A method and system for dynamic sensing and analysis of water and rainfall data

Abstract

This invention relates to the field of water and rainfall perception technology, providing a method and system for dynamic perception and analysis of water and rainfall data. The invention collects data from multiple water and rainfall locations according to the current perception cycle; calculates the future perception cycle; compares it with a preset cycle threshold to determine if there are any suspicious anomalies, and identifies suspicious locations when suspicious anomalies are found; extracts suspicious perception values ​​from suspicious locations and proving perception values ​​from multiple proving locations; calculates the predicted perception range of the suspicious locations and compares it with the suspicious perception values ​​to determine if it is a genuine anomaly. This method enables proactive anomaly identification and judgment, effectively ensuring the authenticity, accuracy, and reliability of the collected perception data.

Description

Technical Field

[0001] This invention belongs to the field of water and rainfall perception technology, and particularly relates to a method and system for dynamic perception and analysis of water and rainfall data. Background Technology

[0002] Rainfall and water condition awareness is a technology that monitors rainfall processes and the resulting hydrological changes. Through multi-source data collection and analysis, it enables collaborative understanding of rainfall and water conditions. Rainfall conditions mainly include data such as rainfall amount and intensity, while water conditions mainly include data such as water level and flow rate. Through rainfall and water condition awareness and data processing and analysis, it is possible to facilitate early warning and scientific decision support for scenarios such as floods, urban waterlogging, and water resource allocation. It is an important foundation for building a modern smart water conservancy system.

[0003] In existing technologies, in scenarios involving distributed sensing and monitoring of multiple water and rainfall locations, the ability to identify and judge abnormal situations is limited. It usually relies solely on the self-checking and automatic error reporting mechanisms of the sensors at each water and rainfall location, without any other effective means of proactively identifying and judging abnormalities. This makes it difficult to fully guarantee the authenticity, accuracy, and reliability of the sensing and collected data. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for dynamic sensing and analysis of water and rainfall data, aiming to solve the technical problems existing in the prior art mentioned in the background.

[0005] The embodiments of the present invention are implemented as follows: A method for dynamic sensing and analysis of water and rainfall data, the method specifically includes the following steps: According to the current sensing cycle, data is collected from multiple locations with varying water and rainfall conditions to obtain the current data. Based on the currently collected data, a dynamic adjustment analysis of perception is performed to calculate the future perception cycle; The future sensing period is compared with a preset period threshold to determine whether there is a suspicious anomaly. If there is a suspicious anomaly, the suspicious location is determined from multiple water and rain conditions. From the multiple water and rainfall locations, select multiple proof locations, and extract the suspicious perception values ​​of the suspicious locations and the proof perception values ​​of the multiple proof locations from the currently collected data; Based on multiple proof perception values, the predicted perception range of the suspicious location is calculated and compared with the suspicious perception values ​​to determine whether it is a real anomaly.

[0006] As a further limitation of the technical solution of this invention embodiment, the step of collecting data from multiple water and rainfall locations according to the current sensing cycle and obtaining the currently collected data specifically includes the following steps: Generate sensing and acquisition instructions according to the current sensing cycle; The sensing and acquisition command is sent to multiple water and rainfall locations; Receive feedback data from multiple locations of the water and rainfall conditions; The feedback data from multiple sources are processed to generate the current collected data.

[0007] As a further limitation of the technical solution of this embodiment of the invention, the step of performing dynamic adjustment analysis of perception based on the currently collected data and calculating the future perception cycle specifically includes the following steps: Acquire historical data; Multiple water and rainfall conditions were identified; According to multiple water and rainfall conditions, the historical and current data are dynamically analyzed, and the target type with the greatest dynamic change is selected from the multiple water and rainfall conditions. Extract the historical type data and current type data of the target type from the historical data and the current data. Based on the historical data, the current data, and the preset standard periodic data, dynamic adjustment analysis of perception is performed to calculate the future perception period.

[0008] As a further limitation of the technical solution of this embodiment of the invention, the calculation formula for the future sensing period is as follows: ; in, For the future perception cycle; For standard sensing cycles; The standard adjustment cycle; The preset target reference threshold; For the first The target perception values ​​for each water and rainfall location are totaling [number]. Location of water and rainfall conditions; For the first The target change value for each water and rainfall location.

[0009] As a further limitation of the technical solution of this embodiment of the invention, the step of comparing the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and determining the suspicious location from multiple water and rainfall locations when there is a suspicious anomaly, specifically includes the following steps: The future perception period is compared with a preset period threshold to determine whether there are any suspicious anomalies. If the future sensing period exceeds the period threshold, it is determined to be a suspicious anomaly; From the multiple target change values, select the largest suspicious change value; Based on the suspected change values, suspicious locations are determined from among the multiple water and rainfall locations.

[0010] As a further limitation of the technical solution of this invention embodiment, the step of selecting multiple verification locations from multiple water and rainfall location locations, and extracting the suspicious perception values ​​of the suspicious locations and the verification perception values ​​of the multiple verification locations from the currently collected data specifically includes the following steps: Obtain the relative distances between the suspected location and multiple other water and rainfall locations; Compare the relative distances of multiple locations and select multiple proof relative distances; Based on the relative distances of the multiple proofs, select multiple corresponding proof locations from the multiple water and rainfall locations; Extract the suspicious perception values ​​of the suspicious locations from the currently collected data; From the currently collected data, extract the proof perception values ​​of multiple proof locations.

[0011] As a further limitation of the technical solution of this embodiment of the invention, the step of calculating the predicted sensing range of the suspicious location based on multiple evidence sensing values, and comparing it with the suspicious sensing values ​​to determine whether it is a real anomaly specifically includes the following steps: The predicted sensing range of the suspected location is calculated based on multiple proof sensing values ​​and multiple proof relative distances. The suspected perceived value is compared with the predicted perceived range to determine whether it is a real anomaly. If the suspected perceived value is within the predicted perceived range, it is determined not to be a real anomaly; If the suspected perceived value is not within the predicted perceived range, it is determined to be a real anomaly.

[0012] As a further limitation of the technical solution of this embodiment of the invention, the calculation formula for the predicted sensing range is as follows: ; ; in, To predict the sensing range; For the first The proof perception values ​​for each proof location are: One proof location; For the first The relative distance between the proof location and the proof location of the suspected location; This is a preset standard range value.

[0013] A dynamic sensing and analysis system for hydrological and rainfall data, the system comprising a location periodic acquisition module, a dynamic adjustment analysis module, a suspected anomaly analysis module, a proof location selection module, and a true anomaly judgment module, wherein: The location periodic acquisition module is used to collect data from multiple water and rainfall locations according to the current sensing period and obtain the currently collected data; The dynamic adjustment analysis module is used to perform dynamic adjustment analysis of perception based on the currently collected data and calculate the future perception cycle. The suspicious anomaly analysis module is used to compare the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and when there is a suspicious anomaly, to determine the suspicious location from multiple water and rain conditions locations; The proof location selection module is used to select multiple proof locations from multiple water and rainfall location locations, and extract the suspicious perception value of the suspicious location and the proof perception value of the multiple proof locations from the currently collected data; The real anomaly judgment module is used to calculate the predicted perception range of the suspicious location based on multiple proof perception values, and compare it with the suspicious perception values ​​to determine whether it is a real anomaly.

[0014] As a further limitation of the technical solution of this embodiment of the invention, the dynamic adjustment analysis module specifically includes: Historical data acquisition unit, used to acquire historically collected data; The type determination unit is used to determine multiple water and rainfall conditions. The dynamic change analysis unit is used to perform dynamic change analysis on the historical data and the current data according to multiple water and rainfall conditions, and select the target type with the greatest dynamic change from the multiple water and rainfall conditions. A type data extraction unit is used to extract historical type data and current type data of the target type from the historical collected data and the current collected data; The future cycle calculation unit is used to perform dynamic adjustment analysis of perception based on the historical type data, the current type data, and the preset standard cycle data, and to calculate the future perception cycle.

[0015] Compared with the prior art, the beneficial effects of the present invention are: (1) This invention compares the future sensing period with the period threshold to determine whether there is a suspicious anomaly. When there is a suspicious anomaly, it calculates the predicted sensing range and compares the values ​​to determine whether it is a real anomaly. This enables proactive anomaly identification and judgment, effectively ensuring the authenticity, accuracy and reliability of the sensing data. (2) This invention selects the target type with the greatest dynamic change from multiple water and rainfall data types, extracts the historical and current data of the target type, and then performs dynamic adjustment analysis of perception according to the historical data, current data and standard period data to calculate the future perception period, thereby realizing dynamic perception adjustment of water and rainfall data, so that the perception period is related to the data change. By calculating the optimal future perception period, the burden of data collection, transmission and processing can be reduced, and the monitoring frequency and response speed can be ensured to meet the requirements of the current situation. Attached Figure Description

[0016] Figure 1 A flowchart of the dynamic sensing and analysis method for water and rainfall data provided in an embodiment of the present invention is shown; Figure 2 The following is an application architecture diagram of the dynamic sensing and analysis system for water and rainfall data provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] Understandably, in current scenarios involving distributed sensing and monitoring across multiple water and rainfall locations, the ability to identify and judge anomalies is limited. Typically, it relies solely on the self-checking and automatic error reporting mechanisms of the sensors at each location, without any other effective means of proactively identifying and judging anomalies. This makes it difficult to fully guarantee the authenticity, accuracy, and reliability of the collected sensing data.

[0019] To address the aforementioned problems, this invention discloses a dynamic sensing and analysis method and system for hydrological and rainfall data. This method collects data from multiple hydrological and rainfall locations according to the current sensing cycle, obtaining the currently collected data. Based on the current collected data, it performs dynamic sensing adjustment analysis to calculate the future sensing cycle. The future sensing cycle is compared with a preset cycle threshold to determine if there are any suspicious anomalies. If suspicious anomalies are found, suspicious locations are identified from the multiple hydrological and rainfall locations. Multiple proof locations are selected from the multiple hydrological and rainfall locations, and suspicious sensing values ​​for the suspicious locations and proof sensing values ​​for the multiple proof locations are extracted from the currently collected data. Based on the multiple proof sensing values, the predicted sensing range for the suspicious locations is calculated and compared with the suspicious sensing values ​​to determine if it is a genuine anomaly. This method can compare the future sensing cycle with the cycle threshold to determine if there are any suspicious anomalies, and when suspicious anomalies are found, calculate the predicted sensing range and compare the values ​​to determine if it is a genuine anomaly, thereby achieving proactive anomaly identification and judgment, effectively ensuring the authenticity, accuracy, and reliability of the sensed and collected data.

[0020] Specifically, Figure 1 A flowchart of the dynamic sensing and analysis method for water and rainfall data provided in an embodiment of the present invention is shown.

[0021] In a preferred embodiment of the present invention, a method for dynamic sensing and analysis of water and rainfall data specifically includes the following steps: Step S101: Collect data from multiple water and rainfall locations according to the current sensing cycle to obtain the current data.

[0022] In this embodiment of the invention, when the sensing and monitoring time corresponding to the current sensing cycle is reached, a sensing and acquisition instruction is generated and then sent to multiple water and rainfall locations. By receiving feedback data transmitted from multiple water and rainfall locations and organizing and recording the multiple feedback data, the current acquisition data corresponding to the current sensing cycle is generated.

[0023] Specifically, in another preferred embodiment provided by the present invention, the step of collecting data from multiple water and rainfall locations according to the current sensing period and obtaining the currently collected data specifically includes the following steps: Generate sensing and acquisition instructions according to the current sensing cycle; The sensing and acquisition command is sent to multiple water and rainfall locations; Receive feedback data from multiple locations of the water and rainfall conditions; The feedback data from multiple sources are processed to generate the current collected data.

[0024] Furthermore, the dynamic sensing and analysis method for water and rainfall data also includes the following steps: Step S102: Based on the currently collected data, perform dynamic adjustment analysis of perception and calculate the future perception cycle.

[0025] In this embodiment of the invention, historical data is acquired, and multiple water and rainfall conditions are identified. Then, according to these conditions, dynamic changes are analyzed on both the historical and current data. The type monitoring change values ​​for all water and rainfall locations under different conditions are statistically analyzed. These change values ​​are compared, and the largest change value is selected as the target type. Next, historical and current type data for the target type are extracted from the historical and current data. Then, based on the historical, current, and preset standard period data, a dynamic adjustment analysis of the sensing period is performed to calculate the future sensing period. Specifically, the formula for calculating the future sensing period is: ; in, For the future perception cycle; For standard sensing cycles; The standard adjustment cycle; The preset target reference threshold; For the first The target perception values ​​for each water and rainfall location are totaling [number]. Location of water and rainfall conditions; For the first The target change value for each water and rainfall location.

[0026] Understandably, the first The target change value of the first water and rainfall location is the first The result is obtained by subtracting the current monitoring value of the target type at each water and rainfall location from the historical monitoring data.

[0027] It is understandable that both the standard sensing cycle and the standard adjustment cycle can be obtained from preset standard cycle data.

[0028] It is understood that, in this embodiment of the invention, historical data refers to data collected from multiple water and rainfall locations in the previous period compared to the current sensing period.

[0029] It is understandable that multiple types of water and rainfall conditions can include rainfall amount, rainfall intensity, water level, flow rate, etc.

[0030] It is understood that, in the embodiments of the present invention, the type monitoring change value is the value obtained by multiplying the actual monitoring change value of different water and rainfall conditions by the corresponding adjustment coefficient, and different water and rainfall conditions have different adjustment coefficients.

[0031] Specifically, in another preferred embodiment provided by the present invention, the step of performing dynamic adjustment analysis based on the currently collected data and calculating the future sensing cycle specifically includes the following steps: Acquire historical data; Multiple water and rainfall conditions were identified; According to multiple water and rainfall conditions, the historical and current data are dynamically analyzed, and the target type with the greatest dynamic change is selected from the multiple water and rainfall conditions. Extract the historical type data and current type data of the target type from the historical data and the current data. Based on the historical data, the current data, and the preset standard periodic data, dynamic adjustment analysis of perception is performed to calculate the future perception period.

[0032] Furthermore, the dynamic sensing and analysis method for water and rainfall data also includes the following steps: Step S103: Compare the future sensing period with the preset period threshold to determine whether there is a suspicious anomaly, and if there is a suspicious anomaly, determine the suspicious location from multiple water and rain conditions.

[0033] In this embodiment of the invention, a suspicious anomaly is determined by comparing the future sensing period with a preset period threshold. Specifically, if the future sensing period is greater than the period threshold, a suspicious anomaly is determined. In this case, multiple target change values ​​are compared, and the largest suspicious change value is selected from the multiple target change values. Based on the suspicious change value, the corresponding suspicious location is determined from multiple water and rainfall locations. If the future sensing period is not greater than the period threshold, no suspicious anomaly is determined. In this case, no further processing is required.

[0034] Specifically, in another preferred embodiment provided by the present invention, the step of comparing the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and when there is a suspicious anomaly, determining the suspicious location from multiple water and rainfall locations specifically includes the following steps: The future perception period is compared with a preset period threshold to determine whether there are any suspicious anomalies. If the future sensing period exceeds the period threshold, it is determined to be a suspicious anomaly; From the multiple target change values, select the largest suspicious change value; Based on the suspected change values, suspicious locations are determined from among the multiple water and rainfall locations.

[0035] Furthermore, the dynamic sensing and analysis method for water and rainfall data also includes the following steps: Step S104: Select multiple proof locations from the multiple water and rainfall locations, and extract the suspicious perception values ​​of the suspicious locations and the proof perception values ​​of the multiple proof locations from the currently collected data.

[0036] In this embodiment of the invention, the relative distances between a suspected location and multiple other water and rainfall locations are obtained from preset location recording data. The relative distances of multiple locations are compared, and the relative distances of multiple locations that are less than a preset distance threshold are selected as the proof relative distances. Then, based on the multiple proof relative distances, multiple corresponding proof locations are selected from the multiple water and rainfall locations. After that, the suspected perception value of the target type of the suspected location is extracted from the currently collected data, and the proof perception value of the target type of the multiple proof locations is extracted.

[0037] Specifically, in another preferred embodiment provided by the present invention, the step of selecting multiple verification locations from multiple water and rainfall location locations, and extracting the suspicious perception values ​​of the suspicious locations and the verification perception values ​​of the multiple verification locations from the currently collected data specifically includes the following steps: Obtain the relative distances between the suspected location and multiple other water and rainfall locations; Compare the relative distances of multiple locations and select multiple proof relative distances; Based on the relative distances of the multiple proofs, select multiple corresponding proof locations from the multiple water and rainfall locations; Extract the suspicious perception values ​​of the suspicious locations from the currently collected data; From the currently collected data, extract the proof perception values ​​of multiple proof locations.

[0038] Furthermore, the dynamic sensing and analysis method for water and rainfall data also includes the following steps: Step S105: Calculate the predicted sensing range of the suspicious location based on multiple proof sensing values, and compare it with the suspicious sensing values ​​to determine whether it is a real anomaly.

[0039] In this embodiment of the invention, based on multiple evidence sensing values ​​and multiple evidence relative distances, a predictive analysis of data impact is performed to calculate the predicted sensing range of the suspicious location. Then, the suspicious sensing value is compared with the predicted sensing range to determine whether it is a genuine anomaly. Specifically, if the suspicious sensing value is within the predicted sensing range, it is determined not to be a genuine anomaly; if the suspicious sensing value is not within the predicted sensing range, it is determined to be a genuine anomaly. In this case, the suspicious location is identified as an anomaly location, and a corresponding anomaly alarm message is generated. An anomaly alarm is triggered, and feedback data from the anomaly location in the currently collected data is removed. Specifically, the formula for calculating the predicted sensing range is: ; ; in, To predict the sensing range; For the first The proof perception values ​​for each proof location are: One proof location; For the first The relative distance between the proof location and the proof location of the suspected location; This is a preset standard range value.

[0040] Specifically, in another preferred embodiment provided by the present invention, the step of calculating the predicted sensing range of the suspicious location based on a plurality of the proven sensing values, and comparing it with the suspicious sensing values ​​to determine whether it is a real anomaly, specifically includes the following steps: The predicted sensing range of the suspected location is calculated based on multiple proof sensing values ​​and multiple proof relative distances. The suspected perceived value is compared with the predicted perceived range to determine whether it is a real anomaly. If the suspected perceived value is within the predicted perceived range, it is determined not to be a real anomaly; If the suspected perceived value is not within the predicted perceived range, it is determined to be a real anomaly.

[0041] Furthermore, Figure 2 The following is an application architecture diagram of the dynamic sensing and analysis system for water and rainfall data provided in an embodiment of the present invention.

[0042] Specifically, in another preferred embodiment provided by the present invention, a dynamic sensing and analysis system for water and rainfall data includes: The location periodic acquisition module 101 is used to collect data from multiple water and rainfall locations according to the current sensing period and obtain the current data.

[0043] In this embodiment of the invention, when the sensing and monitoring time corresponding to the current sensing cycle is reached, the location cycle acquisition module 101 generates a sensing acquisition instruction and then sends the sensing acquisition instruction to multiple water and rainfall locations. By receiving feedback data transmitted from multiple water and rainfall locations and organizing and recording the multiple feedback data, the current acquisition data corresponding to the current sensing cycle is generated.

[0044] The dynamic adjustment analysis module 102 is used to perform dynamic adjustment analysis of perception based on the currently collected data and calculate the future perception cycle.

[0045] In this embodiment of the invention, the dynamic adjustment analysis module 102 acquires historical data and determines multiple water and rainfall conditions. Then, according to these multiple water and rainfall conditions, it performs dynamic change analysis on the historical and current data, statistically analyzes the type monitoring change values ​​for all water and rainfall locations under different water and rainfall conditions, compares these multiple type monitoring change values, selects the largest type monitoring change value, and determines its corresponding water and rainfall condition type as the target type. Next, it extracts historical and current type data of the target type from the historical and current data, and then performs dynamic adjustment analysis of the sensing cycle according to the historical type data, current type data, and preset standard cycle data to calculate the future sensing cycle. Specifically, the formula for calculating the future sensing cycle is: ; in, For the future perception cycle; For standard sensing cycles; The standard adjustment cycle; The preset target reference threshold; For the first The target perception values ​​for each water and rainfall location are totaling [number]. Location of water and rainfall conditions; For the first The target change value for each water and rainfall location.

[0046] Specifically, in another preferred embodiment provided by the present invention, the dynamic adjustment analysis module 102 specifically includes: Historical data acquisition unit, used to acquire historically collected data; The type determination unit is used to determine multiple water and rainfall conditions. The dynamic change analysis unit is used to perform dynamic change analysis on the historical data and the current data according to multiple water and rainfall conditions, and select the target type with the greatest dynamic change from the multiple water and rainfall conditions. A type data extraction unit is used to extract historical type data and current type data of the target type from the historical collected data and the current collected data; The future cycle calculation unit is used to perform dynamic adjustment analysis of perception based on the historical type data, the current type data, and the preset standard cycle data, and to calculate the future perception cycle.

[0047] Furthermore, the dynamic sensing and analysis system for water and rainfall data also includes: The suspicious anomaly analysis module 103 is used to compare the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and when there is a suspicious anomaly, to determine the suspicious location from multiple water and rain conditions.

[0048] In this embodiment of the invention, the suspicious anomaly analysis module 103 determines whether there is a suspicious anomaly by comparing the future sensing period with a preset period threshold. Specifically, if the future sensing period is greater than the period threshold, a suspicious anomaly is determined. At this time, by comparing multiple target change values, the largest suspicious change value is selected from the multiple target change values, and the corresponding suspicious location is determined from multiple water and rainfall locations according to the suspicious change value. If the future sensing period is not greater than the period threshold, no suspicious anomaly is determined. At this time, no further processing is required.

[0049] The proof location selection module 104 is used to select multiple proof locations from multiple water and rainfall location locations, and extract the suspicious perception value of the suspicious location and the proof perception value of the multiple proof locations from the currently collected data.

[0050] In this embodiment of the invention, the proof location selection module 104 obtains the relative distance between the suspected location and multiple other water and rainfall locations from the preset location record data, compares the multiple relative distances, selects the multiple relative distances that are less than the preset distance threshold as the proof relative distances, and then selects multiple corresponding proof locations from the multiple water and rainfall locations based on the multiple proof relative distances. After that, it extracts the suspected perception value of the target type of the suspected location from the currently collected data, and extracts the proof perception value of the target type of the multiple proof locations.

[0051] The real anomaly judgment module 105 is used to calculate the predicted perception range of the suspicious location based on multiple proof perception values, and compare it with the suspicious perception values ​​to determine whether it is a real anomaly.

[0052] In this embodiment of the invention, the real anomaly judgment module 105 performs predictive analysis of data impact based on multiple evidence perception values ​​and multiple evidence relative distances, calculates the predicted perception range of the suspicious location, and then compares the suspicious perception value with the predicted perception range to determine whether it is a real anomaly. Specifically, if the suspicious perception value is within the predicted perception range, it is determined not to be a real anomaly; if the suspicious perception value is not within the predicted perception range, it is determined to be a real anomaly. At this time, the suspicious location is identified as an anomaly location, and corresponding anomaly alarm information is generated to trigger an anomaly alarm. Furthermore, feedback data from the anomaly location in the currently collected data is removed. Specifically, the calculation formula for the predicted perception range is: ; ; in, To predict the sensing range; For the first The proof perception values ​​for each proof location are: One proof location; For the first The relative distance between the proof location and the proof location of the suspected location; This is a preset standard range value.

[0053] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A water regime data dynamic sensing and analyzing method, characterized in that, The method specifically includes the following steps: According to the current sensing cycle, data is collected from multiple locations with varying water and rainfall conditions to obtain the current data. Based on the currently collected data, a dynamic adjustment analysis of perception is performed to calculate the future perception cycle; The future sensing period is compared with a preset period threshold to determine whether there is a suspicious anomaly. If there is a suspicious anomaly, the suspicious location is determined from multiple water and rain conditions. From the multiple water and rainfall locations, select multiple proof locations, and extract the suspicious perception values ​​of the suspicious locations and the proof perception values ​​of the multiple proof locations from the currently collected data; Based on multiple proof perception values, the predicted perception range of the suspicious location is calculated and compared with the suspicious perception values ​​to determine whether it is a real anomaly.

2. The water regime data dynamic sensing and analyzing method according to claim 1, characterized in that, The process of collecting data from multiple water and rainfall locations according to the current sensing cycle and obtaining the currently collected data specifically includes the following steps: Generate sensing and acquisition instructions according to the current sensing cycle; The sensing and acquisition command is sent to multiple water and rainfall locations; Receive feedback data from multiple locations of the water and rainfall conditions; The feedback data from multiple sources are processed to generate the current collected data.

3. The method of claim 1, wherein, The step of performing dynamic adjustment analysis based on the currently collected data and calculating the future sensing cycle specifically includes the following steps: Obtain historical data; Multiple water and rainfall conditions were identified; According to multiple water and rainfall conditions, the historical and current data are dynamically analyzed, and the target type with the greatest dynamic change is selected from the multiple water and rainfall conditions. Extract the historical type data and current type data of the target type from the historical data and the current data. Based on the historical data, the current data, and the preset standard periodic data, dynamic adjustment analysis of perception is performed to calculate the future perception period.

4. The water regime data dynamic sensing and analyzing method according to claim 3, characterized in that, The formula for calculating the future sensing period is: ； wherein, is a future sensing period; is a standard sensing period; is a standard adjustment period; is a preset target reference threshold value; is a target sensing value of the th water regime position, and there are water regime positions in total; is a target change value of the th water regime position.

5. The dynamic sensing and analysis method for water and rainfall data according to claim 4, characterized in that, The step of comparing the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and determining the suspicious location from multiple water and rainfall locations when a suspicious anomaly is found, specifically includes the following steps: The future perception period is compared with a preset period threshold to determine whether there are any suspicious anomalies. If the future sensing period exceeds the period threshold, it is determined to be a suspicious anomaly; From the multiple target change values, select the largest suspicious change value; Based on the suspected change values, suspicious locations are determined from among the multiple water and rainfall locations.

6. The dynamic sensing and analysis method for water and rainfall data according to claim 1, characterized in that, The step of selecting multiple verification locations from multiple water and rainfall location locations and extracting the suspicious perception values ​​of the suspicious locations and the verification perception values ​​of the multiple verification locations from the currently collected data specifically includes the following steps: Obtain the relative distances between the suspected location and multiple other water and rainfall locations; Compare the relative distances of multiple locations and select multiple proof relative distances; Based on the relative distances of the multiple proofs, select multiple corresponding proof locations from the multiple water and rainfall locations; Extract the suspicious perception values ​​of the suspicious locations from the currently collected data; From the currently collected data, extract the proof perception values ​​of multiple proof locations.

7. The dynamic sensing and analysis method for water and rainfall data according to claim 6, characterized in that, The step of calculating the predicted sensing range of the suspicious location based on multiple evidence sensing values ​​and comparing it with the suspicious sensing values ​​to determine whether it is a real anomaly specifically includes the following steps: The predicted sensing range of the suspected location is calculated based on multiple proof sensing values ​​and multiple proof relative distances. The suspected perceived value is compared with the predicted perceived range to determine whether it is a real anomaly. If the suspected perceived value is within the predicted perceived range, it is determined not to be a real anomaly; If the suspected perceived value is not within the predicted perceived range, it is determined to be a real anomaly.

8. The dynamic sensing and analysis method for water and rainfall data according to claim 7, characterized in that, The formula for calculating the predicted sensing range is: ； ； in, To predict the sensing range; For the first The proof perception values ​​for each proof location are: One proof location; For the first The relative distance between the proof location and the proof location of the suspected location; This is a preset standard range value.

9. A dynamic sensing and analysis system for water and rainfall data, characterized in that, The system includes a location periodic acquisition module, a dynamic adjustment analysis module, a suspicious anomaly analysis module, a proof location selection module, and a genuine anomaly judgment module, wherein: The location periodic acquisition module is used to collect data from multiple water and rainfall locations according to the current sensing period and obtain the currently collected data; The dynamic adjustment analysis module is used to perform dynamic adjustment analysis of perception based on the currently collected data and calculate the future perception cycle. The suspicious anomaly analysis module is used to compare the future sensing period with a preset period threshold to determine whether there is a suspicious anomaly, and when there is a suspicious anomaly, to determine the suspicious location from multiple water and rain conditions locations; The proof location selection module is used to select multiple proof locations from multiple water and rainfall location locations, and extract the suspicious perception value of the suspicious location and the proof perception value of the multiple proof locations from the currently collected data; The real anomaly judgment module is used to calculate the predicted perception range of the suspicious location based on multiple proof perception values, and compare it with the suspicious perception values ​​to determine whether it is a real anomaly.

10. The dynamic sensing and analysis system for water and rainfall data according to claim 9, characterized in that, The dynamic adjustment analysis module specifically includes: Historical data acquisition unit, used to acquire historically collected data; The type determination unit is used to determine multiple water and rainfall conditions. The dynamic change analysis unit is used to perform dynamic change analysis on the historical data and the current data according to multiple water and rainfall conditions, and select the target type with the greatest dynamic change from the multiple water and rainfall conditions. A type data extraction unit is used to extract historical type data and current type data of the target type from the historical collected data and the current collected data; The future cycle calculation unit is used to perform dynamic adjustment analysis of perception based on the historical type data, the current type data, and the preset standard cycle data, and to calculate the future perception cycle.

Images