Disease vector biological monitoring and early warning system applied to container goods

Abstract

The invention discloses a vector biological monitoring and early warning system applied to container goods, which belongs to the technical field of vector biological monitoring and comprises a data acquisition module, an intelligent analysis module and an early warning module. The data acquisition module determines an initial acquisition frequency according to the cargo type, calculates a frequency acquisition regulation and control coefficient in combination with factors such as space, temperature and humidity of a monitoring area, and realizes accurate and dynamic data acquisition; the intelligent analysis module divides monitoring areas, accurately judges and confirms abnormal areas and gives an early warning in time by setting a vector information threshold value and an abnormal judgment duration; after receiving the early warning instruction, the early warning module analyzes the vector organisms, calculates a risk value, determines an early warning level and takes corresponding measures; according to the method, the problems that the monitoring frequency cannot be flexibly adjusted and the dynamics and the accuracy are lacked in the existing monitoring means are solved, the efficiency and the accuracy of monitoring and early warning of the container cargo pathogen organisms are effectively improved, and the cargo safety and the public health safety are guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of vector-borne disease monitoring, and specifically relates to a vector-borne disease monitoring and early warning system applied to containerized goods. Background Art

[0002] In international trade, containers, as the main carriers of goods transportation, their frequent cross-border movements provide convenient conditions for the spread of vector-borne diseases; vector-borne diseases may not only damage goods, but more seriously, they may spread diseases and threaten public health security; however, the existing vector-borne disease monitoring methods have the following problems:

[0003] The monitoring frequency cannot be adjusted according to different cargo types and environmental conditions, resulting in low monitoring efficiency; the monitoring of vector-borne diseases lacks dynamics and real-time nature, and potential risks cannot be detected and warned in a timely manner; the identification and risk assessment of vector-borne diseases are not accurate enough, it is difficult to effectively distinguish the harm levels of different vector-borne diseases, and hierarchical management cannot be achieved. For this reason, we propose a vector-borne disease monitoring and early warning system applied to containerized goods. Summary of the Invention

[0004] The purpose of the present invention is to provide a vector-borne disease monitoring and early warning system applied to containerized goods to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: A vector-borne disease monitoring and early warning system applied to containerized goods, including: a data collection module, an intelligent analysis module, and an early warning module:

[0006] Data collection module: Analyze the initial collection frequency according to the cargo type loaded in the container, divide the space inside the container into several monitoring areas, for each monitoring area, analyze the sampling frequency adjustment coefficient according to the monitoring area space, the cargo type loaded, the temperature value, and the humidity value, and analyze the vector information collection frequency of the monitoring area according to the initial collection frequency and the sampling frequency adjustment coefficient;

[0007] Intelligent analysis module: Divide the monitoring area into several monitoring sub-areas, analyze the vector information in the monitoring sub-areas, judge whether it is a confirmed abnormal area, if a confirmed abnormal area appears in the monitoring area, generate a biological early warning instruction and send it to the early warning module;

[0008] Early warning module: When receiving the early warning instruction, mark the monitoring area with a confirmed abnormal area as a risk monitoring area, analyze the vector-borne diseases existing in the risk monitoring area, calculate the vector risk value corresponding to the risk monitoring area, and based on this, sort the risk monitoring areas to obtain the monitoring area risk ranking, then analyze the container vector risk value, and judge the early warning level based on this, and implement corresponding measures according to the early warning level.

[0009] Preferably, the specific process for the data acquisition module to analyze the initial acquisition frequency is as follows:

[0010] Install a vector detection sensor inside the container. The vector detection sensor collects vector information inside the container. The vector detection sensor includes: a thermal infrared sensor, an odor sensor, and a vibration sensor; the vector information includes: temperature, odor type, concentration of the corresponding type of odor, and vibration frequency.

[0011] Obtain the type of goods loaded in the container. The types of goods include: agricultural products, meat products, aquatic products, textiles, chemical products, and electronic products.

[0012] Establish a goods vector library. The goods vector library covers all types of goods. For each type of goods, there is a dedicated vector organism table in the goods vector library corresponding to it. The vector organism table lists all the vector organisms that can breed and be attracted by this type of goods.

[0013] In addition, each vector organism in the vector organism table is assigned a hazard value for this type of goods.

[0014] For each type of goods loaded in the container, first obtain the loading volume of this type of goods in the container; then match this type of goods with all the types of goods in the goods vector library, output the corresponding vector organism table, and then add up the hazard values corresponding to all the vector organisms in the vector organism table to obtain the goods vector value of this type of goods. By multiplying the loading volume corresponding to the type of goods by the corresponding goods vector value, the cargo-borne vector value corresponding to this type of goods is obtained.

[0015] Then sum up the cargo-borne vector values corresponding to all types of goods in the container to obtain the cargo collection risk value.

[0016] Preset several cargo collection risk value intervals. Each cargo collection risk value interval corresponds to a basic acquisition frequency. Match the cargo collection risk value corresponding to the container with all the cargo collection risk value intervals, and output the corresponding basic acquisition frequency.

[0017] Preferably, the specific process for the data acquisition module to analyze the acquisition frequency adjustment coefficient and analyze the vector information acquisition frequency of the monitoring area according to the initial acquisition frequency and the acquisition frequency adjustment coefficient is as follows:

[0018] Divide the space inside the container into several monitoring areas. For each monitoring area, scan the monitoring area with a laser scanner to obtain the three-dimensional coordinate points on the surfaces of all objects within the monitoring area. Combine all the three-dimensional coordinate points to form point cloud data, and use a spatial clustering algorithm to process the point cloud data, dividing the point cloud data into a cargo area, a container wall area, and a void area. The void area includes: the spaces between goods, the spaces between the goods and the adjacent container walls, and the voids inside the goods stacks.

[0019] Calculate the volume of each void area respectively through a voxelization algorithm, and then sum up the volumes of all the void areas to obtain the total void volume KV.

[0020] For each monitoring area, obtain the types of goods loaded in the detection area, and match the corresponding vector - borne organism table for the goods types. Obtain the temperature range and humidity range suitable for the survival of each vector - borne organism in the vector - borne organism table. By using the arithmetic mean calculation method, calculate the mean values of the temperature ranges and humidity ranges suitable for the survival of all vector - borne organisms in the vector - borne organism table respectively, to obtain the average temperature range and average humidity range suitable for the survival of all vector - borne organisms in the vector - borne organism table, and denote them as the vector - borne average temperature area and the vector - borne average humidity area respectively.

[0021] Obtain the temperature value and humidity value of the monitoring area, calculate the absolute value of the difference between the temperature value of the monitoring area and the mid - point value of the vector - borne average temperature area to obtain the temperature deviation value WP, and at the same time calculate the absolute value of the difference between the humidity value of the monitoring area and the mid - point value of the vector - borne average humidity area to obtain the humidity deviation value SP.

[0022] After normalizing the total void volume KV, the temperature deviation value WP, and the humidity deviation value SP, use the formula: , to obtain the sampling frequency regulation coefficient, where a1, a2, and a3 are preset weight coefficients.

[0023] For each monitoring area, multiply the sampling frequency regulation coefficient corresponding to the monitoring area by the basic sampling frequency to obtain the vector - borne information sampling frequency for the monitoring area, and collect the vector - borne information within the monitoring area according to the vector - borne information sampling frequency.

[0024] Preferably, the specific process for the intelligent analysis module to generate a biological warning instruction is as follows:

[0025] For each monitoring area, set normal range thresholds for each item of vector - borne information respectively, and divide the monitoring area into several monitoring sub - areas.

[0026] For each monitored area, obtain the values corresponding to various vector information within the monitored area at each collection time, match the values of various vector information within the monitored area at each collection time with their corresponding normal range thresholds. If the value of the vector information exceeds its corresponding normal range threshold, mark the monitored area as a suspected abnormal area;

[0027] Taking the appearance time of the suspected abnormal area as the starting time, continuously record the duration of the appearance of the suspected abnormal area, denoted as the abnormal determination duration;

[0028] Compare the abnormal determination duration of the monitored area with the corresponding threshold. If the abnormal determination duration is greater than or equal to the corresponding threshold, mark the suspected abnormal area as a confirmed abnormal area;

[0029] When a confirmed abnormal area appears in the monitored area, generate a warning instruction for the vector organisms in the container and send it to the warning module.

[0030] Preferably, the specific process for the intelligent analysis module to judge the confirmed abnormal area is as follows:

[0031] If the monitored area is marked as a suspected abnormal area, but the corresponding abnormal determination duration does not exceed the corresponding threshold, the monitored area remains a normal monitored area. And when the monitored area is marked as a suspected abnormal area again later, take the time when it is newly marked as a suspected abnormal area as the new starting time and recalculate the abnormal determination duration;

[0032] If none of the vector information in the confirmed abnormal area exceeds its corresponding normal range threshold, mark the confirmed abnormal area as a suspected recovery area; taking the appearance time of the suspected recovery area as the starting time, continuously record the duration of the appearance of the suspected recovery area, denoted as the recovery determination duration;

[0033] Preset a recovery determination duration threshold. If the recovery determination duration is greater than or corresponds to the threshold, mark the confirmed abnormal area back as a normal monitored area;

[0034] If the confirmed abnormal area is marked as a suspected recovery area, but the corresponding recovery determination duration does not exceed the corresponding threshold, the confirmed abnormal area remains a confirmed abnormal area. And when the confirmed abnormal area is marked as a suspected recovery area again later, take the time when it is newly marked as a suspected recovery area as the new starting time and recalculate the recovery determination duration.

[0035] Preferably, the specific process for the warning module to analyze the vector organisms existing in the risk monitoring area is as follows:

[0036] Mark the monitored area where a confirmed abnormal area appears as a risk monitoring area. For each risk monitoring area, preset a monitoring period, and obtain the values corresponding to each vector information in each confirmed abnormal area at each collection time within the monitoring period;

[0037] For each confirmed abnormal area, collect the vector information of vectors exceeding the corresponding normal range at each collection time within the confirmed area, and mark these vector information items exceeding the normal range as key detection information;

[0038] For each item of key detection information, calculate the average value of the corresponding values at each collection time within the monitoring period, and record this average value as the characteristic monitoring value of this key detection information within the monitoring period;

[0039] Integrate the characteristic monitoring values corresponding to all vector information to construct a vector characteristic value judgment library; obtain the vector biological list corresponding to the goods loaded in the confirmed area. For each vector biological in this list, a preset vector characteristic evaluation set is associated, and the characteristic monitoring value range of each key detection information corresponding to the presence of this vector biological is covered in the vector characteristic evaluation set;

[0040] For each vector biological in the vector biological list, sequentially extract the characteristic monitoring values corresponding to the key detection information corresponding to the vector biological characteristic evaluation set from the vector characteristic value judgment library, and combine the characteristic monitoring values corresponding to these key detection information to form the actual characteristic vector representing the suspected presence of this vector biological in the confirmed abnormal area;

[0041] Combine the characteristic monitoring value ranges corresponding to the key detection information of the vector biological in the vector characteristic evaluation set to form a standard characteristic vector;

[0042] Through the cosine similarity algorithm, calculate the similarity between the actual characteristic vector and the standard characteristic vector to obtain a biological similarity value; if the biological similarity value is greater than the corresponding preset threshold, it is determined that this type of vector biological exists in the confirmed area, and the vector biological existing in the confirmed area is marked as a harmful biological.

[0043] Preferably, the specific process of the warning module analyzing and obtaining the risk ranking of the monitoring area is as follows:

[0044] For each harmful biological, obtain the characteristic monitoring values corresponding to the key detection information for determining the existence of this harmful biological in the confirmed abnormal area; at the same time, obtain the harm value of this harmful biological to the type of goods loaded in the confirmed abnormal area. By multiplying the characteristic monitoring values corresponding to each key detection information by the harm value corresponding to this harmful biological, obtain the correlation values corresponding to each key detection information, assign a weight coefficient to the correlation value corresponding to each key detection information, and then multiply the correlation values corresponding to each key detection information by the corresponding weight coefficient and add them up to obtain the vector risk value;

[0045] The vector risk value of the confirmed abnormal area is obtained by adding up the corresponding vector risk values of all hazardous organisms in the confirmed abnormal area. Then, the vector risk value of all confirmed abnormal areas in the risk monitoring area is added up to obtain the vector risk value of the risk monitoring area.

[0046] All risk monitoring areas in the container are sorted from high to low according to their corresponding disease vector risk values to obtain the risk ranking of the monitoring areas.

[0047] Preferably, the specific process of the early warning module determining the early warning level and implementing corresponding measures according to the early warning level is as follows:

[0048] The container disease vector risk value is obtained by adding up the disease vector risk values corresponding to all risk monitoring areas in the container. This value is recorded as the container risk value. Multiple warning levels are preset, each corresponding to a container risk value interval, and each warning level corresponds to a corresponding warning measure.

[0049] By matching the container risk value corresponding to the container with the container risk value interval corresponding to all warning levels, the corresponding warning level is output. Then, according to the corresponding warning measures and the risk ranking of the monitoring area, each risk monitoring area is processed in turn. After the processing is completed, the warning release instruction is generated;

[0050] The warning update interval is preset, with each warning instruction as the starting moment and the corresponding warning cancellation instruction as the end moment, to obtain several warning cycles. For each warning cycle, its starting moment is the starting moment. Whenever the warning update interval is reached, the warning level is recalculated.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] (1) The disease vector monitoring and early warning system and system applied to container cargo establishes a cargo disease vector database, calculates the cargo disease vector value based on the disease vector table matched with different cargo types and the corresponding hazard value, and combines the cargo loading volume to determine the cargo collection risk value and the basic collection frequency; at the same time, the sampling frequency control coefficient is analyzed based on the temperature deviation value, humidity deviation value and total volume of the gap in the monitoring area, and the collection frequency of disease vector information is determined for each monitoring area based on the basic collection frequency and the sampling frequency control coefficient of each monitoring area; at the same time, an update interval of the sampling frequency control coefficient is set to achieve accurate setting and dynamic and flexible adjustment of the monitoring frequency, thereby improving the monitoring efficiency.

[0053] (2) The vector-borne organism monitoring and early warning system and system applied to container cargo collects vector information through a preset monitoring period, screens key detection information and calculates characteristic monitoring values, compares them with the vector characteristic evaluation set to determine the harmful organisms, and then calculates the vector risk values at all levels; this method can accurately locate the vector risk, and at the same time, by calculating the overall vector risk value of the risk monitoring area and the container, the warning level can be judged to achieve hierarchical management; through the risk ranking of the monitoring area, all risk monitoring areas in the container can be ranked from high to low according to their corresponding vector risk values, so that management personnel can give priority to high-risk areas, reasonably allocate resources, and improve the targeted and effective prevention and control.

[0054] (3) The disease vector monitoring and early warning system and system applied to container cargo, when processing a large amount of collected disease vector information, adopts a dual judgment mechanism of normal range threshold comparison and abnormal judgment time, which greatly optimizes the data processing flow, reduces the data processing volume, and effectively reduces the misjudgment caused by instantaneous data fluctuations, ensuring the reliability of the monitoring results.

[0055] (4) The vector-borne pathogen monitoring and early warning system and system applied to container cargo divides the early warning cycle into the starting point of each early warning instruction and the end point of the generation of the early warning release instruction. The early warning level is recalculated when the update interval is reached in each cycle, realizing dynamic monitoring of vector-borne pathogen risks, ensuring timely response to risk changes, avoiding damage to cargo due to delayed risk assessment, and ensuring the safety of container cargo during the entire transportation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flowchart of the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 , the present invention provides a disease vector monitoring and early warning system for container cargo, comprising: a data acquisition module, an intelligent analysis module and an early warning module;

[0060] The data acquisition module analyzes the initial acquisition frequency according to the types of goods loaded in the container, divides the space inside the container into several monitoring areas. For each monitoring area, according to the space of the monitoring area, the types of goods loaded, the temperature value and the humidity value, it analyzes the acquisition frequency adjustment coefficient, and analyzes the acquisition frequency of vector information in the monitoring area according to the initial acquisition frequency and the acquisition frequency adjustment coefficient. The specific process is as follows:

[0061] Vector detection sensors are installed inside the container, and vector information inside the container is collected through the vector detection sensors. The vector detection sensors include: thermal infrared sensors, odor sensors, vibration sensors; the vector information includes: temperature, odor type, and the concentration of the corresponding type of odor, vibration frequency;

[0062] Obtain the types of goods loaded in the container. The types of goods include: agricultural products, meat products, aquatic products, textiles, chemical products, electronic products, etc.;

[0063] Establish a goods vector library, which covers all types of goods. For each type of goods, there is a special vector organism table in the goods vector library corresponding to it. All vector organisms that may breed and attract this type of goods are listed in the vector organism table;

[0064] In addition, each vector organism in the vector organism table is assigned a harm value for this type of goods;

[0065] For each type of goods loaded in the container, first obtain the loading volume of this type of goods in the container; then match this type of goods with all types of goods in the goods vector library, output the corresponding vector organism table, and then add up the harm values corresponding to all vector organisms in this vector organism table to obtain the goods vector value of this type of goods. By multiplying the loading volume corresponding to the type of goods by the corresponding goods vector value, the cargo load vector value corresponding to this type of goods is obtained;

[0066] Then sum up the cargo load vector values corresponding to all types of goods in the container to obtain the cargo collection risk value;

[0067] Preset several cargo collection risk value intervals, and each cargo collection risk value interval corresponds to a basic acquisition frequency. Match the cargo collection risk value corresponding to the container with all cargo collection risk value intervals, and output the corresponding basic acquisition frequency;

[0068] Divide the space inside the container into several monitoring areas. For each monitoring area, use a laser scanner to scan the monitoring area to obtain the three-dimensional coordinate points of all object surfaces within the monitoring area. Combine all the three-dimensional coordinate points to form point cloud data, and use a spatial clustering algorithm to process the point cloud data, dividing the point cloud data into different areas such as cargo areas, container wall areas, and void areas; the void areas include: the spaces between goods, the spaces between goods and the adjacent container walls, and the cavities inside the cargo stacks.

[0069] Calculate the volume of each void area through a voxelization algorithm, and then sum up the volumes of all void areas to obtain the total void volume KV. The larger the total void volume, the larger the space where vectors are likely to breed, hide, and move.

[0070] For each monitoring area, obtain the types of goods loaded within the detection area, and match the corresponding vector biological table for the goods types. Obtain the temperature ranges and humidity ranges suitable for the survival of each vector in the vector biological table. By using the arithmetic mean calculation method, calculate the mean values of the temperature ranges and humidity ranges suitable for the survival of all vectors in the vector biological table respectively, to obtain the average temperature range and average humidity range suitable for the survival of all vectors in the vector biological table, and denote them as the vector average temperature area and the vector average humidity area respectively.

[0071] Obtain the temperature value and humidity value of the monitoring area. Calculate the absolute value of the difference between the temperature value of the monitoring area and the midpoint value of the vector average temperature area to obtain the temperature deviation value WP. At the same time, calculate the absolute value of the difference between the humidity value of the monitoring area and the midpoint value of the vector average humidity area to obtain the humidity deviation value SP. The smaller the temperature deviation value and humidity deviation value, the closer the actual temperature and humidity within the monitoring area are to the temperature and humidity conditions suitable for the survival of the vectors recorded in the corresponding vector biological table.

[0072] After normalizing the total void volume KV, the temperature deviation value WP, and the humidity deviation value SP, use the formula: , to obtain the sampling frequency regulation coefficient , where a1, a2, and a3 are preset weight coefficients; set the update interval for the sampling frequency regulation coefficient. Whenever the update interval is reached, recalculate the sampling frequency regulation coefficient within the monitoring area.

[0073] For each monitoring area, multiply the sampling frequency regulation coefficient corresponding to the monitoring area by the basic sampling frequency to obtain the vector information sampling frequency for the monitoring area, and collect the vector information within the monitoring area according to the vector information sampling frequency.

[0074] It should be noted that by establishing a cargo vector library, based on the vector organism list and corresponding hazard values matched for different cargo types, and combining with the cargo loading volume to calculate the cargo vector value, and then determining the cargo collection risk value and the basic collection frequency, it is possible to set the initial monitoring frequency accurately for the potential vector risk differences of different cargo types; dividing the space inside the container into multiple monitoring areas, and analyzing the collection frequency adjustment coefficient according to factors such as the cargo type, temperature, humidity, and void volume in each area, further refining the monitoring granularity, enabling a more accurate grasp of the vector risk in each area and achieving a more efficient allocation of monitoring resources; the collection frequency adjustment coefficient will be updated according to real-time data such as the temperature deviation value, humidity deviation value, and total void volume in the monitoring area to adapt to the potentially changing vector risk environment and achieve dynamic and flexible adjustment of the monitoring frequency.

[0075] The intelligent analysis module divides the monitoring area into several monitoring sub-areas, analyzes the vector information in the monitoring sub-areas, and determines whether it is a confirmed abnormal area. If a confirmed abnormal area appears in the monitoring area, a biological early warning instruction will be issued. The specific process is as follows:

[0076] For each monitoring area, set the normal range threshold for each item of vector information respectively, and divide the monitoring area into several monitoring sub-areas;

[0077] For each monitoring sub-area, obtain the values corresponding to each item of vector information in the monitoring sub-area at each collection moment, and match the values of each item of vector information in the monitoring sub-area at each collection moment with their corresponding normal range thresholds. If the value of the vector information exceeds its corresponding normal range threshold, mark this monitoring sub-area as a suspected abnormal sub-area;

[0078] Taking the appearance moment of the suspected abnormal sub-area as the starting moment, continuously record the duration of the appearance of the suspected abnormal sub-area, which is recorded as the abnormal determination duration, and there is always a situation where the vector information exceeds the corresponding normal range threshold within the abnormal determination duration;

[0079] Preset the abnormal determination duration threshold, compare the abnormal determination duration of the monitoring sub-area with the corresponding threshold. If the abnormal determination duration is greater than or equal to the corresponding threshold, mark this suspected abnormal sub-area as a confirmed abnormal area;

[0080] If the monitoring sub-area is marked as a suspected abnormal sub-area, but the corresponding abnormal determination duration does not exceed the corresponding threshold, this monitoring sub-area is still a normal monitoring sub-area, and when this monitoring sub-area is marked as a suspected abnormal sub-area again later, use the moment when it is re-marked as a suspected abnormal this time as the new starting moment and recalculate the abnormal determination duration;

[0081] If none of the vector information in the diagnosed abnormal area exceeds its corresponding normal range threshold, mark the diagnosed abnormal area as a suspected recovery area; starting from the moment when the suspected recovery area appears, continuously record the duration of the appearance of the suspected recovery area, denoted as the recovery determination duration; during the recovery determination duration, no vector information exceeds its corresponding normal range threshold.

[0082] Preset a recovery determination duration threshold. If the recovery determination duration is greater than or equal to the corresponding threshold, mark the diagnosed abnormal area back as a normal monitoring area.

[0083] If the diagnosed abnormal area is marked as a suspected recovery area, but the corresponding recovery determination duration does not exceed the corresponding threshold, the diagnosed abnormal area remains a diagnosed abnormal area. And when the diagnosed abnormal area is marked as a suspected recovery area again later, use the moment when it is marked as a suspected recovery area this time as a new starting moment to recalculate the recovery determination duration.

[0084] When a diagnosed abnormal area appears in the monitoring area, generate a container vector biological early warning instruction and send it to the early warning module.

[0085] It should be noted that when processing a large amount of vector information collected, for each item of vector information, first conduct a simple comparison with the normal range threshold to determine whether to issue an early warning through this method. This strategy greatly optimizes the data processing process and significantly reduces the amount of data processed; in the actual monitoring scenario, the collection frequency of vector information in the container is relatively high, resulting in a large amount of data; if all data is deeply analyzed, it will not only consume a large amount of computing resources and time, but also may lead to a decrease in the system operation efficiency and an inability to respond to vector biological risks in a timely manner; for the determination of suspected abnormal areas, not only consider whether the vector information exceeds the threshold, but also make a comprehensive judgment in combination with the abnormal determination duration; the same is true for the recovery determination of diagnosed abnormal areas; this dual judgment mechanism effectively reduces misjudgments caused by instantaneous data fluctuations and ensures the reliability of the monitoring results.

[0086] When the early warning module receives the early warning instruction, mark the monitoring area where the diagnosed abnormal area appears as a risk monitoring area, analyze the vector organisms existing in the risk monitoring area, calculate the corresponding vector risk value of the risk monitoring area, and based on this, sort the risk monitoring areas to obtain the monitoring area risk ranking. Subsequently, analyze the container vector risk value and judge the early warning level accordingly, and implement corresponding measures according to the early warning level. The specific process is as follows:

[0087] Mark the monitoring area where the diagnosed abnormal area appears as a risk monitoring area. For each risk monitoring area, preset a monitoring period, and obtain the values corresponding to each vector information in each diagnosed abnormal area at each collection moment within the monitoring period.

[0088] For each confirmed abnormal area, collect the vector information within the confirmed area that exceeds the corresponding normal range at each collection time, and mark these vector information items that exceed the normal range as key detection information;

[0089] For each item of key detection information, calculate the average value of the corresponding values at each collection time within the monitoring period, and record this average value as the characteristic monitoring value of this key detection information within the monitoring period;

[0090] Integrate the characteristic monitoring values corresponding to all vector information to construct a vector characteristic value judgment library; obtain the vector organism list corresponding to the goods loaded in the confirmed area. For each vector organism in this list, there is a preset vector characteristic evaluation set associated with it, and the vector characteristic evaluation set covers the range of characteristic monitoring values of each key detection information when this vector organism exists;

[0091] For each vector organism in the vector organism list, sequentially extract from the vector characteristic value judgment library the characteristic monitoring values corresponding to each key detection information corresponding to the vector organism's characteristic evaluation set, and combine these characteristic monitoring values corresponding to the key detection information to form the actual characteristic vector representing the suspected presence of this vector organism in the confirmed abnormal area;

[0092] Combine the range of characteristic monitoring values corresponding to each key detection information corresponding to the vector organism in the vector characteristic evaluation set to form a standard characteristic vector;

[0093] Through the cosine similarity algorithm, calculate the similarity between the actual characteristic vector and the standard characteristic vector to obtain the biological similarity value; preset the vector organism similarity value judgment threshold; if the biological similarity value is greater than the corresponding preset threshold, it is determined that this type of vector organism exists in the confirmed area, and the vector organism existing in the confirmed area is marked as a harmful organism;

[0094] For each harmful organism, obtain the characteristic monitoring values corresponding to each key detection information that determines the presence of this harmful organism in the confirmed abnormal area; at the same time, obtain the harm value of this harmful organism to the type of goods loaded in the confirmed abnormal area. By multiplying the characteristic monitoring values corresponding to each key detection information by the harm value corresponding to this harmful organism, obtain the correlation values corresponding to each key detection information. Assign a weight coefficient to each correlation value corresponding to each key detection information, and then add the correlation values corresponding to each key detection information multiplied by the corresponding weight coefficients to obtain the vector risk value;

[0095] By adding up the vector risk values corresponding to all harmful organisms in the confirmed abnormal area, obtain the vector risk value of the confirmed abnormal area, and then add up the vector risk values of all confirmed abnormal areas in the risk monitoring area to obtain the vector risk value of the risk monitoring area;

[0096] Sort all the risk monitoring areas in the container in descending order according to their corresponding vector risks to obtain the risk ranking of the monitoring areas;

[0097] By adding up the vector risk values corresponding to all the risk monitoring areas in the container, obtain the vector risk value of the container, denoted as the container risk value. Preset multiple warning levels, each warning level corresponding to a container risk value range, and each warning level corresponding to a corresponding warning measure;

[0098] Match the container risk value corresponding to the container with the container risk value ranges corresponding to all warning levels, output the corresponding warning level, and process each risk monitoring area in turn according to the warning measure and the risk ranking of the monitoring areas. After the processing is completed, generate a warning cancellation instruction;

[0099] Preset a warning update interval. Taking each occurrence of a warning instruction as the start time and the generation of the corresponding warning cancellation instruction as the end time, obtain several warning cycles. For each warning cycle, taking its start time as the start time, whenever the warning update interval is reached, recalculate the warning level.

[0100] It should be noted that after the warning module receives a warning instruction, mark the monitoring area where a confirmed abnormal area appears as a risk monitoring area; collect vector information through preset monitoring periods, screen key detection information and calculate characteristic monitoring values, compare with the vector characteristic evaluation set to determine harmful organisms, and then calculate the vector risk values at all levels; this method can accurately locate the vector biological risk. At the same time, by calculating the vector risk values of the risk monitoring areas and the container as a whole, the warning level can be judged, realizing hierarchical management, enabling managers to take targeted prevention and control measures according to different risk levels, reasonably allocate resources, and improve the pertinence and effectiveness of prevention and control; divide the warning cycle with each warning instruction as the start and the generation of the warning cancellation instruction as the end. When the update interval is reached within each cycle, recalculate the warning level; this implementation method realizes the dynamic monitoring of the vector biological risk, ensures timely response to risk changes, avoids damage to goods caused by lagging risk assessment, and guarantees the safety of container goods during the entire transportation process; prioritize the processing of high-risk areas according to the vector risk value ranking of the risk monitoring areas, realizing the optimal allocation of resources.

[0101] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vector-borne disease monitoring and early warning system applied to containerized goods, comprising: A data acquisition module, an intelligent analysis module, and an early warning module, characterized in that: Data acquisition module: Analyze the initial acquisition frequency according to the type of goods loaded in the container, divide the space inside the container into several monitoring areas, and for each monitoring area, analyze the acquisition frequency adjustment coefficient according to the space of the monitoring area, the type of goods loaded, the temperature value, and the humidity value, and analyze the acquisition frequency of vector information in the monitoring area according to the initial acquisition frequency and the acquisition frequency adjustment coefficient; Intelligent analysis module: Divide the monitoring area into several monitoring sub-areas, analyze the vector information in the monitoring sub-areas, and judge whether it is a confirmed abnormal area. If a confirmed abnormal area appears in the monitoring area, generate a biological early warning instruction and send it to the early warning module; Early warning module: When receiving the early warning instruction, mark the monitoring area where the confirmed abnormal area appears as a risk monitoring area, analyze the vector organisms existing in the risk monitoring area, calculate the vector risk value corresponding to the risk monitoring area, and based on this, sort the risk monitoring areas to obtain the monitoring area risk ranking. Subsequently, analyze the container vector risk value, and judge the early warning level based on this, and implement corresponding measures according to the early warning level.

2. The vector-borne disease biological monitoring and early warning system applied to containerized goods according to claim 1, wherein: The specific process of the data acquisition module analyzing the initial acquisition frequency is as follows: Install vector detection sensors inside the container, and collect vector information in the container through the vector detection sensors. The vector detection sensors include: thermal infrared sensors, odor sensors, and vibration sensors; the vector information includes: temperature, odor type, and the concentration of the corresponding type of odor, vibration frequency; Obtain the type of goods loaded in the container. The types of goods include: agricultural products, meat products, aquatic products, textiles, chemical products, and electronic products; Establish a goods vector library, which covers all types of goods. For each type of goods, there is a dedicated vector organism table in the goods vector library corresponding to it. The vector organism table lists all the vector organisms that can breed and attract this type of goods; In addition, each vector organism in the vector organism table is assigned a harm value for this type of goods; For each type of goods loaded in the container, first obtain the loading volume of this type of goods in the container; then match this type of goods with all the types of goods in the goods vector library, output the corresponding vector organism table, and then add up the harm values corresponding to all the vector organisms in the vector organism table to obtain the goods vector value of this type of goods. By multiplying the loading volume corresponding to the type of goods by the corresponding goods vector value, the cargo load vector value corresponding to this type of goods is obtained; Subsequently, sum up the cargo load vector values corresponding to all types of goods in the container to obtain the cargo collection risk value; Preset several cargo collection risk value intervals, and each cargo collection risk value interval corresponds to a basic acquisition frequency. Match the cargo collection risk value corresponding to the container with all the cargo collection risk value intervals, and output the corresponding basic acquisition frequency.

3. The vector biological monitoring and early warning system for containerized goods according to claim 2, characterized in that: The specific process of the data acquisition module analyzing the acquisition frequency adjustment coefficient and analyzing the acquisition frequency of vector information in the monitoring area according to the initial acquisition frequency and the acquisition frequency adjustment coefficient is as follows: Divide the space inside the container into several monitoring areas. For each monitoring area, use a laser scanner to scan the monitoring area to obtain the three-dimensional coordinate points of all object surfaces within the monitoring area. Combine all the three-dimensional coordinate points with each other to form point cloud data, and use a spatial clustering algorithm to process the point cloud data to divide the point cloud data into a cargo area, a container wall area, and a void area. The void area includes: the intervals between goods, the space between the goods and the adjacent container wall, and the cavities inside the cargo stack. Calculate the volume of each void area through a voxelization algorithm respectively, and then sum up the volumes of all the void areas to obtain the total void volume KV. For each monitoring area, obtain the types of goods loaded in the detection area, and match the vector-borne organism table corresponding to the goods type. Obtain the temperature range and humidity range suitable for the survival of each vector-borne organism in the vector-borne organism table. By using the arithmetic mean calculation method, calculate the mean values of the temperature range and humidity range suitable for the survival of all vector-borne organisms in the vector-borne organism table respectively, to obtain the average temperature range and average humidity range suitable for the survival of all vector-borne organisms in the vector-borne organism table, and record them as the vector-borne average temperature area and the vector-borne average humidity area respectively. Obtain the temperature value and humidity value of the monitoring area, calculate the absolute value of the difference between the temperature value of the monitoring area and the midpoint value of the vector-borne average temperature area to obtain the temperature deviation value WP, and at the same time calculate the absolute value of the difference between the humidity value of the monitoring area and the midpoint value of the vector-borne average humidity area to obtain the humidity deviation value SP. After normalizing the total void volume KV, temperature offset value WP, and humidity offset value SP, using the formula: , the sampling frequency regulation coefficient is obtained , where a1, a2, and a3 are preset weight coefficients; For each monitoring area, multiply the sampling frequency regulation coefficient corresponding to the monitoring area by the basic sampling frequency to obtain the vector-borne information sampling frequency of the monitoring area, and collect the vector-borne information within the monitoring area according to the vector-borne information sampling frequency.

4. The vector biological monitoring and early warning system applied to containerized goods according to claim 3, characterized in that: The specific process of the intelligent analysis module generating a biological warning instruction is as follows: For each monitoring area, set the normal range threshold for each item of vector-borne information respectively, and divide the monitoring area into several monitoring sub-areas. For each monitoring sub-area, obtain the values corresponding to each item of vector-borne information within the monitoring sub-area at each collection moment, and match the values of each item of vector-borne information within the monitoring sub-area at each collection moment with their corresponding normal range thresholds. If the value of the vector-borne information exceeds its corresponding normal range threshold, mark this monitoring sub-area as a suspected abnormal sub-area. Taking the appearance moment of the suspected abnormal sub-area as the starting moment, continuously record the duration of the appearance of the suspected abnormal sub-area, and record it as the abnormal determination duration. Compare the abnormal determination duration of the monitoring sub-area with the corresponding threshold. If the abnormal determination duration is greater than or equal to the corresponding threshold, mark this suspected abnormal sub-area as a confirmed abnormal area. When a confirmed abnormal area appears within the monitoring area, generate a container vector-borne organism warning instruction and send it to the warning module.

5. The vector-borne disease biological monitoring and early warning system applied to containerized goods according to claim 4, characterized in that: The specific process of the intelligent analysis module judging the confirmed abnormal area is as follows: If the monitoring sub-area is marked as a suspected abnormal sub-area, but the corresponding abnormal determination duration does not exceed the corresponding threshold, this monitoring sub-area is still a normal monitoring sub-area, and when this monitoring sub-area is marked as a suspected abnormal sub-area again later, use the moment when it is re-marked as a suspected abnormal this time as the new starting moment, and recalculate the abnormal determination duration. If none of the vector-borne information in the diagnosed abnormal area exceeds its corresponding normal range threshold, then mark the diagnosed abnormal area as a suspected recovery area; Taking the appearance time of the suspected recovery area as the starting time, continuously record the duration of the appearance of the suspected recovery area, denoted as the recovery determination duration; Preset a recovery determination duration threshold. If the recovery determination duration is greater than or equal to the corresponding threshold, then mark the diagnosed abnormal area back as a normal monitoring area; If the diagnosed abnormal area is marked as a suspected recovery area, but the corresponding recovery determination duration does not exceed the corresponding threshold, the diagnosed abnormal area remains a diagnosed abnormal area. And when the diagnosed abnormal area is marked as a suspected recovery area again later, take the time when it is re-marked as a suspected recovery area this time as the new starting time, and recalculate the recovery determination duration.

6. The vector-borne disease monitoring and early warning system applied to containerized goods according to claim 5, wherein: The specific process of the warning module analyzing the vector-borne organisms existing in the risk monitoring area is as follows: Mark the monitoring area where there is a diagnosed abnormal area as a risk monitoring area. For each risk monitoring area, preset a monitoring period, and obtain the values corresponding to each vector-borne information in each diagnosed abnormal area at each collection time within the monitoring period; For each diagnosed abnormal area, collect the vector-borne information that exceeds the corresponding normal range at each collection time within the diagnosed area, and mark these vector-borne information items that exceed the normal range as key detection information; For each item of key detection information, calculate the average value of the corresponding values at each collection time within the monitoring period, and record this average value as the characteristic monitoring value of this key detection information within the monitoring period; Integrate the characteristic monitoring values corresponding to all vector-borne information to construct a vector-borne characteristic value judgment library; obtain the vector-borne organism list corresponding to the goods loaded in the diagnosed area. For each vector-borne organism in this list, there is a preset vector-borne characteristic evaluation set associated with it, and the vector-borne characteristic evaluation set covers the range of the characteristic monitoring values of the corresponding key detection information when this vector-borne organism exists; For each vector-borne organism in the vector-borne organism list, sequentially extract from the vector-borne characteristic value judgment library the characteristic monitoring values corresponding to the key detection information corresponding to the vector-borne organism characteristic evaluation set of this vector-borne organism, and combine the characteristic monitoring values corresponding to these key detection information to form the actual characteristic vector representing the suspected presence of this vector-borne organism in the diagnosed abnormal area; Combine the range of the characteristic monitoring values corresponding to the key detection information corresponding to the vector-borne organism in the vector-borne characteristic evaluation set to form a standard characteristic vector; Through the cosine similarity algorithm, calculate the similarity between the actual characteristic vector and the standard characteristic vector to obtain a biological similarity value; if the biological similarity value is greater than the corresponding preset threshold, then determine that this type of vector-borne organism exists in the diagnosed area, and mark the vector-borne organism existing in the diagnosed area as a harmful organism.

7. The vector biological monitoring and early warning system applied to containerized goods according to claim 6, characterized in that: The specific process of the warning module analyzing and obtaining the risk ranking of the monitoring area is as follows: For each harmful organism, obtain the characteristic monitoring values corresponding to each key detection information that determines the presence of the harmful organism in the confirmed abnormal area; at the same time, obtain the harm value of the harmful organism to the type of goods loaded in the confirmed abnormal area. By multiplying the characteristic monitoring values corresponding to each key detection information by the harm value corresponding to the harmful organism, the correlation values corresponding to each key detection information are obtained. A weight coefficient is assigned to the correlation value corresponding to each key detection information. Subsequently, after multiplying the correlation values corresponding to each key detection information by the corresponding weight coefficients and then adding them up, the vector-borne risk value is obtained; By adding up the vector-borne risk values corresponding to all harmful organisms in the confirmed abnormal area, the vector-borne risk value of the confirmed abnormal area is obtained. Subsequently, by adding up the vector-borne risk values of all confirmed abnormal areas in the risk monitoring area, the vector-borne risk value of the risk monitoring area is obtained; Sort all the risk monitoring areas in the container in descending order according to their corresponding vector-borne risk values to obtain the risk ranking of the monitoring areas.

8. The vector biological monitoring and early warning system applied to containerized goods according to claim 7, characterized in that: The specific process of the warning module judging the warning level and implementing corresponding measures according to the warning level is as follows: By adding up the vector-borne risk values corresponding to all risk monitoring areas in the container, the vector-borne risk value of the container is obtained, denoted as the container risk value. Preset multiple warning levels, each warning level corresponds to a container risk value interval, and each warning level corresponds to a corresponding warning measure; By matching the container risk value corresponding to the container with the container risk value intervals corresponding to all warning levels, the corresponding warning level is output, and according to the corresponding warning measures, the risk monitoring areas are processed in turn according to the risk ranking of the monitoring areas. After the processing is completed, a warning cancellation instruction is generated; Preset a warning update interval. Taking each occurrence of the warning instruction as the starting moment and the generation of the corresponding warning cancellation instruction as the ending moment, several warning cycles are obtained. For each warning cycle, taking its starting moment as the starting time, whenever the warning update interval is reached, the warning level is recalculated.

Images