Mosquito-borne data driven task generation management system and method

Abstract

The invention discloses a mosquito-borne data driven task generation management system and method, and relates to the field of task management, and the system comprises a mosquito-borne data collection module, a mosquito-borne data analysis module, a cross-unit data collaboration mechanism module and a task management module. According to the invention, the task generation is driven through the mosquito-borne data, so that efficient and accurate mosquito-borne monitoring of the target area is realized. Based on a real-time data stream, the size of a regional basic unit is flexibly adjusted in combination with a visual monitoring unit of a geographic information system, and task allocation is optimized through multi-level feature extraction. The data scarcity monitoring unit intelligently obtains assistance data through a cross-unit data collaboration mechanism, and ensures the monitoring coverage of the whole area. Dynamic task scheduling and resource allocation are realized, and the priority of the monitoring task and the rationality of resource allocation are ensured. The monitoring efficiency is improved, the data quality is ensured, the resource allocation is optimized, the mosquito-borne prevention and control decision can be effectively supported, and the public health management capability is enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of task management, and in particular to a mosquito vector data-driven task generation management system and method. BACKGROUND

[0002] Vector-borne data generally refers to monitoring and statistical data related to mosquito-borne diseases such as dengue, Zika, chikungunya, malaria, etc. As the main vector of disease transmission, mosquitoes are involved in their distribution, density, species, activity cycle, breeding conditions, and living environment data. The collection, analysis, and management of mosquito vector data are crucial for effective prediction and control of mosquito-related public health issues.

[0003] Data collection techniques use sensor networks, remote sensing devices, and Internet of Things devices to collect mosquito data in target areas in real time. Sensors can monitor mosquito numbers, environmental conditions such as humidity, temperature, and water accumulation in real time and upload data to the monitoring platform. In addition, spatio-temporal data analysis techniques and machine learning methods are widely used in the processing and analysis of collected data to identify mosquito distribution and predict mosquito activity trends.

[0004] However, data scarcity and quality issues are major challenges, especially in some areas where data collection is limited by environmental and technical constraints, resulting in data scarcity or low quality, which cannot ensure the representativeness and reliability of the data. SUMMARY

[0005] The present application provides a mosquito vector data-driven task generation management system, comprising: A mosquito vector data collection module for collecting mosquito vector data in a target area from external interfaces and sensors through real-time data streams, and transmitting the preprocessed data to a mosquito vector data analysis module.

[0006] A mosquito vector data analysis module for feature extraction of mosquito vector data in a target area to obtain mosquito vector features in the target area, and map visualization of the target area using geographic information systems to obtain monitoring units in the target area.

[0007] A cross-unit data collaboration mechanism module for transmitting mosquito vector data from other monitoring units in the target area to assist a monitoring unit in generating a monitoring task when a monitoring unit in the target area is determined to be a data-scarce unit.

[0008] A task management module for managing monitoring tasks of each monitoring unit in the target area, scheduling and allocating resources for each monitoring unit.

[0009] In addition, a mosquito vector data-driven task generation management method, specifically comprising: The mosquito-borne data of the target area is collected from external interfaces and sensors through real-time data streams, and after preprocessing, it is transmitted to the mosquito-borne data analysis module.

[0010] The mosquito-borne data of the target area is extracted, and the mosquito-borne features of the target area are obtained. The target area is visualized by a geographic information system, and the monitoring unit of the target area is obtained.

[0011] When a certain monitoring unit of the target area is determined to be a data scarce unit, mosquito-borne data is transmitted from other monitoring units of the target area to assist the monitoring unit in generating a monitoring task.

[0012] The monitoring tasks of each monitoring unit of the target area are managed, and the monitoring tasks of each monitoring unit are scheduled and resource allocated.

[0013] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: (1) The present application provides a mosquito-borne data-driven task generation management system, which collects mosquito-borne data through real-time data streams and visualizes the data in combination with a geographic information system, ensuring accurate division and dynamic adjustment of monitoring units. Especially through feature extraction, including density features, periodic fluctuation features and environmental features, the system can flexibly determine the size of the monitoring unit according to the regional characteristics, thereby improving the accuracy of the monitoring area. Through this data-driven dynamic division and real-time adjustment, mosquito-borne monitoring tasks can be timely and reasonably allocated at different risk levels, ensuring the accurate implementation of monitoring tasks.

[0014] (2) The present application realizes data sharing and cooperation among different monitoring units in the region through a cross-unit data collaboration mechanism. The system evaluates the demand according to the data scarcity type (such as insufficient data volume, insufficient data quality or delayed data timeliness), and allocates corresponding assistance tasks for data scarce units. Through the collaborative transmission of data by the assistance units, and combined with the comprehensive evaluation of multiple factors such as data volume, data quality, timeliness, etc., the system can effectively support data scarce areas and reduce monitoring blind spots. This mechanism not only improves the availability of data, but also ensures the stability and responsiveness of the system, especially in areas with highly uneven mosquito distribution and transmission risk.

[0015] (3) The application adjusts the priority of each monitoring unit flexibly through real-time data changes, and intelligently allocates according to data feedback, ensuring that the task resources of each monitoring unit are reasonably configured. During task execution, the system can track the task progress in real time, monitor the resource usage, automatically identify and correct abnormal situations in task execution. This process not only ensures efficient execution of tasks, but also automatically generates data reports to summarize the task execution, data quality and resource consumption in detail, and uploads them to the management platform to form a closed-loop management process. This intelligent task scheduling and resource allocation greatly improves work efficiency and response speed.

[0016] (4) The application introduces a data quality verification mechanism, and implements strict transmission path quality verification for data scarce units with data quality deficiencies and time delay. Through hash calculation and timestamp mechanism, the system can monitor the integrity and timeliness of data transmission in real time, ensuring that the data is not damaged and arrives in time during transmission. This measure effectively solves the problems of data loss and transmission delay in high-noise environment, improves the control ability of the system on data quality. At the same time, through multi-level and all-round data transmission quality inspection, it ensures that the final returned data is not only accurate, but also has high real-time performance, so that the quality of monitoring data is greatly improved, and the overall reliability and security of the system is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0018] Figure 1 It is a schematic diagram of system module.

[0019] Figure 2 It is a schematic diagram of method flow.

[0020] Figure 3 It is a schematic diagram of logical flow.

[0021] Figure 4 It is an interface diagram a of task management system.

[0022] Figure 5 It is an interface diagram b of task management system. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0024] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms “first,” “second,” and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms “an,” “a,” or “the,” and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms “comprising,” “including,” or “including,” and similar terms mean that the element or object preceding the word encompasses the element or object listed following the word and its equivalents, without excluding other elements or objects. The terms “connected,” “linked,” or “connected,” and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0025] It should be noted that the terms "up", "down", "left", "right", "front", and "back" used in this invention are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0026] Please see as follows Figure 1 As shown, this is a mosquito-borne data-driven task generation management system and method according to an embodiment of the present invention, specifically including: like Figure 3The diagram illustrates the logical flow of this invention. The entire process begins with mosquito vector data collection, followed by analysis. This analysis phase extracts mosquito vector characteristics and facilitates collaborative monitoring task data processing. The extracted mosquito vector characteristics are visualized using a geographic information system (GIS). Based on the visualization results, monitoring units are defined. This phase also integrates with the task management module. After unit definition, it first determines whether a basic unit exceeds a threshold. If so, it is marked as a key monitoring unit; otherwise, it proceeds to the risk assessment phase. The risk assessment phase calculates periodic fluctuation deviation and environmental characteristic deviation, then calculates a risk assessment index based on these two deviations. Subsequently, depending on whether the index exceeds a threshold, units are marked as secondary key monitoring units or ordinary monitoring units. The task management module manages task scheduling and resource allocation, tracks task execution progress, and checks for abnormal task status. If abnormal, the status is automatically adjusted; otherwise, task results are summarized, a data report is generated, and uploaded to the task management platform. The collaborative monitoring task data processing simultaneously determines scarce data units and verifies the quality of scarce data types. When determining data scarcity units, the criteria for data scarcity are determined by combining the markings of key, secondary key, and ordinary monitoring units. If the criteria are met, the assisting unit will transmit the data. Before transmission, the assisting unit will be selected and the data will be compressed before the compressed data transmission is completed. The data scarcity type quality verification will first check the quality of the data transmission path and confirm the data integrity through hash verification. If the hash values ​​are inconsistent, the data is considered corrupted; if they are consistent, the data transmission is considered complete. In the assisting unit selection stage, suitable assisting units will be selected before assisting data transmission.

[0027] It should be noted that, in the embodiments of the present invention, the various mapping sets used are predefined sets used to associate two parameters with different dimensions, quantifying the relationship between them through preset rules. In the embodiments of the present invention, the mapping set is in tabular form, recording the correspondence between the two parameters, and is constructed based on historical data, gradually adjusting the correspondence through multiple simulations to generate the mapping set.

[0028] The mosquito vector data acquisition module is used to collect mosquito vector data from external interfaces and sensors in the target area through real-time data streams, and then transmit the pre-processed data to the mosquito vector data analysis module.

[0029] In this embodiment of the invention, mosquito-borne data includes mosquito population, climate data, and the area of ​​water accumulation. Real-time data is collected using real-time data streaming technology; in this embodiment, Apache Kafka is employed. Mosquito population is obtained via infrared sensors. Climate data, including average temperature, average humidity, average precipitation, and average wind speed of the target area, is obtained via IoT sensors. The area of ​​water accumulation is measured using remote sensing data. It should be noted that the average temperature, average humidity, average precipitation, and average wind speed here refer to the average of the geographical properties of data obtained from multiple sensors within the target area, not the average of temporal properties.

[0030] Data errors caused by sensor malfunctions are removed using statistical methods and anomaly detection algorithms. Missing values ​​are filled using linear interpolation to ensure data integrity. Noise reduction is achieved using Kalman filtering to eliminate noise and ensure data smoothness. Data standardization and normalization allow data at different scales to be compared and analyzed under the same standard; Z-score standardization is employed.

[0031] The mosquito vector data analysis module is used to extract features from mosquito vector data in the target area, obtain the mosquito vector characteristics of the target area, and use a geographic information system to visualize the target area on a map to obtain the monitoring units of the target area.

[0032] The ratio of mosquito population to target area is calculated to obtain the total density characteristics of mosquito vector data in the target area.

[0033] ; Where D is the total density of mosquito vector data in the target area, N is the number of mosquitoes in the mosquito vector data, and A is the area of ​​the target area.

[0034] Time series analysis was used to extract the characteristics of mosquito population changes over time, including daily, weekly, and monthly average numbers. Fourier transform was then used to capture the overall periodic fluctuation characteristics of mosquito vector data in the target area.

[0035] ; in, Here are the Fourier coefficients at frequency k. The target area is represented by a time series of mosquito populations, specifically {d1,d2,d3,...,dn}, where j=1,2,3,...,n, j is the time series number, and n is the time length.

[0036] based on Quantifying the characteristics of periodic fluctuations, specifically including: ; in, The overall periodic fluctuation characteristics of mosquito vector data in the target area. It represents the maximum frequency of the low-frequency components, reflecting the intensity of periodic fluctuations.

[0037] In the extraction of climate and environmental characteristics, temperature, humidity, precipitation, and water accumulation area are important factors affecting mosquito activity. The daily average and standard deviation of climate data are calculated to analyze the relationship between the environment and mosquito population, thereby obtaining the overall environmental characteristics of mosquito vector data in the target area. The temperature, humidity, precipitation, and water accumulation area of ​​the target area are collected, and the daily average temperature, humidity, precipitation, and water accumulation area of ​​the target area are calculated. The daily average temperature, humidity, precipitation, and water accumulation area of ​​the target area are then input into the standard deviation calculation formula to obtain the standard deviation of temperature, humidity, precipitation, and water accumulation area of ​​the target area.

[0038] Simultaneously, the daily average temperature, daily average humidity, daily average precipitation, and daily average water accumulation area of ​​the target area are input into the Pearson correlation coefficient calculation formula. Combined with the number of mosquitoes, the Pearson correlation coefficients between the temperature, humidity, precipitation, and water accumulation area of ​​the target area and the number of mosquitoes are obtained.

[0039] The Pearson correlation coefficients between the temperature, humidity, precipitation, and water accumulation area of ​​the target area and the number of mosquitoes are input into the pre-set mapping set of Pearson correlation coefficients and environmental feature weighting factors in the database. This yields the environmental feature weighting factors corresponding to the temperature, humidity, precipitation, and water accumulation area of ​​the target area. The standard deviations of temperature, humidity, precipitation, and water accumulation area of ​​the target area are multiplied by the corresponding environmental feature weighting factors and then summed to obtain the total environmental characteristics of the mosquito vector data of the target area.

[0040] Spatial data of the target area is acquired, including administrative divisions, geographic coordinates, and land use types. Based on wireless positioning technology, the positioning information of mosquito vector monitoring equipment and sensors is collected. The map of the target area is loaded into the geographic information system, and the density characteristics of the mosquito vector data of the target area are overlaid with the map to visualize the density characteristics. It should be noted that, in this embodiment of the invention, map loading needs to support map overlay and multi-level data overlay.

[0041] like Figure 4 and Figure 5 As shown, this is a map loading page of the task management system in another embodiment of the invention, which includes resource statistics, disinfection area, and epidemic area grid management. The map intuitively displays the distribution of various resources in the system, supports dynamic adjustment of task allocation, and improves task management efficiency.

[0042] It should be noted that spatial data of the target area can be obtained through remote sensing imagery.

[0043] Based on the total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area, the size of the basic unit in the target area is determined. The target area is divided into basic units, and the density characteristics, periodic fluctuation characteristics, and environmental characteristics of each basic unit are obtained. If the density characteristic value of a basic unit exceeds the preset density characteristic threshold, the basic unit is marked as a key monitoring unit. If the density characteristic value of a basic unit does not exceed the preset density characteristic threshold, the basic unit enters the risk assessment stage.

[0044] The risk assessment phase specifically includes: The periodic fluctuation characteristics and environmental characteristics of the basic unit are extracted. The periodic fluctuation characteristics of the basic unit are compared with the total periodic fluctuation characteristics of the target area. If the periodic fluctuation characteristics of the basic unit are greater than or equal to the total periodic fluctuation characteristics of the target area, the difference between the periodic fluctuation characteristics of the basic unit and the total periodic fluctuation characteristics of the target area is calculated and the absolute value is taken to obtain the periodic fluctuation deviation. The deviation is input into a preset mapping set of periodic fluctuation deviation-fluctuation risk assessment increase index for mapping and matching to obtain the fluctuation risk assessment increase index of the basic unit. The fluctuation risk assessment increase index is used to measure the degree of influence of the fluctuation characteristics of a basic unit on the risk assessment result of the basic unit.

[0045] It should be noted that a specific basic unit may experience more dramatic periodic changes than the target area as a whole due to its unique geographical, climatic, or ecological environment. For example, a region may have specific mosquito habitats, and these local factors may cause significant periodic fluctuations in mosquito activity within that unit. The overall periodic fluctuation characteristics of the target area are calculated by comprehensively analyzing the periodic fluctuation characteristics of all basic units, and may include multiple mutually canceling fluctuation characteristics. For instance, some areas within a region may experience larger fluctuations while others experience smaller fluctuations; these factors interact to result in a relatively smooth overall periodic fluctuation across the entire region.

[0046] If the periodic fluctuation characteristics of the basic unit are less than the total periodic fluctuation characteristics of the target area, then the volatility risk assessment index of the basic unit is set to zero.

[0047] The environmental characteristics of the basic unit are compared with the total environmental characteristics of the target area. If the environmental characteristics of the basic unit are greater than or equal to the total environmental characteristics of the target area, the difference between the environmental characteristics of the basic unit and the total environmental characteristics of the target area is calculated and the absolute value is taken to obtain the environmental characteristic deviation. The deviation is input into the preset mapping set of environmental characteristic deviation-environmental risk assessment increase index for mapping and matching to obtain the environmental risk assessment increase index of the basic unit. The environmental risk assessment increase index is used to measure the degree of influence of the environmental characteristics of a basic unit on the risk assessment result of the basic unit.

[0048] If the environmental characteristics of the basic unit are less than the total environmental characteristics of the target area, then the environmental risk assessment increase index of the basic unit is set to zero.

[0049] The total risk assessment index of the basic unit is obtained by superimposing the volatility risk assessment increase index and the environmental risk assessment increase index. If the total risk assessment index of the basic unit exceeds the preset risk assessment threshold, the basic unit is recorded as a secondary key monitoring unit.

[0050] If the total risk assessment index of the basic unit is less than or equal to the preset risk assessment threshold, then the basic unit is recorded as an ordinary monitoring unit.

[0051] Based on the total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area, the size of the basic unit in the target area is determined, specifically including: The total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area are input into the corresponding mapping sets of total density characteristics-density-guided adjustment values, total periodic fluctuation characteristics-periodic fluctuation-guided adjustment values, and total environmental characteristics-environment-guided adjustment values, respectively. The mapping and matching are then performed to obtain the density-guided adjustment value, periodic fluctuation-guided adjustment value, and environment-guided adjustment value of the target area. The density-guided adjustment value, periodic fluctuation-guided adjustment value, and environment-guided adjustment value of the target area are then superimposed with the default basic unit size to obtain the basic unit size of the target area.

[0052] The density-guided adjustment value is a value that dynamically adjusts the size of the basic unit based on the mosquito vector density characteristics of the target area. When the mosquito vector density is high, the density-guided adjustment value increases, resulting in a smaller basic unit size for more accurate monitoring of mosquito vector distribution. When the mosquito vector density is low, the density-guided adjustment value decreases, allowing the basic unit size to increase, reducing the complexity and cost of monitoring. Specifically, this value is determined by matching the distribution, uniformity, and abnormal density areas of mosquito vector density with a preset mapping relationship (a mapping between density characteristics and adjustment values).

[0053] The periodic fluctuation-oriented adjustment value dynamically adjusts the base cell size based on the periodic fluctuation characteristics of mosquito vector data in the target area. These periodic fluctuations primarily reflect the volatility of mosquito populations over time, especially short-term and long-term periodic changes. Strong periodic fluctuations indicate frequent short-term fluctuations in mosquito vector data; in this case, a larger periodic fluctuation-oriented adjustment value results in a smaller base cell size, allowing for more flexible capture of these fluctuations. Conversely, weak periodic fluctuations indicate relatively stable mosquito vector data; a smaller periodic fluctuation-oriented adjustment value allows for a larger base cell size, simplifying data monitoring.

[0054] The environmental-oriented adjustment value is a value used to adjust the size of the base unit based on the environmental characteristics of the target area (such as temperature, humidity, and water accumulation area). Environmental factors have a significant impact on mosquito distribution and activity. For example, in areas with high humidity or large water accumulation areas, mosquito breeding density may be high. In such cases, the environmental-oriented adjustment value is increased, resulting in a smaller base unit size, to accurately monitor the impact of these environmental factors on mosquito activity. Conversely, in areas with relatively stable environments and minimal changes, the environmental-oriented adjustment value is smaller, and the base unit size can be increased accordingly to reduce monitoring costs.

[0055] The cross-unit data collaboration mechanism module is used to transfer mosquito vector data from other monitoring units in the target area when a monitoring unit in the target area is determined to be a data-scarce unit, thereby assisting the monitoring unit in generating monitoring tasks.

[0056] Data scarcity criteria were extracted from the database for key monitoring units, secondary key monitoring units, and ordinary monitoring units. The specific criteria for data scarcity criteria include data quantity, data quality, and data timeliness.

[0057] Data volume determination includes thresholds for key monitoring data volume determination, secondary key monitoring data volume determination, and ordinary monitoring data volume determination. The data volume of the monitoring unit is compared with the corresponding data volume determination threshold. If the data volume of the monitoring unit is less than the corresponding data volume determination threshold, the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is insufficient data volume.

[0058] Data quality assessment includes thresholds for key monitoring data quality assessment, secondary key monitoring data quality assessment, and ordinary monitoring data quality assessment. The data quality of a monitoring unit is compared with the corresponding data quality assessment threshold. If the data quality of the monitoring unit is less than the corresponding data quality assessment threshold, the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is data quality deficiency.

[0059] It should be noted that, in this embodiment of the invention, data quality uses completeness as a quantitative indicator, where completeness refers to the proportion of missing data.

[0060] Data timeliness determination includes thresholds for key monitoring data timeliness, secondary key monitoring data timeliness, and ordinary monitoring data timeliness. The data timeliness of the monitoring unit is compared with the corresponding data timeliness threshold. If the data timeliness of the monitoring unit is less than the corresponding data timeliness threshold, the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is data timeliness delay.

[0061] It should be noted that, in this embodiment of the invention, data timeliness refers to the difference between data acquisition time and data transmission time.

[0062] Quality verification is performed on the data transmission path of data-scarce units whose data scarcity types are poor data quality and delayed data timeliness. Specifically, this includes: A data transmission experiment was conducted on the data transmission path of a data-scarce unit with data scarcity types of poor data quality and data timeliness delay. A piece of test data was input into the data transmission path of the data-scarce unit, and a check value was generated by hash calculation on the test data. After receiving the test data, the receiver recalculated the hash value and compared it with the check value to perform data integrity quality verification on the data transmission path. If the hash values ​​were inconsistent, it was determined that the data transmission path had damaged the data.

[0063] If the hash values ​​match, it is determined that the data quality itself is lacking, and assistance is needed to transmit the data.

[0064] The test data is timestamped when it is sent. The receiver confirms the transmission time of the test data based on the timestamp. If the transmission time exceeds the preset time threshold, it is determined that the data transmission path has caused a time delay to the data.

[0065] If the transmission time does not exceed the preset time threshold, it is determined that the data itself has a time delay, and assistance is required to transmit the data.

[0066] If a monitoring unit meets two or more data scarcity criteria simultaneously, the monitoring unit is marked, and location data and a sensor verification request are sent to the management platform.

[0067] Extract the data scarcity type from the data scarcity unit.

[0068] For cases of insufficient data volume, the difference between the data volume of the scarce data unit and the corresponding data volume judgment threshold is used to obtain the data volume compliance difference value. The data volume compliance difference value of the scarce data unit is then input into the preset mapping set of data volume compliance difference value - data volume required for assistance transmission in the database for mapping and matching to obtain the data volume required for assistance transmission of the scarce data unit.

[0069] For cases of data quality deficiencies, the difference between the data quality of the data-scarce unit and the corresponding data quality judgment threshold is used to obtain the data quality compliance difference. The data quality compliance difference of the data-scarce unit is then input into a preset mapping set of data quality compliance difference - required data transmission volume in the database for mapping and matching to obtain the required data transmission volume for the data-scarce unit.

[0070] To address data timeliness delays, the difference between the data timeliness of the scarce data unit and the corresponding data timeliness judgment threshold is used to obtain the data timeliness compliance difference. This data timeliness compliance difference is then input into a preset mapping set of data timeliness compliance difference - required data transmission volume in the data to obtain the required data transmission volume for the scarce data unit.

[0071] It should be noted that regardless of the type of data scarcity, the ultimate goal is to compensate for missing or incomplete data and ensure that the monitoring unit can obtain complete and accurate monitoring data.

[0072] Screening other monitoring units involves correlation analysis between data-scarce units and other monitoring units, data quality analysis of other monitoring units, and data transmission cost analysis of other monitoring units. Specifically, this includes: The correlation analysis between data-scarce units and other monitoring units includes calculating the data similarity between the data-scarce unit and other monitoring units. Specifically, the calculation method is the Pearson correlation coefficient. Observations from the same observation points are extracted from the data-scarce unit and other monitoring units. In this embodiment, mosquito numbers are selected as the observed parameter; in other embodiments, other parameters can be selected based on actual conditions. The observed values ​​from the same observation points extracted from the data-scarce unit and other monitoring units are input into the Pearson correlation coefficient calculation formula to obtain the data similarity between the data-scarce unit and other monitoring units.

[0073] In this embodiment of the invention, the data quality analysis of each other monitoring unit includes the data integrity analysis of each other monitoring unit, that is, obtaining the data missing ratio of each other monitoring unit.

[0074] In this embodiment of the invention, the data transmission cost analysis of each other monitoring unit includes obtaining the transmission bandwidth consumption between each other monitoring unit and the data-scarce unit.

[0075] The data similarity, data missing ratio, and transmission bandwidth consumption of each other monitoring unit are processed with unified dimensions and monotonicity using a standardized method to ensure consistent monotonicity. Simultaneously, preset weighted factors for data similarity, data missing ratio, and transmission bandwidth consumption are extracted from the database, multiplied by these factors, and then summed to obtain the screening coefficients for each other monitoring unit. The monitoring unit with the highest screening coefficient is selected as the assisting unit. Based on the data shortage unit's need for data transmission volume, the assisting data from the assisting unit is compressed and asynchronously transmitted to the data shortage unit.

[0076] It should be noted that the data similarity weighting factor measures the importance of the data similarity between data-scarce units and other monitoring units in the screening process; the data missing proportion weighting factor measures the importance of the degree of data missingness of a monitoring unit during data transmission in the screening process; and the transmission bandwidth consumption weighting factor measures the importance of the bandwidth required to transmit data from the monitoring unit to the data-scarce unit in the screening process. The system was constructed based on historical data and gradually adjusted through multiple simulations.

[0077] Multi-scale analysis is performed on the assist data of the assisting unit. The assist data is decomposed into different scales by Fourier transform to obtain the short-period change points and long-period change points of the assist data.

[0078] The high-frequency components (i.e., the higher-frequency parts) after the Fourier transform correspond to short-period fluctuations. By extracting these high-frequency components, short-period change points in the data can be identified. These short-period change points typically represent moments of frequent change in the data. The low-frequency components (i.e., the lower-frequency parts) after the Fourier transform correspond to long-period fluctuations. By extracting these low-frequency components, long-period change points in the data can be identified. These long-period change points typically represent changes in long-term trends or slower fluctuations in the data. The Fourier transform decomposes data into components of different frequencies, which is equivalent to decomposing it into different scales.

[0079] The auxiliary data is compressed based on short-cycle and long-cycle change points. Data differences within the time window corresponding to the change point type are recorded, and differential encoding is used to store and transmit the change value data. Differential encoding is a data compression technique that reduces data volume by storing changes (differences) between data points. For example, for short-cycle change points, differential encoding stores short-term data fluctuations (such as temperature or mosquito population fluctuations) with small numerical differences. For short-cycle change points, the time window typically encompasses data within multiple data points. For long-cycle change points, the time window typically encompasses data across multiple periods. In this embodiment of the invention, the time window corresponding to the change point type is preset, and the setting method is based on historical data, gradually adjusted through multiple simulations.

[0080] The task management module is used to manage the monitoring tasks of each monitoring unit in the target area, and to schedule and allocate resources for each monitoring unit.

[0081] The system dynamically adjusts the rating of each monitoring unit based on real-time data changes. For example, if the sensor data of a key monitoring unit shows a sudden change or anomaly, the system will automatically upgrade that key monitoring unit to a higher level to ensure timely handling.

[0082] The system tracks the task execution progress of each monitoring unit and monitors the task status and resource usage in real time. If an abnormal task status occurs, it automatically adjusts according to preset rules. For example, it obtains the current resource status data of each monitoring unit, including the computing power and transmission bandwidth of the local computing unit, and dynamically adjusts the assignment of real-time response tasks (such as environmental monitoring, emergency handling, etc.), or reschedules tasks or allocates additional resources to ensure that tasks are completed on time. After the task is completed, the task results are summarized and a data report is generated, which includes task execution status, data quality, and resource consumption, and then uploaded to the task management platform.

[0083] like Figure 2 The diagram illustrates a mosquito-borne data-driven task generation and management method, which specifically includes: Mosquito vector data of the target area is collected from external interfaces and sensors through real-time data streams, and then preprocessed and transmitted to the mosquito vector data analysis module.

[0084] Feature extraction is performed on mosquito vector data in the target area to obtain mosquito vector characteristics of the target area. Geographic information system is used to visualize the target area on a map to obtain the monitoring units of the target area.

[0085] When a monitoring unit in the target area is identified as a data-scarce unit, mosquito vector data is transmitted from other monitoring units in the target area to assist that monitoring unit in generating monitoring tasks.

[0086] Manage the monitoring tasks of each monitoring unit in the target area, and schedule and allocate resources for each monitoring unit.

[0087] The following points need to be explained: (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0088] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the invention, i.e., these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element or there may be intermediate elements.

[0089] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0090] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A mosquito-borne data-driven task generation and management system, characterized in that: include: The mosquito vector data acquisition module is used to collect mosquito vector data of the target area from external interfaces and sensors through real-time data streams, and transmit the pre-processed data to the mosquito vector data analysis module. The mosquito vector data analysis module is used to extract features from mosquito vector data in the target area, obtain mosquito vector characteristics of the target area, and use a geographic information system to visualize the target area on a map to obtain the monitoring units of the target area. The cross-unit data collaboration mechanism module is used to transfer mosquito vector data from other monitoring units in the target area when a monitoring unit in the target area is determined to be a data-scarce unit, in order to assist the monitoring unit in generating monitoring tasks. The task management module is used to manage the monitoring tasks of each monitoring unit in the target area, and to schedule and allocate resources for each monitoring unit.

2. The mosquito-borne data-driven task generation and management system according to claim 1, characterized in that: The step of extracting features from mosquito vector data in the target area to obtain mosquito vector features of the target area specifically includes: The ratio of mosquito population to target area is calculated to obtain the total density characteristics of mosquito vector data in the target area. The characteristics of mosquito population changes over time were extracted using time series analysis, including daily, weekly, and monthly average numbers. The total periodic fluctuation characteristics of mosquito vector data in the target area were captured by Fourier transform. The daily mean and standard deviation of climate data are calculated, and the relationship between the environment and mosquito population is analyzed to obtain the overall environmental characteristics of mosquito vector data in the target area.

3. The mosquito-borne data-driven task generation and management system according to claim 1, characterized in that: The step of visualizing the target area to obtain monitoring units for the target area specifically includes: Acquire spatial data of the target area, including administrative divisions, geographic coordinates and land use types; collect location information of mosquito vector monitoring equipment and sensors; load the map of the target area into the geographic information system; and overlay the density characteristics of mosquito vector data of the target area with the map to visualize the density characteristics. Based on the total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area, the size of the basic unit in the target area is determined, the target area is divided into basic units, and the density characteristics, periodic fluctuation characteristics, and environmental characteristics of each basic unit are obtained. If the density characteristic value of a basic unit exceeds the preset density characteristic threshold, the basic unit is marked as a key monitoring unit. If the density characteristic value of a basic unit does not exceed the preset density characteristic threshold, the basic unit enters the risk assessment stage. The risk assessment phase specifically includes: Extract the periodic fluctuation characteristics and environmental characteristics of the basic unit, compare the periodic fluctuation characteristics of the basic unit with the total periodic fluctuation characteristics of the target area, and if the periodic fluctuation characteristics of the basic unit are greater than or equal to the total periodic fluctuation characteristics of the target area, the periodic fluctuation deviation between the periodic fluctuation characteristics of the basic unit and the total periodic fluctuation characteristics of the target area is obtained. Input the deviation into the preset periodic fluctuation deviation-fluctuation risk assessment increase index mapping set for mapping and matching to obtain the fluctuation risk assessment increase index of the basic unit. If the periodic fluctuation characteristics of the basic unit are less than the total periodic fluctuation characteristics of the target area, then the volatility risk assessment increase index of the basic unit is set to zero. The environmental characteristics of the basic unit are compared with the total environmental characteristics of the target area. If the environmental characteristics of the basic unit are greater than or equal to the total environmental characteristics of the target area, the environmental characteristic deviation between the environmental characteristics of the basic unit and the total environmental characteristics of the target area is obtained. The deviation is input into the preset mapping set of environmental characteristic deviation-environmental risk assessment increase index for mapping and matching to obtain the environmental risk assessment increase index of the basic unit. If the environmental characteristics of the basic unit are less than the total environmental characteristics of the target area, then the environmental risk assessment increase index of the basic unit is set to zero; The total risk assessment index of the basic unit is obtained by superimposing the volatility risk assessment increase index and the environmental risk assessment increase index. If the total risk assessment index of the basic unit exceeds the preset risk assessment threshold, the basic unit is recorded as a secondary key monitoring unit. If the total risk assessment index of the basic unit is less than or equal to the preset risk assessment threshold, then the basic unit is recorded as an ordinary monitoring unit.

4. The mosquito-borne data-driven task generation and management system according to claim 1, characterized in that: A certain monitoring unit in the target area was identified as a data-scarce unit, specifically including: Data scarcity determination criteria for key monitoring units, secondary key monitoring units, and ordinary monitoring units are extracted from the database. The data scarcity determination criteria specifically include data quantity determination, data quality determination, and data timeliness determination. The data volume determination process includes extracting the key monitoring data volume determination threshold, the secondary key monitoring data volume determination threshold, and the ordinary monitoring data volume determination threshold, comparing the data volume of the monitoring unit with the corresponding data volume determination threshold, and if the data volume of the monitoring unit is less than the corresponding data volume determination threshold, then the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is insufficient data volume. The data quality determination process includes extracting the key monitoring data quality determination threshold, the secondary key monitoring data quality determination threshold, and the ordinary monitoring data quality determination threshold, comparing the data quality of the monitoring unit with the corresponding data quality determination threshold, and if the data quality of the monitoring unit is less than the corresponding data quality determination threshold, then the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is data quality deficiency. The process of determining the timeliness of data includes extracting the timeliness determination thresholds for key monitoring data, secondary key monitoring data, and ordinary monitoring data; comparing the timeliness of the data of the monitoring unit with the corresponding timeliness determination thresholds; if the timeliness of the data of the monitoring unit is less than the corresponding timeliness determination threshold, then the monitoring unit is determined to be a data-scarce unit, and the data scarcity type is data timeliness delay. Perform quality verification on the data transmission path of data-scarce units whose data scarcity types are poor data quality and delayed data timeliness; If a monitoring unit meets two or more data scarcity criteria simultaneously, the monitoring unit is marked, and location data and a sensor verification request are sent to the management platform.

5. The mosquito-borne data-driven task generation and management system according to claim 1, characterized in that: The transmission of mosquito vector data from other monitoring units in the target area to assist the monitoring unit in generating monitoring tasks specifically includes: Extract the data scarcity type from the data scarcity unit; For cases of insufficient data volume, the difference between the data volume of the scarce data unit and the corresponding data volume judgment threshold is used to obtain the data volume compliance difference value. The data volume compliance difference value of the scarce data unit is then input into the preset mapping set of data volume compliance difference value - data volume required for assistance transmission in the database for mapping and matching to obtain the data volume required for assistance transmission of the scarce data unit. For data quality deficiencies, the difference between the data quality of the data-scarce unit and the corresponding data quality judgment threshold is used to obtain the data quality compliance difference. The data quality compliance difference of the data-scarce unit is then input into the preset data quality compliance difference - required data volume for data transmission in the database for mapping and matching to obtain the required data volume for data-scarce unit. To address data timeliness delays, the difference between the data timeliness of the scarce data unit and the corresponding data timeliness judgment threshold is used to obtain the data timeliness compliance difference. The data timeliness compliance difference of the scarce data unit is then input into the preset data timeliness compliance difference - required data volume for data transmission mapping set in the data to obtain the required data volume for data timeliness compliance. Screening other monitoring units includes correlation analysis between data-scarce units and other monitoring units, data quality analysis of other monitoring units, and data transmission cost analysis of other monitoring units; The selected monitoring units are designated as assistance units. Based on the data volume required by the data-scarce units, the assistance data of the assistance units is compressed and then asynchronously transmitted to the data-scarce units.

6. The mosquito-borne data-driven task generation and management system according to claim 5, characterized in that: The compression processing of the assistance data from the assistance unit also includes change point analysis, specifically including: Multi-scale analysis is performed on the assist data of the assisting unit. The assist data is decomposed into different scales by Fourier transform to obtain the short-period change points and long-period change points of the assist data. The auxiliary data is compressed based on short-cycle and long-cycle change points, the data differences in the time window corresponding to the change point type are recorded, the change values ​​are stored by differential encoding, and the change value data of the change points are transmitted.

7. The mosquito-borne data-driven task generation and management system according to claim 1, characterized in that: The scheduling and resource allocation of monitoring tasks for each monitoring unit specifically includes: The ratings of each monitoring unit are dynamically adjusted based on real-time data changes. Track the task execution progress of each monitoring unit and monitor the task status and resource usage in real time. If the task status is abnormal, it will be automatically adjusted according to preset rules. After the task is completed, the task results will be summarized and a data report will be generated. The report includes task execution status, data quality and resource consumption, and will be uploaded to the task management platform.

8. The mosquito-borne data-driven task generation and management system according to claim 3, characterized in that: The determination of the basic unit size of the target area based on the total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area specifically includes: The total density characteristics, total periodic fluctuation characteristics, and total environmental characteristics of mosquito vector data in the target area are input into the corresponding mapping sets of total density characteristics-density-guided adjustment values, total periodic fluctuation characteristics-periodic fluctuation-guided adjustment values, and total environmental characteristics-environment-guided adjustment values, respectively. The mapping and matching are then performed to obtain the density-guided adjustment value, periodic fluctuation-guided adjustment value, and environment-guided adjustment value of the target area. The density-guided adjustment value, periodic fluctuation-guided adjustment value, and environment-guided adjustment value of the target area are then superimposed with the default basic unit size to obtain the basic unit size of the target area.

9. The mosquito-borne data-driven task generation and management system according to claim 4, characterized in that: It also includes quality verification of the data transmission path for data scarce units whose data scarcity types are poor data quality and delayed data timeliness, specifically including: A data transmission experiment was conducted on the data transmission path of a data-scarce unit with data scarcity types of poor data quality and data timeliness delay. A piece of test data was input into the data transmission path of the data-scarce unit, and a hash calculation was performed on the test data to generate a check value. After receiving the test data, the receiver performed the hash value calculation again and compared it with the check value to perform data integrity quality verification on the data transmission path. If the hash values ​​were inconsistent, it was determined that the data transmission path had damaged the data. The test data is timestamped when it is sent. The receiver confirms the transmission time of the test data based on the timestamp. If the transmission time exceeds the preset time threshold, it is determined that the data transmission path has caused a time delay to the data.

10. A method for using a mosquito-borne data-driven task generation and management system as described in any one of claims 1-9, characterized in that, include: Mosquito vector data of the target area is collected from external interfaces and sensors through real-time data streams, and then pre-processed and transmitted to the mosquito vector data analysis module. Feature extraction is performed on mosquito vector data in the target area to obtain mosquito vector characteristics of the target area. Geographic information system is used to visualize the target area on a map to obtain the monitoring units of the target area. When a monitoring unit in the target area is identified as a data-scarce unit, mosquito vector data is transmitted from other monitoring units in the target area to assist that monitoring unit in generating monitoring tasks. Manage the monitoring tasks of each monitoring unit in the target area, and schedule and allocate resources for each monitoring unit.

Images