CN113889284A - A contact target tracking method for infectious diseases based on public transportation knowledge graph - Google Patents

A contact target tracking method for infectious diseases based on public transportation knowledge graph Download PDF

Info

Publication number
CN113889284A
CN113889284A CN202111086108.3A CN202111086108A CN113889284A CN 113889284 A CN113889284 A CN 113889284A CN 202111086108 A CN202111086108 A CN 202111086108A CN 113889284 A CN113889284 A CN 113889284A
Authority
CN
China
Prior art keywords
passengers
public transportation
knowledge graph
infectious disease
trip
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111086108.3A
Other languages
Chinese (zh)
Other versions
CN113889284B (en
Inventor
李健
陈�田
张懿木
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Priority to CN202111086108.3A priority Critical patent/CN113889284B/en
Publication of CN113889284A publication Critical patent/CN113889284A/en
Application granted granted Critical
Publication of CN113889284B publication Critical patent/CN113889284B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to an infectious disease contact target tracking method based on a public transport knowledge graph, which specifically comprises the following steps: s1, constructing a public transportation knowledge map based on a trip chain model by adopting a construction mode combining top-down and bottom-up; s2, obtaining travel data of a plurality of passengers, determining the travel sequence of the passengers according to the public transportation knowledge graph, and determining the type of infectious disease contact among the passengers; and S3, extracting the travel data of the infected persons in the travel data of the passengers, marking, selecting the infected persons with a preset proportion for tracking, and positioning the secondary infected individuals in the traffic system according to the contact type of the infectious diseases among the passengers. Compared with the prior art, the method has the advantages of reducing data redundancy, facilitating data expansion, improving the accuracy of judging the infectious disease contact target when a plurality of scene conversion and recursive query exist, realizing effective and rapid tracking in a large-scale contact network and the like.

Description

一种基于公共交通知识图谱的传染病接触目标追踪方法A contact target tracking method for infectious diseases based on public transportation knowledge graph

技术领域technical field

本发明涉及交通大数据挖掘与交通应急管理领域，尤其是涉及一种基于公共交通知识图谱的传染病接触目标追踪方法。The invention relates to the fields of traffic big data mining and traffic emergency management, in particular to a contact target tracking method for infectious diseases based on a public traffic knowledge map.

背景技术Background technique

公共交通工具和车站由于其相对封闭的空间和高客运量，成为病毒传播的关键模式。许多国家对公共交通实施各种控制措施，包括定期消毒、强制戴口罩、降低社交距离能力、改变运营时间表，甚至完全暂停服务。然而，相较于总体管控策略，及时发现和隔离感染个体的目标针对策略更加有效。而目前，如何从大规模非结构化出行数据中高效挖掘准确知识以缓解疾病方面仍然存在挑战。Public transport and stations are key modes of virus transmission due to their relatively enclosed spaces and high passenger traffic. Many countries have implemented various control measures on public transport, including regular disinfection, mandatory wearing of masks, reduced social distancing capabilities, changes to operating schedules, and even complete suspension of services. However, a targeted strategy to detect and isolate infected individuals in a timely manner is more effective than an overall control strategy. However, there are still challenges in how to efficiently mine accurate knowledge from large-scale unstructured travel data for disease mitigation.

在传染病学领域，通常采用人工接触者追踪，但对于大规模调查的应用手动跟踪效率低下，而具有固定路线和运行时间表的智能卡数据被认为有助于在公共交通系统中捕获接触者和追踪感染。以往研究通常使用关系数据库，但考虑到关系型数据库的数据结构，联系人存储在乘客对之间，因此不适用于直接表示实际的网络结构，并且可能导致在执行用于联系追踪的多个递归连接和查询时性能不佳。In the field of epidemiology, manual contact tracing is commonly employed, but is inefficient for applications in large-scale investigations, and smart card data with fixed routes and operating schedules is believed to be useful in capturing contacts and Track infection. Previous studies usually use relational databases, but considering the data structure of relational databases, contacts are stored between pairs of passengers, so it is not suitable for directly representing the actual network structure, and may lead to multiple recursion in performing contact tracing. Poor performance when connecting and querying.

知识图谱是近年来被广泛应用的技术，对高效构建高分辨率联系网络具有重要意义。知识图谱不同于传统的关系数据库，采用节点和边的形式存储数据，通常支持数百亿个节点和边的网络规模，能够直观地表示现实世界中的任何事物，并从理论上构建一个语义丰富的网络。Knowledge graph is a widely used technology in recent years, which is of great significance for efficiently constructing high-resolution contact networks. Different from traditional relational databases, knowledge graphs store data in the form of nodes and edges, usually supporting a network scale of tens of billions of nodes and edges, and can intuitively represent anything in the real world, and theoretically build a semantically rich network of.

发明内容SUMMARY OF THE INVENTION

本发明的目的就是为了克服上述现有技术存在的关系数据库在执行用于联系追踪的多个递归连接和查询时性能不佳的缺陷而提供一种基于公共交通知识图谱的传染病接触目标追踪方法。The purpose of the present invention is to provide a contact target tracing method for infectious diseases based on public transport knowledge graph in order to overcome the defect of poor performance of the relational database in the above-mentioned prior art when executing multiple recursive connections and queries for contact tracing. .

本发明的目的可以通过以下技术方案来实现：The object of the present invention can be realized through the following technical solutions:

一种基于公共交通知识图谱的传染病接触目标追踪方法，具体包括以下步骤：A contact target tracing method for infectious diseases based on public transportation knowledge graph, which specifically includes the following steps:

S1、采用自上而下与自下而上结合的构建方式，基于出行链模型构建公交知识图谱；S1. Using the combination of top-down and bottom-up construction methods, build a public transport knowledge map based on the travel chain model;

S2、获取多个乘客的出行数据，根据公交知识图谱确定乘客的出行顺序，并确定乘客之间的传染病接触类型；S2. Acquire the travel data of multiple passengers, determine the travel order of the passengers according to the bus knowledge map, and determine the type of infectious disease contact between the passengers;

S3、提取多个乘客的出行数据中感染者的出行数据，并进行标记，选取预设比例的感染者进行追踪，根据乘客之间的传染病接触类型，定位交通系统中的二次感染个体。S3. Extract travel data of infected persons from travel data of multiple passengers, mark them, select a preset proportion of infected persons for tracking, and locate secondary infected individuals in the transportation system according to the type of infectious disease contact between passengers.

所述公交知识图谱中将本体作为模式层，对应的数据映射为实体和关系。In the public transport knowledge graph, ontology is used as a schema layer, and corresponding data is mapped into entities and relationships.

进一步地，所述公交知识图谱从乘客的出行数据中提取实体和关系，并作为数据层导入图形数据库。Further, the public transport knowledge graph extracts entities and relationships from the travel data of passengers, and imports them into a graph database as a data layer.

所述步骤S1中构建公交知识图谱的过程还包括整合从智能卡、自动车辆定位(AVL)设备、班次记录以及公共汽车、快速公交(BRT)和地铁系统的路线单中收集的多源数据。The process of constructing the public transport knowledge graph in the step S1 also includes integrating multi-source data collected from smart cards, automatic vehicle location (AVL) equipment, shift records, and route lists for bus, bus rapid transit (BRT) and subway systems.

所述步骤S2中公交知识图谱简化为边图G＝(V，E)，对应的节点V1与节点Vn的连接路径如下所示：In the step S2, the public transportation knowledge graph is simplified as the edge graph G=(V, E), and the connection path between the corresponding node V 1 and the node V n is as follows:

Figure RE-GDA0003364593620000021
Figure RE-GDA0003364593620000021

节点V1与节点Vn之间的关系Ec如下所示：The relationship E c between node V 1 and node V n is as follows:

Figure RE-GDA0003364593620000022
Figure RE-GDA0003364593620000022

其中，E1、E2…En-1为公交知识图谱中的边，

Figure RE-GDA0003364593620000023
表示为组合运算符。Among them, E 1 , E 2 . . . E n-1 are the edges in the public transportation knowledge graph,
Figure RE-GDA0003364593620000023
Represented as a combinatorial operator.

进一步地，所述乘客的出行顺序中若出行三次，对应的表示关系如下所示：Further, if the passenger travels three times in the travel sequence, the corresponding representation relationship is as follows:

Figure RE-GDA0003364593620000024
Figure RE-GDA0003364593620000024

其中，Tp表示乘客p在一天内的一系列出行，

Figure RE-GDA0003364593620000025
表示乘客一天内的第nth次出行，ET表示下一个行程，ET＝1表示两次出行记录之间有换乘，ET＝0表示两次出行记录之间没有换乘。where T p represents a series of trips of passenger p in one day,
Figure RE-GDA0003364593620000025
Indicates the passenger's nth trip in a day, ET represents the next trip, ET = 1 indicates that there is a transfer between two travel records, and ET = 0 indicates that there is no transfer between the two travel records.

进一步地，所述乘客的出行顺序中第一次旅行

Figure RE-GDA0003364593620000026
和最后一次旅行
Figure RE-GDA0003364593620000027
的表示关系如下所示：Further, the first trip in the travel sequence of the passenger
Figure RE-GDA0003364593620000026
and the last trip
Figure RE-GDA0003364593620000027
The representation relationship is as follows:

Figure RE-GDA0003364593620000028
Figure RE-GDA0003364593620000028

Figure RE-GDA0003364593620000029
Figure RE-GDA0003364593620000029

其中，

Figure RE-GDA00033645936200000210
表示存在，
Figure RE-GDA00033645936200000211
表示不存在；in,
Figure RE-GDA00033645936200000210
means to exist,
Figure RE-GDA00033645936200000211
means that it does not exist;

对于连续出行链(即连续乘车)两端的行程，综合关系由上下文表示，具体如下所示：For trips at both ends of a continuous travel chain (i.e., continuous rides), the composite relationship is represented by the context as follows:

Figure RE-GDA0003364593620000031
Figure RE-GDA0003364593620000031

其中，transfer＝1表示乘客在行程中换乘一次。Among them, transfer=1 indicates that the passenger transfers once in the itinerary.

所述乘客之间的传染病接触类型包括直接接触和间接接触，具体关系如下所示：The contact types of infectious diseases between the passengers include direct contact and indirect contact, and the specific relationship is as follows:

Figure RE-GDA0003364593620000032
Figure RE-GDA0003364593620000032

其中，Vp1、Vp2和Vp3分别表示乘客p1、p2和p3所对应的节点，EDC表示直接接触，EIC表示间接接触。Among them, V p1 , V p2 and V p3 represent the nodes corresponding to passengers p1, p2 and p3, respectively, E DC represents direct contact, and E IC represents indirect contact.

进一步地，所述直接接触包括共同乘车和共同候车，表示关系如下：Further, the direct contact includes common riding and common waiting, and the relationship is as follows:

Figure RE-GDA0003364593620000033
Figure RE-GDA0003364593620000033

Figure RE-GDA0003364593620000034
Figure RE-GDA0003364593620000034

其中，EH表示有一次出行，

Figure RE-GDA0003364593620000035
表示乘客p的某一次出行，ER表示乘坐车辆的行为，EB表示在车站上车的行为，Vvehicle表示车辆场景，Vstation表示车站场景。Among them, E H represents a trip,
Figure RE-GDA0003364593620000035
Represents a certain trip of passenger p, ER represents the behavior of taking a vehicle, EB represents the behavior of getting on the bus at the station, V vehicle represents the vehicle scene, and V station represents the station scene.

进一步地，两名乘客乘坐同一辆公共交通工具定义为共同乘车，判定公式如下所示：Further, two passengers taking the same public transport vehicle is defined as a shared ride, and the determination formula is as follows:

Figure RE-GDA0003364593620000036
Figure RE-GDA0003364593620000036

其中，，j，k∈{1，2}，j≠k，ECR表示共同乘坐，

Figure RE-GDA0003364593620000037
表示乘客j该次出行的乘车时间，
Figure RE-GDA0003364593620000038
表示乘客k该次出行的下车时间；where , j, k∈{1, 2}, j≠k, E CR denotes shared ride,
Figure RE-GDA0003364593620000037
represents the travel time of passenger j for this trip,
Figure RE-GDA0003364593620000038
Indicates the alighting time of passenger k for this trip;

两名乘客在预设的候车时间间隔阈值内在同一车站上车，则定义为共同候车，判定公式如下所示：If two passengers get on the bus at the same station within the preset waiting time interval threshold, they are defined as waiting together. The determination formula is as follows:

Figure RE-GDA0003364593620000039
Figure RE-GDA0003364593620000039

其中，ECW表示共同候车，Tthreshold表示候车时间间隔阈值；Among them, E CW represents common waiting, and T threshold represents the waiting time interval threshold;

出行顺序中存在直接接触和间接接触的出行联系如下所示：Travel links with direct and indirect contact in the travel sequence are as follows:

Figure RE-GDA00033645936200000310
Figure RE-GDA00033645936200000310

其中，EA∈{ECR，ECW}，

Figure RE-GDA00033645936200000311
表示乘客p的第nth出行。where E A ∈ {E CR , E CW },
Figure RE-GDA00033645936200000311
represents the nth trip of passenger p.

所述步骤S3中将公交知识图谱中所有感染者所在的节点标记为“感染”，选择预设比例的感染者的节点作为索引病例，标记为“索引”，根据乘客之间的传染病接触类型进行追踪，若有其他乘客所在的节点被搜索到，则被标记为“选中”，同时也被标记为“发现”，其他节点被标记为“未选中”。In the step S3, the nodes where all infected persons are located in the public transport knowledge graph are marked as "infection", and the nodes with a preset proportion of infected persons are selected as index cases, marked as "index", according to the type of infectious disease contact between passengers. For tracking, if the node where other passengers are located is searched, it is marked as "selected", and also marked as "discovered", and other nodes are marked as "unselected".

与现有技术相比，本发明具有以下有益效果：Compared with the prior art, the present invention has the following beneficial effects:

本发明通过利用出行链模型，整合基于智能卡和公共交通系统的多源数据，基于公共交通图谱重建一个语义丰富的公共交通系统的接触网络，从构建的知识图中提取有针对性的简化联系网络，减少数据冗余，并有利于数据扩展，基于个体接触特征的感染风险预测模型来模拟接触网络中的疫情传播，基于已经检测到的病例有效定位交通系统中的二次感染个体，支持有效的疫情传播建模和有效的数字接触追踪，有效提高了存在多个场景转换和递归查询时判断传染病接触目标的准确性，在大规模联系网络中实现有效且快速的追踪。The invention integrates the multi-source data based on smart cards and public transportation systems by using the travel chain model, reconstructs a semantic-rich contact network of the public transportation system based on the public transportation map, and extracts a targeted simplified contact network from the constructed knowledge map. , reduce data redundancy, and facilitate data expansion. The infection risk prediction model based on individual contact characteristics simulates the spread of the epidemic in the contact network, effectively locates the secondary infected individuals in the transportation system based on the detected cases, and supports effective Epidemic spread modeling and effective digital contact tracing can effectively improve the accuracy of judging the contact target of infectious diseases when there are multiple scene transitions and recursive queries, and achieve effective and fast tracing in large-scale contact networks.

附图说明Description of drawings

图1为本发明的流程示意图；Fig. 1 is the schematic flow chart of the present invention;

图2为本发明实施例中数字接触追踪的示意图，其中图2(a)～图2(e)为从索引节点追踪感染者以及确定密切接触者的示意图。FIG. 2 is a schematic diagram of digital contact tracing in an embodiment of the present invention, wherein FIG. 2( a ) to FIG. 2 ( e ) are schematic diagrams of tracing infected persons from index nodes and determining close contacts.

具体实施方式Detailed ways

下面结合附图和具体实施例对本发明进行详细说明。本实施例以本发明技术方案为前提进行实施，给出了详细的实施方式和具体的操作过程，但本发明的保护范围不限于下述的实施例。The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and provides a detailed implementation manner and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

实施例Example

如图1所示，一种基于公共交通知识图谱的传染病接触目标追踪方法，具体包括以下步骤：As shown in Figure 1, an infectious disease contact target tracking method based on public transportation knowledge graph includes the following steps:

S1、采用自上而下与自下而上结合的构建方式，基于出行链模型构建公交知识图谱；S1. Using the combination of top-down and bottom-up construction methods, build a public transport knowledge map based on the travel chain model;

S2、获取多个乘客的出行数据，根据公交知识图谱确定乘客的出行顺序，并确定乘客之间的传染病接触类型；S2. Acquire the travel data of multiple passengers, determine the travel order of the passengers according to the bus knowledge map, and determine the type of infectious disease contact between the passengers;

S3、提取多个乘客的出行数据中感染者的出行数据，并进行标记，选取预设比例的感染者进行追踪，根据乘客之间的传染病接触类型，定位交通系统中的二次感染个体。S3. Extract travel data of infected persons from travel data of multiple passengers, mark them, select a preset proportion of infected persons for tracking, and locate secondary infected individuals in the transportation system according to the type of infectious disease contact between passengers.

公交知识图谱中将本体作为模式层，对应的数据映射为实体和关系。In the public transport knowledge graph, the ontology is used as a schema layer, and the corresponding data is mapped to entities and relationships.

公交知识图谱从乘客的出行数据中提取实体和关系，并作为数据层导入图形数据库。Transit Knowledge Graph extracts entities and relationships from passengers' travel data and imports them into a graph database as a data layer.

步骤S1中构建公交知识图谱的过程还包括整合从智能卡、自动车辆定位(AVL) 设备、班次记录以及公共汽车、快速公交(BRT)和地铁系统的路线单中收集的多源数据。The process of constructing the bus knowledge graph in step S1 also includes integrating multi-source data collected from smart cards, automatic vehicle location (AVL) devices, shift records, and route lists for bus, bus rapid transit (BRT), and subway systems.

步骤S2中公交知识图谱简化为边图G＝(V，E)，对应的节点V1与节点Vn的连接路径如下所示：In step S2, the public transportation knowledge graph is simplified to the edge graph G=(V, E), and the connection path between the corresponding node V 1 and the node V n is as follows:

Figure RE-GDA0003364593620000051
Figure RE-GDA0003364593620000051

节点V1与节点Vn之间的关系Ec如下所示：The relationship E c between node V 1 and node V n is as follows:

Figure RE-GDA0003364593620000052
Figure RE-GDA0003364593620000052

其中，E1、E2…En-1为公交知识图谱中的边，

Figure RE-GDA0003364593620000053
表示为组合运算符。Among them, E 1 , E 2 . . . E n-1 are the edges in the public transportation knowledge graph,
Figure RE-GDA0003364593620000053
Represented as a combinatorial operator.

乘客的出行顺序中若出行三次，对应的表示关系如下所示：If a passenger travels three times in the travel sequence, the corresponding representation relationship is as follows:

Figure RE-GDA0003364593620000054
Figure RE-GDA0003364593620000054

其中，Tp表示乘客p在一天内的一系列出行，

Figure RE-GDA0003364593620000055
表示乘客一天内的第nth次出行，ET表示下一个行程，ET＝1表示两次出行记录之间有换乘，ET＝0表示两次出行记录之间没有换乘。where T p represents a series of trips of passenger p in one day,
Figure RE-GDA0003364593620000055
Indicates the passenger's nth trip in a day, ET represents the next trip, ET = 1 indicates that there is a transfer between two travel records, and ET = 0 indicates that there is no transfer between the two travel records.

乘客的出行顺序中第一次旅行

Figure RE-GDA0003364593620000056
和最后一次旅行
Figure RE-GDA0003364593620000057
的表示关系如下所示：The first trip in the passenger's travel order
Figure RE-GDA0003364593620000056
and the last trip
Figure RE-GDA0003364593620000057
The representation relationship is as follows:

Figure RE-GDA0003364593620000058
Figure RE-GDA0003364593620000058

Figure RE-GDA0003364593620000059
Figure RE-GDA0003364593620000059

其中，

Figure RE-GDA00033645936200000510
表示存在，
Figure RE-GDA00033645936200000511
表示不存在；in,
Figure RE-GDA00033645936200000510
means to exist,
Figure RE-GDA00033645936200000511
means that it does not exist;

对于连续出行链(即连续乘车)两端的行程，综合关系由上下文表示，具体如下所示：For trips at both ends of a continuous travel chain (i.e., continuous rides), the composite relationship is represented by the context as follows:

Figure RE-GDA00033645936200000512
Figure RE-GDA00033645936200000512

其中，transfer＝1表示乘客在行程中换乘一次。Among them, transfer=1 indicates that the passenger transfers once in the itinerary.

乘客之间的传染病接触类型包括直接接触和间接接触，具体关系如下所示：The types of infectious disease contact between passengers include direct contact and indirect contact, and the specific relationship is as follows:

Figure RE-GDA00033645936200000513
Figure RE-GDA00033645936200000513

其中，Vp1、Vp2和Vp3分别表示乘客p1、p2和p3所对应的节点，EDC表示直接接触，EIC表示间接接触。Among them, V p1 , V p2 and V p3 represent the nodes corresponding to passengers p1, p2 and p3, respectively, E DC represents direct contact, and E IC represents indirect contact.

直接接触包括共同乘车和共同候车，表示关系如下：Direct contact includes shared rides and shared waiting, which means the relationship is as follows:

Figure RE-GDA00033645936200000514
Figure RE-GDA00033645936200000514

Figure RE-GDA00033645936200000515
Figure RE-GDA00033645936200000515

其中，EH表示有一次出行，

Figure RE-GDA0003364593620000061
表示乘客p的某一次出行，ER表示乘坐车辆的行为，EB表示在车站上车的行为，Vvehicle表示车辆场景，Vstation表示车站场景。Among them, E H represents a trip,
Figure RE-GDA0003364593620000061
Represents a certain trip of passenger p, ER represents the behavior of taking a vehicle, EB represents the behavior of getting on the bus at the station, V vehicle represents the vehicle scene, and V station represents the station scene.

两名乘客乘坐同一辆公共交通工具定义为共同乘车，判定公式如下所示：Two passengers taking the same public transport vehicle is defined as a shared ride, and the determination formula is as follows:

Figure RE-GDA0003364593620000062
Figure RE-GDA0003364593620000062

其中，，j，k∈{1，2}，j≠k，ECR表示共同乘坐，

Figure RE-GDA0003364593620000063
表示乘客j该次出行的乘车时间，
Figure RE-GDA0003364593620000064
表示乘客k该次出行的下车时间；where , j, k∈{1, 2}, j≠k, E CR denotes shared ride,
Figure RE-GDA0003364593620000063
represents the travel time of passenger j for this trip,
Figure RE-GDA0003364593620000064
Indicates the alighting time of passenger k for this trip;

两名乘客在预设的候车时间间隔阈值内在同一车站上车，则定义为共同候车，判定公式如下所示：If two passengers get on the bus at the same station within the preset waiting time interval threshold, they are defined as waiting together. The determination formula is as follows:

Figure RE-GDA0003364593620000065
Figure RE-GDA0003364593620000065

其中，ECW表示共同候车，Tthreshold表示候车时间间隔阈值；Among them, E CW represents common waiting, and T threshold represents the waiting time interval threshold;

出行顺序中存在直接接触和间接接触的出行联系如下所示：Travel links with direct and indirect contact in the travel sequence are as follows:

Figure RE-GDA0003364593620000066
Figure RE-GDA0003364593620000066

其中，EA∈{ECR，ECW}，

Figure RE-GDA0003364593620000067
表示乘客p的第nth出行。where E A ∈ {E CR , E CW },
Figure RE-GDA0003364593620000067
represents the nth trip of passenger p.

步骤S3中将公交知识图谱中所有感染者所在的节点标记为“感染”，选择预设比例的感染者的节点作为索引病例，标记为“索引”，根据乘客之间的传染病接触类型进行追踪，若有其他乘客所在的节点被搜索到，则被标记为“选中”，同时也被标记为“发现”，其他节点被标记为“未选中”。In step S3, the nodes where all infected persons are located in the bus knowledge graph are marked as "infected", and the nodes with a preset proportion of infected persons are selected as index cases, marked as "index", and traced according to the type of infectious disease contact between passengers , if the node where other passengers are located is searched, it is marked as "selected", and also marked as "discovered", and other nodes are marked as "unselected".

基于知识图谱的数字接触追踪算法：Digital Contact Tracing Algorithm Based on Knowledge Graph:

Figure RE-GDA0003364593620000068
Figure RE-GDA0003364593620000068

Figure RE-GDA0003364593620000071
Figure RE-GDA0003364593620000071

此外，需要说明的是，本说明书中所描述的具体实施例，所取名称可以不同，本说明书中所描述的以上内容仅仅是对本发明结构所做的举例说明。凡依据本发明构思的构造、特征及原理所做的等效变化或者简单变化，均包括于本发明的保护范围内。本发明所属技术领域的技术人员可以对所描述的具体实例做各种各样的修改或补充或采用类似的方法，只要不偏离本发明的结构或者超越本权利要求书所定义的范围，均应属于本发明的保护范围。In addition, it should be noted that the names of the specific embodiments described in this specification may be different, and the above content described in this specification is only an example to illustrate the structure of the present invention. All equivalent changes or simple changes made according to the structures, features and principles of the present invention are included in the protection scope of the present invention. Those skilled in the art to which the present invention pertains can make various modifications or additions to the specific examples described or adopt similar methods, as long as they do not deviate from the structure of the present invention or go beyond the scope defined by the claims, all It belongs to the protection scope of the present invention.

Claims (10)

1. An infectious disease contact target tracking method based on a public transport knowledge graph is characterized by comprising the following steps:
s1, constructing a public transportation knowledge map based on a trip chain model by adopting a construction mode combining top-down and bottom-up;
s2, obtaining travel data of a plurality of passengers, determining the travel sequence of the passengers according to the public transportation knowledge graph, and determining the type of infectious disease contact among the passengers;
and S3, extracting the travel data of the infected persons in the travel data of the passengers, marking, selecting the infected persons with a preset proportion for tracking, and positioning the secondary infected individuals in the traffic system according to the contact type of the infectious diseases among the passengers.
2. The method for tracking the infectious disease contact target based on the public transportation knowledge graph as claimed in claim 1, wherein the public transportation knowledge graph has an ontology as a model layer, and corresponding data are mapped into entities and relations.
3. The method for tracking the infectious disease contact target based on the public transportation knowledge graph as claimed in claim 2, wherein the public transportation knowledge graph extracts entities and relations from the travel data of passengers and imports the entities and relations into a graph database as a data layer.
4. The method for tracking the infectious disease contact target based on the public transportation knowledge graph as claimed in claim 1, wherein the public transportation knowledge graph is simplified to an edge graph G (V, E) in the step S2, and the corresponding node V is a node V1And node VnThe connection paths of (a) are as follows:
Figure FDA0003265801850000011
node V1And node VnRelation E betweencAs follows:
Figure FDA0003265801850000012
wherein E is1、E2…En-1Is an edge in the public transportation knowledge map,
Figure FDA0003265801850000015
represented as a combination operator.
5. The method for tracking the infectious disease contact target based on the public transportation knowledge graph according to claim 2, wherein if the passenger goes three times in the passenger's travel sequence, the corresponding expression relationship is as follows:
Figure FDA0003265801850000013
wherein, TpRepresenting a series of trips of passenger p during the day,
Figure FDA0003265801850000014
indicating the nth day of the passengerthSecond trip, ETIndicating the next trip, ET1 indicates a transfer between two travel records, ET0 means that there is no transfer between the two trip recordings.
6. The method for tracking the infectious disease contact target based on the public transportation knowledge graph of claim 5, wherein the passenger travels for the first time in the travel sequence
Figure FDA0003265801850000021
And last trip
Figure FDA0003265801850000022
The expression of (a) is as follows:
Figure FDA0003265801850000023
Figure FDA0003265801850000024
wherein,
Figure FDA0003265801850000025
indicating the presence of the substance,
Figure FDA0003265801850000026
indicates absence;
for trips at both ends of a continuous trip chain (i.e., continuous rides), the overall relationship is represented by context, as follows:
Figure FDA0003265801850000027
wherein transfer ═ 1 indicates that the passenger transfers once during the trip.
7. An infectious disease contact target tracking method based on public transportation knowledge graph according to claim 2, wherein the type of infectious disease contact between passengers comprises direct contact and indirect contact, and the specific relationship is as follows:
Figure FDA0003265801850000028
wherein, Vp1、Vp2And Vp3Respectively representing nodes, E, corresponding to passengers p1, p2 and p3DCDenotes direct contact, EICIndicating indirect contact.
8. The infectious disease contact target tracking method based on the public transportation knowledge graph according to claim 7, wherein the direct contact comprises a common bus taking and a common waiting, and the expression relationship is as follows:
Figure FDA0003265801850000029
Figure FDA00032658018500000210
wherein E isHIt is shown that there is one trip,
Figure FDA00032658018500000211
indicating a certain trip of passenger p, ERIndicating the behaviour of the ride vehicle, EBShows the behaviour of getting on the bus at the station, VvehicleRepresenting a vehicle scene, VstationRepresenting a station scene.
9. The method for tracking the infectious disease contact target based on the public transportation knowledge graph according to claim 8, wherein the determination formula of the shared bus is as follows:
Figure FDA00032658018500000212
where j, k is E {1,2}, j ≠ k, ECRA co-ride is shown as being provided,
Figure FDA00032658018500000213
representing the ride time of passenger j for that trip,
Figure FDA00032658018500000214
the getting-off time of the passenger on the trip is represented;
the common waiting judgment formula is as follows:
Figure FDA00032658018500000215
wherein E isCWIndicating a common waiting, TthresholdRepresenting a waiting interval threshold;
the trip relations in the trip sequence for the presence of direct contact and indirect contact are as follows:
Figure FDA0003265801850000031
wherein E isA∈{ECR,ECW},
Figure FDA0003265801850000032
N-th of passenger pthAnd (5) going out.
10. The method for tracking the infectious disease contact target based on the public transportation knowledge graph as claimed in claim 1, wherein in step S3, the nodes where all the infected persons are located in the public transportation knowledge graph are marked as "infected", the nodes of the infected persons with a preset proportion are selected as index cases and marked as "index", the tracking is performed according to the type of infectious disease contact among the passengers, if the nodes where other passengers are located are searched, the nodes are marked as "selected", and meanwhile, the nodes are marked as "found", and the nodes are marked as "unselected".
CN202111086108.3A 2021-09-16 2021-09-16 A contact target tracking method for infectious diseases based on public transportation knowledge graph Active CN113889284B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111086108.3A CN113889284B (en) 2021-09-16 2021-09-16 A contact target tracking method for infectious diseases based on public transportation knowledge graph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111086108.3A CN113889284B (en) 2021-09-16 2021-09-16 A contact target tracking method for infectious diseases based on public transportation knowledge graph

Publications (2)

Publication Number Publication Date
CN113889284A true CN113889284A (en) 2022-01-04
CN113889284B CN113889284B (en) 2022-07-05

Family

ID=79009682

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111086108.3A Active CN113889284B (en) 2021-09-16 2021-09-16 A contact target tracking method for infectious diseases based on public transportation knowledge graph

Country Status (1)

Country Link
CN (1) CN113889284B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117690600A (en) * 2024-02-01 2024-03-12 北方健康医疗大数据科技有限公司 Knowledge-graph-based infectious disease prediction method, system, terminal and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147419A (en) * 2019-04-25 2019-08-20 中国科学院深圳先进技术研究院 Infectious disease diffusion analysis method and system based on Metro Space
CN110400065A (en) * 2019-07-12 2019-11-01 北京交通大学 Construction method of risk chain group in rail transit system based on infectious disease model
CN111383771A (en) * 2020-02-26 2020-07-07 汤一平 Epidemic disease virus field-based prevention and control system
CN111428045A (en) * 2020-03-06 2020-07-17 北京明略软件系统有限公司 Method and device for constructing knowledge graph, computer storage medium and terminal
CN111446000A (en) * 2020-02-26 2020-07-24 汤一平 System for tracing infection source based on epidemic disease virus field
CN111524612A (en) * 2020-04-26 2020-08-11 腾讯科技（深圳）有限公司 Infectious disease tracing method and device, computer equipment and storage medium
CN111933299A (en) * 2020-08-14 2020-11-13 工银科技有限公司 Infectious disease infection risk assessment method and apparatus, electronic device, and storage medium
CN112511982A (en) * 2020-11-19 2021-03-16 同济大学 Subway passenger track real-time tracing and restoring method with automatic trip semantic annotation
CN112786210A (en) * 2021-01-15 2021-05-11 华南师范大学 Epidemic propagation tracking method and system
CN112883195A (en) * 2019-11-29 2021-06-01 中国科学技术大学 Method and system for constructing traffic knowledge map of individual trip
CN113241188A (en) * 2021-04-14 2021-08-10 大连理工大学 Cross-region transmission prediction method for new infectious disease under open system
CN113256987A (en) * 2021-06-30 2021-08-13 深圳市城市交通规划设计研究中心股份有限公司 Multi-source data fusion-based resident trip chain generation method and co-multiplication query method

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147419A (en) * 2019-04-25 2019-08-20 中国科学院深圳先进技术研究院 Infectious disease diffusion analysis method and system based on Metro Space
CN110400065A (en) * 2019-07-12 2019-11-01 北京交通大学 Construction method of risk chain group in rail transit system based on infectious disease model
CN112883195A (en) * 2019-11-29 2021-06-01 中国科学技术大学 Method and system for constructing traffic knowledge map of individual trip
CN111383771A (en) * 2020-02-26 2020-07-07 汤一平 Epidemic disease virus field-based prevention and control system
CN111446000A (en) * 2020-02-26 2020-07-24 汤一平 System for tracing infection source based on epidemic disease virus field
CN111428045A (en) * 2020-03-06 2020-07-17 北京明略软件系统有限公司 Method and device for constructing knowledge graph, computer storage medium and terminal
CN111524612A (en) * 2020-04-26 2020-08-11 腾讯科技（深圳）有限公司 Infectious disease tracing method and device, computer equipment and storage medium
CN111933299A (en) * 2020-08-14 2020-11-13 工银科技有限公司 Infectious disease infection risk assessment method and apparatus, electronic device, and storage medium
CN112511982A (en) * 2020-11-19 2021-03-16 同济大学 Subway passenger track real-time tracing and restoring method with automatic trip semantic annotation
CN112786210A (en) * 2021-01-15 2021-05-11 华南师范大学 Epidemic propagation tracking method and system
CN113241188A (en) * 2021-04-14 2021-08-10 大连理工大学 Cross-region transmission prediction method for new infectious disease under open system
CN113256987A (en) * 2021-06-30 2021-08-13 深圳市城市交通规划设计研究中心股份有限公司 Multi-source data fusion-based resident trip chain generation method and co-multiplication query method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117690600A (en) * 2024-02-01 2024-03-12 北方健康医疗大数据科技有限公司 Knowledge-graph-based infectious disease prediction method, system, terminal and storage medium
CN117690600B (en) * 2024-02-01 2024-04-30 北方健康医疗大数据科技有限公司 Knowledge-graph-based infectious disease prediction method, system, terminal and storage medium

Also Published As

Publication number Publication date
CN113889284B (en) 2022-07-05

Similar Documents

Publication Publication Date Title
CN100573506C (en) A kind of space-time fusion method of natural language expressing dynamic traffic information
Chen et al. A knowledge graph-based method for epidemic contact tracing in public transportation
CN110968617B (en) Road network key road section correlation analysis method based on position field
CN110753307B (en) Method for acquiring mobile phone signaling track data with label based on resident survey data
CN105243128A (en) Sign-in data based user behavior trajectory clustering method
Xu et al. Mobile cellular big data: Linking cyberspace and the physical world with social ecology
CN106649656A (en) Spatial-temporal trajectory big data storage method for database
CN113784292B (en) Urban epidemic situation risk assessment method based on mobile phone signaling data
CN114530038B (en) A method and system for extracting travel interest areas based on spatio-temporal data clustering
CN109002961A (en) Functional structure planing method between a kind of trans-regional cultural landscape based on network data
CN113889284B (en) A contact target tracking method for infectious diseases based on public transportation knowledge graph
CN110377680A (en) The method of mountain flood database sharing and update based on web crawlers and semantics recognition
CN107229682A (en) A kind of taxi position data processing method based on large database
CN116416478B (en) Bioinformatics classification model based on graph structure data characteristics
Goh et al. Twitter-informed crowd flow prediction
Ding et al. An Internet of Things based scalable framework for disaster data management
CN107798440A (en) A kind of subway based on circuit Candidate Set is plugged into bus layout of roads method
CN115862331A (en) Vehicle trajectory reconstruction method considering bayonet network topology
CN109146757B (en) A method and system for obtaining key passenger flow sections of rail transit
CN112883195B (en) Method and system for constructing traffic knowledge graph for individual travel
CN111626502A (en) Dynamic commuting path planning method for urban traffic network
CN107610031A (en) A kind of tourist communications associated region big data generation method
CN111678531A (en) Subway path planning method based on LightGBM
Beigi et al. Bike Share’s Impact on COVID-19 Transmission and Bike Share’s Responses to COVID-19: A case study of Washington DC
CN117194679A (en) Urban disaster event knowledge graph construction and representation methods, devices and storage media

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant