use a soil sampler to vertically collect soil samples from the strawberry root zone; after collecting an equal amount of soil at each point, mix all the samples evenly to form a mixed monitoring sample; and put the mixed monitoring sample into a sterile sampling container labeled with the greenhouse number and monitoring date.

[0055] S5.3: The pre-treated mixed monitoring samples are sent to the detection module, and the quantitative detection process is followed: detection is carried out on common soil-borne pathogens of strawberries, and pathogen content data in a unified numerical format is output; the detection module judges the validity of the data, removes outliers caused by operational errors, and if outliers are found, the retesting process is automatically triggered, and finally the valid monitoring data is output; the system associates the current monitoring data with the historical monitoring data of the greenhouse in chronological order, generates a structured trend record of greenhouse number-monitoring time-pathogen content, and stores it in the system database.

[0056] S6 further includes the following:

[0057] S6.1: Retrieve structured trend records, new greenhouse thresholds, old greenhouse thresholds, and greenhouse classification results from the system database; based on the retrieved information, reclassify each type of greenhouse according to preset judgment rules:

[0058] For greenhouses currently classified as old, their current pathogen content is compared with the old greenhouse threshold. If the pathogen content is lower than the old greenhouse threshold, they are reclassified as transitional greenhouses. For greenhouses currently classified as transitional greenhouses, their pathogen content data from the two most recent consecutive monitoring sessions are extracted. If both data are lower than the new greenhouse threshold, they are reclassified as new greenhouses. For greenhouses currently classified as new greenhouses, their current pathogen content is compared with the new greenhouse threshold. If the pathogen content is higher than the new greenhouse threshold, they are temporarily classified as transitional greenhouses. After reclassification, a structured classification adjustment record containing the greenhouse number, original type, new type, and judgment criteria is generated and stored in the system database.

[0059] S6.2: Based on the classification adjustment records, retrieve the corresponding structured prevention and control plan from the system database according to the new shed type; push the plan switching notification to the user via mobile terminal, the notification content includes the key points of operation of the new shed type and the new prevention and control plan, and simultaneously update the standardized execution guidelines in the mobile terminal; at the same time, the system automatically updates the current shed type in the database to the re-determined type, replaces the current execution prevention and control plan with the corresponding new type of plan, and associates the classification adjustment records and monitoring data of this adjustment to provide the latest shed status and plan information for the next periodic monitoring and adjustment.

[0060] An intelligent management system for identifying strawberry diseases includes a basic information collection module, a soil pathogen detection module, a data correlation analysis module, a greenhouse type determination module, a prevention and control plan generation module, an execution guidance generation module, a mobile terminal interaction module, a data storage and management module, and a greenhouse type and plan adjustment module.

[0061] The basic information collection module is used to collect the continuous planting years and planting patterns of the greenhouse in the past three years through a standardized input interface, automatically verify the data and form a structured dataset to provide basic background data for subsequent processes. The soil pathogen detection module is used to perform quantitative detection of soil-borne pathogens on pretreated soil samples, output standardized data and remove outliers, providing quantitative data for greenhouse classification and pathogen trend tracking. The data correlation analysis module is used to correlate greenhouse basic information with pathogen data, analyze data patterns through group statistics and disease correlation verification, and provide threshold references for greenhouse type determination. The greenhouse type determination module is used to calibrate pathogen thresholds through field trials, determine greenhouse type according to the planting years + threshold rule, and generate structured classification results. The prevention and control plan generation module is used to set the prevention and control intensity benchmark based on greenhouse type, call the list of compliant agricultural inputs to match differentiated soil treatment and above-ground control measures, and integrate... The system is structured into a prevention and control plan. The execution guidance generation module parses the execution information within the plan, constructs a standardized guidance framework, and calculates drug dosage and concentration using formulas to generate executable operational text. The mobile terminal interaction module pushes combined text and image execution guidance to users, collects user operation feedback data, and pushes notifications and updates the guidance when the plan is adjusted. The data storage and management module stores core data throughout the entire process, including basic greenhouse information, pathogen data, related datasets, greenhouse classification results, structured prevention and control plans, execution guidance, user feedback data, pathogen monitoring trend records, and classification adjustment records, providing data retrieval and association services for each module. The greenhouse type and plan adjustment module re-determines the greenhouse type based on pathogen monitoring data, retrieves the corresponding prevention and control plan, pushes adjustment notifications via mobile terminal, and updates the execution guidance, ensuring that prevention and control measures remain adapted to changes in pathogens within the greenhouse.

[0062] Compared with the prior art, the beneficial effects of the present invention are:

[0063] 1. By standardizing the collection of basic information of the greenhouse, the layout of soil sampling points and sample preprocessing, and with the detection module's mechanism for removing outliers and retesting pathogen data, the problems of logical contradictions and insufficient representativeness in traditional data collection have been solved. This provides accurate and reusable basic data for subsequent greenhouse classification and scheme formulation, avoiding errors in prevention and control decisions due to data deviation.

[0064] 2. Based on the dual-dimensional judgment logic of continuous planting years and pathogen content, the specific thresholds for new and old greenhouses are calibrated through field trials. The greenhouses are classified according to the rule that "new greenhouses are those with ≤3 years of continuous planting and pathogen content < new greenhouse threshold, old greenhouses are those with >3 years of continuous planting and pathogen content > old greenhouse threshold, and the rest are transition greenhouses". This breaks through the limitations of the traditional classification based solely on the single dimension of planting years, and makes the classification results highly consistent with the actual pathogen accumulation status in the greenhouse, providing a precise basis for differentiated prevention and control.

[0065] 3. Set tiered control intensity according to greenhouse type, and match soil treatment and above-ground control measures accordingly. At the same time, use the list of compliant agricultural inputs for the planting area to screen pesticides. This not only avoids the waste of resources such as "excessive use of pesticides in new greenhouses and insufficient control in old greenhouses", but also ensures that the measures comply with local agricultural standards.

[0066] 4. By monitoring pathogens at fixed times and with unified sampling standards every month, and by re-determining the greenhouse type based on the monitoring results and switching the plan in sync, a closed loop of the whole process of "collection-classification-plan-execution-monitoring-adjustment" is formed. This completely solves the pain point of traditional management "lack of dynamic adjustment and prevention and control lagging behind changes in pathogens" and realizes real-time adaptive prevention and control of soil-borne diseases of strawberries. Attached Figure Description

[0067] Figure 1 This is a flowchart of an intelligent management method for identifying strawberry diseases according to the present invention.

[0068] Figure 2 This is a flowchart illustrating the greenhouse classification process of an intelligent management method for identifying strawberry diseases, as described in this invention.

[0069] Figure 3 This is a flowchart illustrating the adjustment process of greenhouse type and scheme for an intelligent management method for identifying strawberry diseases according to the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] Example: Figures 1-3 As shown, the present invention provides a technical solution.

[0072] A smart management method for identifying strawberry diseases includes the following steps:

[0073] S1. Collect basic information about strawberry greenhouses and soil pathogen data. The basic information includes the number of years of continuous planting in the greenhouse and the planting pattern in the past 3 years. The soil pathogen data is obtained by quantitative detection to obtain the content of soil-borne pathogens in the root zone of the greenhouse.

[0074] S2. Based on the two dimensions of continuous planting years and soil pathogen content, the greenhouse type is determined. The threshold of soil pathogen content for the two types of soil is calibrated through preliminary field trials, corresponding to the pathogen accumulation level of new and old greenhouses respectively. The greenhouse is classified according to the preset rules to form a classification result that matches the pathogen accumulation status.

[0075] S3. Generate differentiated prevention and control plans based on the classification results of the greenhouses. The plans include two parts: soil treatment and above-ground control. Different types of greenhouses correspond to different intensities of soil treatment measures and above-ground pesticide application measures.

[0076] S4. Transform the prevention and control plan into standardized implementation guidelines. Use mobile terminals to clarify the operation steps, dosage of pesticides, concentration of pesticides for above-ground application, and spraying locations, and guide users to follow the guidelines.

[0077] S5. Regularly monitor soil pathogen content. Collect soil samples from the root zone of the greenhouse at a fixed time each month, obtain pathogen content data through quantitative detection, and track the changing trend of pathogens in the greenhouse.

[0078] S6. Adjust the greenhouse type and prevention and control plan based on the pathogen content data obtained from monitoring. Re-determine the greenhouse type based on the changes in pathogen content and switch to the corresponding prevention and control plan for the greenhouse type simultaneously.

[0079] S1 further includes the following:

[0080] S1.1: Set up an information entry interface through the greenhouse management terminal. The interface includes two mandatory data collection items: one is the continuous planting years of the greenhouse, which is filled in by the user according to the actual planting cycle; the other is the planting mode of the past 3 years, with standardized options for users to choose from, covering common modes such as strawberry continuous cropping and strawberry rotation with other crops. After the data collection is completed, the terminal automatically performs format verification on the information, removes logically contradictory data, and forms a structured greenhouse basic information dataset.

[0081] S1.2: Based on the overall area of ​​the strawberry greenhouse and the spacing between the plant rows, delineate the sampling area: Within the greenhouse, determine 5 sampling points according to the spatial distribution principle of edge-middle-center. The distance from the edge of the greenhouse to the edge of the greenhouse should be consistent with the spacing between the plant rows. The middle and center points should be evenly distributed in the remaining area, and a permanent mark should be made at each sampling point.

[0082] S1.3: At each marked sampling point, use a soil sampler to vertically collect soil samples from the strawberry root zone; after collecting an equal amount of soil at each point, mix all soil samples thoroughly, remove plant debris and stones from the samples, and form a mixed soil sample that is representative of the entire greenhouse; dispense the mixed sample into sterile sampling containers, and label the containers with the greenhouse number and sampling date;

[0083] S1.4: The pretreated mixed soil sample is sent to the detection module, which performs quantitative detection on common soil-borne pathogens in strawberry cultivation. After the detection is completed, the detection module outputs the content data of various pathogens. The data format is uniformly set to numerical form that can be directly used for calculation and comparison. At the same time, the detection module judges the validity of the data and removes outliers caused by detection operation errors. If outliers are found, the retesting process is automatically triggered.

[0084] S2 further includes the following:

[0085] S2.1: Based on the basic information dataset of the greenhouse and the soil pathogen content data, the two types of data are uniquely associated according to the greenhouse number to form a binary association dataset of continuous planting years and pathogen content.

[0086] S2.2: Based on the binary association dataset constructed in S2.1, an analysis was conducted using a combination of grouped statistics and association verification methods: First, the dataset was divided into ≤3 years and >3 years groups according to the continuous planting years, and the distribution range and concentration value of pathogen content within each group were statistically analyzed; then, soil pathogen detection technology was used to conduct actual disease surveys on the two groups of greenhouses to verify the correspondence between pathogen content within each group and the disease occurrence status of the greenhouse.

[0087] During the investigation, the two groups of greenhouses were further subdivided according to the planting patterns of the past three years: the group with ≤3 years of continuous planting was subdivided into two subgroups: ≤3 years + continuous cropping and ≤3 years + crop rotation; the group with >3 years of continuous planting was subdivided into two subgroups: >3 years + continuous cropping and >3 years + crop rotation. By comparing the pathogen content distribution characteristics and disease occurrence patterns of each subgroup, the differences in the impact of different planting patterns on pathogen accumulation were clarified.

[0088] Within the same year group, the pathogen content of the continuous cropping subgroup showed a high degree of concentration and a fast accumulation rate. The disease occurrence was also more concentrated. That is, when the pathogen content reached a certain level, most greenhouses showed similar disease characteristics.

[0089] Within the same year group, the pathogen content of the rotation subgroup showed a high degree of dispersion and a slow accumulation rate. The disease occurrence status fluctuated relatively greatly, and the correlation between pathogen content and disease manifestation was more moderate.

[0090] Based on the above differences, when setting preliminary reference thresholds, for the continuous cropping subgroup, the strong correlation between pathogen content and disease occurrence should be used as the basis to ensure that the preliminary reference values ​​better reflect its rapid accumulation characteristics; for the crop rotation subgroup, the gradual correlation between pathogen content and disease occurrence should be used as the basis to ensure that the preliminary reference values ​​match its gradual accumulation characteristics.

[0091] When the pathogen content reaches a certain value, the occurrence of diseases in the greenhouse exhibits a characteristic behavior that fluctuates within a preset range. The pathogen content value that meets the characteristic behavior is used as a preliminary reference for the threshold of pathogen content in the corresponding planting year group.

[0092] S2.3: Based on the preliminary threshold reference determined in S2.2, conduct field calibration experiments: Select strawberry greenhouses that match the characteristics of the two groups of planting years, set temporary thresholds according to the preliminary threshold reference values, and use soil pathogen quantitative detection technology to regularly monitor the matching of threshold judgment results under different temporary thresholds with the actual pathogen accumulation and disease occurrence status of the greenhouse.

[0093] Then, based on the monitoring results, the temporary threshold values ​​are gradually adjusted according to the preset standards until the matching degree between the judgment result and the actual state of the shed remains within the preset range.

[0094] During the calibration process, the threshold matching degree of greenhouses with different planting modes is verified and adjusted separately, and the logic is as follows:

[0095] For greenhouses in the continuous cropping mode: If judged according to the initially calibrated threshold, some greenhouses show a deviation where the pathogen content does not exceed the threshold, but the actual disease risk has increased significantly. This indicates that the initial threshold is not fully adapted to the characteristics of rapid pathogen accumulation. The corresponding threshold needs to be appropriately lowered to ensure that the threshold can accurately reflect the true disease risk.

[0096] For greenhouses using crop rotation: If, based on the initially calibrated threshold, some greenhouses show pathogen content exceeding the threshold, but the actual disease risk remains at a low level, this indicates that the initial threshold is not adapted to the characteristics of the gradual accumulation of pathogens. The corresponding threshold needs to be appropriately increased to avoid wasting control resources due to an excessively low threshold.

[0097] For different planting mode subgroups within the same type of greenhouse, the calibrated thresholds need to form a system of basic thresholds + planting mode correction rules: basic thresholds are set for new greenhouses and old greenhouses respectively, and the threshold standards for greenhouses under continuous cropping and crop rotation modes are adjusted according to the preset correction rules. The threshold range for transition greenhouses is simultaneously optimized based on the corrected thresholds for new and old greenhouses, ensuring that the classification thresholds of greenhouses under all planting modes match the actual pathogen accumulation status.

[0098] After calibrating the basic thresholds for new and old greenhouses through preliminary field trials, the two types of basic thresholds were revised based on the planting patterns of the past three years, resulting in four types of thresholds:

[0099] For greenhouses with continuous planting years ≤3 years and continuous cropping, the threshold for new greenhouses is adjusted downward based on the basic threshold for new greenhouses and the characteristic that the pathogen enrichment rate is higher under continuous cropping mode than under crop rotation mode. This results in the new greenhouse-continuous cropping correction threshold.

[0100] For greenhouses with continuous planting years ≤ 3 years + crop rotation, the threshold for new greenhouses is adjusted upwards based on the basic threshold for new greenhouses and the characteristic that pathogen reproduction is inhibited under the crop rotation mode, resulting in the new greenhouse-crop rotation correction threshold.

[0101] For greenhouses with continuous planting years > 3 years and continuous cropping, based on the basic threshold of old greenhouses and combined with the characteristics of continuous enrichment and stable accumulation of pathogens under the continuous cropping mode, the threshold is kept unchanged to obtain the old greenhouse-continuous cropping correction threshold.

[0102] For greenhouses with continuous planting years > 3 years and crop rotation, the old greenhouse base threshold is adjusted upward based on the characteristic that the pathogen accumulation rate under the crop rotation mode is lower than that under continuous cropping, and the old greenhouse-crop rotation correction threshold is obtained.

[0103] All four thresholds are stored in the system database to provide a quantitative basis for shed classification.

[0104] S2.4: According to the preset rules: if the continuous planting period is ≤3 years and the pathogen is < new greenhouse threshold, it is a new greenhouse; if the continuous planting period is >3 years and the pathogen is > old greenhouse threshold, it is an old greenhouse; the rest are transition greenhouses.

[0105] For greenhouses where pathogen levels are within the threshold range (i.e., pathogen levels are close to but not yet at or just above the corresponding threshold), supplementary assessment should be conducted in conjunction with the planting patterns of the past three years. This is to avoid classification bias caused by relying solely on the years of planting and pathogen levels. The specific assessment logic is as follows:

[0106] If the greenhouse has been continuously used for planting for ≤3 years, the pathogen content is within the critical range of the new greenhouse threshold:

[0107] If the planting pattern is continuous cropping, the risk of exceeding the threshold of the new greenhouse in the short term is relatively high because continuous cropping will continuously accelerate the accumulation of pathogens, and it is judged as a transition greenhouse.

[0108] If the planting pattern is crop rotation, it is considered a new greenhouse because crop rotation can inhibit the accumulation of pathogens and maintain strong stability within the threshold of a new greenhouse in the short term.

[0109] If the greenhouse has been continuously used for planting for more than 3 years, the pathogen content is in the critical range of the old greenhouse threshold:

[0110] If the planting pattern is continuous cropping, the risk of disease will continue to rise because continuous cropping will further aggravate the accumulation of pathogens; therefore, it is considered an old greenhouse.

[0111] If the planting pattern is crop rotation, since crop rotation can delay the accumulation of pathogens, the current disease risk has not yet reached the typical level of the old greenhouse, and it is judged as a transitional greenhouse.

[0112] Finally, a structured classification result containing greenhouse number, continuous planting years, pathogen content, and determination type is generated and stored in the system database after being associated with the planting pattern information of the past 3 years in S1.1.

[0113] S2.4 further includes:

[0114] Threshold critical interval definition: Based on each specific threshold, a floating range is set up and down according to a preset ratio to form the threshold critical interval corresponding to the specific threshold; this interval is suitable for scenarios where the disease occurrence state of the greenhouse does not show stable characteristics when the pathogen content fluctuates.

[0115] Threshold range definition for transition greenhouses: Based on the continuous planting years of the greenhouse and the planting patterns of the past 3 years, the threshold range for transition greenhouses is defined according to different scenarios:

[0116] For greenhouses with ≤3 years of continuous planting: When the planting mode is continuous cropping, the threshold range for transition greenhouses is: new greenhouse - continuous cropping correction threshold ≤ pathogen content < lower limit of the critical interval corresponding to old greenhouse - continuous cropping correction threshold; when the planting mode is crop rotation, the threshold range for transition greenhouses is: new greenhouse - crop rotation correction threshold ≤ pathogen content < lower limit of the critical interval corresponding to old greenhouse - crop rotation correction threshold.

[0117] For greenhouses with a continuous planting period of more than 3 years: When the planting mode is continuous cropping, the threshold range for transition greenhouses is the upper limit of the critical interval corresponding to the new greenhouse-continuous cropping correction threshold ≤ pathogen content < old greenhouse-continuous cropping correction threshold; when the planting mode is crop rotation, the threshold range for transition greenhouses is the upper limit of the critical interval corresponding to the new greenhouse-crop rotation correction threshold ≤ pathogen content < old greenhouse-crop rotation correction threshold.

[0118] Greenhouse classification is implemented as follows: Based on the four specific thresholds, threshold critical ranges, and transition greenhouse threshold ranges defined above, the classification is completed according to the following rules: Greenhouses with continuous planting years ≤ 3 years and pathogen content < the corresponding new greenhouse correction threshold are classified as new greenhouses; Greenhouses with continuous planting years > 3 years and pathogen content > the corresponding old greenhouse correction threshold are classified as old greenhouses; Greenhouses with pathogen content within the transition greenhouse threshold range, or within the corresponding specific threshold critical range and deemed to meet the transition status by planting mode assistance, are classified as transition greenhouses.

[0119] S3 further includes the following:

[0120] S3.1: Based on the structured greenhouse classification results and considering the differences in pathogen accumulation levels among the three types of greenhouses, a control intensity benchmark is set: new greenhouses correspond to basic control intensity, suitable for their low pathogen accumulation state; old greenhouses correspond to enhanced control intensity, suitable for their high pathogen accumulation state; transitional greenhouses correspond to medium control intensity, suitable for their pathogen accumulation state between new and old greenhouses; then, the greenhouse type-control intensity relationship is stored in the system's control plan database to clarify the control intensity boundary for each type of greenhouse.

[0121] S3.2: Based on the control intensity benchmark set in S3.1, and combined with the planting patterns of the past three years associated with the classification results in S2.4, corresponding soil treatments and above-ground control measures are matched for each type of greenhouse:

[0122] The new greenhouse adopts a soil treatment method that combines root dipping with biological agents with regular fertigation of biological agents. For above-ground control, protective pesticides are used, with the application focused on the leaves of the strawberry plants.

[0123] The old greenhouse uses a soil treatment method that combines fumigation soil disinfection with biological agent mixing. For above-ground prevention and control, therapeutic pesticides are used, and the application area covers the strawberry plant leaves and the soil around the root zone.

[0124] The transition greenhouse uses a combination of fumigation soil disinfection and regular biological agent soil treatment. For above-ground pest control, pesticides with both protective and curative effects are selected, and the application area focuses on the leaves and base of the stems of strawberry plants.

[0125] All biological agents, fumigants, and pesticides involved in the measures are screened using the system's built-in list of compliant agricultural inputs for the planting area; this ensures that the measures comply with local agricultural production standards and provides clear operational content for the subsequent conversion of S4 into standardized implementation guidelines;

[0126] S3.3: Integrate soil treatment measures and above-ground control measures into a structured control plan. The plan fields include greenhouse number, greenhouse type, control intensity, key points of soil treatment operation, key points of above-ground control operation, and adaptation instructions for planting patterns in the past 3 years. Then, store the structured plan in the system database, and link it with the greenhouse classification results of S2.4 and the basic greenhouse information of S1.1.

[0127] S4 further includes the following:

[0128] S4.1: Retrieve the structured prevention and control plan from the system database, associate the basic information of the shed with the shed classification results according to the shed number, and parse out the execution information in the prevention and control plan for each type of shed: the type of agent for soil treatment, the application sequence, operation requirements and corresponding agent dosage, and the type of agent for aboveground application, the basis for concentration conversion, the spraying location and application time requirements;

[0129] S4.2: Based on the parsed execution information, a standardized execution guidance framework is constructed for the soil treatment module, the above-ground pest control module, and operational precautions: The soil treatment module is broken down into operational steps in chronological order, and the dosage of pesticides and operating tools for each step are determined based on the area of ​​the greenhouse. The pesticide dosage calculation formula is as follows:

[0130] Q = S × q;

[0131] Where Q represents the total amount of soil treatment agent used in a certain step; S represents the actual planting area of ​​the strawberry greenhouse; q represents the recommended amount of soil treatment agent per unit area in this step, and the data comes from the key points of soil treatment operation in the S3.3 structured control scheme.

[0132] The above-ground control module specifies the exact pesticide concentration and spraying location based on the ratio of the concentrate concentration to the target application concentration; the operation precautions module indicates the requirements for compatibility with the greenhouse planting patterns of the past three years and general operational contraindications; the pesticide concentration conversion formula is as follows:

[0133] C1×V1=C2×V2;

[0134] Wherein, C1 represents the concentration of the active ingredient in the pesticide concentrate, and the data comes from the information on the type of pesticide agent for aboveground application analyzed in S4.1; V1 represents the required volume of pesticide concentrate, which is an unknown quantity to be calculated; C2 represents the target concentration of the active ingredient for aboveground application, and the data comes from the key points of aboveground control operation in the structured control plan in S3.3; V2 represents the total volume of pesticide solution required for a single application, and the data comes from the information on the application time requirements analyzed in S4.1.

[0135] S4.3: The completed standardized execution guidelines will be pushed to the user accounts of the corresponding greenhouses via mobile terminals. The push content will be in the form of a combination of text and images: step instructions will be accompanied by a real-scene map of the greenhouse, including a schematic diagram of soil treatment sampling points and application sites, and then the pesticide parameters will be given based on the soil treatment results. At the same time, an execution feedback entry will be set up on the mobile terminal. After completing the operation, the user needs to fill in the actual execution steps, pesticide dosage, completion time and upload photos of the operation site. The system will automatically associate the feedback information with the corresponding greenhouse's prevention and control plan and classification results and store it in the database.

[0136] S5 further includes the following:

[0137] S5.1: Based on the monitoring needs of the greenhouse, a fixed time each month is set as the monitoring node for soil pathogens. The system pushes monitoring reminders to mobile terminals, and the reminder content includes the sampling time and sampling requirements for the corresponding greenhouse. At the same time, the permanent sampling point information deployed in S1.2 and the greenhouse classification results stored in S2.4 are retrieved from the system database, and the monitoring node is uniquely associated with the sampling point and greenhouse information to ensure that each monitoring is based on a unified sampling benchmark.

[0138] S5.2: At the set monitoring time, perform the sample collection procedure according to S1.3: At each sampling point marked in S1.2, use a soil sampler to vertically collect soil samples from the strawberry root zone; after collecting an equal amount of soil at each point, mix all the samples evenly to form a mixed monitoring sample; put the mixed monitoring sample into a sterile sampling container labeled with the greenhouse number and monitoring date;

[0139] S5.3: The pre-processed mixed monitoring sample is sent to the detection module, and the operation is performed according to the quantitative detection process in S1.4: the detection is carried out for common soil-borne pathogens of strawberries, and the pathogen content data in a uniform numerical format is output; the detection module judges the validity of the data, removes outliers caused by operational errors, and if outliers exist, the retest process is automatically triggered, and finally the valid monitoring data is output; the system associates the current monitoring data with the historical monitoring data of the greenhouse in chronological order, generates a structured trend record of greenhouse number-monitoring time-pathogen content, and stores it in the system database.

[0140] S6 further includes the following:

[0141] S6.1: Retrieve structured trend records, new greenhouse thresholds, old greenhouse thresholds, and greenhouse classification results from the system database; based on the retrieved information, reclassify each type of greenhouse according to preset judgment rules:

[0142] For greenhouses currently classified as old, their current pathogen content is compared with the old greenhouse threshold. If the pathogen content is lower than the old greenhouse threshold, they are reclassified as transitional greenhouses. For greenhouses currently classified as transitional greenhouses, their pathogen content data from the two most recent consecutive monitoring sessions are extracted. If both data are lower than the new greenhouse threshold, they are reclassified as new greenhouses. For greenhouses currently classified as new greenhouses, their current pathogen content is compared with the new greenhouse threshold. If the pathogen content is higher than the new greenhouse threshold, they are temporarily classified as transitional greenhouses. After reclassification, a structured classification adjustment record containing the greenhouse number, original type, new type, and judgment criteria is generated and stored in the system database.

[0143] S6.2: Based on the classification adjustment record generated in S6.1, retrieve the corresponding structured prevention and control plan stored in S3.3 from the system database according to the new shed type; push the plan switching notification to the user via mobile terminal, the notification content includes the key points of operation of the new shed type and the new prevention and control plan, and simultaneously update the standardized execution guidelines in the mobile terminal; at the same time, the system automatically updates the current shed type in the database to the re-determined type, replaces the current execution prevention and control plan with the corresponding new type of plan, and associates the classification adjustment record and monitoring data of this adjustment to provide the latest shed status and plan information for the next periodic monitoring and adjustment.

[0144] An intelligent management system for identifying strawberry diseases includes a basic information collection module, a soil pathogen detection module, a data correlation analysis module, a greenhouse type determination module, a prevention and control plan generation module, an execution guidance generation module, a mobile terminal interaction module, a data storage and management module, and a greenhouse type and plan adjustment module.

[0145] The basic information collection module is used to collect the continuous planting years and planting patterns of the greenhouse in the past three years through a standardized input interface, automatically verify the data and form a structured dataset to provide basic background data for subsequent processes. The soil pathogen detection module is used to perform quantitative detection of soil-borne pathogens on pretreated soil samples, output standardized data and remove outliers, providing quantitative data for greenhouse classification and pathogen trend tracking. The data correlation analysis module is used to correlate greenhouse basic information with pathogen data, analyze data patterns through group statistics and disease correlation verification, and provide threshold references for greenhouse type determination. The greenhouse type determination module is used to calibrate pathogen thresholds through field trials, determine greenhouse type according to the planting years + threshold rule, and generate structured classification results. The prevention and control plan generation module is used to set the prevention and control intensity benchmark based on greenhouse type, call the list of compliant agricultural inputs to match differentiated soil treatment and above-ground control measures, and integrate... The system is structured into a prevention and control plan. The execution guidance generation module parses the execution information within the plan, constructs a standardized guidance framework, and calculates drug dosage and concentration using formulas to generate executable operational text. The mobile terminal interaction module pushes combined text and image execution guidance to users, collects user operation feedback data, and pushes notifications and updates the guidance when the plan is adjusted. The data storage and management module stores core data throughout the entire process, including basic greenhouse information, pathogen data, related datasets, greenhouse classification results, structured prevention and control plans, execution guidance, user feedback data, pathogen monitoring trend records, and classification adjustment records, providing data retrieval and association services for each module. The greenhouse type and plan adjustment module re-determines the greenhouse type based on pathogen monitoring data, retrieves the corresponding prevention and control plan, pushes adjustment notifications via mobile terminal, and updates the execution guidance, ensuring that prevention and control measures remain adapted to changes in pathogens within the greenhouse.

[0146] In a contiguous strawberry planting base, to verify the effectiveness of the intelligent management system and methods in the prevention and control of soil-borne diseases, three planting sheds with different characteristics (numbered P1, P2, and P3) were selected for full-process application. Each link was closely connected to form a complete closed loop for disease prevention and control management.

[0147] First, basic information collection was initiated. Using the standardized input interface of the greenhouse management terminal, core basic information for three greenhouses was collected one by one: Greenhouse P1 had been continuously planted for two years, using a "strawberry-tomato rotation" pattern for the past three years; Greenhouse P2 had been continuously planted for five years, maintaining a "strawberry continuous cropping" pattern; and Greenhouse P3 had been continuously planted for three years, implementing a "strawberry-cucumber rotation" pattern. After collection, the terminal automatically verified the data logic, finding no contradictory information, and successfully forming a structured basic information dataset. Next, sampling points were set up according to a unified standard. Each of the three greenhouses had an area of ​​500 square meters and a plant row spacing of 0.8 meters. Therefore, five sampling points were determined according to the "edge-center-middle" principle, with edge points 0.8 meters from the edge of the greenhouse, and the remaining points evenly distributed and permanently marked. During sampling, 200 grams of soil from the root zone at a depth of 20 cm was vertically collected at each marked point using a soil sampler. The soil from the five points in the same greenhouse was mixed evenly, and after removing debris, stones, and other impurities, it was placed into a sterile container labeled with the greenhouse number and sampling date. These pretreated samples were sent to the soil pathogen detection module for quantitative detection of common strawberry fungi, such as Fusarium oxysporum and Phytophthora. The final standardized data output were as follows: P1: Fusarium oxysporum 0.3×10³ CFU / g, Phytophthora 0.1×10³ CFU / g; P2: Fusarium oxysporum 2.8×10³ CFU / g, Phytophthora 1.5×10³ CFU / g; P3: Fusarium oxysporum 1.2×10³ CFU / g, Phytophthora 0.6×10³ CFU / g. The validity was determined to be without abnormal values, and no retesting was required.

[0148] Based on the collected basic information and pathogen data, the system establishes a unique association by "greenhouse number," forming a binary dataset of "continuous planting years - pathogen content," providing a complete basis for greenhouse classification. Subsequently, the data is analyzed using a "group statistics + association verification" method, dividing the dataset into a ≤3-year group (P1, P3) and a >3-year group (P2). The former has a concentrated value of 0.75×10³ CFU / g for Fusarium oxysporum content, while the latter has 2.8×10³ CFU / g. Combined with actual disease surveys, it was found that when the Fusarium oxysporum content in ≤3-year greenhouses is below 0.8×10³ CFU / g, and in >3-year greenhouses it is above 2.5×10³ CFU / g, the disease occurrence status fluctuates stably. This was used as a preliminary threshold reference. To further improve the accuracy of the thresholds, five greenhouses of similar age were selected for field calibration experiments. Through multiple adjustments to the temporary thresholds, the final thresholds were determined as follows: for new greenhouses (suitable for greenhouses ≤3 years old), the thresholds were 0.7 × 10³ CFU / g for *Fusarium oxysporum* and 0.3 × 10³ CFU / g for *Phytophthora*; and for old greenhouses (suitable for greenhouses >3 years old), the thresholds were 2.6 × 10³ CFU / g for *Fusarium oxysporum* and 1.2 × 10³ CFU / g for *Phytophthora*. According to preset rules, P1 was classified as a new greenhouse because its planting age was ≤3 years and the pathogen content was below the new greenhouse threshold; P2 was classified as an old greenhouse because its planting age was >3 years and the pathogen content was above the old greenhouse threshold; and P3 was classified as a transitional greenhouse because its planting age was ≤3 years but the pathogen content exceeded the new greenhouse threshold. The classification results were then stored in the system database after being correlated with the planting mode.

[0149] Based on the classification results, the system first sets control intensity benchmarks for different types of greenhouses: new greenhouses (P1) correspond to basic control intensity, old greenhouses (P2) correspond to enhanced control intensity, and transitional greenhouses (P3) correspond to medium control intensity. This relationship is synchronously stored in the control plan database. Combining the planting mode of each greenhouse, the system calls upon the local list of compliant agricultural inputs to match differentiated control measures: P1 (new greenhouse + crop rotation) adopts a soil treatment method of "Bacillus subtilis root dipping + Trichoderma harzianum drenching every 15 days", and uses the protective pesticide mancozeb for foliar spraying on the ground; P2 (old greenhouse + continuous cropping) adopts a soil treatment method of "dazomet fumigation + Paecilomyces lilacin mixed with soil", and uses the therapeutic pesticide hymexazol to cover the leaves and 30 cm of soil in the root zone; P3 (transitional greenhouse + crop rotation) adopts a soil treatment method of "Vapamil fumigation + Bacillus subtilis and Trichoderma harzianum compound preparation drenching every 10 days", and uses azoxystrobin, which has both protective and therapeutic effects, for foliar spraying and stem base spraying on the ground. These measures have been integrated into a structured solution that includes "greenhouse number, type, prevention and control intensity, key points of operation, and instructions for adapting planting models" to ensure that each step can be accurately adapted to the actual conditions of the greenhouse.

[0150] To ensure the implementation of the prevention and control plan, the system retrieves structured plans from the database, associates basic information with classification results according to the greenhouse number, and analyzes specific implementation details, such as the type of soil treatment agent and application cycle for P1, and the concentration conversion basis for aboveground application. Based on this information, the system constructs a standardized guidance framework of "soil treatment - aboveground control - operation precautions," in which the dosage and concentration of agents are precisely calculated using formulas: In the P1 soil treatment, the dosage of Bacillus subtilis per unit area is q = 0.02 liters / square meter, the greenhouse area is S = 500 square meters, and the total dosage is calculated as Q = S × q, resulting in a dosage of Q = 10 liters. The operating tools used are a root dipping bucket and an electric flushing pump; When applying aboveground pesticides, the concentration of mancozeb stock solution is C1 = 80%, the target concentration is C2 = 0.2%, and the total liquid volume is V2 = 200 liters. The required stock solution is calculated as C1 × V1 = C2 × V2, resulting in a required volume of V1 = 0.5 liters, and the spraying site is specified as both the upper and lower surfaces of the leaves. The guidelines are pushed to farmers' mobile terminals in a combination of text and images, marking sampling points, application sites, and pesticide parameters. A feedback portal is also set up. After completing the operation, farmers need to fill in the actual dosage and upload on-site photos. The feedback information is automatically linked and stored to provide a basis for subsequent traceability and adjustment.

[0151] The 15th of each month is designated as a fixed monitoring date. The system sends reminders to farmers in advance, including sampling requirements, and retrieves previously established sampling points and greenhouse classification information to ensure consistent monitoring standards. Sampling strictly follows the S1 process: soil samples are collected from the root zone at marked points, mixed, and sent to the detection module for quantitative testing according to the same standards. March monitoring data showed a slight decrease in pathogen content in P1, a slight increase in P2, and relative stability in P3. In April, the Fusarium oxysporum content in P3 dropped to 0.6 × 10³ CFU / g, and both monitoring results were below the threshold for new greenhouses. Based on these trends, the system re-determines greenhouse types by combining the thresholds for new and old greenhouses: P1 and P2 remain the original types, while P3 is adjusted from a transitional greenhouse to a new greenhouse. Subsequently, the system automatically retrieves the new greenhouse control plan and sends adjustment notifications to P3 farmers via mobile terminals, simultaneously updating the implementation guidelines. The greenhouse type and implementation plan for P3 in the database are also updated accordingly, linking the adjustment basis with the monitoring data to complete the "monitoring-analysis-adjustment" closed loop.

[0152] After the complete implementation process, the disease control effect in the three greenhouses was significant: the disease incidence rate in the new greenhouses (P1 and P3) was controlled within 3%, and the disease incidence rate in the old greenhouse (P2) dropped from 15% before implementation to 8%. This not only avoided the problem of excessive use of pesticides in the new greenhouses and insufficient control in the old greenhouses, but also ensured that the measures were always adapted to the changes in pathogens through dynamic adjustments, providing a replicable practical example for the precise control of soil-borne diseases in strawberries.

[0153] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An intelligent management method applied to strawberry disease identification, characterized in that: Comprise the following steps: S1, collect strawberry planting shed body basic information and soil pathogen data, basic information contains shed body continuous planting year limit, nearly 3 years planting mode, soil pathogen data is obtained through quantitative detection shed body root zone soil pathogen content value; S2, based on the continuous planting year limit of shed body and the content of soil pathogen, the type of shed body is determined, the content threshold of two kinds of soil pathogen is calibrated through the field test in advance, which corresponds to the pathogen accumulation level of new shed and old shed respectively, and the classification result matched with the accumulation state of pathogen is formed according to the preset rule; S3, according to the classification result of shed body, the difference prevention and control scheme is generated, the scheme includes soil treatment and above-ground prevention and control two parts, different types of shed body correspond to different intensity of soil treatment measures and above-ground pesticide application measures; S4, the prevention and control scheme is converted into standardized execution guide, the operation steps of soil treatment, the dosage of pesticide and the concentration of above-ground pesticide application are determined through mobile terminal, and the user is guided to execute according to the guide; S5, regularly monitor the content of soil pathogen, select fixed time to collect shed body root zone soil sample every month, and obtain pathogen content data through quantitative detection to track the change trend of shed body pathogen; S6, according to the pathogen content data obtained by monitoring, adjust the type of shed body and the prevention and control scheme, re-determine the type of shed body according to the change of pathogen content, and switch to the prevention and control scheme of corresponding type of shed body at the same time.

2. The intelligent management method for strawberry disease identification according to claim 1, characterized in that: S1 further comprises the following contents: S1.1: set information input interface through shed body management terminal, the interface includes two compulsory collection items: one is shed body continuous planting year limit, which is filled by user according to actual planting period;The second is the planting mode in the past three years, set standardized options for user to choose, which covers common modes of strawberry continuous cropping and strawberry and other crops rotation;After the collection is completed, the terminal automatically checks the information format, removes the logically inconsistent data, and forms a structured shed body basic information data set; S1.2: according to the overall area of strawberry planting shed body and the planting row spacing of plants, the sampling area is determined: five sampling points are determined in the shed body according to the spatial distribution principle of edge-middle-center, the distance between edge point and shed body edge is consistent with the plant row spacing, and the middle and center points are evenly distributed in the remaining area, and permanent mark is made at each sampling point; S1.3: at each marked sampling point, use soil sampler to collect strawberry root zone soil sample vertically;After equal amount of soil is collected at each point, mix all the soil samples of the points uniformly, remove plant residues and stones in the sample, and form a mixed soil sample with full shed representation;The mixed soil sample is divided into sterile sampling container, and the container is labeled with shed body number and sampling date; S1.4: The pretreated mixed soil sample is sent to the detection module, which performs quantitative detection operation on the common soil-borne pathogens in strawberry planting; after the detection is completed, the detection module outputs the content data of each pathogen, and the data format is unified as a numerical form that can be directly used for calculation and comparison; at the same time, the detection module performs validity judgment on the data, and eliminates abnormal values caused by detection operation errors, and if there are abnormal values, the automatic retest process is triggered.

3. The intelligent management method for strawberry disease identification according to claim 1, characterized in that: S2 further comprises the following contents: S2.1: According to the shed foundation information data set and the soil pathogen content data, the two types of data are uniquely associated according to the shed number, forming a binary associated data set of continuous planting years-pathogen content; S2.2: Based on the binary associated data set constructed in S2.1, a combination of grouping statistics and association verification method is used for analysis: first, the data set is divided into ≤3 years group and >3 years group according to the continuous planting years, and the distribution range and central value of the pathogen content in each group are counted respectively; then the soil pathogen detection technology is used to carry out actual disease investigation on the two groups of sheds, verify the corresponding relationship between the pathogen content and the shed disease occurrence state in each group, and determine that when the pathogen content reaches a certain value, the shed disease occurrence presents the characteristic performance that the fluctuation does not exceed the preset range, and the pathogen content value that meets the characteristic performance is taken as the threshold preliminary reference of the pathogen content corresponding to the planting year group; S2.3: Based on the threshold preliminary reference determined in S2.2, field calibration test is carried out: select strawberry planting sheds matching the characteristics of two groups of planting years, set temporary threshold according to the value of threshold preliminary reference, use soil pathogen quantitative detection technology to regularly monitor the matching situation of threshold judgment results and actual pathogen accumulation and disease occurrence state under different temporary threshold values; Then according to the monitoring results, the temporary threshold value is adjusted gradually according to the preset standard, until the matching degree of the judgment results and the actual state of the shed keeps the fluctuation within the preset range, at this time the temporary threshold value is the final calibrated two types of soil pathogen content threshold: one type of threshold matches the pathogen accumulation level of the shed with continuous planting years not exceeding 3 years, which is the new shed threshold, and the other type of threshold matches the pathogen accumulation level of the shed with continuous planting years exceeding 3 years, which is the old shed threshold; According to the obtained new shed threshold and old shed threshold, combined with the planting mode in the past 3 years, the two types of basic thresholds are modified to form four types of thresholds respectively adapting to the sheds with continuous planting years ≤3 years+continuous cropping, continuous planting years ≤3 years+rotation, continuous planting years >3 years+continuous cropping and continuous planting years >3 years+rotation, and the four types of thresholds are stored in the system database; S2.4: Classification operation is performed according to the preset rules, the rules are as follows: Continuous planting years ≤3 years, and pathogen < new shed threshold is new shed; Continuous planting years >3 years, and pathogen > old shed threshold is old shed; The rest is transition shed; The transition shed pathogen content is in the transition shed threshold range and the planting mode is determined to be in the transition state, and the transition shed pathogen content is in the corresponding specific threshold critical interval and the planting mode is determined to be in the transition state. Then generate a structured classification result containing the shed number, continuous planting years, pathogen content, and determination type, and store it in the system database after associating the planting mode information in the past three years.

4. The intelligent management method for strawberry disease identification according to claim 1, characterized in that: S3 further includes the following: S3.1: According to the structured shed classification result, combined with the difference of pathogen accumulation level of three types of sheds, set the prevention and control intensity benchmark: new shed corresponds to basic prevention and control intensity, adapts to its low pathogen accumulation state; old shed corresponds to strengthened prevention and control intensity, adapts to its high pathogen accumulation state; transition shed corresponds to medium prevention and control intensity, adapts to its pathogen accumulation state between new shed and old shed; then store the shed type-prevention and control intensity association relationship to the system prevention and control scheme database, and clarify the prevention and control intensity boundary of each type of shed; S3.2: Based on the prevention and control intensity benchmark set in S3.1, combined with the planting mode in the past three years, match the corresponding soil treatment and above-ground control measures for each type of shed: New shed adopts soil treatment mode of biological agent root dipping combined with regular biological agent flushing, and above-ground control selects protective pesticide, and the pesticide application range focuses on strawberry plant foliage; Old shed adopts soil treatment mode of fumigant soil disinfection combined with biological agent soil mixing, and above-ground control selects therapeutic pesticide, and the pesticide application range covers strawberry plant foliage and soil around the root zone; Transition shed adopts soil treatment mode of fumigant soil disinfection combined with regular biological agent, and above-ground control selects pesticide with both protective and therapeutic effects, and the pesticide application range focuses on strawberry plant foliage and stem base; The biological agent, fumigant, and pesticide types involved in all measures are screened by calling the built-in planting region compliant agricultural input list in the system; S3.3: Integrate soil treatment measures and above-ground control measures into a structured prevention and control scheme, and the scheme field includes shed number, shed type, prevention and control intensity, soil treatment operation points, above-ground control operation points, and near-3-year planting mode adaptation instructions; then store the structured scheme to the system database.

5. The intelligent management method for strawberry disease identification according to claim 4, characterized in that: S4 further includes the following: S4.1: Retrieve the structured prevention and control scheme from the system database, associate the shed basic information and shed classification result according to the shed number, and analyze the execution information in each type of shed prevention and control scheme: soil treatment agent type, application sequence, operation requirements, and corresponding agent dosage, above-ground pesticide type, concentration conversion basis, spraying site, and pesticide application time period requirements; S4.2: Based on the analyzed execution information, construct a standardized execution guide framework of soil treatment module-above-ground control module-operation precautions: the soil treatment module is decomposed into operation steps in time sequence, and the agent dosage and operation tool of each step are determined according to the shed area, and the agent dosage calculation formula is as follows: Q=S×q; Wherein, Q represents the total dosage of soil treatment agent of a step; S represents the actual planting area of strawberry shed. q represents the recommended dosage per unit area of soil treatment agent at each step, and the data is derived from the soil treatment operation points of the structured prevention and control scheme; The ground prevention and control module clearly defines the pesticide concentration, the specific definition of the spraying site according to the proportional relationship between the concentration of the pesticide stock solution and the target application concentration; The operation precautions module marks the requirements and general operation taboos adapted to the planting mode of the greenhouse body in the past three years; wherein, the pesticide concentration conversion formula is as follows: C1×V1=C2×V2; Wherein, C1 represents the effective component concentration of the pesticide stock solution, the data is derived from the ground application pesticide type correlation information analyzed in S4.1; V1 represents the volume of the required pesticide stock solution, which is an unknown quantity to be calculated; C2 represents the target effective component concentration of the ground application, the data is derived from the ground prevention and control operation points of the structured prevention and control scheme; V2 represents the total liquid volume required for single application, which is derived from the application time period requirement correlation information analyzed in S4.1; S4.3: The completed standardized execution guide is pushed to the user account of the corresponding greenhouse body through the mobile terminal, and the push content adopts the form of combination of text and picture: step explanation is matched with greenhouse real scene mark graph, including soil treatment sampling point, spraying site schematic diagram, and then pesticide parameters are given according to soil treatment results; At the same time, the mobile terminal is set to execute feedback entrance, and the user needs to fill in the actual execution step, pesticide dosage, completion time and upload operation site photos after completing the operation, and the system automatically stores the feedback information and the corresponding greenhouse body prevention and control scheme, classification result into the database.

6. The intelligent management method for strawberry disease identification according to claim 1, characterized in that: S5 further includes the following contents: S5.1: According to the monitoring demand of the greenhouse, set the fixed time every month as the soil pathogen monitoring node, and push the monitoring reminder to the mobile terminal through the system, the reminder content contains the sampling time and sampling requirements of the corresponding greenhouse; S5.2: At the set monitoring time, execute the operation according to the sample collection process: at each sampling point, use the soil sampler to collect the strawberry root zone soil sample vertically; After collecting equal amount of soil at each point, mix all the point samples uniformly to form one mixed monitoring sample; Put the mixed monitoring sample into a sterile sampling container labeled with the greenhouse number and the monitoring date; S5.3: The pretreated mixed monitoring sample is sent to the detection module, and the operation is carried out according to the quantitative detection process: detection is carried out for common strawberry soil-borne pathogens, and unified numerical format of pathogen content data is output; The detection module judges the validity of the data, and eliminates the abnormal values caused by operation errors, and if there are abnormal values, the automatic trigger measurement process is triggered, and finally the effective monitoring data is output; The system associates the monitoring data of this time with the historical monitoring data of the greenhouse in chronological order to generate a structured trend record of greenhouse number-monitoring time-pathogen content, and stores it in the system database.

7. The intelligent management method for strawberry disease identification according to claim 1, characterized in that: S6 further includes the following contents: S6.1: Retrieve the structured trend record, new greenhouse threshold, old greenhouse threshold and greenhouse classification result from the system database; According to the above retrieved information, reclassify each type of greenhouse according to the preset judgment rule: For the current determination of the old shed, compare the current pathogen content with the old shed threshold value. If the pathogen content is lower than the old shed threshold value, re-determine it as a transition shed. For the current determination of the transition shed, extract its near two consecutive monitoring pathogen content data. If both data are lower than the new shed threshold value, re-determine it as a new shed. For the current determination of the new shed, compare the current pathogen content with the new shed threshold value. If the pathogen content is higher than the new shed threshold value, temporarily determine it as a transition shed. After re-determination, generate a structured classification adjustment record containing the shed number, original type, new type, and determination basis, and store it in the system database. S6.2: According to the classification adjustment record, the corresponding type of structured prevention and control scheme is retrieved from the system database according to the new shed type; the scheme switching notification is pushed to the user through the mobile terminal, and the notification content includes the new shed type, the operation points of the new prevention and control scheme, and the synchronous update of the standardized execution guide in the mobile terminal; at the same time, the system automatically updates the current shed type of the shed in the database to the re-determined type, replaces the current execution prevention and control scheme with the scheme corresponding to the new type, and associates the classification adjustment record and the monitoring data of this adjustment with the latest shed state and scheme information for the next regular monitoring and adjustment.

8. An intelligent management system for strawberry disease identification, applied to the intelligent management method for strawberry disease identification according to any one of claims 1-7, characterized in that: It includes a basic information acquisition module, a soil pathogen detection module, a data correlation analysis module, a shed type determination module, a prevention and control scheme generation module, an execution guide generation module, a mobile terminal interaction module, a data storage and management module, and a shed type and scheme adjustment module. The basic information acquisition module is used to collect the continuous planting years of the shed through a standardized input interface, the planting mode in the past three years, automatically verify the data and form a structured data set, and provide basic background data for subsequent processes; the soil pathogen detection module is used to perform quantitative detection of soil-borne pathogens on pretreated soil samples, output standardized data and eliminate outliers, and provide quantitative data for shed classification and pathogen trend tracking; the data correlation analysis module is used to correlate the basic information of the shed and the pathogen data, analyze the data rules through grouping statistics and disease correlation verification, and provide threshold reference for shed type determination; the shed type determination module is used to calibrate the pathogen threshold value through field test, determine the shed type according to the planting years + threshold value rule, and generate a structured classification result; The prevention and control scheme generation module is used to set the prevention and control intensity benchmark based on the shed type, call the compliant agricultural input product list to match the differentiated soil treatment and above-ground prevention and control measures, and integrate to form a structured prevention and control scheme; the execution guide generation module is used to analyze the execution information in the prevention and control scheme, construct a standardized guide framework, and calculate the dosage and concentration of pesticides through formula, forming an executable operation text; The mobile terminal interaction module is used for pushing the execution guidance of the combination of texts and images to the user, collecting user operation feedback data, pushing the notification and updating the guidance when the scheme is adjusted; the data storage and management module is used for storing the whole-process core data, including the shed body basic information, the pathogenic bacteria data, the associated data set, the shed body classification result, the structured prevention and control scheme, the execution guidance, the user feedback data, the pathogenic bacteria monitoring trend record, the classification adjustment record, and providing the data calling and association services for each module; the shed body type and scheme adjustment module is used for re-determining the shed body type according to the pathogenic bacteria monitoring data, calling the corresponding prevention and control scheme, pushing the adjustment notification and updating the execution guidance through the mobile terminal, so that the prevention and control measures are adapted to the pathogenic bacteria change of the shed body.

Images