A method, system, server and storage medium for tracing the origin of an infectious disease

Abstract

The present application discloses a method, a system, a server and a storage medium for tracking and tracing infectious diseases, belonging to the field of tracking and tracing the source of transmission, and capable of solving the problems that the existing methods for tracking and tracing infectious diseases have a large amount of calculation and the positioning is not very accurate. The method includes: respectively obtaining big data information of multiple entities; establishing a spatio-temporal relationship graph network according to the multiple big data information; if an infectious disease-infected entity is found, a tracing process is carried out, wherein the tracing process includes: tracking all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all associated entities; if an infected entity appears among the associated entities, the infected entity is used as an infectious disease-infected entity to carry out the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained. Using the method of the present application for tracking and tracing infectious diseases, the amount of calculation is relatively smaller and the positioning is more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of tracing the source of transmission, and particularly to a method, a system, a server and a storage medium for tracing the source of an infectious disease. Background Art

[0002] Currently, tracing the source of transmission refers to the process of tracing and locating the source of the transmitted information that breaks out in reality, so as to carry out control and risk assessment. Since the transmission phenomena triggered by the source of transmission are widespread in the real world, such as major epidemics that affect human health, etc., therefore, timely and effectively locating the source of transmission is of extremely important significance for reducing people's losses.

[0003] In recent years, many research scholars have done a lot of related research on tracing the source of infectious diseases, including the source tracing algorithms for the tree-shaped networks propagated by traditional SI model, SIS model, SIR model, and SEIR model. With the further development of technology, the source tracing algorithms are no longer limited to the tree-shaped network algorithms, and begin to study the risk tracing problems in general network structures.

[0004] Currently, tracing the source either seeks the optimal solution through rigorous and highly complex calculations, or achieves the best time performance through simplified heuristic algorithms. However, the existing methods for tracing the source of infectious diseases have a large amount of calculation (it is necessary to test all users in the network), and at the same time, the positioning is not very accurate. Summary of the Invention

[0005] The embodiments of the present application solve the problems that the existing methods for tracing the source of infectious diseases have a large amount of calculation and the positioning is not very accurate by providing a method, a system, a server and a storage medium for tracing the source of an infectious disease.

[0006] In a first aspect, an embodiment of the present invention provides a method for tracing the source of an infectious disease, including:

[0007] Obtaining the big data information of multiple entities respectively;

[0008] Establishing a spatio-temporal relationship graph network according to the multiple pieces of big data information;

[0009] If an infectious disease-infected entity is found, a tracing process is performed, where the tracing process includes: tracing all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities;

[0010] If an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity to perform the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained.

[0011] In combination with the first aspect, in a possible implementation manner, the specific steps of establishing the spatio-temporal relationship graph network based on the multiple big data information include:

[0012] Using big data technology to perform data cleaning and data analysis on the multiple big data information to obtain the information to be used;

[0013] Establishing a data dictionary according to the information to be used;

[0014] Establishing an association analysis table through association analysis according to the data dictionary;

[0015] Forming a spatio-temporal relationship graph network according to the association analysis table.

[0016] In combination with the first aspect, in a possible implementation manner, the specific steps of establishing a data dictionary according to the information to be used include:

[0017] Establishing a data dictionary with attributes of geographical information, time information, and security level information according to the information to be used.

[0018] In combination with the first aspect, in a possible implementation manner, the method for infectious disease tracking and tracing further includes:

[0019] Obtaining a training data set according to the multiple tracing paths and the security level information of each region on each tracing path. The calculation formula of the training data in the training data set is where L represents the comprehensive security risk level of the tracing path, l i represents the security risk level corresponding to any region in the tracing path, and n i represents the number of people infected with the entity in the region with the security risk level of l i and N represents the total number of all infected entities in the tracing path;

[0020] Inputting the training data set into a deep convolutional neural network to converge the weights of the model until convergence is stable to obtain a stable model;

[0021] Inputting the new path to be detected into the stable model to obtain the prediction of the comprehensive risk level of the new path.

[0022] In combination with the first aspect, in a possible implementation manner, the specific steps of inputting the training data set into a deep convolutional neural network include:

[0023] Inputting the training data set into a residual neural network.

[0024] In combination with the first aspect, in a possible implementation manner, the method for infectious disease tracking and tracing further includes:

[0025] Add the new path and the security level information of the regions on the new path to the training dataset, and input them into the deep convolutional neural network for self-learning.

[0026] In a second aspect, another embodiment of the present invention provides an infectious disease tracking and tracing system, including:

[0027] An acquisition module, configured to respectively acquire big data information of multiple entities;

[0028] A building module, configured to build a spatio-temporal relationship graph network according to the multiple big data information;

[0029] A tracing module, configured to perform a tracing process if an infectious disease-infected entity is found, where the tracing process includes: tracing all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities;

[0030] A selection module, configured to use the infected entity as the infectious disease-infected entity to perform the tracing process if an infected entity appears among the associated entities; if no infected entity appears among the associated entities, the infectious disease-infected entity is the origin entity, and a tracing path is obtained.

[0031] In a third aspect, another embodiment of the present invention provides a server, including: a memory and a processor;

[0032] The memory is used to store program instructions;

[0033] The processor is configured to execute the program instructions in the memory, so that the server executes the above-mentioned infectious disease tracking and tracing method.

[0034] In a fourth aspect, another embodiment of the present invention provides a computer-readable storage medium, and the computer-readable storage medium stores executable instructions, and when a computer executes the executable instructions, it can implement the above-mentioned infectious disease tracking and tracing method.

[0035] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0036] The method for tracking and tracing infectious diseases provided by the embodiments of the present invention includes: respectively obtaining big data information of multiple entities; establishing a spatio-temporal relationship graph network according to the multiple pieces of big data information; if an infectious disease-infected entity is found, a tracing process is performed, where the tracing process includes: tracking all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities; if an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity to perform the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained. This application utilizes big data information and big data technology to integrate and associate the travel of the group, establish a spatio-temporal relationship graph network, perform the tracing process, quickly obtain the originating entity and obtain the tracing path, and reduce the repetitive work of traditional large-scale regional detection. When using the method for tracking and tracing infectious diseases of this application to track and trace infectious diseases, the amount of calculation is relatively smaller and the positioning is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a flowchart of the method for tracking and tracing infectious diseases provided by the embodiments of this application;

[0039] Figure 2 It is a schematic diagram of the method for tracking and tracing infectious diseases provided by the embodiments of this application Figure 1 ;

[0040] Figure 3 It is a schematic diagram of the method for tracking and tracing infectious diseases provided by the embodiments of this application Figure 2 ;

[0041] Figure 4 It is a schematic diagram of the method for tracking and tracing infectious diseases provided by the embodiments of this application Figure 3 . DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0043] Please refer to Figure 1 As shown, an embodiment of the present invention provides a method for tracking and tracing infectious diseases, including:

[0044] Step 101: Obtain big data information of multiple entities respectively.

[0045] Specifically, a mobile intelligent terminal, a smart phone, a smart wearable device with positioning, etc. can be used to obtain structured, unstructured, and semi-structured big data information such as the daily public positioning itinerary information, time information, and health status information of the wearer.

[0046] Step 102: Establish a spatio-temporal relationship graph network according to multiple big data information.

[0047] Specifically, step 102 includes:

[0048] Step 1021: Use big data technology to clean and analyze multiple big data information to obtain information to be used.

[0049] Among them, with the development of Internet technology, big data technology is a data set whose scale is so large that it far exceeds the capabilities of traditional database software tools in terms of acquisition, storage, management, and analysis. It has four major characteristics: a huge data scale, fast data flow, diverse data types, and low value density. The powerful computing power and data correlation and integration ability of big data technology can effectively improve the ability of infectious disease traceability and risk assessment and prediction. The strategic significance of big data technology lies in the professional processing of these meaningful data and in improving the ability to process and analyze large amounts of data.

[0050] Through big data technology, multiple big data information obtained is aggregated and stored to obtain information to be used for big data analysis. The information to be used is to convert structured data, unstructured data, and semi-structured data with spatio-temporal geographical information, time information, security level information, etc. into a knowledge base structure convenient for classification and management.

[0051] Step 1022: Establish a data dictionary according to the information to be used.

[0052] Further, step 1022 specifically includes: establishing a data dictionary with attributes of geographical information, time information, and security level information according to the information to be used, so as to simplify the information to be used and obtain the most important and useful information.

[0053] Step 1023: Establish an association analysis table through association analysis according to the data dictionary.

[0054] Step 1024: Form a spatio-temporal relationship graph network according to the association analysis table.

[0055] Among them, the spatiotemporal relationship graph network is a relationship graph network established between individuals, individuals and groups, and groups and groups, which connects geographic information, time information, and security level information between multiple entities. The establishment of the spatiotemporal relationship graph network provides a more intuitive representation mode for traceability information query and calculation.

[0056] The process of establishing the spatiotemporal relationship graph network is based on the spatiotemporal overlap, for example Figure 2 As shown in the figure, taking entities 1, 2, 3, and 4 as examples, firstly, a large amount of big data information of entities is obtained through the device, and the big data technology is used to clean and analyze the multiple big data information to obtain the information to be used. Then, according to the information to be used, a data dictionary with attributes of geographic information, time information, and security level information is established, such as Figure 2 As shown, the geographic information of entity 1 is Beijing, Xi'an, and Shanghai; the time information is Beijing (BEIJING), the stay time in Beijing is from 15:00 on October 01, 2021 to 11:45 on October 02, 2021, expressed as 202110011500-202110011145, Xi'an (XIAN), the stay time in Xi'an is from 14:00 on October 02, 2021 to 09:30 on October 03, 2021, expressed as 202110021400-202110030930, Shanghai (SHANGHAI), the stay time in Shanghai is 2021 From 12:00 on October 3, 2021 to the present, it is represented as 202110031200-NULL, where NULL means that the person is still staying in this place. The security level information is divided into four levels: (1) low risk, (2) medium risk, (3) high risk, and (4) severe risk. During the period of time that entity 1 stayed in Beijing, the risk level information of Beijing was (3) high risk, during the period of time that entity 1 stayed in Xi'an, the risk level information of Xi'an was (3) high risk, and during the period of time that entity 1 stayed in Shanghai, the risk level information of Shanghai was (4) severe risk. The representation of geographic information, time information, and security level information in the data dictionary of entity 2, entity 3, and entity 4 is similar.

[0057] like Figure 2 As shown, after that, an association analysis table is established based on the data dictionary through association analysis, where the association analysis table includes a strong association analysis table and a weak association analysis table. Among them, the strong association analysis table indicates that there are direct overlapping association areas between two entities, and the weak association analysis table indicates that there are indirect overlapping association areas between two entities, such as Figure 2As shown, both Entity 1 and Entity 4 have been to Beijing during the same time period, thus showing a strong association in the strong association analysis table. Other strong association analyses are carried out in the same way. Entity 1 and Entity 3 are indirectly associated through Entity 2, thus forming a weak association analysis table. In the association analysis table, solid lines represent direct associations and dashed lines represent indirect associations.

[0058] Continue to refer to Figure 2 As shown, finally, a spatio-temporal relationship graph network is formed based on the association analysis table.

[0059] Step 103: If an infectious disease-infected entity is found, a tracing process is carried out. Among them, the tracing process includes: tracing all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all associated entities.

[0060] Step 104: If an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity for the tracing process. If no infected entity appears among the associated entities, the infectious disease-infected entity is the source entity, and the tracing path is obtained.

[0061] Steps 103 and 104 are the tracing grouping round-robin tracing technology. Using the spatio-temporal relationship graph network of multiple entities and combining the principles of sorting and classification algorithms, the propagation path of the entity is traced and the source is located. Specifically, it is assumed that the infectious disease conforms to the SI model (dividing the population into S class and I class. The S class is the susceptible group, referring to those who have not gotten sick but lack immunity and are easily infected after contacting the infected. The I class is the infected group, referring to those who have contracted the infectious disease and can transmit it to members of the S class). Among them, the incubation period patients can be known through detection means. The example is as Figure 3 As shown, in the figure, S 0 ~S n represent each spatio-temporal layer for upward tracing, ● represents the infectious disease-infected entity or the infected entity, and ○ represents the non-infected entity. a 0 is the discovered infectious disease-infected entity (at the S 0 layer, the outbreak area is C 0 ). According to the spatio-temporal relationship graph network, trace the associated entities a 0 associated with a 1 (at the S 1 layer, the outbreak area is C 1 ) and a 2 (at the S 1 layer, the outbreak area is C 2 ), and judge the infection status of a 1 and a 2 . As can be seen from Figure 3 , a 1 and a 2 are both infected entities, then a 1 and a2 Trace the process respectively as the infected entities of infectious diseases. That is, track the associated entities associated with a according to the spatio-temporal relationship graph network 1 associated with a 3 (which is layer S 2 and the outbreak area is C 3 ) and a 4 (which is layer S 2 and the outbreak area is C 4 ), and judge the infection status of a 3 and a 4 . As can be seen from Figure 3 , a 3 is an infected entity, so a 3 is traced as an infected entity of infectious diseases. a 4 and the uninfected area where it is located are no longer traced. At the same time, track the associated entities associated with a 2 according to the spatio-temporal relationship graph network 5 (which is layer S 2 and the outbreak area is C 5 ) and a 6 (which is layer S 2 and the outbreak area is C 6 ), and judge the infection status of a 5 and a 6 . As can be seen from Figure 3 , a 5 is an infected entity, so a 5 is traced as an infected entity of infectious diseases. a 6 and the uninfected area where it is located are no longer traced. And so on, the infected entity and the infected area where it is located continue to be traced according to the spatio-temporal relationship graph network until no infected entity appears among all the associated entities of the infected entity of infectious diseases. This infected entity of infectious diseases is the origin entity, and the traceability path is obtained. As Figure 3 shown, for the infected entity of infectious diseases a n-1 (which is layer S n-1 and the outbreak area is S n-1 ), all its associated entities a n (which is layer S n and the outbreak area is C n ), a n+1 (which is layer S n and the outbreak area is C n+1 ) and a n+2 (which is layer S n and the outbreak area is C n+2 ) do not have infected entities, then a n-1 is the origin entity, and the traceability path is obtained.

[0062] The method for tracking and tracing infectious diseases provided by the embodiments of the present invention includes: respectively obtaining big data information of multiple entities; establishing a spatio-temporal relationship graph network according to the multiple pieces of big data information; if an infectious disease-infected entity is found, a tracing process is performed, where the tracing process includes: tracking all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities; if an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity to perform the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained. This application utilizes big data information and big data technology to integrate and associate the travel of the group, establish a spatio-temporal relationship graph network, perform a tracing process, quickly obtain the originating entity and obtain a tracing path, and reduce the repetitive work of traditional large-scale regional detection. When using the method for tracking and tracing infectious diseases of this application to track and trace infectious diseases, the amount of calculation is relatively smaller and the positioning is more accurate.

[0063] Please refer to Figure 1 and Figure 4 As shown, the method for tracking and tracing infectious diseases provided by the embodiments of the present invention further includes:

[0064] Step 105: Obtain a training data set according to multiple tracing paths and the security level information of the regions on each tracing path. The calculation formula for the training data in the training data set is where L represents the comprehensive security risk level of the tracing path, l i represents the security risk level corresponding to any region in the tracing path, n i represents the number of infected entities in the region with a security risk level of l i and N represents the total number of all infected entities in the tracing path.

[0065] Exemplarily, as Figure 4 shown, in the training data set, the city codes corresponding to Beijing - Xi'an - Tianjin - Tangshan are (1101 - 6101 - 1201 - 1302). Referring to the administrative division code table of the Ministry of Civil Affairs in 2020, the corresponding risk levels are 3, 3, 2, 3 respectively, and the corresponding numbers of infected people are 3, 4, 2, 1 respectively. Substituting into it can be obtained that L = 2.8, and generally rounded to 3 after rounding.

[0066] Step 106: Input the training data set into a deep convolutional neural network to converge the weights of the model until convergence is stable to obtain a stable model. Through the algorithm of the convolutional neural network itself, the weights of the model are converged until the model converges stably, and the output result has a high accuracy rate (greater than 96%).

[0067] Among them, inputting the training data set into the deep convolutional neural network specifically includes: inputting the training data set into the residual neural network. The residual neural network is thinner, controlling the number of parameters. It has obvious hierarchies, and the number of feature maps increases layer by layer, ensuring the output feature expression ability. It uses fewer pooling layers, extensively uses downsampling to improve the propagation efficiency, does not use Dropout, and uses BN and global average pooling for normalization, accelerating the training speed.

[0068] Step 107: Input the new path to be detected into the stability model to obtain the comprehensive risk level prediction of the new path, thereby completing the comprehensive risk level prediction of the current new path, and taking prevention and control measures in a timely manner for this prediction.

[0069] The method for infectious disease tracking and tracing provided by the embodiments of the present application, based on obtaining the spatio-temporal relationship graph network of multiple entities and the tracing path, can, by using the deep convolutional neural network, analyze and predict the infectious disease risk level and scale in a certain region and at a certain spatio-temporal in the future, and take preventive measures in a timely manner.

[0070] Please continue to refer to Figure 1 As shown, the method for infectious disease tracking and tracing provided by the embodiments of the present invention further includes:

[0071] Step 108: Add the new path and the safety level information of the regions on the new path to the training data set, and input them into the deep convolutional neural network for self-learning, that is, re-expand the new path and the safety level information of the regions on the new path into the training data set, increasing the diversity of the tracing path, and thus improving the prediction accuracy.

[0072] Compared with the current method of entity infectious disease tracking and tracing through simple big data formation models, although big data information is also utilized, the entities are not deeply associated with spatio-temporal information for spatio-temporal associated tracing, and at the same time, a deep learning convolutional neural network for self-learning is not established for safety risk assessment, so the prediction ability of the system is poor. The method for infectious disease tracking and tracing provided by the embodiments of the present application, while utilizing big data information, deeply associates entities with spatial information for spatio-temporal associated tracing, and moreover, establishes a deep learning convolutional neural network for self-learning for safety risk assessment, and the prediction ability of the system is strong.

[0073] Another embodiment of the present invention provides a system for infectious disease tracking and tracing, including:

[0074] An acquisition module, configured to respectively acquire big data information of multiple entities.

[0075] A building module, configured to build a spatio-temporal relationship graph network according to multiple big data information.

[0076] The tracing module is used to carry out the tracing process if an infectious disease entity is found, wherein the tracing process includes: tracking all related entities associated with the infectious disease entity according to the spatiotemporal relationship graph network, and determining the infectious conditions of all related entities.

[0077] The selection module is used to trace the infected entity as the infectious disease entity if there is an infected entity in the associated entity. If there is no infected entity in the associated entity, the infectious disease entity is the source entity and the traceability path is obtained.

[0078] The infectious disease tracking and tracing system of the present application is used to track and trace the source of infectious diseases, with relatively less calculation amount and more accurate positioning.

[0079] Furthermore, the establishment module specifically includes:

[0080] The data cleaning and analysis submodule is used to use big data technology to clean and analyze multiple big data information to obtain information to be used.

[0081] A submodule is established to establish a data dictionary based on the information to be used.

[0082] The association analysis submodule is used to establish an association analysis table through association analysis according to the data dictionary.

[0083] A submodule is formed to form a spatiotemporal relationship map based on the association analysis table.

[0084] Another embodiment of the present invention provides a system for tracking and tracing the source of infectious diseases, further comprising:

[0085] The acquisition module is used to obtain a training data set based on multiple traceability paths and the security level information of the regions on each traceability path. The calculation formula of the training data in the training data set is: Where L represents the comprehensive security risk level of the traceability path, l i Indicates the security risk level of any region in the traceability path, n i Indicates that the security risk level is l i The number of infected entities in the region, N represents the total number of infected entities in all the traceability paths.

[0086] The training module is used to input the training data set into the deep convolutional neural network and converge the weights of the model until the convergence is stable to obtain a stable model.

[0087] The input module is used to input the new path to be detected into the stability model to obtain the comprehensive risk level prediction of the new path.

[0088] Another embodiment of the present invention provides a system for tracking and tracing the source of infectious diseases, further comprising:

[0089] An adding module is configured to add the security level information of the new path and the regions on the new path to the training data set and input it into a deep convolutional neural network for self-learning.

[0090] Another embodiment of the present invention provides a server, including: a memory and a processor; the memory is used to store program instructions; the processor is used to execute the program instructions in the memory, so that the server executes the above-mentioned method for tracing the origin of infectious diseases.

[0091] Another embodiment of the present invention provides a computer-readable storage medium, which stores executable instructions, and when the computer executes the executable instructions, it can implement the above-mentioned method for tracing the origin of infectious diseases.

[0092] The above storage medium includes but is not limited to Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions.

[0093] Although the present application provides method operation steps such as in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The step order listed in this embodiment is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or client product executes, it can be executed in the order shown in this embodiment or the drawings, or executed in parallel (such as in an environment with parallel processors or multi-threaded processing).

[0094] The systems or modules illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above systems, they are divided into various modules according to functions for separate description. When implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware. Of course, the module implementing a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0095] The methods, systems or modules in this application can be implemented in the form of computer-readable program code. The controller can be implemented in any appropriate manner. For example, the controller can take the form of a microprocessor or a processor, and a computer-readable medium that stores computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, application specific integrated circuit (ASIC), programmable logic controller, and embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the controller can be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the systems for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0096] Some modules in the system of this application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0097] From the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, or can also be reflected in the implementation process of data migration. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods of various embodiments or some parts of the embodiments of this application.

[0098] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. All or part of the present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, mobile communication terminals, multi-processor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0099] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A method for tracing the origin of an infectious disease, characterized in that, it includes: respectively obtaining big data information of multiple entities; establishing a spatio-temporal relationship graph network according to the multiple big data information; if an infectious disease-infected entity is found, a tracing process is carried out, wherein the tracing process includes: tracing all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities; if an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity to carry out the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained; The specific steps of establishing a spatio-temporal relationship graph network according to the multiple big data information include: using big data technology to perform data cleaning and data analysis on the multiple big data information to obtain information to be used; establishing a data dictionary according to the information to be used; establishing an association analysis table through association analysis according to the data dictionary; forming a spatio-temporal relationship graph network according to the association analysis table; The specific steps of establishing a data dictionary according to the information to be used include: establishing a data dictionary with attributes of geographical information, time information, and security level information according to the information to be used; It further includes: A training data set is obtained according to the multiple traceability paths and the security level information of the regions on each traceability path. The calculation formula of the training data in the training data set is where L represents the comprehensive security risk level of the traceability path, and l i represents the security risk level corresponding to any region in the traceability path, and n i represents the number of infected entities in the region with the security risk level of l i , and N represents the total number of all infected entities in the traceability path; inputting the training data set into a deep convolutional neural network, and converging the weights of the model until convergence is stable to obtain a stable model; inputting a new path to be detected into the stable model to obtain a comprehensive risk level prediction of the new path; The specific steps of inputting the training data set into a deep convolutional neural network include: inputting the training data set into a residual neural network.

2. The method for tracing the origin of an infectious disease according to claim 1, characterized in that, it further includes: adding the new path and the security level information of the area on the new path to the training data set, and inputting them into the deep convolutional neural network for self-learning.

3. A system for tracing the origin of an infectious disease, characterized in that, it includes: an acquisition module, used for respectively obtaining big data information of multiple entities; a establishment module, used for establishing a spatio-temporal relationship graph network according to the multiple big data information; a tracing module, used for carrying out a tracing process if an infectious disease-infected entity is found, wherein the tracing process includes: tracing all associated entities associated with the infectious disease-infected entity according to the spatio-temporal relationship graph network, and judging the infection status of all the associated entities; a selection module, used for if an infected entity appears among the associated entities, the infected entity is used as the infectious disease-infected entity to carry out the tracing process; if no infected entity appears among the associated entities, the infectious disease-infected entity is the originating entity, and a tracing path is obtained; The specific steps of establishing a spatio-temporal relationship graph network according to the multiple big data information include: using big data technology to perform data cleaning and data analysis on the multiple big data information to obtain information to be used; establishing a data dictionary according to the information to be used; establishing an association analysis table through association analysis according to the data dictionary; forming a spatio-temporal relationship graph network according to the association analysis table; Establishing a data dictionary according to the information to be used specifically includes: Establishing a data dictionary with attributes of geographic information, time information, and security level information according to the information to be used; It further includes: A training dataset is obtained based on the multiple traceability paths and the security level information of the regions on each traceability path. The calculation formula for the training data in the training dataset is where L represents the comprehensive security risk level of the traceability path, and l i represents the security risk level corresponding to any region in the traceability path, and n i represents the number of infected entities in the region with a security risk level of l i , and N represents the total number of all infected entities in the traceability path; Inputting the training data set into a deep convolutional neural network to converge the weights of the model until convergence is stable to obtain a stable model; Inputting a new path to be detected into the stable model to obtain a comprehensive risk level prediction of the new path; The step of inputting the training data set into the deep convolutional neural network specifically includes: Inputting the training data set into a residual neural network.

4. A server, characterized in that, it includes: a memory and a processor; the memory is used for storing program instructions; the processor is used for executing the program instructions in the memory, so that the server executes the method for tracking and tracing infectious diseases as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores executable instructions, and when a computer executes the executable instructions, it can implement the method for tracking and tracing infectious diseases as described in any one of claims 1 to 2.

Images