A wall bee pollination environment control method and system based on the Internet of Things

Abstract

The application discloses a wall bee pollination environment control method and system based on the Internet of Things, relates to the technical field of environment control, and comprises a control center, wherein the control center is connected with an environment collection module, a data processing module, a response analysis module and an integrated regulation and control module; survival environment data of a wall bee activity range is collected; a live virtual space is constructed, visual feature extraction is carried out after environment extraction of the survival environment data, and an environment time sequence change graph is obtained; the environment time sequence change graph is subjected to span grading and color display marking, and a color coverage activity graph is obtained; the path of the survival environment data is extracted and marked through the color coverage activity graph, a regulation and control feature display graph is obtained, environment block adjustment is carried out in the regulation and control feature display graph, and an intelligent regulation and control scheme is obtained; a more stable and suitable environment is provided, pollination efficiency is greatly improved, a wall bee population is protected, and the yield and quality of crops are improved.

Description

Technical Field

[0001] This invention relates to the field of environmental control technology, specifically to a method and system for controlling the pollination environment of mason bees based on the Internet of Things. Background Technology

[0002] With the advancement of technology, bee pollination has gradually become an effective means of agricultural production. Mason bees, as pollinating insects, have advantages such as high pollination efficiency and strong adaptability. However, traditional mason bee pollination techniques also have certain limitations, such as complex mason bee breeding and management and significant susceptibility to weather conditions.

[0003] In recent years, the Internet of Things (IoT) technology has been widely applied in agriculture. Through sensors, data transmission, and data processing, IoT technology enables real-time monitoring and intelligent control of the agricultural production environment. Mason bees, as pollinating insects, possess advantages such as high pollination efficiency, strong adaptability, and easy reproduction. Based on these advantages, an IoT-based method and system for controlling the pollination environment of mason bees is proposed. By real-time monitoring and control of factors such as temperature, humidity, and light in the pollination environment, optimal growth and activity conditions are provided for the mason bees. Based on the behavioral feedback of the mason bees and changes in environmental parameters, the control strategy is continuously optimized to achieve adaptive adjustment, thereby improving pollination efficiency and ensuring crop yield and quality. Summary of the Invention

[0004] The purpose of this invention is to provide an IoT-based method and system for controlling the pollination environment of mason bees, in order to solve the problems of slow response speed and inaccurate control precision in the background art.

[0005] An Internet of Things-based mason bee pollination environment control system includes a control center, which is connected to an environmental acquisition module, a data processing module, a response analysis module, and an integrated control module.

[0006] The environmental acquisition module is used to delineate the activity range of mason bees, obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes.

[0007] The data processing module is used to construct a real-time virtual space, extract and process living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain an environmental time series change map.

[0008] The response analysis module is used to classify the environmental time series change map by span, obtain environmental classification gradient segments, and display and mark the hierarchical activity block map according to the environmental classification gradient segments to obtain a color-covered activity map.

[0009] The integrated control module is used to extract traces from living environment data and mark the traces in a color-overlay activity map to obtain a control feature display map. Through real-time virtual space, environmental blocks are adjusted in the control feature display map to obtain an intelligent control scheme.

[0010] Preferably, the process of obtaining a hierarchical activity block map includes:

[0011] The survival area of ​​mason bees is divided to obtain a safe range of activity. The boundaries of the obtained safe range of activity are supplemented to obtain a rectangular map of the activity range.

[0012] Divide the activity range rectangle into regions to obtain evenly divided activity blocks, and record the activity range rectangle after regional division as a hierarchical activity block map.

[0013] Preferably, the process of collecting living environment data includes:

[0014] Set up the data acquisition parameters for the hierarchical activity block map to obtain the sensor acquisition terminal;

[0015] Based on the hierarchical activity block map, the activity of evenly divided activity blocks is collected by the sensor acquisition terminal to obtain living environment data;

[0016] The acquired environmental data is recorded over time to obtain the data collection time points.

[0017] Preferably, the process of obtaining measurement environment data includes:

[0018] Construct a live virtual space, upload the hierarchical activity block map to the live virtual space, and mark the collected living environment data at the corresponding positions on the hierarchical activity block map;

[0019] Based on the real-world virtual space, the obtained living environment data is quantified and extracted to obtain measurement environment data.

[0020] Preferably, the process of setting a statistical period for visual feature extraction of measurement environment data includes:

[0021] The statistical period is set according to the collection time node, and the measurement environment data is cleaned and sorted based on the statistical period to obtain the time series measurement sequence.

[0022] A two-dimensional rectangular coordinate system is constructed based on the data acquisition time nodes. The time-series measurement sequences are uploaded to the two-dimensional rectangular coordinate system, and the time-series measurement sequences are combined in series to obtain environmental measurement curves. The two-dimensional rectangular coordinate system containing the environmental measurement curves is recorded as the environmental time-series change diagram.

[0023] Preferably, the process of classifying the environmental time-series change map by span includes:

[0024] Obtain the environmental time series change map, set a sliding boundary axis for the environmental time series change map, upload the obtained sliding boundary axis to the starting position of the environmental time series change map, and set a shift interval for the obtained sliding boundary axis;

[0025] Based on the environmental time-series change map, the sliding boundary axis is sequentially adjusted according to the obtained shift interval to obtain the environmental classification gradient segment.

[0026] Preferably, the process of obtaining the color overlay activity map includes:

[0027] Obtain environmental gradation gradient segments, perform hierarchical statistics on the obtained environmental gradation gradient segments based on the environmental time series change map, and obtain the total number of gradient segments;

[0028] The transparency marker color is obtained by color grading based on the total amount of gradient segments in a real-world virtual space.

[0029] Based on the data collection time point, the layered activity block map is color-covered using the transparency markers in the real-time virtual space to obtain a color-covered activity map.

[0030] Preferably, the process of obtaining the regulatory feature visualization map includes:

[0031] Acquire survival environment data, extract traces from the survival environment data, and obtain activity traces within the range;

[0032] Based on the statistical period, the color coverage activity map is integrated by range activity traces to obtain a dynamic trace color map.

[0033] The obtained activity traces are uploaded to the trace color dynamic map. The trace color dynamic map is then marked based on the activity traces in the real-time virtual space to obtain a control feature display map.

[0034] Preferably, the process of obtaining an intelligent control scheme includes:

[0035] Accumulate the routes from the regulation feature display map to obtain a dynamic map of the aggregation route;

[0036] By identifying the activity environment of the dynamic map of the aggregation route in a real-time virtual space, the results of regional activities can be obtained.

[0037] Based on the results of regional activities, environmental adjustments are made to the dynamic map of aggregation routes to obtain activity blocks to be adjusted.

[0038] Based on the real-time virtual space, the elements of the activity block to be regulated are adjusted to obtain an intelligent control plan.

[0039] Based on the above-mentioned IoT-based mason bee pollination environment control system, the present invention also provides an IoT-based mason bee pollination environment control method, comprising the following steps:

[0040] Step 1: Divide the activity range of mason bees into regions to obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes;

[0041] Step 2: Construct a real-world virtual space, extract and process the living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain a time-series change map of the environment;

[0042] Step 3: Perform span classification on the environmental time series change map to obtain environmental classification gradient segments. Based on the environmental classification gradient segments, display and mark the hierarchical activity block map to obtain a color-covered activity map.

[0043] Step 4: Extract the traces from the living environment data and mark the traces in the color-overlay activity map to obtain a control feature display map. Adjust the environmental blocks in the control feature display map through the real-time virtual space to obtain an intelligent control scheme.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] 1. The activity range of mason bees is divided into more detailed sections to obtain evenly distributed activity blocks. The survival environment data of each block is collected. By dividing the activity range into detailed sections, the environmental parameters of each small area can be monitored more accurately, thereby providing a more suitable pollination environment for mason bees.

[0046] 2. Then, the environmental monitoring data in the living environment data is transformed into graphics, and the curve is divided into levels. Different levels of environmental monitoring data are marked with color blocks of different display transparency to obtain a color coverage activity map, which provides an intuitive interactive method. It can quickly identify and respond to environmental changes through visual differences, which helps the intelligent decision-making of the mason bee pollination environment control system.

[0047] 3. Construct a real-time virtual space and mark the activity trajectories of mason bees within their activity range on a color-coded activity map. By identifying the active areas of mason bees, pollination resource allocation can be optimized, ensuring that mason bees pollinate in the most effective locations, thereby improving pollination efficiency and crop yield. Simultaneously, by marking active areas based on the activity trajectories of different mason bees, personalized management strategies can be implemented to improve the adaptability of mason bees and pollination effectiveness. Furthermore, inactive areas can be identified, and environmental factors can be adjusted in these inactive areas within the real-time virtual space to obtain intelligent control solutions, helping mason bees better adapt to different environmental conditions and enhancing their survival and reproductive capabilities. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0050] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] like Figure 1 As shown, an IoT-based bee pollination environment control system includes a control center, which is connected to an environmental acquisition module, a data processing module, a response analysis module, and an integrated control module.

[0052] The environmental acquisition module is used to delineate the activity range of mason bees, obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes.

[0053] The data processing module is used to construct a real-time virtual space, extract and process living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain an environmental time series change map.

[0054] The response analysis module is used to classify the environmental time series change map by span, obtain environmental classification gradient segments, and display and mark the hierarchical activity block map according to the environmental classification gradient segments to obtain a color-covered activity map.

[0055] The integrated control module is used to extract traces from living environment data and mark the traces in a color-overlay activity map to obtain a control feature display map. Through real-time virtual space, environmental blocks are adjusted in the control feature display map to obtain an intelligent control scheme.

[0056] In practical applications, traditional environmental control systems may lack precise monitoring equipment, making it difficult to accurately control the pollination environment of mason bees. This can lead to mason bees becoming unsuitable for their environment, affecting their health and pollination ability, and significantly impacting crop yields. However, by using Internet of Things (IoT) technology to intelligently regulate the environment in which mason bees are active, pollination efficiency can be improved, resource utilization optimized, pests and diseases prevented, climate change adapted, and ultimately, crop yields and quality increased. Firstly, an environmental data acquisition module is used to delineate the activity range of mason bees, obtaining a hierarchical activity block map, and collecting environmental data. The specific process includes:

[0057] Divide the mason bees' living areas to obtain their safe activity range;

[0058] The defined living area refers to the marking of the living and activity areas of a mason bee population that requires environmental control for mason bee pollination. That is, marking the living area of ​​the mason bee population and recording it as the safe range of activity. The living area refers to the living area where mason bees can interact after leaving the hive. It is usually the maximum range of activity that they can move around in, excluding the activity range of lost mason bees. It is defined according to the survival habits of mason bees, that is, the activity area that mason bees are usually accustomed to.

[0059] The obtained activity safety range is supplemented by boundary addition to obtain an activity range rectangle. Boundary addition means supplementing the boundaries of the obtained activity safety range so that the final activity range is represented as a rectangle, i.e., the activity range rectangle. "Supplementing the boundaries of the activity safety range" means supplementing the boundaries of the activity safety range with irregular boundaries to obtain a rectangle with the smallest supplemented area. This rectangle is the rectangle with the smallest supplemented area under the premise of completely covering the activity safety range.

[0060] The obtained activity range rectangle map is divided into regions to obtain equally divided activity blocks, and the activity range rectangle map after region division is recorded as a hierarchical activity block map;

[0061] The regional division is represented by further reducing the size of the activity range rectangle in the activity range rectangle to obtain rectangular blocks of equal area. The activity range of each block is recorded as an equally divided activity block, and the area and size of each equally divided activity block are the same. The number of equally divided activity blocks is related to the size of the activity safety range. In order to obtain more accurate environmental data, a sufficient number of equally divided activity blocks are used to obtain more detailed environmental changes in different areas.

[0062] Set up the data acquisition for the hierarchical activity block map, obtain the sensor acquisition end, and associate the obtained sensor acquisition end with the corresponding equally divided activity block;

[0063] The acquisition setup means that each equally divided activity block is equipped with an acquisition terminal for collecting data information within the equally divided activity block, denoted as the sensor acquisition terminal.

[0064] Based on the hierarchical activity block map, the activity of the evenly divided activity blocks is collected by the sensor acquisition terminal to obtain the survival environment data, and the obtained survival environment data is associated with the corresponding evenly divided activity blocks.

[0065] The activity data collection refers to the collection of all activity data and environmental data of the area within the evenly divided activity blocks in the hierarchical activity block map through the sensor acquisition terminal. This constitutes the survival environment data, which includes block environmental data and mason bee activity data. The block environmental data includes, but is not limited to, real-time temperature, real-time humidity, light intensity, air circulation data, nectar source information, and environmental pollutant data. The mason bee activity data represents all activity data of mason bees within the evenly divided activity blocks, including but not limited to the activity level, pollination behavior, and flight path of the mason bees.

[0066] The obtained living environment data is recorded over time to obtain the collection time nodes, and the obtained collection time nodes are associated with the corresponding living environment data.

[0067] The time record indicates that while collecting living environment data, the time node of data collection is marked, which is the collection time point. That is, each living environment data has a corresponding collection time node.

[0068] The data processing module is used to construct a real-world virtual space, extract and process living environment data to obtain measurement environment data, set statistical periods to extract visual features from the measurement environment data, and obtain environmental time-series change maps. The specific process includes:

[0069] Construct a live virtual space, which is a blank virtual space used to visualize the layered activity block diagram.

[0070] The obtained hierarchical activity block map is uploaded to the live virtual space, and the collected living environment data is marked at the corresponding position in the hierarchical activity block map, that is, marked at the equally distributed activity block associated with the living environment data.

[0071] Based on the real-world virtual space, the obtained living environment data is quantified and extracted to obtain measurement environment data;

[0072] The quantification extraction refers to extracting quantifiable data from the living environment data, which is recorded as measurement environment data. Based on the block environment data and mason bee activity data included in the living environment data, quantifiable data is extracted as measurement environment data, such as real-time temperature, real-time humidity, light intensity, air circulation data, environmental pollution data, and nectar source distance data.

[0073] The statistical period is set according to the collection time nodes, and the statistical period is a period of time that includes several collection time nodes.

[0074] The obtained measurement environment data is cleaned and sorted based on the statistical period to obtain a time-series measurement sequence;

[0075] The cleaning and sorting refers to sorting the data according to the acquisition time node corresponding to each measurement environment data, and deleting redundant and duplicate measurement environment data to obtain a time-series measurement sequence sorted by time within the statistical period.

[0076] Furthermore, based on the real-time temperature, real-time humidity, light intensity, air circulation data, environmental pollution data, and nectar source distance data included in the measured environmental data, the time series measurement sequence includes the real-time temperature sequence, real-time humidity sequence, light intensity sequence, air circulation sequence, environmental pollution sequence, and nectar source distance sequence.

[0077] A two-dimensional rectangular coordinate system is constructed based on the acquisition time nodes. The obtained time-series measurement sequences are uploaded to the two-dimensional rectangular coordinate system, and the time-series measurement sequences are combined in series to obtain environmental measurement curves. The two-dimensional rectangular coordinate system containing the environmental measurement curves is recorded as an environmental time-series change diagram.

[0078] It should be further explained that, in the specific implementation process, the horizontal axis of the constructed two-dimensional rectangular coordinate system represents the data collection time node. Within the statistical period, the time series measurement sequence is marked on the two-dimensional rectangular coordinate system in chronological order according to the data collection time node. The vertical axis represents the value of the environmental measurement data, and adjacent data points are connected in sequence to obtain the environmental measurement curve. Based on the real-time temperature sequence, real-time humidity sequence, light intensity sequence, air circulation sequence, environmental pollution sequence, and nectar source distance sequence included in the time series measurement sequence, the environmental measurement curve includes the temperature measurement curve, humidity measurement curve, light intensity measurement curve, air circulation measurement curve, environmental pollution measurement curve, and nectar source distance measurement curve, and finally, an environmental time series change map including the environmental measurement curve is obtained.

[0079] The response analysis module is used to classify the environmental time-series change map by span, obtain environmental classification gradient segments, and display and mark the hierarchical activity block map according to the environmental classification gradient segments to obtain a color-covered activity map. The specific process includes:

[0080] Obtain an environmental time-series change map, and set a sliding boundary axis on the obtained environmental time-series change map. The sliding boundary axis is a straight line parallel to the horizontal axis of the environmental time-series change map, and it is a straight line that can be horizontally translated and slid up and down.

[0081] The obtained sliding boundary axis is uploaded to the starting position of the environmental time series change map, and a shift interval is set for the obtained sliding boundary axis. The starting position is the position where the sliding boundary axis is uploaded to coincide with the horizontal axis of the environmental time series change map, and the shift interval is the distance between each translation of the sliding boundary axis to the next position. In this embodiment, the shift interval is set according to the actual situation of the activity safety range corresponding to the wall bee, and is used to distinguish different environmental levels.

[0082] Based on the environmental time-series change map, the sliding boundary axis is sequentially adjusted according to the obtained shift interval to obtain the environmental classification gradient segment;

[0083] It should be further explained that, in the specific implementation process, the sequential adjustment means that in the environmental time series change diagram, the sliding boundary axis is translated upward from the starting position. The distance of each translation is the distance of the shift interval. Then, each time it is moved, an environmental measurement curve of an interval segment can be obtained. The environmental measurement curve within the interval segment is recorded as the environmental classification gradient segment.

[0084] The first movement involves moving one shift interval from the starting position. The portion of the environmental measurement curve falling within this interval is recorded as the first environmental gradient segment. Moving another shift interval, the portion of the environmental measurement curve between one and two shift intervals from the starting position is recorded as the second environmental gradient segment. Moving another shift interval, the portion of the environmental measurement curve between two and three shift intervals from the starting position is recorded as the third environmental gradient segment. This process continues until the highest point of the environmental measurement curve is contained within an interval that is an integer multiple of the shift interval from the starting position. Once the environmental gradient segment within the last interval is obtained, the sequential movement is complete.

[0085] Specifically, for the environmental measurement curves including temperature measurement curve, humidity measurement curve, light intensity measurement curve, air circulation measurement curve, environmental pollution measurement curve, and nectar source distance measurement curve, each environmental measurement curve has a corresponding environmental grading gradient segment, namely, the temperature grading gradient segment corresponding to the temperature measurement curve, the humidity grading gradient segment corresponding to the humidity measurement curve, the light intensity grading gradient segment corresponding to the light intensity measurement curve, the air circulation grading gradient segment corresponding to the air circulation measurement curve, the pollution grading gradient segment corresponding to the environmental pollution measurement curve, and the nectar source grading gradient segment corresponding to the nectar source distance measurement curve.

[0086] Obtain environmental gradation gradient segments, perform hierarchical statistics on the obtained environmental gradation gradient segments based on the environmental time series change map, and obtain the total number of gradient segments;

[0087] The hierarchical statistics refer to the number of environmental grading gradient segments obtained by sequentially adjusting the environmental measurement curves for each type in the environmental time-series change graph, and the total number of environmental grading gradient segments is recorded as the total number of gradient segments.

[0088] The color is graded according to the total amount of gradient segments in the real-world virtual space to obtain the transparency marker color, and the transparency marker color is associated with the corresponding environmental grading gradient segment;

[0089] The color grading refers to classifying the transparency of the color corresponding to each environmental grading gradient segment based on the total number of gradient segments, thus obtaining the transparency marker color corresponding to each environmental grading gradient segment. For example, if the total number of gradient segments is 5, then there are 5 categories of transparency marker colors after grading: 100% transparency, 80% transparency, 60% transparency, 40% transparency, 20% transparency, and 0% transparency. Different levels of color intensity are used to distinguish different levels of measurement environment data, and the higher the index of the measurement environment data, the darker the color. If marked as green, then it represents 100% transparency green, 80% transparency green, 60% transparency green, 40% transparency green, 20% transparency green, and 0% transparency green, respectively. Among them, 100% transparency color represents blank, displaying no color, while 0% transparency represents displaying the brightest green. As the transparency increases, the green brightness decreases until it reaches 100% transparency, which is blank, displaying no color.

[0090] Based on the data collection time point, the layered activity block map is color-covered by marking colors according to transparency in the real-time virtual space to obtain a color-covered activity map.

[0091] It should be further explained that, in the specific implementation process, the color overlay refers to the color overlay of the evenly distributed activity blocks in the hierarchical activity blocks in the real-world virtual space where survival environment data can be collected. That is, the transparency marker color of the environmental grading gradient segment corresponding to the measurement environment data at the same collection time node is used to mark the corresponding evenly distributed activity blocks. In this embodiment, green is used for marking and overlay. That is, the corresponding color is marked according to the transparency marker color corresponding to the environmental grading gradient segment of the evenly distributed activity block. The final color overlay activity map is that the evenly distributed activity blocks where measurement environment data can be collected have the corresponding transparency marker color. Therefore, for the entire color overlay activity map, the different degrees of change of the measurement environment data at the corresponding collection time node can be obtained by the different shades of color.

[0092] Specifically, based on the measured environmental data including real-time temperature, real-time humidity, light intensity, air circulation data, environmental pollution data, and nectar source distance data, a corresponding color overlay activity map is generated for each type of measured environmental data. Through the color overlay activity map of each type of measured environmental data, the real-time changes of environmental data at the current collection time point can be obtained. For example, for the color overlay activity map of real-time temperature, the transparency marker colors in different evenly distributed activity blocks are different. Therefore, based on the transparency displayed by different colors, the different temperature ranges corresponding to the mason bees within their safe activity range can be observed intuitively. Combined with the mason bee activity data within the safe activity range, the evenly distributed activity blocks corresponding to the environmental range that mason bees prefer or can adapt to and are highly active can be determined.

[0093] The integrated control module is used to extract activity patterns from environmental data and mark these patterns in a color-coded activity map to obtain a control feature display map. Then, through a real-time virtual space, adjustments are made to environmental blocks within the control feature display map to obtain an intelligent control scheme. The specific process includes:

[0094] Acquire survival environment data, extract traces from the acquired survival environment data, and obtain activity traces within the range;

[0095] The trace extraction refers to extracting the activity traces and flight paths of mason bees within their safe activity range from the collected living environment data to obtain the range activity trace. This range activity trace is the flight path of mason bees within their safe activity range within a statistical period, and the pollination locations they pass through are marked in the range activity trace.

[0096] Based on the statistical period, the color coverage activity map is integrated by range activity traces to obtain a dynamic trace color map.

[0097] It should be further explained that, in the specific implementation process, the track integration means that within a statistical period, the color coverage activity maps corresponding to all collection time nodes are integrated through the real-time virtual space, that is, placed in the same color coverage activity map and corresponding according to different collection time nodes, to obtain the dynamic color changes of the color coverage activity maps at different collection time nodes within a statistical period. That is, at different collection time nodes, the transparency marker color of the same evenly divided activity block is different, so integrating it into a color coverage activity map can obtain the dynamic color change situation, which is recorded as the track color dynamic map.

[0098] The obtained activity traces within the range are uploaded to the trace color dynamic map. The traces are then marked on the trace color dynamic map based on the activity traces within the range in the real-time virtual space to obtain a control feature display map.

[0099] Furthermore, the trace identification indicates that the range of activity traces of each mason bee is marked in the trace color dynamic map. That is, the route is marked in a dynamic form in the trace color dynamic map, which can intuitively obtain the flight path of each mason bee and mark the pollination location point. Then, in the trace color dynamic map corresponding to a statistical period, the flight path of the mason bee, including the pollination location and the relationship between the active location and environmental changes, can be dynamically observed to obtain the control feature display map. In the control feature display map, not only can the dynamic environmental changes be obtained, but also the dynamic flight of the mason bee can be obtained.

[0100] The obtained control characteristic display map is accumulated to obtain a dynamic map of aggregation routes;

[0101] The cumulative route is represented in the control feature display map, which shows the different flight routes marked according to the activity traces of different mason bees within their ranges. Overlapping flight routes can be visually observed in the control feature display map. The overlapping flight routes are accumulated and displayed using route markers with width. The more overlapping areas there are, the wider the route width of the activity traces within that range, indicating that the mason bees in that area are more active and prefer that area. The marked control feature display map is recorded as a dynamic aggregation route map. In the dynamic aggregation route map, the preferred activity area of ​​the mason bees can be determined by the route width of the activity traces within the range, and the degree of influence of environmental changes on the flight area of ​​mason bees can be analyzed.

[0102] Specifically, since each type of measurement environment data has a corresponding color-coded activity map, the aggregation route dynamic map is the cumulative route of all range activity traces of wall bees under the same statistical period. However, the background map of the cumulative route is a display map of different types of control features. For example, the route obtained by accumulating the control feature display map of real-time temperature and the control feature display map of real-time humidity is the same. It is just a cumulative display map of flight paths under the dynamic changes of different measurement environment data with the collection time node.

[0103] The activity environment of the aggregation route dynamic map is identified by real-time virtual space to obtain regional activity results, which include static environment areas and active environment areas.

[0104] Furthermore, the activity environment identification refers to the threshold determination of the route width of the range of activity traces in the real-time virtual space. When the route width of the largest range of activity traces in the aggregation route dynamic map is less than the width threshold, the width threshold is the required flight activity level of the mason bee based on the minimum pollination requirements of the environmental conditions that the mason bee can withstand, that is, the flight activity activity level of the mason bee within the safe activity range; then the activity environment identification result is recorded as a static environment area, indicating that the activity level of the mason bee does not meet the safety threshold, and the environmental conditions within the safe activity range are not conducive to pollination. That is, the environmental conditions within the safe activity range are intelligently adjusted to make the activity range suitable for the activity state of the mason bee.

[0105] When the width of the route with the largest range of activity traces in the aggregation route dynamic map is greater than the width threshold, the activity environment identification result is recorded as a dynamic environment area, indicating that the activity level of mason bees meets the safety threshold and is conducive to pollination. However, there may be ranges of activity traces smaller than the width threshold. That is, in the aggregation route dynamic map, some areas are dynamic environment areas and some areas are static environment areas. Therefore, it is necessary to adjust the environmental conditions of the equally divided activity blocks corresponding to the static environment areas to promote all mason bees within the safe activity range to reach the highest pollination conditions.

[0106] Based on the obtained regional activity results, environmental regulation is carried out on the dynamic map of aggregation routes to obtain activity blocks to be regulated;

[0107] Furthermore, the environmental control refers to obtaining the evenly distributed activity blocks of the static environment area based on the regional activity results of the aggregation route dynamic map in the real-time virtual space. These are recorded as the activity blocks to be adjusted. That is, the evenly distributed activity blocks whose activity does not meet the width threshold condition need to have their environmental data adjusted to promote the activity of the mason bees and thus improve the pollination rate.

[0108] Based on the real-time virtual space, the elements of the activity block to be regulated are adjusted to obtain an intelligent control scheme;

[0109] It should be further explained that, in the specific implementation process, the element adjustment refers to determining the type of living environment data to be adjusted based on the type of measurement environment data in the dynamic map of the aggregation route corresponding to the activity block to be adjusted. For example, adjusting the activity block to be adjusted in the dynamic map of the aggregation route of real-time humidity means adjusting the real-time humidity level in the real-time virtual space according to the transparency ratio corresponding to the transparency marker color. If the activity block to be adjusted is caused by low humidity, the humidity will be increased by one transparency marker color. If the total gradient segment of real-time humidity is 5, and the activity block to be adjusted is located in the 2nd segment, then the element adjustment is... The humidity was increased by 20%, and the elements of the dynamic maps of all aggregation routes corresponding to the measured environmental data were adjusted separately to obtain the adjustment of each type of dynamic map ...

[0110] Based on the above-mentioned IoT-based mason bee pollination environment control system, the present invention also provides an IoT-based mason bee pollination environment control method, comprising the following steps:

[0111] Step 1: Divide the activity range of mason bees into regions to obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes;

[0112] Step 2: Construct a real-world virtual space, extract and process the living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain a time-series change map of the environment;

[0113] Step 3: Perform span classification on the environmental time series change map to obtain environmental classification gradient segments. Based on the environmental classification gradient segments, display and mark the hierarchical activity block map to obtain a color-covered activity map.

[0114] Step 4: Extract the traces from the living environment data and mark the traces in the color-overlay activity map to obtain a control feature display map. Adjust the environmental blocks in the control feature display map through the real-time virtual space to obtain an intelligent control scheme.

[0115] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An Internet of Things-based mason bee pollination environment control system, comprising a control center, characterized in that, The control center is connected to an environmental acquisition module, a data processing module, a response analysis module, and an integrated control module; The environmental acquisition module is used to delineate the activity range of mason bees, obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes. The data processing module is used to construct a real-time virtual space, extract and process living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain an environmental time series change map. The response analysis module is used to classify the environmental time series change map by span, obtain environmental classification gradient segments, and display and mark the hierarchical activity block map according to the environmental classification gradient segments to obtain a color-covered activity map. The integrated control module is used to extract traces from living environment data and mark the traces in a color-overlay activity map to obtain a control feature display map. Through real-time virtual space, environmental blocks are adjusted in the control feature display map to obtain an intelligent control scheme.

2. The Internet of Things-based mound bee pollination environment control system according to claim 1, characterized in that, The process of obtaining a hierarchical activity block map includes: The survival area of ​​mason bees is divided to obtain a safe range of activity. The boundaries of the obtained safe range of activity are supplemented to obtain a rectangular map of the activity range. Divide the activity range rectangle into regions to obtain evenly divided activity blocks, and record the activity range rectangle after regional division as a hierarchical activity block map.

3. The Internet of Things-based mound bee pollination environment control system according to claim 2, characterized in that, The process of collecting environmental data includes: Set up the data acquisition parameters for the hierarchical activity block map to obtain the sensor acquisition terminal; Based on the hierarchical activity block map, the activity of evenly divided activity blocks is collected by the sensor acquisition terminal to obtain living environment data; The acquired environmental data is recorded over time to obtain the data collection time points.

4. The Internet of Things-based mound bee pollination environment control system according to claim 1, characterized in that, The process of obtaining measurement environment data includes: Construct a live virtual space, upload the hierarchical activity block map to the live virtual space, and mark the collected living environment data at the corresponding positions on the hierarchical activity block map; Based on the real-world virtual space, the obtained living environment data is quantified and extracted to obtain measurement environment data.

5. A wall bee pollination environment control system based on the Internet of Things according to claim 1, characterized in that, The process of setting a statistical period to perform visualization feature extraction on measurement environment data includes: The statistical period is set according to the collection time node, and the measurement environment data is cleaned and sorted based on the statistical period to obtain the time series measurement sequence. A two-dimensional rectangular coordinate system is constructed based on the data acquisition time nodes. The time-series measurement sequences are uploaded to the two-dimensional rectangular coordinate system, and the time-series measurement sequences are combined in series to obtain environmental measurement curves. The two-dimensional rectangular coordinate system containing the environmental measurement curves is recorded as the environmental time-series change diagram.

6. A bee pollination environment control system based on the Internet of Things according to claim 1, characterized in that, The process of classifying the span of an environmental time-series change map includes: Obtain the environmental time series change map, set a sliding boundary axis for the environmental time series change map, upload the obtained sliding boundary axis to the starting position of the environmental time series change map, and set a shift interval for the obtained sliding boundary axis; Based on the environmental time-series change map, the sliding boundary axis is sequentially adjusted according to the obtained shift interval to obtain the environmental classification gradient segment.

7. A wall bee pollination environment control system based on the Internet of Things according to claim 1, characterized in that, The process of obtaining the color overlay activity map includes: Obtain environmental gradation gradient segments, perform hierarchical statistics on the obtained environmental gradation gradient segments based on the environmental time series change map, and obtain the total number of gradient segments; The transparency marker color is obtained by color grading based on the total amount of gradient segments in a real-world virtual space. Based on the data collection time point, the layered activity block map is color-covered using the transparency markers in the real-time virtual space to obtain a color-covered activity map.

8. A bee pollination environment control system based on the Internet of Things according to claim 1, characterized in that, The process of obtaining the regulatory feature visualization includes: Acquire survival environment data, extract traces from the survival environment data, and obtain activity traces within the range; Based on the statistical period, the color coverage activity map is integrated by range activity traces to obtain a dynamic trace color map. The obtained activity traces are uploaded to the trace color dynamic map. The trace color dynamic map is then marked based on the activity traces in the real-time virtual space to obtain a control feature display map.

9. A wall bee pollination environment control system based on the Internet of Things according to claim 1, characterized in that, The process of obtaining an intelligent control scheme includes: Accumulate the routes from the regulation feature display map to obtain a dynamic map of the aggregation route; By identifying the activity environment of the dynamic map of the aggregation route in a real-time virtual space, the results of regional activities can be obtained. Based on the results of regional activities, environmental adjustments are made to the dynamic map of aggregation routes to obtain activity blocks to be adjusted. Based on the real-time virtual space, the elements of the activity block to be regulated are adjusted to obtain an intelligent control plan.

10. A method for controlling the pollination environment of a mason bee based on an Internet of Things (IoT) system according to any one of claims 1 to 9, characterized in that, Includes the following steps: Step 1: Divide the activity range of mason bees into regions to obtain a hierarchical activity block map, collect living environment data, and mark the collection time nodes; Step 2: Construct a real-world virtual space, extract and process the living environment data to obtain measurement environment data, set a statistical period to extract visual features from the measurement environment data, and obtain a time-series change map of the environment; Step 3: Perform span classification on the environmental time series change map to obtain environmental classification gradient segments. Based on the environmental classification gradient segments, display and mark the hierarchical activity block map to obtain a color-covered activity map. Step 4: Extract the traces from the living environment data and mark the traces in the color-overlay activity map to obtain a control feature display map. Adjust the environmental blocks in the control feature display map through the real-time virtual space to obtain an intelligent control scheme.

Images