Infectious disease tracing method based on hypergraph structure and related equipment

Abstract

The invention relates to the technical field of data analysis, and provides an infectious disease tracing method based on a hypergraph structure and related equipment. The infectious disease tracing method based on the hypergraph structure comprises the following steps: constructing an initial hypergraph according to propagation individuals, propagation media and propagation events related to the propagation individuals and the propagation media; for each hyperedge, acquiring a node set included in the hyperedge, and determining binary edges between each node in the node set and other nodes to obtain a binary edge set; wherein two nodes determine a binary edge; dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infection characteristics of the infectious diseases to obtain an updated weight; determining an inter-node shortest path set and a precursor node set corresponding to all nodes from the binary edge set according to the update weight; and tracing the transmission end point of the infectious disease according to the shortest path set and the precursor node set to obtain a transmission source point of the infectious disease.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and specifically relates to a method for tracing the source of an infectious disease based on a hypergraph structure, a device for tracing the source of an infectious disease based on a hypergraph structure, an electronic device, and a computer-readable storage medium. Background Art

[0002] Traditional investigation methods for tracing the source of infectious diseases mostly require a lot of manpower and time costs. In today's complex urban environment, the transmission characteristics of infectious diseases are becoming increasingly complex, and the transmission paths of diseases are highly spatially heterogeneous and temporally different.

[0003] In related technologies, the tracing of infectious diseases is usually limited to binary relationships and cannot fully simulate the transmission path in the actual environment. At the same time, the transmission analysis models of infectious diseases are mostly simplified analyses at the macro level. There is no accurate tracing and transmission prediction of the transmitting individuals, and it is impossible to provide accurate data support for the prevention of infectious diseases, which may lead to problems such as the spread of infectious diseases. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a method for tracing the source of infectious diseases based on a hypergraph structure, which can more accurately and quickly trace the source of infectious diseases and flexibly adjust and optimize the transmission path according to actual conditions.

[0005] In the first aspect, an embodiment of the present application provides an infectious disease tracing method based on a hypergraph structure, including: constructing an initial hypergraph based on transmitting individuals, transmitting media, and transmission events related to transmitting individuals and transmitting media; for each hyperedge, obtaining the node set included in the hyperedge, determining the binary edges between each node in the node set and other nodes, and obtaining a binary edge set; wherein, two nodes determine a binary edge; dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight; determining the shortest path set between nodes and the predecessor node set corresponding to all nodes from the binary edge set according to the updated weight; tracing the transmission end point of the infectious disease based on the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease.

[0006] In some embodiments, the method further includes: calculating a hyperedge weight of each hyperedge in the initial hypergraph; and using the hyperedge weight as the binary edge weight of each binary edge in the binary edge set corresponding to the hyperedge.

[0007] In some embodiments, an initial hypergraph is constructed based on the propagation individuals, propagation media, and propagation events related to the propagation individuals and propagation media, including: using the propagation individuals and / or propagation media as nodes of the initial hypergraph, and using the propagation events as hyperedges connecting the nodes; constructing the initial hypergraph based on the nodes and the hyperedges; wherein the propagation events include propagation events between propagation individuals and propagation individuals, propagation events between propagation individuals and propagation media, and propagation events between propagation media and propagation media.

[0008] In some embodiments, the infectious characteristics include the infectious disease's transmission potential, the contact duration between nodes, and the transmission environment in which the nodes are located. Dynamically adjusting the binary edge weight of each binary edge in the binary edge set based on the infectious disease's transmission characteristics to obtain an updated weight includes:

[0009] W(u→v,t)=αgStrength(u,v)+βgContactDuration(u,v)+γgEnvironment(u,v)

[0010] Among them, Strength(u,v) represents the potential for infectious disease transmission between node u and node v, ContactDuration(u,v) represents the contact duration between node u and node v, Environment(u,v) represents the transmission environment in which node u and node v are located, α represents the adjustable parameter corresponding to the transmission potential, β represents the adjustable parameter corresponding to the contact duration, and γ represents the adjustable parameter corresponding to the transmission environment. α, β, and γ are obtained based on the hyperedges corresponding to the binary edges.

[0011] In some embodiments, after dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease and obtaining the updated weight, the method also includes: determining the shortest propagation path weight d[v] between the propagation end point and the node v, determining the shortest propagation path weight d[u] between the propagation end point and the node u, and determining the updated weight W(u→v) of the binary edge between the node u and the node v; if the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v is less than the shortest propagation path weight d[v] between the propagation end point and the node v, then the shortest propagation path weight d[v] between the propagation end point and the node v is updated to the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v, and determining that the predecessor node of the node v is the node u, and adding the node u to the priority queue.

[0012] In some embodiments, the method also includes: calculating the time difference between the infection time of each node in the priority queue and the infection time of the propagation end point; for each node in the priority queue, determining an estimated value based on the time difference and the weight of the shortest propagation path between the propagation end point and the node; updating the shortest path and predecessor node of the nodes in the priority queue in order of the estimated values ​​from small to large.

[0013] In some embodiments, the transmission end point of an infectious disease is traced based on a shortest path set and a predecessor node set to obtain the transmission source point of the infectious disease, including: obtaining a target predecessor node of the transmission end point, and gradually tracing back from the predecessor node set and the shortest path set according to the target predecessor node until the transmission source point of the infectious disease is obtained.

[0014] The infectious disease tracing method based on the hypergraph structure provided in this application uses a hypergraph model to build the contact relationship of the spread of infectious diseases, accurately restores complex transmission scenarios, and further combines the infectious characteristics and transmission events of infectious diseases. Through the shortest path inference algorithm of the hypergraph, the actual transmission path is comprehensively and efficiently calculated in a complex transmission network, the transmission source of the infectious disease is accurately traced, and the accurate transmission path is obtained, providing important data support for the prevention and control of infectious diseases.

[0015] In the second aspect, an embodiment of the present application provides an infectious disease tracing device based on a hypergraph structure, including: a construction module, configured to construct an initial hypergraph based on the transmitting individuals, transmitting media and the transmission events related to the transmitting individuals and transmitting media; a determination module, configured to obtain the node set included in each hyperedge, determine the binary edges between each node in the node set and other nodes, and obtain a binary edge set; wherein, two nodes determine a binary edge; an update module, configured to dynamically adjust the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease, and obtain an updated weight; a predecessor module, configured to determine the shortest path set between nodes and the predecessor node set corresponding to all nodes from the binary edge set according to the updated weight; a tracing module, configured to trace the transmission end point of the infectious disease based on the shortest path set and the predecessor node set, and obtain the transmission source point of the infectious disease.

[0016] The infectious disease tracing device based on a hypergraph structure provided in this application uses a hypergraph model to build the contact relationship of the spread of infectious diseases, accurately restores complex transmission scenarios, and further combines the infectious characteristics and transmission events of infectious diseases. Through the shortest path inference algorithm of the hypergraph, the actual transmission path is comprehensively and efficiently calculated in a complex transmission network, the transmission source of the infectious disease is accurately traced, and the accurate transmission path is obtained, providing important data support for the prevention and control of infectious diseases.

[0017] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the infectious disease tracing method based on a hypergraph structure as in the first aspect are implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the infectious disease tracing method based on a hypergraph structure as in the first aspect are implemented.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0021] Figure 1 A flowchart of a method for tracing the source of an infectious disease based on a hypergraph structure provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of a priority queue updating method for an infectious disease tracing method based on a hypergraph structure provided in an embodiment of the present application;

[0023] Figure 3 Schematic diagram of an infectious disease tracing device based on a hypergraph structure provided in an embodiment of the present application;

[0024] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.

[0025] Figure numerals: 300 - infectious disease tracing device based on hypergraph structure; 310 - construction module; 320 - determination module; 330 - update module; 340 - precursor module; 350 - tracing module; 410 - processor; 420 - memory; 430 - input / output interface; 440 - communication interface; 450 - bus. DETAILED DESCRIPTION

[0026] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0027] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0028] As described in the background technology section, when responding to sudden infectious diseases, tracing the source of the infectious disease is the key to controlling the spread of the infectious disease. Traditional epidemiological surveys require a lot of time and manpower costs, and the modern complex urban environment further increases the difficulty and cost of epidemiological surveys. In addition, in a complex urban environment, the transmission paths of infectious diseases also show a high degree of spatial heterogeneity and temporal differences. Traditional infectious disease tracing methods can no longer meet the needs of current disease prevention and control. To this end, this application provides an infectious disease tracing method based on a hypergraph structure, which can efficiently and accurately trace the source and transmission path of infectious diseases, thereby providing key data support for disease prevention and control.

[0029] The technical solution of the present application is further described in detail below through specific examples.

[0030] refer to Figure 1 , which is a flow chart of the infectious disease tracing method based on the hypergraph structure provided in an embodiment of the present application.

[0031] Step S101: construct an initial hypergraph based on the communication individuals, communication media, and communication events related to the communication individuals and communication media.

[0032] Specifically, the hypergraph model is an extension of the traditional graph model. Compared with the traditional graph model, the hypergraph model introduces the concept of hyperedges. The traditional graph model consists of nodes and edges, and an edge can only connect two nodes. In the hypergraph model, hyperedges can connect multiple nodes, and can be applied to complex network structures.

[0033] The nodes in the hypergraph model are used to represent entities or objects. In the hypergraph model provided in the present application, the nodes can be communication individuals and / or communication media, where the communication individuals can be people or movable objects, and the communication media can be places where people are active or places where objects are stored, etc.; the hyperedges in the hypergraph model are used to represent high-order relationships connecting any number of nodes, representing group interactions between multiple nodes, that is, representing many-to-many contact relationships. A hyperedge can connect two or more nodes. In the hypergraph model provided in the present application, the hyperedge can be a communication event related to the communication media, such as person A is in place a, or person A and person B are in contact in place b.

[0034] Furthermore, the hypergraph model G can be expressed as G = (V, E), where V = {v1, v2, L, v n} is a node set, i.e., a set of communication individuals and / or communication media; E = {e1, e2, L, e n} is a hyperedge set, i.e., a set of propagation events. Any hyperedge e in the hyperedge set i is also a subset, hyperedge e i ={v n ,L,v m}, represents the relationship between the nodes included in any hyperedge, that is, the transmission event related to the transmission individual and / or the transmission medium. The transmission event can be a transmission event between transmission individuals, such as the contact between person A and person B; the transmission event can also be a transmission event between transmission individuals and transmission media, such as the contact between person A and person C in place a, or person A can be in place a; the transmission event can also be a transmission event between transmission media, such as person A moves from place a to place b, and transmits the source of disease in place a to place b, etc.

[0035] Step S102 : for each hyperedge, obtain the node set included in the hyperedge, determine the binary edges between each node in the node set and other nodes, and obtain a binary edge set; wherein two nodes determine one binary edge.

[0036] Specifically, by expanding the hyperedge, we can get the binary edge set corresponding to the hyperedge. For each node set included in the hyperedge, any node in it can form a binary edge with any other node in the hyperedge node set (v i ,v j ),in i≠j; any binary edge is a directional edge. For example, the binary edges represented by the binary edge (v1, v2) and the binary edge (v2, v1) are two different binary edges. The number of binary edges contained in each hyperedge can be calculated by permutation.

[0037] As an optional embodiment, the method further includes: calculating the hyperedge weight of each hyperedge in the initial hypergraph; and using the hyperedge weight as the binary edge weight of each binary edge in the binary edge set corresponding to the hyperedge.

[0038] Specifically, the initial data of the hypergraph model also includes the weight of the hyperedge, which is a quantitative description of the hyperedge. In the embodiment of the present application, the weight of the hyperedge is the propagation weight of the infectious disease, which reflects the degree of influence of a certain propagation path (i.e., multiple nodes connected by hyperedges) on the spread of infectious diseases.

[0039] The weight of any hyperedge W(e i) can be obtained by extracting relevant features of all nodes in the hyperedge and further calculating the nodes by statistical methods or by using a machine learning model. It can be understood that the weight W(u→v) of any binary edge corresponding to the hyperedge at this time is the same as the weight of the hyperedge where the binary edge is located, where u and v both represent arbitrary nodes.

[0040] As an optional embodiment, when constructing a hypergraph model, it is necessary to confirm the propagation endpoint S in the hypergraph model. The propagation endpoint is a known current infected node, which can also be understood as the end point of propagation.

[0041] As an optional embodiment, when constructing the hypergraph model, it is also necessary to confirm the spread time t of the infectious disease. For any node v i , its propagation time can be understood as the node v i Obtain the infection time t(v i ).

[0042] As an optional embodiment, the method provided in this application also requires initializing the hypergraph model.

[0043] Specifically, for the propagation endpoint S, the weight d[v] of the node v corresponding to the shortest propagation path from the propagation endpoint S is set to:

[0044]

[0045] That is, when the node is the end point of the propagation, the weight of the shortest propagation path is zero, and when the node is not the end point of the propagation, the weight of the shortest propagation path is infinite.

[0046] Furthermore, the predecessor node vector p[v] of the previous node in the propagation path of node v is initialized to NULL, that is, it is assumed that there is no predecessor node for the node.

[0047] Step S103 : dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight.

[0048] Specifically, when tracing the source of infectious diseases, since the spread of the disease has complex infectious characteristics, these infectious characteristics will change dynamically with changes in time, place and different transmission scenarios. Therefore, the weights of the hyperedges need to be dynamically adjusted. Furthermore, for binary edges, it is also necessary to update the weights of the traced binary edges and other binary edges in the hyperedges according to the infectious characteristics of the infectious disease.

[0049] Taking the tracing of the propagation end point S and node v as an example, after the propagation end point S is traced forward to node v, the next step of tracing needs to be performed based on node v. When node v is added to the tracing process, the node set of the traced hyperedge will change, that is, the influencing factors of the hyperedge weight will change. Furthermore, the weight of the binary edge where the propagation end point S and node v are located will also change. At this time, the weight of the current node set needs to be updated to ensure that the correct propagation source node can be traced back.

[0050] For the method provided in this application, the infectious characteristics include the transmission potential of the infectious disease, the contact time between nodes, and the transmission environment in which the nodes are located. Among them, the transmission potential of the infectious disease can be understood as the probability of the infectious disease spreading between nodes, the contact time between nodes can be understood as the transmission time between nodes, and the transmission environment in which the nodes are located can be the impact of the environment on the transmission, such as the degree of air circulation or the degree of airtightness of the transmission environment.

[0051] Furthermore, the calculation formula for updating the binary edge weight from node u to node v is:

[0052] W(u→v,t)=αgStrength(u,v)+βgContactDuration(u,v)+γgEnvironment(u,v)

[0053] Among them, Strength(u,v) represents the potential for infectious disease transmission between node u and node v; ContactDuration(u,v) represents the contact duration between node u and node v, Environment(u,v) represents the transmission environment in which node u and node v are located, α represents the adjustable parameter corresponding to the transmission potential, β represents the adjustable parameter corresponding to the contact duration, and γ represents the adjustable parameter corresponding to the transmission environment. α, β, and γ are obtained based on the hyperedges corresponding to the binary edges.

[0054] Step S104 : determining the shortest path set between nodes and the predecessor node set corresponding to all nodes from the binary edge set according to the updated weights.

[0055] Specifically, during the tracing process, starting from the propagation endpoint, it is necessary to trace forward to the node with the shortest propagation path weight relative to the propagation endpoint, further update the weight of the hyperedge in the hypergraph model, and further trace the traced nodes in depth based on the updated weights, so as to ultimately determine the shortest path set between nodes from the binary edge set of the hypergraph model. That is, the weights of all binary edges on this path are the shortest propagation path weights of the corresponding nodes. The shortest path set includes all binary edges that constitute the shortest path, and the predecessor node set includes all nodes covered by the shortest path set. By updating the weights of the shortest path and the predecessor nodes, the shortest path can be obtained efficiently, while ensuring that all possible paths are traced, thereby obtaining the global optimal solution.

[0056] As an optional embodiment, after dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease and obtaining the updated weight, the method also includes: determining the shortest propagation path weight d[v] between the propagation end point and the node v, determining the shortest propagation path weight d[u] between the propagation end point and the node u, and determining the updated weight W(u→v) of the binary edge between the node u and the node v; if the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v is less than the shortest propagation path weight d[v] between the propagation end point and the node v, then the shortest propagation path weight d[v] between the propagation end point and the node v is updated to the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v, and determining that the predecessor node of the node v is the node u, and adding the node u to the priority queue.

[0057] Specifically, taking any pair of nodes u and v in the tracing process as an example, for the propagation endpoint S, first determine the shortest propagation path weight d[v] between the propagation endpoint S and the node v, and the shortest propagation path weight d[u] between the propagation endpoint S and the node u. Further, according to the nodes in the current set, the weight of the binary edge between the node u and the node v is updated to obtain the updated weight W(u→v).

[0058] Furthermore, if the weight relationship satisfies:

[0059] d[u]+W(u→v) <d[v]

[0060] That is, when the sum of the shortest propagation path weight d[u] between the propagation endpoint S and the node u and the binary edge update weight W(u→v) between the node u and the node v is less than the shortest propagation path weight d[v] between the propagation endpoint S and the node u, the shortest propagation path weight d[v] between the propagation endpoint S and the node v is updated to the sum of the shortest propagation path weight d[u] between the propagation endpoint S and the node u and the binary edge update weight W(u→v) between the node u and the node v, that is: d[v]=d[u]+W(u→v). At this time, it can be determined that the predecessor node of node v is u, and the node u is further added to the priority queue.

[0061] For example, when the shortest propagation path weight d[u] between the propagation endpoint S and node u is 2, and the shortest propagation path weight d[v] between the propagation endpoint S and node v is 4, and the weight between node u and node v obtained by updating the weight of node u and node v is -1, the calculation formula is:

[0062]

[0063] At this time, the calculation formula is valid, and the shortest propagation path weight between the propagation end point S and node v is defined as d[v]=d[u]+W(u→v)=1. Node u is further determined to be the predecessor node of node v, and node u is added to the retrospective priority queue.

[0064] refer to Figure 2 , which is a flow chart of the priority queue update method of the infectious disease tracing method based on the hypergraph structure provided in an embodiment of the present application.

[0065] Step S201, calculating the time difference between the infection duration of each node in the priority queue and the infection duration of the propagation endpoint;

[0066] Step S202 , for each node in the priority queue, determining an estimated value based on the time difference and the weight of the shortest propagation path between the propagation endpoint and the node;

[0067] Step S203 : updating the shortest paths and predecessor nodes of the nodes in the priority queue in ascending order of estimated values.

[0068] Specifically, during the tracing process, the priority queue will sort the nodes according to their estimated values, and each time the node with the smallest priority value will be selected for processing. Taking node v as an example, its estimated value is calculated as follows:

[0069] f(v)=d[v]+h[v]

[0070] Where f(v) is the estimated value of node v; h[v] is the heuristic function, which is determined by the difference between the infection time of node v and the infection time of the propagation endpoint S. Its calculation formula is:

[0071] h[v]=t[v]-t[S]

[0072] Among them, t[v] is the infection duration of node v; t[S] is the infection time of the propagation endpoint S.

[0073] Furthermore, by updating the shortest paths of the nodes in the priority queue and the predecessor nodes corresponding to each node according to the sorted node order, the tracing process can be dynamically analyzed through the infection time of the node, thereby tracing the propagation path efficiently and accurately.

[0074] Step S105 , tracing the transmission end point of the infectious disease according to the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease.

[0075] Specifically, by continuously tracing back the predecessor node with the shortest path to the transmission destination, the transmission path of the infectious disease is reversely searched, and the starting point of the transmission can be located. The traceability method provided in this application can ultimately output the information, including:

[0076] The current transmission path of the infectious disease, which includes the corresponding nodes and the transmission order of the nodes;

[0077] The source of transmission, that is, the point of transmission traced back to (i.e., patient 0);

[0078] Time series, which is the infection time of each node and the time interval between propagation events;

[0079] The total propagation weight of the propagation path. The calculation formula of the total propagation weight is:

[0080]

[0081] Among them, v0, v1, L, v i ,L,v k is the order of nodes in the propagation path.

[0082] It should be noted that, during the tracing process, if there are multiple possible transmission sources, the paths can be screened according to the infection time and the binary edge weights of the nodes to obtain the earliest transmission source.

[0083] As an optional embodiment, the transmission end point of the infectious disease is traced based on the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease, including: obtaining the target predecessor node of the transmission end point, and gradually tracing back from the predecessor node set and the shortest path set according to the target predecessor node until the transmission source point of the infectious disease is obtained.

[0084] Specifically, for example, assume that the predecessor node of the transmission endpoint S is v, that is, for the transmission endpoint S, its shortest infection path is infected through node v. Further, trace back to node v, and obtain the predecessor node of node v as node u. Further, continue to trace back to node u, and obtain the predecessor node of node u as node m. Repeat this process until in a certain round of iteration, the weight of any node in the node set is not updated, that is:

[0085]

[0086] This means that the propagation path has converged, that is, it has been traced back to the source of propagation and tracing can be stopped.

[0087] Assuming that the current infection spread endpoint is S, the backtracking process can be expressed as follows:

[0088] v0=S

[0089] v i+1 =p[v i ]

[0090] When p[v i ]=NULL, that is, when the predecessor node is empty, it means that the transmission source has been traced back.

[0091] According to the infectious disease tracing method based on the hypergraph structure of the embodiment of the present application, the hypergraph model is used to build the contact relationship of the spread of infectious diseases, and the complex transmission scenarios are accurately restored. Further combined with the infectious characteristics and transmission events of infectious diseases, the shortest path inference algorithm of the hypergraph is used to comprehensively and efficiently calculate the actual transmission path in the complex transmission network, accurately trace the source point of the infectious disease, and obtain the accurate transmission path, providing important data support for the prevention and control of infectious diseases.

[0092] refer to Figure 3 , which is a schematic diagram of an infectious disease tracing device based on a hypergraph structure provided in an embodiment of the present application.

[0093] Based on the same concept, corresponding to the infectious disease tracing method based on the hypergraph structure provided in the above embodiment, the present application also provides an infectious disease tracing device 300 based on the hypergraph structure.

[0094] The infectious disease tracing device 300 based on a hypergraph structure includes: a construction module 310 , a determination module 320 , an update module 330 , a predecessor module 340 and a tracing module 350 .

[0095] Specifically, the construction module 310 is configured to construct an initial hypergraph based on the transmitting individuals, transmitting media and the transmitting events related to the transmitting individuals and transmitting media; the determination module 320 is configured to obtain the node set included in each hyperedge, determine the binary edges between each node in the node set and other nodes, and obtain a binary edge set; wherein, two nodes determine a binary edge; the update module 330 is configured to dynamically adjust the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease, and obtain an updated weight; the predecessor module 340 is configured to determine the shortest path set between nodes and the predecessor node set corresponding to all nodes from the binary edge set according to the updated weight; the tracing model 350 is configured to trace the transmission end point of the infectious disease based on the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease.

[0096] Optionally, the determination module 320 is further configured to: calculate the hyperedge weight of each hyperedge in the initial hypergraph; and use the hyperedge weight as the binary edge weight of each binary edge in the binary edge set corresponding to the hyperedge.

[0097] Optionally, the construction module 310 is further configured to: use the propagation individuals and / or propagation media as nodes of the initial hypergraph, and use the propagation events as hyperedges connecting the nodes; construct the initial hypergraph based on the nodes and hyperedges; wherein the propagation events include propagation events between propagation individuals and propagation individuals, propagation events between propagation individuals and propagation media, and propagation events between propagation media and propagation media.

[0098] Optionally, the infectious characteristics include the potential for transmission of the infectious disease, the contact duration between nodes, and the transmission environment in which the nodes are located. The updating module 330 is further configured to:

[0099] The binary edge weight of each binary edge in the binary edge set is dynamically adjusted according to the infectious characteristics of the infectious disease to obtain the updated weight, including:

[0100] W(u→v,t)=αgStrength(u,v)+βgContactDuration(u,v)+γgEnvironment(u,v)

[0101] Among them, Strength(u,v) represents the potential for infectious disease transmission between node u and node v, ContactDuration(u,v) represents the contact duration between node u and node v, Environment(u,v) represents the transmission environment in which node u and node v are located, α represents the adjustable parameter corresponding to the transmission potential, β represents the adjustable parameter corresponding to the contact duration, and γ represents the adjustable parameter corresponding to the transmission environment. α, β, and γ are obtained based on the hyperedges corresponding to the binary edges.

[0102] Optionally, the predecessor module 340 is also configured to: determine the shortest propagation path weight d[v] between the propagation end point and the node v, determine the shortest propagation path weight d[u] between the propagation end point and the node u, and determine the updated weight W(u→v) of the binary edge between the node u and the node v; if the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v is less than the shortest propagation path weight d[v] between the propagation end point and the node v, then the shortest propagation path weight d[v] between the propagation end point and the node v is updated to the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v, and determine that the predecessor node of the node v is the node u, and add the node u to the priority queue.

[0103] Optionally, the predecessor module 340 is also configured to: calculate the time difference between the infection duration of each node in the priority queue and the infection duration of the propagation endpoint; for each node in the priority queue, determine an estimated value based on the time difference and the weight of the shortest propagation path between the propagation endpoint and the node; and update the shortest path of the nodes in the priority queue and the predecessor node in order of the estimated values ​​from small to large.

[0104] Optionally, the traceability module 350 is further configured to: obtain the target predecessor node of the transmission end point, and trace back step by step from the predecessor node set and the shortest path set according to the target predecessor node until the transmission source point of the infectious disease is obtained.

[0105] From the above, it can be seen that the infectious disease tracing device based on the hypergraph structure provided in the embodiment of the present application uses a hypergraph model to build the contact relationship of the spread of infectious diseases, accurately restores complex transmission scenarios, and further combines the infectious characteristics and transmission events of infectious diseases. Through the shortest path inference algorithm of the hypergraph, the actual transmission path is comprehensively and efficiently calculated in a complex transmission network, the transmission source of the infectious disease is accurately traced, and the accurate transmission path is obtained, providing important data support for the prevention and control of infectious diseases.

[0106] Based on the same concept, corresponding to the infectious disease tracing method based on the hypergraph structure provided in any of the above embodiments, the present application also provides an electronic device, including a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the infectious disease tracing method based on the hypergraph structure of the first aspect are implemented.

[0107] Figure 4A more specific hardware structure diagram of an electronic device provided in this embodiment is shown. The device may include: a processor 410, a memory 420, an input / output interface 430, a communication interface 440, and a bus 450. The processor 410, the memory 420, the input / output interface 430, and the communication interface 440 are communicatively connected to each other within the device via the bus 450.

[0108] The processor 410 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0109] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 420 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 420 and is called and executed by the processor 410.

[0110] The input / output interface 430 is used to connect an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0111] The communication interface 440 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0112] The bus 450 comprises a pathway for transmitting information between the various components of the device, such as the processor 410 , the memory 420 , the input / output interface 430 , and the communication interface 440 .

[0113] It should be noted that although the above device only shows the processor 410, the memory 420, the input / output interface 430, the communication interface 440, and the bus 450, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0114] The electronic device of the above embodiment is used to implement the corresponding infectious disease tracing method based on hypergraph structure in any of the above embodiments, and has the beneficial effects of the corresponding infectious disease tracing method based on hypergraph structure embodiment, which will not be repeated here.

[0115] Based on the same concept, corresponding to the infectious disease tracing method based on the hypergraph structure provided in any of the above embodiments, the present application also provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by the processor, the steps of the infectious disease tracing method based on the hypergraph structure as in the first aspect are implemented.

[0116] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NANDFLASH), solid-state drives (SSDs)), etc.

[0117] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the corresponding infectious disease tracing method based on the hypergraph structure in any of the above embodiments, and have the beneficial effects of the corresponding infectious disease tracing method based on the hypergraph structure embodiment, which will not be repeated here.

[0118] It should be noted that, in this document, the terms "first," "second," and similar terms used in the embodiments do not indicate any order, quantity, or importance, but are merely used to distinguish different components; the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, article, or device comprising that element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0119] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0120] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0121] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A method for tracing the source of infectious diseases based on a hypergraph structure, characterized in that: include: Constructing an initial hypergraph according to the spreading individuals, the spreading media, and the spreading events related to the spreading individuals and the spreading media; For each hyperedge, obtain a node set included in the hyperedge, determine binary edges between each node in the node set and other nodes, and obtain a binary edge set; wherein two nodes determine a binary edge; Dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight; Determining a set of shortest paths between nodes and a set of predecessor nodes corresponding to all nodes from the set of binary edges according to the updated weights; The transmission end point of the infectious disease is traced according to the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease.

2. The infectious disease tracing method based on hypergraph structure according to claim 1 is characterized in that: The method further comprises: Calculating a hyperedge weight for each hyperedge in the initial hypergraph; The hyperedge weight is used as the binary edge weight of each binary edge in the binary edge set corresponding to the hyperedge.

3. The infectious disease tracing method based on hypergraph structure according to claim 2 is characterized in that: The constructing of an initial hypergraph based on the propagation individuals, the propagation media, and the propagation events related to the propagation individuals and the propagation media includes: The propagation individuals and / or the propagation media are used as nodes of the initial hypergraph, and the propagation events are used as hyperedges connecting the nodes; The initial hypergraph is constructed based on the nodes and the hyperedges; wherein the propagation events include propagation events between propagation individuals, propagation events between propagation individuals and propagation media, and propagation events between propagation media and propagation media.

4. The infectious disease tracing method based on hypergraph structure according to claim 3 is characterized in that: The infectious characteristics include the transmission potential of the infectious disease, the contact duration between nodes, and the transmission environment in which the nodes are located; The dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight includes: W(u→v,t)=αgStrength(u,v)+βgContactDuration(u,v)+γgEnvironment(u,v) Among them, Strength(u,v) represents the transmission potential of infectious diseases between nodes u and v, ContactDuration(u,v) represents the contact duration between nodes u and v, Environment(u,v) represents the transmission environment in which nodes u and v are located, α represents the adjustable parameter corresponding to the transmission potential, β represents the adjustable parameter corresponding to the contact duration, and γ represents the adjustable parameter corresponding to the transmission environment. α, β, and γ are obtained based on the hyperedges corresponding to the binary edges.

5. The infectious disease tracing method based on hypergraph structure according to claim 4 is characterized in that: After dynamically adjusting the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight, the method further includes: Determine the shortest propagation path weight d[v] between the propagation endpoint and node v, determine the shortest propagation path weight d[u] between the propagation endpoint and node u, and determine the updated weight W(u→v) of the binary edge between node u and node v; If the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v is less than the shortest propagation path weight d[v] between the propagation end point and the node v, then the shortest propagation path weight d[v] between the propagation end point and the node v is updated to the sum of the shortest propagation path weight d[u] between the propagation end point and the node u and the updated weight W(u→v) of the binary edge between the node u and the node v, and the predecessor node of the node v is determined to be the node u, and the node u is added to the priority queue.

6. The infectious disease tracing method based on hypergraph structure according to claim 5, characterized in that: The method further comprises: Calculating the time difference between the infection duration of each node in the priority queue and the infection duration of the propagation endpoint; For each node in the priority queue, determining an estimated value according to the time difference and a weight of the shortest propagation path between the propagation endpoint and the node; The shortest paths and predecessor nodes of the nodes in the priority queue are updated in the order of estimated values ​​from small to large.

7. The infectious disease tracing method based on hypergraph structure according to claim 6, characterized in that: Tracing the transmission endpoint of the infectious disease based on the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease includes: The target predecessor node of the transmission end point is obtained, and according to the target predecessor node, the path is gradually traced back from the predecessor node set and the shortest path set until the transmission source point of the infectious disease is obtained.

8. An infectious disease tracing device based on a hypergraph structure, characterized in that: include: A construction module is configured to construct an initial hypergraph according to the spreading individuals, the spreading media, and the spreading events related to the spreading individuals and the spreading media; A determination module is configured to obtain, for each hyperedge, a node set included in the hyperedge, determine binary edges between each node in the node set and other nodes, and obtain a binary edge set; wherein two nodes determine a binary edge; an updating module configured to dynamically adjust the binary edge weight of each binary edge in the binary edge set according to the infectious characteristics of the infectious disease to obtain an updated weight; a predecessor module configured to determine, from the binary edge set according to the updated weights, a set of shortest paths between nodes and a set of predecessor nodes corresponding to all nodes; The tracing module is configured to trace the transmission end point of the infectious disease according to the shortest path set and the predecessor node set to obtain the transmission source point of the infectious disease.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of infectious disease tracing based on a hypergraph structure as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of tracing the source of infectious diseases based on the hypergraph structure as described in any one of claims 1 to 8 are implemented.

Images