A method and system for intelligent monitoring and early warning of port infectious diseases

Abstract

The application provides a kind of port infectious disease intelligent monitoring early warning method and system, the method comprises: obtaining the health condition information of passenger self-declaration, the transmission condition data of infectious disease appeared in flight origin and flight destination environment data;According to the health condition information corresponding to each passenger, the health classification data of each passenger is determined;According to health classification data, whether each passenger is a suspicious passenger is analyzed;According to the transmission condition data of infectious disease appeared in flight origin and flight destination environment data, the transmission speed score of infectious disease in destination is calculated;The number of suspicious passengers is counted, and different warning information is sent to airport staff according to the number of suspicious passengers and the transmission speed score of infectious disease in destination.The individual health anomaly and external transmission environment are organically combined in the application, a comprehensive risk assessment system is formed, which is beneficial to precise early warning.

Description

Technical Field

[0001] This invention relates to the field of infectious disease technology, and more specifically, to a method and system for intelligent monitoring and early warning of infectious diseases at ports of entry. Background Technology

[0002] As the first line of defense for national public health security, ports of entry are crucial for infectious disease control. Traditional port infectious disease surveillance methods rely primarily on passenger self-declaration of health, manual temperature checks, and limited epidemiological investigations, exhibiting significant lag and passivity. Furthermore, current technologies lack the ability to effectively integrate and intelligently analyze multi-source information, failing to dynamically correlate the epidemic characteristics of the flight's origin, the environmental conditions of the destination, and the individual health status of passengers, resulting in crude risk assessments. In the context of increasingly frequent global population movement, the risk of emerging infectious disease outbreaks is constantly increasing, and traditional methods are insufficient to cope with the complex and ever-changing epidemic transmission landscape. There is an urgent need for an early warning method capable of accurate assessment to reduce the risk of transmission. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for intelligent monitoring and early warning of infectious diseases at ports of entry, so as to improve the above-mentioned problems.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] On the one hand, embodiments of this application provide a method for intelligent monitoring and early warning of infectious diseases at ports of entry, the method comprising:

[0006] Obtain information on passengers' self-reported health status, data on the transmission conditions of infectious diseases at the flight's origin, and environmental data at the flight's destination;

[0007] Determine the health classification data for each passenger based on their corresponding health status information; analyze whether each passenger is a suspected passenger based on the health classification data; calculate the spread rate score of infectious diseases at the destination based on the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination.

[0008] The system counts the number of suspicious passengers and sends different warning messages to airport staff based on the number of suspicious passengers and the speed at which infectious diseases spread at the destination.

[0009] Secondly, embodiments of this application provide an intelligent monitoring and early warning system for port infectious diseases, the system comprising:

[0010] The acquisition module is used to acquire health status information voluntarily declared by passengers, data on the transmission conditions of infectious diseases occurring at the flight's origin, and environmental data at the flight's destination;

[0011] The calculation module is used to determine the health classification data of each passenger based on the health status information of each passenger; analyze whether each passenger is a suspicious passenger based on the health classification data; and calculate the spread rate score of infectious diseases at the destination based on the data on the transmission conditions of infectious diseases at the origin of the flight and the environmental data of the destination.

[0012] The screening module is used to count the number of suspicious passengers and send different warning messages to airport staff based on the number of suspicious passengers and the speed of infectious disease spread at the destination.

[0013] Thirdly, embodiments of this application provide an intelligent monitoring and early warning device for port infectious diseases, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the aforementioned intelligent monitoring and early warning method for port infectious diseases.

[0014] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned intelligent monitoring and early warning method for port infectious diseases.

[0015] The beneficial effects of this invention are as follows:

[0016] Traditional methods rely on a single data source (such as body temperature or reported symptoms), making judgments simplistic and prone to error. This invention integrates multi-dimensional information, including passengers' self-reported health status, infectious disease transmission conditions at the flight's origin (such as suitable temperature and humidity), and destination environmental data. It employs clustering and residual analysis techniques to filter suspicious passengers based on historical health information. Simultaneously, natural language processing technology is used to extract features and perform semantic matching on textual transmission conditions and environmental data, enabling rapid calculation of the destination transmission speed score. This multi-dimensional data fusion and analysis method makes risk assessment results more comprehensive and reliable, thereby improving the accuracy of early warnings.

[0017] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the intelligent monitoring and early warning method for port infectious diseases described in this embodiment of the invention;

[0020] Figure 2 This is a schematic diagram of the intelligent monitoring and early warning system for port infectious diseases described in this embodiment of the invention;

[0021] Figure 3 This is a schematic diagram of the intelligent monitoring and early warning device for port infectious diseases described in this embodiment of the invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0023] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] Example 1

[0025] like Figure 1 As shown in the figure, this embodiment provides a method for intelligent monitoring and early warning of infectious diseases at ports, which includes steps S1, S2 and S3.

[0026] Step S1: Obtain passenger self-reported health status information, data on the transmission conditions of infectious diseases at the flight's origin, and environmental data at the flight's destination;

[0027] This embodiment is applicable to monitoring passengers on each flight at the airport; the passengers in this step are those who take the plane; the health status information voluntarily declared by the passengers includes infectious disease-related symptoms (including whether they have a fever), risk exposure history, etc., such as "whether they have symptoms such as fever, dry cough, sore throat, fatigue, muscle aches, loss of taste, diarrhea, etc.; when the symptoms appeared; whether they have had close contact with confirmed cases, suspected cases, or asymptomatic infected persons recently"; the health status information voluntarily declared by the passengers can be text information;

[0028] Data on the transmission conditions of infectious diseases at the flight's origin, including the optimal temperature and humidity for transmission, is presented as text information. For example: "Take dengue fever as an example. This is a viral infectious disease transmitted by Aedes mosquitoes. Its transmission relies on mosquito vectors. When a female Aedes mosquito bites a patient in the viremic stage, the virus multiplies within the mosquito and is then transmitted through bites of healthy individuals. The transmission efficiency of this virus is closely related to environmental temperature and humidity, being most rapid at temperatures between 25°C and 30°C and humidity levels between 60% and 80%. These conditions greatly accelerate viral replication within mosquitoes, while also extending their lifespan and activity levels, significantly increasing their biting frequency." The flight destination environmental data includes the destination's temperature and humidity data.

[0029] Step S2: Determine the health classification data for each passenger based on their corresponding health status information; analyze whether each passenger is a suspected passenger based on the health classification data; calculate the spread rate score of infectious diseases at the destination based on the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination.

[0030] In this step, the health classification data of each passenger is determined based on the health status information of each passenger; the specific implementation steps for analyzing whether each passenger is a suspicious passenger based on the health classification data include step S21.

[0031] Step S21: Obtain multiple historical health status information, calculate the first feature information of each historical health status information, cluster the historical health status information according to the first feature information to obtain multiple first clusters, calculate the mean of all first feature information in each first cluster to obtain the first cluster center corresponding to each first cluster; calculate the distance between the first feature information and each first cluster center, and take the closest corresponding first cluster center as the target cluster center corresponding to the first feature information; calculate the residual between each first feature information and its corresponding target cluster center; cluster the residuals corresponding to all first feature information to obtain multiple second clusters, calculate the mean of all residuals in each second cluster to obtain the second cluster center corresponding to each second cluster; based on the feature information, first cluster center and second cluster center of each health status information, filter out the first target health status information corresponding to each health status information from all historical health status information, and analyze whether each passenger is a suspicious passenger based on the first target health status information.

[0032] In this step, historical health information can be some health information that has been artificially constructed in the past; the residual can be calculated by vector subtraction, that is, subtracting the first feature information from its corresponding target cluster center; calculating the distance between the first feature information and each first cluster center, and taking the first cluster center with the smallest distance as the target cluster center for the first feature information can be understood as follows: if there are three first cluster centers, then for a first feature information, calculate the distance between it and each of these three first cluster centers, and take the first cluster center with the smallest distance as the target cluster center for this first feature information;

[0033] Meanwhile, in this step, based on the feature information of each health status information, the first cluster center and the second cluster center, the first target health status information corresponding to each health status information is selected from all historical health status information, and the specific implementation steps of analyzing whether each passenger is a suspicious passenger based on the first target health status information include step S211.

[0034] Step S211: Extract the second feature information of the health status information; calculate the first distance between the second feature information and each first cluster center; and record the first cluster center corresponding to the first distance less than a preset first distance threshold as the third cluster center; calculate the second distance between the second feature information and each second cluster center; and record the second cluster center corresponding to the second distance less than a preset second distance threshold as the fourth cluster center; extract the historical health status information belonging to the third and fourth cluster centers and perform deduplication; after deduplication, use the remaining historical health status information as the first target health status information corresponding to each health status information; calculate the similarity between each health status information and each corresponding first target health status information; extract the first target health status information with a similarity greater than a preset similarity threshold and record it as the second target health status information; obtain the annotation information corresponding to each second target health status information; the annotation information is health classification data, which includes the probability of health level 1, the probability of health level 2, and the probability of health level 3; and analyze whether each passenger is a suspicious passenger based on the annotation information corresponding to each second target health status information.

[0035] In this step, there may be one or more second target health status information; the annotation information corresponding to each second target health status information is manually annotated; at the same time, the specific implementation steps of analyzing whether each passenger is a suspicious passenger based on the annotation information corresponding to each second target health status information include step S2111.

[0036] Step S2111: Calculate the average of the probabilities of health level 1, health level 2, and health level 3 corresponding to all the second target health status information, and obtain the average probability of health level 1, health level 2, and health level 3. Take the health level corresponding to the highest average probability as the target health level for each passenger. Determine whether the passenger has a fever based on the health status information declared by the passenger, and mark the passenger with a fever and a target health level of 3 as a suspicious passenger.

[0037] In this step, a lower health level represents better health. For example, a health level of 1 represents healthy, 2 represents good, and 3 represents high risk. The average probability of a health level of 1, 2, and 3 corresponding to all the health status information of the second target is calculated. This can be understood as follows: if there are three health status information of the second target, the average probability of a health level of 2 corresponding to these three health status information is calculated to obtain the average probability of a health level of 2. The average probability of a health level of 1 and 3 is calculated in the same way.

[0038] The health information voluntarily declared by passengers includes information on whether passengers have a fever. Therefore, it is possible to determine whether a passenger has a fever based on the health information voluntarily declared by the passenger.

[0039] In step S2, the specific implementation steps for calculating the spread rate score of infectious diseases at the destination based on the data on the spread conditions of infectious diseases at the origin of the flight and the environmental data of the destination include step S22.

[0040] Step S22: Concatenate the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination to form combined text information. Both the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination are text information. Obtain the clusters corresponding to the historical combined text information. Each cluster has its corresponding annotation information. The annotation information corresponding to each historical combined text information in a cluster is the same as the annotation information of its respective cluster. The annotation information is a score of the speed of infectious disease transmission at the destination. The clusters are obtained by clustering based on the feature information corresponding to each historical combined text information. Specifically, each historical combined text information is segmented, and features are extracted from each segment. Local pooling is then performed on the extracted features to obtain multiple pooled features corresponding to each historical combined text information. All of these are then combined. Pooling features are clustered to obtain multiple clustering results. The cluster centers of each clustering result are then subtracted from all pooling features to obtain multiple difference results. Each difference result is assigned a weight: if a pooling feature belongs to a cluster, its corresponding difference result has the first weight; otherwise, it has the second weight. All difference results are then weighted and summed to obtain the first calculation result for each clustering result. The first calculation results for all clustering results are concatenated and then subjected to global average pooling to obtain the feature information corresponding to each historical combined text information. The TF-IDF algorithm is used to calculate the similarity between the combined text information and the historical combined text information in each cluster. The historical combined text information with the highest similarity in each cluster is selected and recorded as the first historical combined text information.

[0041] In this step, the historical combined text information refers to combined text information collected in the past. The first and second weights can be customized. Simultaneously, when calculating the feature information corresponding to each piece of historical combined text information, the data on the transmission conditions of infectious diseases occurring at the flight's origin and the environmental data of the flight's destination are concatenated. Key risk segments are retained through segmented feature extraction and local pooling. Then, weighted cluster difference calculation is used to strengthen the core features within the cluster and weaken external noise, ultimately generating a high-dimensional feature representation that combines local sensitivity and global consistency. This method can improve the accuracy of clustering. Furthermore, this step uses TF-IDF similarity calculation to quickly match the most relevant historical combined text information within each cluster.

[0042] Step S23: Calculate the semantic similarity between all the first historical combined text information and the combined text information. Record the first historical combined text information with the highest semantic similarity as the target historical combined text information. Use the annotation information corresponding to the target historical combined text information as the annotation information corresponding to the combined text information to obtain the infectious disease transmission speed score at the destination corresponding to the combined text information.

[0043] In step S22, a coarse screening is first performed using the TF-IDF algorithm. Then, a second screening is conducted using semantic similarity. This two-step screening strategy is essentially a strategy of coarse screening followed by fine-tuning. TF-IDF ensures retrieval speed, laying an efficient foundation for subsequent fine-tuning; while semantic matching, based on this, delivers the accuracy and reliability of the final result. This method ensures both the precision and speed of the screening process.

[0044] Step S3: Count the number of suspicious passengers and send different warning messages to airport staff based on the number of suspicious passengers and the speed of infectious disease spread at the destination.

[0045] The specific implementation steps of this step include step S31;

[0046] Step S31: Count the number of suspicious passengers, calculate the ratio between the number of suspicious passengers and the total number of passengers, and look up the passenger risk score corresponding to the ratio in the preset ratio risk score table. Each ratio in the ratio risk score table corresponds to a passenger risk score. Weight the passenger risk score with the infectious disease spread speed score at the destination to obtain the risk score. Compare the risk score with the preset risk score threshold. If it is less than the preset risk score threshold, send an early warning message to the airport staff to maintain the current level of epidemic prevention and control. If it is greater than or equal to the preset risk score threshold, send an early warning message to the airport staff to strengthen the level of epidemic prevention and control.

[0047] In this step, the weights of passenger risk score and infectious disease spread rate score at the destination can be 0.6 and 0.4, respectively. When the early warning information on strengthening the intensity of epidemic prevention and control is issued, staff can conduct key screening of passengers on this flight when carrying out epidemic prevention and control. In addition, after all passengers have disembarked, the cabin, cargo hold, passageways and isolation areas of the flight can be thoroughly disinfected immediately to ensure environmental safety.

[0048] When the warning message indicates an increase in the intensity of epidemic prevention and control, after completing the epidemic prevention and control measures for this flight, airport staff can also evaluate the epidemic prevention and control strategy. This involves obtaining the scores from an even number of airport staff members, calculating the average of all scores and recording the average as the first value, and using the absolute value of the difference between each score and the first value as the second value for each score. All the second values ​​are then sorted in ascending order, and the second value with an even position in the sorting is selected as the third value.

[0049] For each third value, the scores corresponding to second values ​​greater than this third value are grouped together to obtain the first score set corresponding to this third value, and the scores corresponding to second values ​​less than or equal to this third value are grouped together to obtain the second score set corresponding to this third value. In the first score set, one score is selected each time as a comparison score, and the absolute value of the difference between the comparison score and the remaining scores in the first score set is calculated. The mean of all absolute values ​​of the differences is taken as the fourth value corresponding to the comparison score. Simultaneously, the absolute value of the difference between the comparison score and each score in the second score set is also calculated, and the mean of all absolute values ​​of the differences is taken as the fifth value corresponding to the comparison score. The fifth value is then subtracted from the fourth value. The sixth value is obtained by dividing the sixth value by the maximum value between the fourth and fifth values ​​to obtain the target value corresponding to the comparison score. Similarly, in the second score set, a score is selected as the comparison score each time, and the absolute value of the difference between the comparison score and the remaining scores in the second score set is calculated. The mean of all the absolute values ​​of the difference is taken as the seventh value corresponding to the comparison score. At the same time, the absolute value of the difference between the comparison score and each score in the first score set is also calculated. The mean of all the absolute values ​​of the difference is taken as the eighth value corresponding to the comparison score. The seventh value is subtracted from the eighth value to obtain the ninth value. The ninth value is divided by the maximum value between the seventh and eighth values ​​to obtain the target value corresponding to the comparison score.

[0050] In the first score set, sum the target values ​​corresponding to each score to obtain the first summation result. In the second score set, sum the target values ​​corresponding to each score to obtain the second summation result. Add the first summation result and the second summation result to obtain the third summation result. Compare the third summation results corresponding to each third value, select the third value corresponding to the largest third summation result and use it as the target score. Among all scores, the average of the scores less than or equal to the target score is used as the final score.

[0051] The final score is compared with a preset score threshold. If the score is greater than the threshold, the first message is output, indicating that the epidemic prevention and control work is successful. Otherwise, the second message is output, indicating that there are defects in the epidemic prevention and control work, so as to prompt airport staff to adjust the epidemic prevention and control strategy.

[0052] This step involves constructing a complex yet sophisticated consensus screening mechanism. Its core advantage lies in its ability to effectively eliminate extreme scoring interference, thereby extracting the highest-quality final evaluation that best represents collective consensus. This method significantly enhances the robustness and representativeness of the evaluation results. After recognizing shortcomings in the epidemic prevention and control work, staff can review the current strategy and improve it for better future epidemic prevention and control efforts.

[0053] This embodiment can not only locate suspicious passengers based on health declaration information, but also dynamically calculate the overall risk value of a flight by statistically analyzing the proportion of suspicious passengers and combining it with a destination transmission speed score. This mechanism organically combines individual health abnormalities with the external transmission environment, forming a comprehensive risk assessment system that is conducive to accurate early warning.

[0054] Example 2

[0055] like Figure 2 As shown in the figure, this embodiment provides an intelligent monitoring and early warning system for port infectious diseases. The system includes an acquisition module 1, a calculation module 2, and a screening module 3.

[0056] Module 1 is used to acquire health status information declared by passengers, data on the transmission conditions of infectious diseases at the flight's origin, and environmental data at the flight's destination.

[0057] Calculation module 2 is used to determine the health classification data of each passenger based on the health status information of each passenger; analyze whether each passenger is a suspicious passenger based on the health classification data; and calculate the spread rate score of infectious diseases at the destination based on the transmission condition data of infectious diseases appearing at the flight origin and the environmental data of the flight destination.

[0058] The screening module 3 is used to count the number of suspicious passengers and send different warning messages to airport staff based on the number of suspicious passengers and the speed of infectious disease spread at the destination.

[0059] In one specific embodiment of this disclosure, the computing module 2 further includes a first computing unit 21.

[0060] The first calculation unit 21 is used to acquire multiple historical health status information, calculate the first feature information of each historical health status information, cluster the historical health status information according to the first feature information to obtain multiple first clusters, calculate the mean of all first feature information in each first cluster to obtain the first cluster center corresponding to each first cluster; calculate the distance between the first feature information and each first cluster center, and take the closest corresponding first cluster center as the target cluster center corresponding to the first feature information; calculate the residual between each first feature information and its corresponding target cluster center; cluster the residuals corresponding to all first feature information to obtain multiple second clusters, calculate the mean of all residuals in each second cluster to obtain the second cluster center corresponding to each second cluster; based on the feature information, first cluster center and second cluster center of each health status information, filter out the first target health status information corresponding to each health status information from all historical health status information, and analyze whether each passenger is a suspicious passenger based on the first target health status information.

[0061] In one specific embodiment of this disclosure, the first computing unit 21 further includes a second computing unit 211.

[0062] The second calculation unit 211 is used to extract second feature information of health status information, calculate the first distance between the second feature information and each first cluster center, and record the first cluster center corresponding to the first distance less than a preset first distance threshold as the third cluster center; calculate the second distance between the second feature information and each second cluster center, and record the second cluster center corresponding to the second distance less than a preset second distance threshold as the fourth cluster center; extract the historical health status information belonging to the third and fourth cluster centers and perform deduplication operation, and use the remaining historical health status information as the first target health status information corresponding to each health status information; calculate the similarity between each health status information and each corresponding first target health status information, and extract the first target health status information with a similarity greater than a preset similarity threshold and record it as the second target health status information; obtain the annotation information corresponding to each second target health status information, the annotation information being health classification data, including the probability of health level 1, the probability of health level 2, and the probability of health level 3; and analyze whether each passenger is a suspicious passenger based on the annotation information corresponding to each second target health status information.

[0063] In one specific embodiment of this disclosure, the second calculation unit 211 further includes a third calculation unit 2111.

[0064] The third calculation unit 2111 is used to calculate the average of the probabilities of health level 1, health level 2, and health level 3 corresponding to all the second target health status information, and obtain the average probability of health level 1, health level 2, and health level 3. The health level corresponding to the maximum average probability is taken as the target health level for each passenger. Based on the health status information declared by the passenger, it is determined whether the passenger has a fever, and passengers with fever and target health level 3 are marked as suspicious passengers.

[0065] In one specific embodiment of this disclosure, the calculation module 2 further includes a fourth calculation unit 22 and a fifth calculation unit 23.

[0066] The fourth calculation unit 22 is used to concatenate data on the transmission conditions of infectious diseases occurring at the flight's origin and environmental data at the flight's destination to form combined text information. Both the data on the transmission conditions of infectious diseases occurring at the flight's origin and the environmental data at the flight's destination are text information. It obtains the clusters corresponding to the historical combined text information, each cluster having its corresponding annotation information. The annotation information corresponding to each historical combined text information within a cluster is the same as the annotation information of its respective cluster. The annotation information is a score of the speed of infectious disease transmission at the destination. The clusters are obtained by clustering based on the feature information corresponding to each historical combined text information. Specifically, each historical combined text information is segmented, and features are extracted from each segment. Local pooling is then performed on the extracted features to obtain multiple pooled features corresponding to each historical combined text information. The pooling features of each part are clustered to obtain multiple clustering results. The difference between the cluster center of each clustering result and all pooling features is calculated to obtain multiple difference results. Each difference result is assigned a weight, where the weight of the difference result corresponding to the pooling feature is the first weight if it belongs to the clustering result, and the second weight otherwise. All difference results are weighted and summed to obtain the first calculation result corresponding to each clustering result. The first calculation results corresponding to all clustering results are concatenated and then global average pooling is performed to obtain the feature information corresponding to each historical combined text information. The TF-IDF algorithm is used to calculate the similarity between the combined text information and the historical combined text information in each cluster. The historical combined text information with the highest similarity in each cluster is selected and recorded as the first historical combined text information.

[0067] The fifth calculation unit 23 is used to perform semantic similarity calculation on all the first historical combined text information and combined text information, record the first historical combined text information with the maximum semantic similarity as the target historical combined text information, and use the annotation information corresponding to the target historical combined text information as the annotation information corresponding to the combined text information to obtain the infectious disease transmission speed score at the destination corresponding to the combined text information.

[0068] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0069] Example 3

[0070] Corresponding to the above method embodiments, this disclosure also provides a port infectious disease intelligent monitoring and early warning device. The port infectious disease intelligent monitoring and early warning device described below and the port infectious disease intelligent monitoring and early warning method described above can be referred to each other.

[0071] Figure 3This is a block diagram illustrating a port infectious disease intelligent monitoring and early warning device 300 according to an exemplary embodiment. Figure 3 As shown, the port infectious disease intelligent monitoring and early warning device 300 may include: a processor 301 and a memory 302. The port infectious disease intelligent monitoring and early warning device 300 may also include one or more of the following: a multimedia component 303, an I / O interface 304, and a communication component 305.

[0072] The processor 301 controls the overall operation of the port infectious disease intelligent monitoring and early warning device 300 to complete all or part of the steps in the aforementioned port infectious disease intelligent monitoring and early warning method. The memory 302 stores various types of data to support the operation of the port infectious disease intelligent monitoring and early warning device 300. This data may include, for example, instructions for any application or method operating on the port infectious disease intelligent monitoring and early warning device 300, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 302 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 302 or transmitted via the communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 305 is used for wired or wireless communication between the port infectious disease intelligent monitoring and early warning device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 305 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0073] In an exemplary embodiment, the port infectious disease intelligent monitoring and early warning device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the aforementioned port infectious disease intelligent monitoring and early warning method.

[0074] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, these program instructions implement the steps of the aforementioned intelligent monitoring and early warning method for port infectious diseases. For example, the computer-readable storage medium may be the aforementioned memory 302 including program instructions, which may be executed by the processor 301 of the intelligent monitoring and early warning device 300 for port infectious diseases to complete the aforementioned intelligent monitoring and early warning method for port infectious diseases.

[0075] Example 4

[0076] Corresponding to the above method embodiments, this disclosure also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the port infectious disease intelligent monitoring and early warning method described above.

[0077] A readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the port infectious disease intelligent monitoring and early warning method of the above method embodiments.

[0078] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0079] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent monitoring and early warning of infectious diseases at ports of entry, characterized in that, include: Obtain information on passengers' self-reported health status, data on the transmission conditions of infectious diseases at the flight's origin, and environmental data at the flight's destination; Each passenger's health classification data is determined based on their corresponding health status information. Based on health classification data, analyze whether each passenger is a suspicious passenger; calculate the spread rate score of infectious diseases at the destination based on data on the conditions for the spread of infectious diseases at the flight's origin and environmental data at the flight's destination; The number of suspicious passengers is counted, and different warning messages are sent to airport staff based on the number of suspicious passengers and the speed of infectious disease spread at the destination. This includes determining each passenger's health classification data based on their corresponding health status information; and analyzing each passenger's health classification data to determine whether they are a suspicious passenger, including: Multiple historical health status information is acquired. First feature information is calculated for each historical health status information. Based on the first feature information, the historical health status information is clustered to obtain multiple first clusters. The mean of all first feature information in each first cluster is calculated to obtain the first cluster center corresponding to each first cluster. The distance between each first feature information and each first cluster center is calculated, and the closest corresponding first cluster center is taken as the target cluster center corresponding to the first feature information. The residual between each first feature information and its corresponding target cluster center is calculated. The residuals corresponding to all first feature information are clustered to obtain multiple second clusters. The mean of all residuals in each second cluster is calculated to obtain the second cluster center corresponding to each second cluster. The process involves: extracting the second feature information of health status information; calculating the first distance between the second feature information and each first cluster center; designating the first cluster center corresponding to a first distance less than a preset first distance threshold as the third cluster center; calculating the second distance between the second feature information and each second cluster center; designating the second cluster center corresponding to a second distance less than a preset second distance threshold as the fourth cluster center; extracting and deduplicating the historical health status information belonging to the third and fourth cluster centers; using the remaining historical health status information as the first target health status information corresponding to each health status information; calculating the similarity between each health status information and each corresponding first target health status information; extracting the first target health status information with a similarity greater than a preset similarity threshold and designating it as the second target health status information; and obtaining the annotation information corresponding to each second target health status information, where the annotation information is health classification data, including the probability of health level 1, health level 2, and health level 3. The probabilities of health level 1, health level 2, and health level 3 corresponding to all the second target health status information are averaged to obtain the average probability of health level 1, health level 2, and health level 3. The health level corresponding to the highest average probability is taken as the target health level for each passenger. Based on the health status information self-reported by the passenger, it is determined whether the passenger has a fever. Passengers with fever and a target health level of 3 are marked as suspicious passengers.

2. The intelligent monitoring and early warning method for port infectious diseases according to claim 1, characterized in that, A score for the rate of spread of infectious diseases at the destination is calculated based on data on the conditions for the spread of infectious diseases at the flight's origin and environmental data at the flight's destination. This score includes: Data on the transmission conditions of infectious diseases at the flight's origin and environmental data at the flight's destination are concatenated to form combined text information. Both the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination are text information. Clusters corresponding to the historical combined text information are obtained, and each cluster has its corresponding annotation information. The annotation information for each historical combined text information within a cluster is the same as the annotation information for its respective cluster. The annotation information is a score of the rate of infectious disease transmission at the destination. The clusters are obtained by clustering based on the feature information corresponding to each historical combined text information. Each historical combined text information is segmented, and features are extracted from each segment. Local pooling is then applied to the extracted features to obtain multiple pooled features corresponding to each historical combined text information. All pooled features are then combined. Clustering is performed to obtain multiple clustering results. The cluster centers corresponding to each clustering result are then compared with all pooling features to calculate multiple difference results. Each difference result is assigned a weight: if a pooling feature belongs to a given cluster, its corresponding difference result receives the first weight; otherwise, it receives the second weight. All difference results are then weighted and summed to obtain the first calculation result for each clustering result. These first calculation results are then concatenated and subjected to global average pooling to obtain the feature information corresponding to each historical combined text information. The TF-IDF algorithm is used to calculate the similarity between the combined text information and the historical combined text information in each cluster. The historical combined text information with the highest similarity in each cluster is selected and recorded as the first historical combined text information. The semantic similarity of all first historical combined text information with combined text information is calculated. The first historical combined text information with the highest semantic similarity is recorded as the target historical combined text information. The annotation information corresponding to the target historical combined text information is used as the annotation information corresponding to the combined text information to obtain the infectious disease transmission speed score at the destination corresponding to the combined text information.

3. A port infectious disease intelligent monitoring and early warning system, characterized in that, include: The acquisition module is used to acquire health status information voluntarily declared by passengers, data on the transmission conditions of infectious diseases occurring at the flight's origin, and environmental data at the flight's destination; The calculation module is used to determine the health classification data of each passenger based on the health status information corresponding to each passenger; Based on health classification data analysis, determine whether each passenger is a suspicious passenger; A score is calculated based on data on the transmission conditions of infectious diseases at the flight's origin and environmental data at the flight's destination to determine the rate of spread of infectious diseases at the destination. The screening module is used to count the number of suspicious passengers and send different warning messages to airport staff based on the number of suspicious passengers and the speed of infectious disease spread at the destination. The calculation module includes: The first calculation unit is used to acquire multiple historical health status information, calculate the first feature information of each historical health status information, cluster the historical health status information according to the first feature information to obtain multiple first clusters, calculate the mean of all first feature information in each first cluster to obtain the first cluster center corresponding to each first cluster; calculate the distance between the first feature information and each first cluster center, and take the closest corresponding first cluster center as the target cluster center corresponding to the first feature information; calculate the residual between each first feature information and its corresponding target cluster center; cluster the residuals corresponding to all first feature information to obtain multiple second clusters, calculate the mean of all residuals in each second cluster to obtain the second cluster center corresponding to each second cluster; The process involves: extracting the second feature information of health status information; calculating the first distance between the second feature information and each first cluster center; designating the first cluster center corresponding to a first distance less than a preset first distance threshold as the third cluster center; calculating the second distance between the second feature information and each second cluster center; designating the second cluster center corresponding to a second distance less than a preset second distance threshold as the fourth cluster center; extracting and deduplicating the historical health status information belonging to the third and fourth cluster centers; using the remaining historical health status information as the first target health status information corresponding to each health status information; calculating the similarity between each health status information and each corresponding first target health status information; extracting the first target health status information with a similarity greater than a preset similarity threshold and designating it as the second target health status information; and obtaining the annotation information corresponding to each second target health status information, where the annotation information is health classification data, including the probability of health level 1, health level 2, and health level 3. The probabilities of health level 1, health level 2, and health level 3 corresponding to all the second target health status information are averaged to obtain the average probability of health level 1, health level 2, and health level 3. The health level corresponding to the highest average probability is taken as the target health level for each passenger. Based on the health status information self-reported by the passenger, it is determined whether the passenger has a fever. Passengers with fever and a target health level of 3 are marked as suspicious passengers.

4. The port infectious disease intelligent monitoring and early warning system according to claim 3, characterized in that, The calculation module includes: The fourth calculation unit is used to concatenate data on the transmission conditions of infectious diseases at the flight's origin and environmental data at the flight's destination to form combined text information. Both the data on the transmission conditions of infectious diseases at the flight's origin and the environmental data at the flight's destination are text information. It obtains the clusters corresponding to the historical combined text information. Each cluster has its corresponding annotation information, and the annotation information for each historical combined text information within a cluster is the same as the annotation information of its respective cluster. The annotation information is a score of the speed of infectious disease transmission at the destination. The clusters are obtained by clustering based on the feature information corresponding to each historical combined text information. Specifically, each historical combined text information is segmented, and features are extracted from each segment. Local pooling is then performed on the extracted features to obtain multiple pooled features corresponding to each historical combined text information. The pooling features of each part are clustered to obtain multiple clustering results. The cluster center corresponding to each clustering result is then compared with all the pooling features to obtain multiple difference results. Each difference result is assigned a weight, where if a pooling feature belongs to this clustering result, its corresponding difference result has the first weight, otherwise it has the second weight. All difference results are then weighted and summed to obtain the first calculation result corresponding to each clustering result. The first calculation results corresponding to all clustering results are then concatenated and then subjected to global average pooling to obtain the feature information corresponding to each historical combined text information. The TFIDF algorithm is used to calculate the similarity between the combined text information and the historical combined text information in each cluster. The historical combined text information with the highest similarity in each cluster is selected and recorded as the first historical combined text information. The fifth calculation unit is used to calculate the semantic similarity between all the first historical combined text information and the combined text information, record the first historical combined text information with the highest semantic similarity as the target historical combined text information, and use the annotation information corresponding to the target historical combined text information as the annotation information corresponding to the combined text information to obtain the infectious disease transmission speed score at the destination corresponding to the combined text information.

Images