WO2023246797A1 - 流行病学调查中目标对象的识别方法、装置和计算机设备 - Google Patents

流行病学调查中目标对象的识别方法、装置和计算机设备 Download PDF

Info

Publication number
WO2023246797A1
WO2023246797A1 PCT/CN2023/101457 CN2023101457W WO2023246797A1 WO 2023246797 A1 WO2023246797 A1 WO 2023246797A1 CN 2023101457 W CN2023101457 W CN 2023101457W WO 2023246797 A1 WO2023246797 A1 WO 2023246797A1
Authority
WO
WIPO (PCT)
Prior art keywords
objects
contact
sub
data
information
Prior art date
Application number
PCT/CN2023/101457
Other languages
English (en)
French (fr)
Inventor
陈涛
吴东波
孙占辉
黄丽达
袁宏永
苏国锋
戴佳昆
Original Assignee
清华大学
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 清华大学 filed Critical 清华大学
Publication of WO2023246797A1 publication Critical patent/WO2023246797A1/zh

Links

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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present disclosure relates to the field of big data processing technology, and specifically to a method, device and computer equipment for identifying target objects in epidemiological surveys.
  • the present disclosure aims to solve one of the technical problems in the related art, at least to a certain extent.
  • the purpose of this disclosure is to propose a method, device, computer equipment and storage medium for identifying target objects in epidemiological investigations, which can achieve rapid determination of target objects during the epidemiological investigation process, thereby providing information for epidemic diseases.
  • Traceability provides a reliable reference object, which can effectively improve the execution efficiency of epidemic prevention and control while reducing labor costs.
  • the method for identifying target objects in epidemiological surveys proposed by the embodiment of the first aspect of the present disclosure includes: determining multiple objects to be processed by epidemiological investigation, wherein the multiple objects respectively have multiple corresponding object attribute data; determining contact relationship data between some of the objects; determining infection status information of each of the objects according to the plurality of object attribute data and the contact relationship data; and based on a plurality of the infection status information, from the plurality of infection status information Determine the target object among the objects.
  • the method for identifying target objects in epidemiological surveys proposed by the embodiment of the first aspect of the present disclosure determines a plurality of objects to be processed by epidemiology, wherein the plurality of objects respectively have corresponding plurality of object attribute data, and determines the number of objects among some of the objects. contact relationship data between multiple objects, determine the infection status information of each object based on multiple object attribute data and contact relationship data, and determine the target object from multiple objects based on multiple infection status information. From this, the epidemiology can be The target object can be quickly identified during the investigation process, thereby providing a reliable reference object for tracing the source of the epidemic, which can effectively improve the execution efficiency of epidemic prevention and control while reducing labor costs.
  • the device for identifying target objects in epidemiological surveys proposed by the embodiment of the second aspect of the present disclosure includes: a first determination module for determining multiple objects to be processed for epidemiological investigation, wherein each of the multiple objects has corresponding A plurality of object attribute data; a second determination module, used to determine the contact relationship data between some of the objects; a third determination module, used to determine each of the plurality of object attribute data and the contact relationship data. infection status information of the object; and a fourth determination module, configured to determine a target object from the plurality of objects according to a plurality of the infection status information.
  • the device for identifying target objects in epidemiological surveys determines a plurality of objects to be processed for epidemiological investigation, wherein the plurality of objects respectively have corresponding plurality of object attribute data, and determines among some objects. contact relationship data between multiple objects, determine the infection status information of each object based on multiple object attribute data and contact relationship data, and determine the target object from multiple objects based on multiple infection status information. From this, the epidemiology can be The target object can be quickly identified during the investigation process, thereby providing a reliable reference object for tracing the source of the epidemic, which can effectively improve the execution efficiency of epidemic prevention and control while reducing labor costs.
  • the computer device proposed in the third aspect of the present disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the program, it implements the first aspect of the present disclosure.
  • the embodiment proposes a method for identifying target objects in epidemiological surveys.
  • the fourth embodiment of the present disclosure provides a non-transitory computer-readable storage medium on which a computer program is stored.
  • the epidemiological investigation as proposed in the first embodiment of the present disclosure is implemented.
  • Target object recognition method
  • the fifth embodiment of the present disclosure provides a computer program product.
  • instructions in the computer program product are executed by a processor, the identification of target objects in epidemiological surveys as proposed by the first embodiment of the present disclosure is performed. method.
  • the sixth embodiment of the present disclosure provides a computer program that, when the computer program code is run on a computer, causes the computer to perform the identification method of target objects in epidemiological surveys as proposed by the first embodiment of the present disclosure.
  • Figure 1 is a schematic flow chart of a method for identifying target objects in epidemiological surveys proposed by an embodiment of the present disclosure
  • Figure 2 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure
  • Figure 3 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure
  • Figure 4 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure
  • Figure 5 is a schematic structural diagram of a device for identifying target objects in epidemiological surveys proposed by an embodiment of the present disclosure
  • Figure 6 is a schematic structural diagram of a device for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure
  • FIG. 7 illustrates a block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure.
  • Figure 1 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by an embodiment of the present disclosure.
  • the execution subject of the method for identifying target objects in epidemiological surveys in this embodiment is a device for identifying target objects in epidemiological surveys.
  • This device can be implemented by software and/or hardware.
  • the device can be configured in computer equipment to plan Computer equipment may include but is not limited to terminals, servers, etc.
  • the terminal may be a mobile phone, a handheld computer, etc.
  • the identification method of target objects in this epidemiological investigation includes: S101-S104.
  • S101 Determine multiple objects to be processed by flow adjustment, where the multiple objects respectively have multiple corresponding object attribute data.
  • epidemic investigation which can also be called epidemiological investigation, refers to investigation activities carried out for an epidemic and can be used to determine the transmission chain and contacts of the epidemic.
  • the object may refer to a user who is at risk of epidemic infection.
  • the object attribute data can refer to the object's corresponding personal number, age, gender, disease status, contact category, influenza status, earliest symptom onset time, positive specimen detection time and other related data.
  • the incubation time corresponding to the epidemic and the diagnosis time corresponding to the patient can be determined, and then the corresponding itinerary information of the patient is determined based on the above incubation time and diagnosis time, and combined with The itinerary information determines multiple objects to be processed by the epidemic investigation.
  • the contact information between the objects can be obtained in advance, and then combined with the corresponding contact information of the epidemic patients to determine the multiple objects to be processed by the epidemic investigation. This is not done limit.
  • the number of people in the epidemic spreading place may be large, but the available epidemic prevention and control resources are limited.
  • the scope of the epidemic control processing can be effectively narrowed and the epidemic control resources can be improved. Convective treatment efficiency.
  • contact relationship data refers to relevant data describing contact information between objects, such as: number corresponding to the contact relationship, contact time information, contact type information, etc.
  • related information such as contact time and contact type between multiple objects may be determined based on multiple object attribute data, and the contact relationship between the objects may be determined. Numbering is performed to generate corresponding contact relationship data, or multiple trip information corresponding to each object can be obtained in advance, and then the multiple trip information can be matched to determine the contact relationship data between some objects. Make restrictions.
  • the infection status information of the epidemic has a high degree of correlation with the contact relationship data between objects (such as contact time and contact type), therefore, when determining the contact relationship data between some objects, It can provide a reliable analysis basis for subsequent determination of the infection status information of each object.
  • S103 Determine the infection status information of each object based on multiple object attribute data and contact relationship data.
  • the infection status information can be used to describe relevant information about the infection status of each object, such as the infection time, contact relationship, etc. of each object.
  • an infection status information table may be generated based on the object attribute data and contact relationship data, and then the infection status information table may be determined based on the infection status information table. Infection status information for each object.
  • third-party infection status information may also be used to process the multiple object attribute data and contact relationship data to determine each object's infection status information. Information about the infection status of the object.
  • any other possible method can be used to determine the infection status information of each object based on multiple object attribute data and contact relationship data, and there is no limit to this.
  • S104 Determine the target object from multiple objects based on multiple infection status information.
  • the target object may refer to the first infected person of the epidemic among multiple objects.
  • the multiple infection status information may be input into a pre-trained machine learning model to determine the target from multiple objects.
  • Object or you can also pre-configure the corresponding reference infection status information of the target object, and then determine the similarity between multiple infection status information and the reference infection status information, and determine the target object from multiple objects based on the obtained similarity. No restrictions.
  • the contact relationship data between some objects is determined, and based on the multiple object attribute data and contact relationship data, determine the infection status information of each object, and determine the target object from multiple objects based on multiple infection status information, thus enabling the rapid determination of the target object during the epidemiological investigation process, thereby providing a basis for the epidemic Traceability provides a reliable reference object, which can effectively improve the execution efficiency of epidemic prevention and control while reducing labor costs.
  • Figure 2 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure.
  • the identification methods of target objects in this epidemiological survey include: S201-S209.
  • S201 Determine multiple objects to be processed by flow adjustment, where the multiple objects respectively have multiple corresponding object attribute data.
  • S203 Construct a social contact network model based on multiple object attribute data and contact relationship data.
  • the social contact network model includes: multiple nodes, at least some of which have contact edges between them.
  • the nodes describe the object attribute data, and the contact edges describe the contacts. relational data.
  • the social contact network model may refer to a real contact network generated based on multiple object attribute data and contact relationship data, and may be used to describe contact information between multiple objects as well as the attributes of each object itself. information.
  • the contact edge E i,j (i,j), E i,j ⁇ G.
  • the contact information between multiple objects may be complex.
  • a social contact network model is constructed based on multiple object attribute data and contact relationship data, the resulting social contact network model can clearly and accurately represent the relationships between each object.
  • the contact relationship between each object can provide reliable reference information for the determination process of the target risk value of each object.
  • S204 Determine the infection status information of each object based on the social contact network model.
  • the social contact network model can be a real contact network, and the social contact network model can effectively map the individuals and contact relationships involved in the epidemic spread process to simulate the spread of the epidemic in social groups.
  • the embodiment of the present disclosure can construct a social contact network model based on multiple object attribute data and contact relationship data, where the social contact network model includes: multiple nodes , there are contact edges between at least some nodes.
  • the nodes describe object attribute data
  • the contact edges describe contact relationship data.
  • each pair is determined Because the contact relationships between multiple objects may be complex, when building a social contact network model based on multiple object attribute data and contact relationship data, it can provide clear reference information for the infection status information determination process. This ensures the reliability of the infection status information obtained.
  • S205 Determine multiple spatiotemporal trajectory data corresponding to multiple objects in the social contact network model.
  • the spatiotemporal trajectory data refers to the travel trajectory data of the object within a set time range.
  • P m ⁇ ID i ,p x, p y ,t start ,t end >, which means that the coordinates of the trajectory point of the node with ID number i between time (t start ,t end ) are (p x ,py y ), p
  • the epidemic has been spreading for a period of time before the epidemic is processed.
  • the multiple spatio-temporal trajectory data corresponding to multiple objects in the social contact network model it is possible to determine the number of multiple objects in the future. Provide reliable analysis basis for potential contact relationships between them.
  • S206 Determine potential contact relationships between multiple objects based on multiple spatiotemporal trajectory data.
  • the potential contact relationship refers to the contact relationship between multiple objects determined based on multiple spatiotemporal trajectory data.
  • the multiple spatio-temporal trajectory data when determining potential contact relationships between multiple objects based on multiple spatio-temporal trajectory data, can be input into a pre-trained potential contact relationship determination model to determine multiple objects.
  • potential contact relationships between multiple objects, or a digital-shape combination method can be used to generate corresponding trajectory maps based on multiple spatio-temporal trajectory data, and the potential contact relationships between multiple objects can be determined based on the trajectory maps. There is no limit to this. .
  • a trajectory point-based judgment algorithm can be used, or a trajectory segment-based judgment algorithm can be used.
  • the judgment algorithm based on trajectory points can be divided into a global matching similarity measurement method and a local matching similarity measurement method.
  • Global matching similarity measurement methods can be Dynamic Time Warping (DTW), Euclidean distance method (Euclidean), etc.
  • local matching similarity measurement methods include Longest Common Subsequence (LCSS) , Fréchet distance method (Fréchet distance), etc.
  • the trajectory points on the two trajectories need to be globally matched.
  • DTW dynamic time warping algorithm
  • This algorithm can dynamically copy a certain point on the trajectory to achieve a "one-to-many" matching method.
  • the trajectory R has m trajectory points (r 1 ,..., ri ,...,r m ,i ⁇ m)
  • the trajectory Q has n trajectory points (q 1 ,...,q i ,...,q n ,i ⁇ n)
  • the calculation formula for calculating trajectory similarity using DTW can be:
  • This solution stretches the trajectory points along the time dimension to realize the similarity judgment of trajectories with different sampling frequencies and number of trajectory points.
  • partial trajectory points on the two trajectories can be matched.
  • LCSS longest common subsequence
  • the calculation formula for calculating trajectory similarity using the LCSS algorithm can be:
  • the social contact network model simulates the authenticity of epidemic transmission characteristics in application scenarios.
  • the embodiment of the present disclosure can determine multiple spatio-temporal trajectory data corresponding to multiple objects in the social contact network model, and determine the distance between multiple objects based on the multiple spatio-temporal trajectory data. potential contact relationships. Based on the potential contact relationships, the existing contact edges in the social contact network model are expanded. This can effectively improve the integrity of the contact edges in the resulting social contact network model and make the social contact network model adaptable. Based on personalized application scenarios, it can effectively improve the accuracy of the social contact network model in characterizing epidemic transmission characteristics.
  • S208 Determine multiple subnetworks in the social contact network model, where objects within the subnetworks are connected via one or more contact edges, and there are no contact edges between different subnetworks.
  • subnetwork refers to a collection of multiple independent objects in the social contact network model.
  • S209 Determine the target object from the subnetwork based on multiple infection status information.
  • the confidence information of multiple objects in the sub-network may be determined based on the multiple infection status information, and then based on the obtained confidence information, the target object is determined from the sub-network.
  • the target object is determined from the sub-network, or a third-party target object determination device can also process multiple infection status information and determine the target object from the sub-network, without limitation.
  • the embodiments of the present disclosure can determine multiple subnetworks in the social contact network model, where the objects in the subnetworks They are connected through one or more contact edges. There are no contact edges between different sub-networks. According to multiple infection status information, the target objects are determined from the sub-networks, thus achieving parallel processing of target objects in multiple sub-networks. , so as to be suitable for multi-threaded application scenarios and effectively improve the practicality of the obtained target objects.
  • a social contact network model is constructed based on multiple object attribute data and contact relationship data.
  • the social contact network model includes: multiple nodes, at least some of the nodes have contact edges between them, and the nodes describe the object attribute data.
  • contact edge description Contact relationship data based on the social contact network model, determines the infection status information of each object. Since the contact relationship between multiple objects may be more complex, when building a social contact network model based on multiple object attribute data and contact relationship data, you can Provide clear reference information for the infection status information determination process, thereby ensuring the reliability of the infection status information obtained.
  • the contact network model By determining multiple spatio-temporal trajectory data corresponding to multiple objects in the social contact network model, based on the multiple spatio-temporal trajectory data, determine Potential contact relationships between multiple objects. Based on the potential contact relationships, the existing contact edges in the social contact network model are expanded and processed. This can effectively improve the integrity of the contact edges in the resulting social contact network model and make the society
  • the contact network model is adapted to personalized application scenarios, thereby effectively improving the accuracy of the social contact network model in characterizing epidemic transmission characteristics.
  • By determining multiple sub-networks in the social contact network model among which, between objects within the sub-network They are connected through one or more contact edges. There are no contact edges between different sub-networks. According to multiple infection status information, the target objects are determined from the sub-networks. Therefore, parallel processing of multiple sub-network target objects can be achieved. It is suitable for multi-threaded application scenarios and effectively improves the practicality of the obtained target objects.
  • Figure 3 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure.
  • the identification method of target objects in this epidemiological survey includes: S301-S310.
  • S301 Determine multiple objects to be processed by the flow adjustment, where the multiple objects respectively have multiple corresponding object attribute data.
  • S303 Construct a social contact network model based on multiple object attribute data and contact relationship data.
  • the social contact network model includes: multiple nodes, at least some of which have contact edges between them.
  • the nodes describe the object attribute data, and the contact edges describe the contacts. relational data.
  • S304 Determine the infection status information of each object according to the social contact network model.
  • the propagation characteristics may refer to the relevant characteristics corresponding to the epidemic propagation process.
  • the preset propagation characteristics are propagation characteristics preconfigured based on the epidemic propagation characteristics according to the embodiment of the present disclosure. For example, they may be the survival time of the epidemic propagation factor in the environment, the propagation mode of the epidemic propagation factor, etc.
  • the transmission characteristics corresponding to different epidemics may be different.
  • reliable reference information can be provided for subsequent acquisition of spatiotemporal trajectory data.
  • epidemic-infected persons may have an incubation period before onset of illness. During the incubation period, epidemic-infected persons may have the ability to spread the epidemic but not have symptoms.
  • the social contact network model with multiple Multiple spatio-temporal trajectory data corresponding to each object can achieve effective flow control processing of multiple objects.
  • the embodiment of the present disclosure can determine the preset propagation characteristics, and obtain the information corresponding to multiple objects in the social contact network model based on the preset propagation characteristics.
  • Multiple spatio-temporal trajectory data thus, the corresponding spatio-temporal trajectory data can be effectively combined with the preset propagation characteristics to flexibly obtain the corresponding spatio-temporal trajectory data, thereby effectively improving the adaptability between spatio-temporal trajectory data and epidemic propagation characteristics, and ensuring that multiple spatio-temporal trajectory data are obtained of practicality.
  • matching information may refer to similarity information between multiple spatiotemporal trajectory data.
  • the multiple spatio-temporal trajectory data when determining the matching information between multiple spatio-temporal trajectory data, may be input into a pre-trained matching information generation model to determine the matching between the multiple spatio-temporal trajectory data. information, or it can also be based on multiple time and space
  • the trajectory data generates multiple spatio-temporal trajectory maps, and then the multiple spatio-temporal trajectory maps are compared to determine the matching information between the multiple spatio-temporal trajectory data. There is no limit to this.
  • multiple trajectory stretching data respectively corresponding to the multiple spatio-temporal trajectory data may be obtained according to the preset propagation characteristics, and based on the preset propagation characteristics and Multiple trajectory stretching data determines the matching information between multiple spatiotemporal trajectory data. Therefore, the stretching processing of spatiotemporal trajectory data can be realized based on the preset propagation characteristics, thereby effectively improving the accuracy of the obtained trajectory stretching data for the corresponding object trajectory. Point representation effect, and then preset propagation characteristics and multiple trajectory stretching data to determine the matching information between multiple spatiotemporal trajectory data, which can effectively improve the accuracy of the obtained matching information.
  • the trajectory stretching data may refer to data obtained by stretching the spatiotemporal trajectory data.
  • the contact relationship information between objects has a high degree of correlation with the corresponding multiple spatio-temporal trajectory data.
  • the matching information between multiple spatio-temporal trajectory data is determined, it can be used to subsequently determine the relationship between multiple objects. provide a reliable reference for potential contact relationships.
  • S308 Determine potential contact relationships between multiple objects based on the matching information.
  • the matching information when determining the potential contact relationship between multiple objects based on the matching information, the matching information may be input into a pre-trained machine learning model to determine the potential contact relationship between the multiple objects, Alternatively, the correlation degree information between multiple objects can also be determined based on the matching information, and then the potential contact relationship between the multiple objects can be determined based on the correlation degree information, without limitation.
  • potential contact relationships include: direct contact relationships, indirect contact relationships, and no-contact relationships.
  • some objects may be determined based on matching information.
  • a first probability value indicating that there is a direct contact relationship between some objects. Based on the first probability value, it is determined whether there is a direct contact relationship between some objects. Therefore, the obtained first probability value can quantify the possibility of a direct contact relationship between some objects. , thereby providing clear judgment criteria for the determination process of direct contact relationships to improve the rationality of the determination process of direct contact relationships.
  • direct contact relationship refers to the contact relationship between the subject and suspected cases, confirmed cases and asymptomatic infected persons, and the corresponding subjects can be called close contacts.
  • indirect contact relationship means that the subject has a contact relationship with the above-mentioned close contacts, and the corresponding subject can be called a secondary close contact.
  • the first probability value can be used to describe the possibility of a direct contact relationship between some objects.
  • the second probability value of the contact relationship is based on the second probability value to determine whether there is an indirect contact relationship between some objects. Therefore, when there is no direct contact relationship between some objects, the relationship between some objects can be quantified based on the second probability value. The probability of whether there is an indirect contact relationship between multiple objects ensures the potential Comprehensiveness of the contact relationship determination process.
  • the second probability value can be used to describe the possibility of whether there is an indirect contact relationship between some objects.
  • the first probability value F(R,Q) can be used to determine the possibility of direct contact between node q and node r.
  • the calculation formula of F(R,Q) can be:
  • F(R s ,Q) can be used to judge the possibility of indirect contact between node q and node r.
  • the calculation formula of F(R s ,Q) can be:
  • T(q j ) start represents the starting time of node q reaching the original trajectory point
  • T(r js ) start represents the starting time of node r’s stretched trajectory point (ri ,s ,ri ,y )
  • the interval between the sick node r leaving (x, y) and the node q visiting (x, y) can be calculated by T(q j ) start -T(r js ) start .
  • the embodiment of the present disclosure can determine the matching information between the multiple spatio-temporal trajectory data.
  • Matching information determines the potential contact relationship between multiple objects. Therefore, the matching information can effectively represent the degree of similarity between multiple spatio-temporal trajectory data. Based on the matching information, it is possible to accurately determine the potential contact relationship between multiple objects. Determination, thereby effectively improving the reliability of the obtained potential contact relationships.
  • a contact relationship inference algorithm can be used to determine whether all isolated nodes in the social contact network model have undiscovered potential contact relationships with other nodes.
  • the main data structure types of the contact relationship inference algorithm include lists and values.
  • the list type data structure includes:
  • Orphan node list (orphanNodeList): Contains all orphan nodes.
  • Infected node list (infectedNodeList): Contains all infected nodes.
  • OrphanNodeTrajectoryList Contains the trajectory information of all orphan nodes.
  • Infected node trajectory list (infectedNodeTrajectoryList): Contains the trajectory information of all infected nodes.
  • the data structure of the data type includes:
  • Contact Factor that is, F (R, Q), based on this value, the corresponding contact relationship is established.
  • the main process of the contact relationship reasoning algorithm can include: traversing the isolated node and all other diseased nodes, calculating the corresponding contact factor according to the trajectories of the isolated node and the diseased node in each cycle, and judging the contact type of the two nodes (direct contact, indirect contact or no contact), supplementing the contact relationships that do not exist in the social contact network model.
  • the method for judging the contact form in this algorithm is: 1) Direct contact: If the original trajectory point of the isolated node o is equal to the original trajectory point of the diseased node i, and there is an overlapping relationship in the time dimension, then the two nodes are considered to be in contact.
  • any original trajectory point of the isolated node o does not coincide with all the original trajectory points and stretched trajectory points of the diseased node i, it means that there is no potential contact relationship between o and i, and the social contact network model G will not be processed. .
  • S310 Determine the target object from multiple objects based on multiple infection status information.
  • the potential contact relationship between multiple objects is determined based on the matching information. Therefore, the matching information can effectively represent the similarity between multiple spatio-temporal trajectory data. Degree, based on the matching information, the accurate determination of potential contact relationships between multiple objects is achieved, thereby effectively improving the reliability of the obtained potential contact relationships.
  • the social contact network model is obtained based on the preset propagation characteristics. Multiple spatio-temporal trajectory data corresponding to multiple objects respectively, thus, the corresponding spatio-temporal trajectory data can be effectively combined with the preset propagation characteristics to flexibly obtain, thereby effectively improving the adaptability between spatio-temporal trajectory data and epidemic propagation characteristics.
  • multiple trajectory stretching data corresponding to the multiple spatio-temporal trajectory data are obtained according to the preset propagation characteristics, and multiple trajectory stretching data are determined based on the preset propagation characteristics and multiple trajectory stretching data.
  • the matching information between the spatio-temporal trajectory data thus, the stretching processing of the spatio-temporal trajectory data can be realized based on the preset propagation characteristics, thereby effectively improving the representation effect of the obtained trajectory stretching data on the corresponding object trajectory points, and then the preset propagation Features and multiple trajectory stretching data determine the matching information between multiple spatio-temporal trajectory data, which can effectively improve the accuracy of the obtained matching information.
  • the obtained first probability value can quantify the possibility of a direct contact relationship between some objects, thereby providing a clear process for determining the direct contact relationship.
  • Determination criteria in order to improve the rationality of the direct contact relationship determination process, by determining the second probability value that there is an indirect contact relationship between some objects based on matching information when there is no direct contact relationship between some objects, based on the second probability value to determine whether there is an indirect contact relationship between some objects. Therefore, when there is no direct contact relationship between some objects, the probability of whether there is an indirect contact relationship between some objects can be quantified based on the second probability value, ensuring that multiple Potential contact relationships between objects determine the comprehensiveness of the process.
  • Figure 4 is a schematic flowchart of a method for identifying target objects in epidemiological surveys proposed by another embodiment of the present disclosure.
  • the identification method of target objects in this epidemiological investigation includes: S401-S408.
  • S401 Determine multiple objects to be processed by the flow adjustment, where the multiple objects respectively have multiple corresponding object attribute data.
  • S403 Determine the infection status information of each object based on multiple object attribute data and contact relationship data.
  • S404 Determine multiple subnetworks in the social contact network model, where objects within the subnetworks are connected via one or more contact edges, and there are no contact edges between different subnetworks.
  • S405 Determine reference objects in the subnetwork based on multiple infection status information.
  • the reference object may refer to the object in the sub-network that first exhibits epidemic symptoms.
  • the corresponding epidemic inspection information of multiple objects in the sub-network may be determined based on the multiple infection status information, and then based on Epidemic inspection information determination sub-network Reference object, or you can also determine the symptom level information of multiple objects in the sub-network based on multiple infection status information, and then determine the reference object in the sub-network based on the symptom level information. There is no limit to this.
  • the corresponding infection time information of multiple objects in the sub-network may be determined based on the multiple infection status information, and based on the infection time information , determine the reference object in the sub-network. Since the infection time information has a high degree of correlation with the epidemic source tracing process, when the reference object in the sub-network is determined based on the infection time information, the difference between the reference object and the first case can be effectively reduced. The number of contact edges between objects to quickly determine the target object based on the reference object.
  • the infection time information may refer to the time when epidemic symptoms of the corresponding subject appear, the time corresponding to when the epidemic test result is positive, etc., and there is no limit to this.
  • S406 Determine adjacent objects of the reference object.
  • adjacent objects may refer to objects connected to the reference object by a contact edge, and the number of adjacent objects may be one or more.
  • feature information can be used to describe the relevant features of adjacent objects, such as the contact time between the adjacent object and the reference object, the onset time of epidemic symptoms of the adjacent object, etc., and there is no limit to this.
  • the characteristic information of adjacent objects when determining the characteristic information of adjacent objects, it may be determined that the adjacent objects have the first characteristics based on the adjacent objects satisfying the first set condition, and based on the second set condition being satisfied by the adjacent objects, then It is determined that the adjacent object has the second feature, and feature information is generated based on the first feature and the second feature. Therefore, multi-dimensional relevant information can be effectively combined to determine the relevant features of the adjacent object, thus enriching the content to a greater extent.
  • the representation content of the obtained feature information when determining the characteristic information of adjacent objects, it may be determined that the adjacent objects have the first characteristics based on the adjacent objects satisfying the first set condition, and based on the second set condition being satisfied by the adjacent objects, then It is determined that the adjacent object has the second feature, and feature information is generated based on the first feature and the second feature. Therefore, multi-dimensional relevant information can be effectively combined to determine the relevant features of the adjacent object, thus enriching the content to a greater extent.
  • the representation content of the obtained feature information when determining the characteristic information of adjacent
  • the first set condition may refer to a condition configured in advance for the adjacent object, and may be used to determine whether the adjacent object possesses the first characteristic.
  • the second setting condition can be used to determine whether the adjacent object has the second characteristic.
  • the first characteristic may refer to the possibility that a neighboring object has a candidate first case of infection.
  • the second feature may refer to the possibility that the contact relationship between the reference object and the adjacent object causes the onset of the candidate first case.
  • the relational expression corresponding to the first set condition is: T1-T2 ⁇ 14 days, where T1 refers to the starting time of the onset of epidemic symptoms in the adjacent object, and T2 refers to the contact time between the reference object and the adjacent object. time, and 14 days refers to the incubation period corresponding to the epidemic.
  • T1 refers to the starting time of the onset of epidemic symptoms in the adjacent object
  • T2 refers to the contact time between the reference object and the adjacent object.
  • time, and 14 days refers to the incubation period corresponding to the epidemic.
  • the relational expression corresponding to the second setting condition is: T2-T3 ⁇ 14 days, where T3 refers to the start time of the reference object showing epidemic symptoms.
  • S408 Determine the target object in the sub-network based on the feature information.
  • the corresponding set characteristic information of the target object when determining the target object in the sub-network based on the characteristic information, can be configured in advance, and then the characteristic information and the set characteristic information are analyzed and compared to determine the sub-network
  • the target object in the sub-network, or multiple feature information can be analyzed and compared, and the target object in the sub-network can be determined based on the comparison results. There is no limit to this.
  • the third set condition when determining the target object in the sub-network based on the characteristic information, the third set condition may be satisfied based on the characteristic information, and then a to-be-processed list is generated based on the adjacent objects, and multiple objects in the to-be-processed list are obtained.
  • the contact time information of the target object is determined based on the contact time information. Therefore, when the characteristic information meets the third set condition, the corresponding adjacent object may be the source of infection of the reference object, and the contact time information is consistent with the infection process of the reference object. With a high degree of correlation, when the target object is determined based on contact time information, it can To effectively improve the reliability of the target object determination process.
  • the to-be-processed list refers to an object list generated based on adjacent objects.
  • the third set condition may refer to a condition configured in advance for the feature information.
  • the feature information may include both the first feature and the second feature.
  • the contact time information may refer to information related to the contact time between the object and the reference object.
  • the embodiment of the present disclosure can determine the reference objects in the sub-networks, determine the adjacent objects of the reference objects, and determine the adjacent objects based on multiple infection status information Based on the characteristic information, the target object in the sub-network is determined. Therefore, the reference object in the sub-network with a small number of contact edges with the first case can be determined based on multiple infection status information, and then the reference object is combined with The relevant information of adjacent objects can accurately and quickly determine the target object.
  • the current adjacent node may be the infection source of the reference object, and it can be used as an infection source candidate for the test object. All adjacent objects of the candidate object are judged, and all possible sources of infection are obtained and stored in a to-be-processed list.
  • the nodes in the to-be-processed list may be the parent nodes that cause the reference object to become ill. Then the to-be-processed list is traversed, and the object with the earliest contact time with the reference object is determined as the source of infection. On this basis, the entire sub-network is traversed.
  • the infection source of the reference object cannot be obtained anymore, the current reference object can be used as the source of the current sub-network. target.
  • the reference object in the sub-network by determining the reference object in the sub-network based on multiple infection status information, determining the adjacent objects of the reference object, determining the characteristic information of the adjacent objects, and determining the target object in the sub-network based on the characteristic information,
  • the reference object with a small number of contact edges with the first case in the sub-network can be determined based on multiple infection status information, and then the target object can be accurately and quickly determined by combining the relevant information of the reference object and adjacent objects.
  • the number of contact edges between the reference object and the first case can be effectively reduced to quickly determine the target object based on the reference object.
  • characteristic information is generated, whereby , can effectively combine multi-dimensional relevant information to determine the relevant features of adjacent objects, thus greatly enriching the representation content of the obtained feature information.
  • the feature information meets the third setting condition, based on the adjacent objects, Generate a to-be-processed list, obtain the contact time information of multiple objects in the to-be-processed list, and determine the target object based on the contact time information. Therefore, when the feature information satisfies the third set condition, the corresponding adjacent object may be the reference object.
  • the source of infection, and the contact time information has a high degree of correlation with the infection process of the reference object.
  • the target object is determined based on the contact time information, the reliability of the target object determination process can be effectively improved.
  • Figure 5 is a schematic structural diagram of a device for identifying target objects in epidemiological surveys proposed by an embodiment of the present disclosure.
  • the target object identification device 50 in the epidemiological survey includes:
  • the first determination module 501 is used to determine multiple objects to be processed by flow adjustment, wherein the multiple objects respectively have multiple corresponding object attribute data;
  • the second determination module 502 is used to determine the contact relationship data between some objects
  • the third determination module 503 is used to determine the infection status information of each object based on multiple object attribute data and contact relationship data;
  • the fourth determination module 504 is used to determine the target object from multiple objects according to the multiple infection status information.
  • the third determination module 503 includes:
  • Generating sub-module 5031 used to construct a social contact network model based on multiple object attribute data and contact relationship data, where the social contact network model includes: multiple nodes, at least some of the nodes have contact edges, and the nodes describe the object attribute data , the contact edge describes the contact relationship data;
  • the first determination sub-module 5032 is used to determine the infection status information of each object according to the social contact network model.
  • the third determination module 503 further includes:
  • the second determination sub-module 5033 is used to determine multiple spatio-temporal trajectory data corresponding to multiple objects in the social contact network model
  • the third determination sub-module 5034 is used to determine potential contact relationships between multiple objects based on multiple spatiotemporal trajectory data
  • the processing sub-module 5035 is used to extend processing of existing contact edges in the social contact network model based on potential contact relationships.
  • the third determination sub-module 5034 is specifically used for:
  • the second determination sub-module 5033 is specifically used for:
  • multiple spatio-temporal trajectory data corresponding to multiple objects in the social contact network model are obtained.
  • the third determination sub-module 5034 is also used to:
  • the matching information between multiple spatiotemporal trajectory data is determined.
  • potential contact relationships include: direct contact relationships, indirect contact relationships, and no contact relationships;
  • the third determination sub-module 5034 is also used for:
  • the third determination sub-module 5034 is also used to:
  • the fourth determination module 504 includes:
  • the fourth determination sub-module 5041 is used to determine multiple sub-networks in the social contact network model, where objects within the sub-networks are connected through one or more contact edges, and there are no contact edges between different sub-networks;
  • the fifth determination sub-module 5042 is used to determine the target object from the sub-network based on multiple infection status information.
  • the fifth determination sub-module 5042 is specifically used for:
  • the target object in the sub-network is determined.
  • the fifth determination sub-module 5042 is also used to:
  • reference objects in the subnetwork are determined.
  • the fifth determination sub-module 5042 is also used for;
  • Feature information is generated based on the first feature and the second feature.
  • the fifth determination sub-module 5042 is also used to:
  • a to-be-processed list is generated based on adjacent objects
  • the contact relationship data between some objects is determined, and based on the multiple object attribute data and contact Relational data, determine the infection status information of each object, and determine the target object from multiple objects based on multiple infection status information, thus enabling rapid determination of the target object during the epidemiological investigation process, thus providing a basis for the epidemic Disease source tracing provides a reliable reference object, which can effectively improve the execution efficiency of epidemic prevention and control while reducing labor costs.
  • FIG. 7 illustrates a block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure.
  • the computer device 12 shown in FIG. 7 is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present disclosure.
  • computer device 12 is embodied in the form of a general purpose computing device.
  • the components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting various system components, including system memory 28 and processing unit 16.
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics accelerated port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to Industry Standard Architecture (hereinafter referred to as: ISA) bus, Micro Channel Architecture (Micro Channel Architecture; hereafter referred to as: MAC) bus, enhanced ISA bus, video electronics Standards Association (Video Electronics Standards Association; hereinafter referred to as: VESA) local bus and Peripheral Component Interconnection (hereinafter referred to as: PCI) bus.
  • ISA Industry Standard Architecture
  • MAC Micro Channel Architecture
  • VESA Video Electronics Standards Association
  • PCI Peripheral Component Interconnection
  • Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and nonvolatile media, removable and non-removable media.
  • the memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory; hereinafter referred to as: RAM) 30 and/or cache memory 32.
  • Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media.
  • storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in Figure 7, commonly referred to as a "hard drive").
  • a disk drive for reading and writing to a removable non-volatile disk may be provided, and For removable non-volatile optical discs (such as Compact Disc Read Only Memory; CD-ROM), Digital Video Disc Read Only Memory; DVD-ROM ) or other optical media) that reads and writes optical disc drives.
  • each drive may be connected to bus 18 through one or more data media interfaces.
  • Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of embodiments of the present disclosure.
  • a program/utility 40 having a set of (at least one) program modules 42 may be stored, for example, in memory 28 , each of these examples or some combination may include the implementation of a network environment.
  • Program modules 42 generally perform functions and/or methods in the embodiments described in this disclosure.
  • Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable human interaction with computer device 12, and/or with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. This communication may occur through input/output (I/O) interface 22.
  • the computer device 12 can also communicate with one or more networks (such as a local area network (Local Area Network; hereinafter referred to as: LAN), a wide area network (Wide Area Network; hereinafter referred to as: WAN)) and/or a public network, such as the Internet, through the network adapter 20 ) communication.
  • networks such as a local area network (Local Area Network; hereinafter referred to as: LAN), a wide area network (Wide Area Network; hereinafter referred to as: WAN)
  • a public network such as the Internet
  • network adapter 20 communicates with other modules of computer device 12 via bus 18 .
  • bus 18 It should be understood that, although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.
  • the processing unit 16 executes various functional applications and identification of target objects in epidemiological surveys by running programs stored in the system memory 28, for example, implementing the method for identifying target objects in epidemiological surveys mentioned in the previous embodiments. .
  • the present disclosure also proposes a non-transitory computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the objectives of the epidemiological investigation as proposed in the previous embodiments of the present disclosure are achieved.
  • Object identification methods are achieved.
  • the present disclosure also proposes a computer program product.
  • the instruction processor in the computer program product is executed, the method for identifying target objects in epidemiological surveys as proposed in the previous embodiments of the present disclosure is executed.
  • the present disclosure also proposes a computer program.
  • the computer program code When the computer program code is run on a computer, it causes the computer to perform the identification method of target objects in epidemiological surveys as proposed in the previous embodiments of the present disclosure.
  • the collection, storage, use, processing, transmission, provision and disclosure of user personal information are in compliance with relevant laws and regulations and do not violate public order and good customs.
  • various parts of the present disclosure may be implemented in hardware, software, firmware, or combinations thereof.
  • various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a logic gate circuit with a logic gate circuit for implementing a logic function on a data signal.
  • Discrete logic circuits application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.
  • each functional unit in various embodiments of the present disclosure may be integrated into one processing module, each unit may exist physically alone, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or software function modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
  • the storage media mentioned above can be read-only memory, magnetic disks or optical disks, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Pathology (AREA)
  • Computing Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

提出一种流行病学调查中目标对象的识别方法、装置和计算机设备，该方法包括：确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据，确定部分对象之间的接触关系数据，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，以及根据多个感染状态信息，从多个对象中确定目标对象。

Description

流行病学调查中目标对象的识别方法、装置和计算机设备
相关申请的交叉引用
本申请基于申请号为2022107109940、申请日为2022年6月22日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及大数据处理技术领域，具体涉及一种流行病学调查中目标对象的识别方法、装置和计算机设备。
背景技术
在流行病防控工作过程中，通常需要对现有流行病患者的传播链进行溯源处理，确定流行病感染源，以针对感染源进行相应的防控工作。
相关技术中，在确定流行病感染源时，可能会受到流行病学特征和流行病传播网络的影响，导致对首例病例的推断准确性较低。
发明内容
本公开旨在至少在一定程度上解决相关技术中的技术问题之一。
为此，本公开的目的在于提出一种流行病学调查中目标对象的识别方法、装置、计算机设备和存储介质，可以在流行病学调查过程中实现对目标对象的快速确定，从而为流行病溯源提供可靠的参考对象，能够在降低人力成本的同时，有效提升流行病防控工作的执行效率。
本公开第一方面实施例提出的流行病学调查中目标对象的识别方法，包括：确定待流调处理的多个对象，其中，所述多个对象分别具有对应的多个对象属性数据；确定部分所述对象之间的接触关系数据；根据所述多个对象属性数据和所述接触关系数据，确定各个所述对象的感染状态信息；和根据多个所述感染状态信息，从所述多个对象中确定目标对象。
本公开第一方面实施例提出的流行病学调查中目标对象的识别方法，通过确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据，确定部分对象之间的接触关系数据，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，以及根据多个感染状态信息，从多个对象中确定目标对象，由此，可以在流行病学调查过程中实现对目标对象的快速确定，从而为流行病溯源提供可靠的参考对象，能够在降低人力成本的同时，有效提升流行病防控工作的执行效率。
本公开第二方面实施例提出的流行病学调查中目标对象的识别装置，包括：第一确定模块，用于确定待流调处理的多个对象，其中，所述多个对象分别具有对应的多个对象属性数据；第二确定模块，用于确定部分所述对象之间的接触关系数据；第三确定模块，用于根据所述多个对象属性数据和所述接触关系数据，确定各个所述对象的感染状态信息；以及第四确定模块，用于根据多个所述感染状态信息，从所述多个对象中确定目标对象。
本公开第二方面实施例提出的流行病学调查中目标对象的识别装置，通过确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据，确定部分对象之间的接触关系数据，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，以及根据多个感染状态信息，从多个对象中确定目标对象，由此，可以在流行病学调查过程中实现对目标对象的快速确定，从而为流行病溯源提供可靠的参考对象，能够在降低人力成本的同时，有效提升流行病防控工作的执行效率。
本公开第三方面实施例提出的计算机设备，包括：存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如本公开第一方面实施例提出的流行病学调查中目标对象的识别方法。
本公开第四方面实施例提出了一种非临时性计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本公开第一方面实施例提出的流行病学调查中目标对象的识别方法。
本公开第五方面实施例提出了一种计算机程序产品，当所述计算机程序产品中的指令由处理器执行时，执行如本公开第一方面实施例提出的流行病学调查中目标对象的识别方法。
本公开第六方面实施例提出了一种计算机程序，当所述计算机程序代码在计算机上运行时，使得计算机执行如本公开第一方面实施例提出的流行病学调查中目标对象的识别方法。
本公开附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本公开的实践了解到。
附图说明
本公开上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1是本公开一实施例提出的流行病学调查中目标对象的识别方法的流程示意图；
图2是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图；
图3是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图；
图4是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图；
图5是本公开一实施例提出的流行病学调查中目标对象的识别装置的结构示意图；
图6是本公开另一实施例提出的流行病学调查中目标对象的识别装置的结构示意图；
图7示出了适于用来实现本公开实施方式的示例性计算机设备的框图。
具体实施方式
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本公开，而不能理解为对本公开的限制。相反，本公开的实施例包括落入所附加权利要求书的精神和内涵范围内的所有变化、修改和等同物。
图1是本公开一实施例提出的流行病学调查中目标对象的识别方法的流程示意图。
其中，需要说明的是，本实施例的流行病学调查中目标对象的识别方法的执行主体为流行病学调查中目标对象的识别装置，该装置可以由软件和/或硬件的方式实现，该装置可以配置在计算机设备中，计 算机设备可以包括但不限于终端、服务器端等，如终端可为手机、掌上电脑等。
如图1所示，该流行病学调查中目标对象的识别方法，包括：S101-S104。
S101：确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据。
本公开实施例中，流调，也可以称为流行病学调查，是指针对某流行病所展开的调查活动，可以被用于确定流行病的传播链和接触者。
本公开实施例中，对象，可以是指存在流行病感染风险的用户。而对象属性数据，可以是指对象相应的个人编号、年龄、性别、患病情况、接触类别、流调状态、最早出现症状时间、阳性标本检出时间等相关数据。
本公开实施例在确定待流调处理的多个对象时，可以是确定流行病对应的潜伏时间和患者对应的确诊时间，而后结合上述潜伏时间和确诊时间，确定患者对应的行程信息，并结合该行程信息确定待流调处理的多个对象，或者，也可以预先获取对象之间的接触信息，而后结合流行病患者对应的接触信息，确定待流调处理的多个对象，对此不做限制。
本公开实施例中，流行病传播地的人员数量可能较多，而可供调用的流行病防控资源有限，当确定待流调处理的多个对象时，可以有效缩小流调处理范围，提升对流调处理效率。
S102：确定部分对象之间的接触关系数据。
本公开实施例中，接触关系数据，是指描述对象之间接触信息的相关数据，例如：接触关系对应的编号、接触时间信息、接触类型信息等。
本公开实施例中，在确定部分对象之间的接触关系数据时，可以是基于多个对象属性数据确定多个对象之间的接触时间、接触类型等相关信息，并对对象之间的接触关系进行编号，以生成对应的接触关系数据，或者，还可以预先获取各个对象相应的多个行程信息，而后对多个行程信息进行匹配处理，以确定部分对象之间的接触关系数据，对此不做限制。
本公开实施例中，由于流行病的感染状态信息与对象之间的接触关系数据(如接触时间和接触类型)具有较高的关联程度，由此，当确定部分对象之间的接触关系数据，可以为后续确定各个对象的感染状态信息提供可靠的分析依据。
S103：根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息。
本公开实施例中，感染状态信息，可以被用于描述各个对象感染状态的相关信息，例如可以是各个对象的感染时间、接触关系等。
一些实施例中，在根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息时，可以是基于对象属性数据和接触关系数据生成感染状态信息表，而后基于该感染状态信息表确定各个对象的感染状态信息。
另一些实施例中，在根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息时，还可以是采用第三方感染状态信息处理多个对象属性数据和接触关系数据，以确定各个对象的感染状态信息。
当然，一些实施例中，还可以采用其他任意可能的方法，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，对此不做限制。
S104：根据多个感染状态信息，从多个对象中确定目标对象。
本公开实施例中，目标对象，可以是指多个对象中的流行病首例感染者。
本公开实施例中，在根据多个感染状态信息，从多个对象中确定目标对象时，可以是将多个感染状态信息输入至预训练的机器学习模型中，以从多个对象中确定目标对象，或者，还可以预先配置目标对象相应的参考感染状态信息，而后确定多个感染状态信息与参考感染状态信息之间的相似度，根据所得相似度从多个对象中确定目标对象，对此不做限制。
本实施例中，通过确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据，确定部分对象之间的接触关系数据，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，以及根据多个感染状态信息，从多个对象中确定目标对象，由此，可以在流行病学调查过程中实现对目标对象的快速确定，从而为流行病溯源提供可靠的参考对象，能够在降低人力成本的同时，有效提升流行病防控工作的执行效率。
图2是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图。
如图2所示，该流行病学调查中目标对象的识别方法，包括：S201-S209。
S201：确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据。
S202：确定部分对象之间的接触关系数据。
S201和S202的描述说明可以具体参见上述实施例，在此不再赘述。
S203：根据多个对象属性数据和接触关系数据，构建社会接触网络模型，其中，社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，节点描述对象属性数据，接触边描述接触关系数据。
本公开实施例中，社会接触网络模型，可以是指基于多个对象属性数据和接触关系数据所生成的真实接触网络，可以被用于描述多个对象之间的接触信息以及各个对象自身的属性信息。
举例而言，社会接触网络可以用一组节点和接触边的集合表示，记为G＝(V,E)。其中，节点集V＝{1,2,...,N}表示处于流行病传播事件中的N个对象，对于两个不同的节点i,j∈G，当节点i和j之间具有接触关系时建立接触边Ei,j＝(i,j)，Ei,j∈G。
当然，社会接触网络G还可以使用邻接矩阵A表示：A＝(ai,j)N×N，其中，在ai与aj存在接触关系时，ai,j＝1，而在ai与aj不存在接触关系时，ai,j＝0，而接触边Ei,j是节点i和节点j之间存在接触关系的证明。
假设节点i和节点j之前存在m次时间长短不同的接触，每次接触都具有最早接触时间和最晚接触时间(两时间可以相等)，则他们之间第x次接触可以通过接触关系Ei,j的接触时间和接触类型属性表示为“接触类型x:[最早接触时间x，最晚接触时间x](其中x≤m)”。
可以理解的是，多个对象之间的接触信息可能较为复杂，当根据多个对象属性数据和接触关系数据，构建社会接触网络模型时，所得社会接触网络模型可以清晰、准确地表征各个对象之间的接触关系，从而为各个对象的目标风险值确定过程提供可靠的参考信息。
S204：根据社会接触网络模型，确定各个对象的感染状态信息。
可以理解的是，社会接触网络模型可以是真实接触网络，该社会接触网络模型可以有效映射流行病传播过程中所涉及的个体和接触关系，以模拟流行病在社会群体中的传播情况。
也即是说，本公开实施例在确定部分对象之间的接触关系数据之后，可以根据多个对象属性数据和接触关系数据，构建社会接触网络模型，其中，社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，节点描述对象属性数据，接触边描述接触关系数据，根据社会接触网络模型，确定各个对 象的感染状态信息，由于多个对象之间的接触关系可能较为复杂，当根据多个对象属性数据和接触关系数据构建社会接触网络模型时，可以为感染状态信息确定过程提供清晰的参考信息，从而保证所得感染状态信息的可靠性。
S205：确定社会接触网络模型中与多个对象分别对应的多个时空轨迹数据。
本公开实施例中，时空轨迹数据，是指对象在设定时间范围内的行程轨迹数据。
举例而言，社会接触网络模型中N个节点的时空轨迹数据组成的集合TR＝{TR1,TR2,…,TRN}，其中TRi(1≤i≤N)表示节点i对应的轨迹数据。假设节点i的轨迹信息由K个轨迹点组成，则TRi又可以表示为TRi＝{P1,P2,…,PK}，其中Pm(1≤m≤K)表示节点i的一个轨迹点，假设流调报告中对某一个体的轨迹信息记录为“个体i在tstart时刻到达地点Z，并于tend时刻离开”，则该轨迹信息可以表示为轨迹点Pm＝<IDi,px,py,tstart,tend>，意为ID编号为i的节点在时间(tstart,tend)之间所处轨迹点的坐标为(px,py)，px表示地点Z的经度，py表示地点Z的纬度。
可以理解的是，在进行流调处理之前，流行病较大概率已传播一段时间，通过确定社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，可以为后续确定多个对象之间的潜在接触关系提供可靠的分析依据。
S206：根据多个时空轨迹数据，确定多个对象之间的潜在接触关系。
本公开实施例中，潜在接触关系，是指基于多个时空轨迹数据所确定的多个对象之间的接触关系。
本公开实施例中，在根据多个时空轨迹数据，确定多个对象之间的潜在接触关系时，可以将多个时空轨迹数据输入至预训练的潜在接触关系确定模型中，以确定多个对象之间的潜在接触关系，或者，还可以采用数形结合的方法，基于多个时空轨迹数据生成对应的轨迹图，并根据轨迹图确定多个对象之间的潜在接触关系，对此不做限制。
举例而言，在根据多个时空轨迹数据，确定多个对象之间的潜在接触关系时，可以采用基于轨迹点的判断算法，也可以是采用基于轨迹段的判断算法。
本公开实施例中，基于轨迹点的判断算法可以分为全局匹配相似性度量方法和局部匹配相似性度量方法。全局匹配相似性度量方法可以是动态时间弯曲算法(Dynamic Time Warping，DTW)、欧氏距离法(Euclid)等，而局部匹配相似性度量方法有最长公共子序列算法(Longest Common Subsequence，LCSS)、弗雷歇距离方法(Fréchet distance)等。
对于全局匹配相似性度量方法，两条轨迹上的轨迹点需要全局匹配。以动态时间弯曲算法(DTW)为例，该算法可以动态地将轨迹上的某一点进行复制以实现“一对多”的匹配方式。假设轨迹R有m个轨迹点(r1,…,ri,…,rm,i≤m)，轨迹Q有n个轨迹点(q1,…,qi,…,qn,i≤n)，则使用DTW计算轨迹相似性的计算公式可以是：
该方案沿时间维对轨迹点进行拉伸的方式实现了对具有不同采样频率和轨迹点数量的轨迹相似性判断。
对于局部匹配相似性度量方法，可以是两条轨迹上的部分轨迹点匹配即可。以最长公共子序列(LCSS)算法为例，它可以忽略匹配程度超过一定阈值的轨迹点，只将两轨迹上的相似部分作为相似性度量内容。使用LCSS算法计算轨迹相似性的计算公式可以是：
对于上述两轨迹R和Q，其对应轨迹点ri和qi在x和y方向上距离分别小于等于阈值δ和ε时，则认为两轨迹点相似，即存在潜在接触关系。
可以理解的是，患病节点离开某环境后，其他到访该环境的个体仍然存在被环境中流行病传播因子感染的风险，并由此产生对象之间的接触关系数据，本公开实施例基于多个时空轨迹数据，可以实现对多个对象之间潜在接触关系的快速确定。
S207：基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理。
可以理解的是，社会接触网络模型与应用场景中的流行病传播信息可能存在差异，当基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理时，可以有效提升社会接触网络模型对应用场景中流行病传播特征的模拟真实性。
也即是说，本公开实施例在构建社会接触网络模型之后，可以确定社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，根据多个时空轨迹数据，确定多个对象之间的潜在接触关系，基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理，由此，可以有效提升所得社会接触网络模型中接触边的完整性，使社会接触网络模型适配于个性化的应用场景，从而有效提升社会接触网络模型对流行病传播特征的表征准确性。
S208：确定社会接触网络模型中的多个子网络，其中，子网络内的对象之间经由一个或多个接触边相连，不同子网络之间不存在接触边。
本公开实施例中，子网络，是指社会接触网络模型中的多个相互独立的对象集合。
可以理解的是，在社会接触网络模型中，可能同时存在多条流行病传播链，当确定社会接触网络模型中的多个子网络，可以后续目标对象的确定过程提供可靠的分析对象。
S209：根据多个感染状态信息，从子网络中确定目标对象。
本公开实施例中，在根据多个感染状态信息，从子网络中确定目标对象时，可以是根据多个感染状态信息确定子网络中多个对象的置信度信息，而后根据所得置信度信息从子网络中确定目标对象，或者，还可以由第三方目标对象确定装置处理多个感染状态信息，从子网络中确定目标对象，对此不做限制。
也即是说，本公开实施例在基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理之后，可以确定社会接触网络模型中的多个子网络，其中，子网络内的对象之间经由一个或多个接触边相连，不同子网络之间不存在接触边，根据多个感染状态信息，从子网络中确定目标对象，由此，可以实现对多个子网络目标对象的并行处理，以适用于多线程的应用场景，有效提升所得目标对象的实用性。
本公开实施例中，通过根据多个对象属性数据和接触关系数据，构建社会接触网络模型，其中，社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，节点描述对象属性数据，接触边描述 接触关系数据，根据社会接触网络模型，确定各个对象的感染状态信息，由于多个对象之间的接触关系可能较为复杂，当根据多个对象属性数据和接触关系数据构建社会接触网络模型时，可以为感染状态信息确定过程提供清晰的参考信息，从而保证所得感染状态信息的可靠性，通过确定社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，根据多个时空轨迹数据，确定多个对象之间的潜在接触关系，基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理，由此，可以有效提升所得社会接触网络模型中接触边的完整性，使社会接触网络模型适配于个性化的应用场景，从而有效提升社会接触网络模型对流行病传播特征的表征准确性，通过确定社会接触网络模型中的多个子网络，其中，子网络内的对象之间经由一个或多个接触边相连，不同子网络之间不存在接触边，根据多个感染状态信息，从子网络中确定目标对象，由此，可以实现对多个子网络目标对象的并行处理，以适用于多线程的应用场景，有效提升所得目标对象的实用性。
图3是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图。
如图3所示，该流行病学调查中目标对象的识别方法，包括：S301-S310。
S301：确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据。
S302：确定部分对象之间的接触关系数据。
S303：根据多个对象属性数据和接触关系数据，构建社会接触网络模型，其中，社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，节点描述对象属性数据，接触边描述接触关系数据。
S304：根据社会接触网络模型，确定各个对象的感染状态信息。
S301-S304的描述说明可以具体参见上述实施例，在此不再赘述。
S305：确定预设传播特征。
本公开实施例中，传播特征，可以是指流行病传播过程对应的相关特征。而预设传播特征，则是本公开实施例基于流行病传播特征所预先配置的传播特征，例如可以是流行病传播因子在环境中的存活时间、流行病传播因子传播方式等。
可以理解的是，不同流行病对应的传播特征可能存在差异，当确定预设传播特征，可以为后续获取时空轨迹数据提供可靠的参考信息。
S306：根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据。
可以理解的是，流行病感染者在发病之前可能存在潜伏期，处于潜伏期内流行病感染者可能存在流行病传播能力而不存在发病症状，当根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，可以实现对多个对象的有效流调处理。
也即是说，本公开实施例在根据社会接触网络模型，确定各个对象的感染状态信息之后，可以确定预设传播特征，根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，由此，可以有效结合预设传播特征灵活获取对应的时空轨迹数据，从而有效提升时空轨迹数据与流行病传播特征之间的适配性，保证所得多个时空轨迹数据的实用性。
S307：确定多个时空轨迹数据之间的匹配信息。
本公开实施例中，匹配信息，可以是指多个时空轨迹数据之间的相似度信息。
本公开实施例中，在确定多个时空轨迹数据之间的匹配信息时，可以是将多个时空轨迹数据输入至预训练的匹配信息生成模型中，以确定多个时空轨迹数据之间的匹配信息，或者，还可以基于多个时空 轨迹数据生成多个时空轨迹图，而后将多个时空轨迹图进行对比处理，以确定多个时空轨迹数据之间的匹配信息，对此不做限制。
一些实施例中，在确定多个时空轨迹数据之间的匹配信息时，可以是根据预设传播特征，获取与多个时空轨迹数据分别对应的多个轨迹拉伸数据，根据预设传播特征和多个轨迹拉伸数据，确定多个时空轨迹数据之间的匹配信息，由此，可以基于预设传播特征实现对时空轨迹数据的拉伸处理，从而有效提升所得轨迹拉伸数据对相应对象轨迹点的表征效果，而后预设传播特征和多个轨迹拉伸数据确定多个时空轨迹数据之间的匹配信息，可以有效提升所得匹配信息的准确性。
本公开实施例中，轨迹拉伸数据，可以是指时空轨迹数据经由拉伸处理所得到的数据。
举例而言，可以采用DTW的方法获取与多个时空轨迹数据分别对应的多个轨迹拉伸数据：假设节点r为患病节点，具备传播病毒的能力，则其k个轨迹点组成的原始轨迹表示为R＝{r1,r2,…,rk}，其中ri＝<IDR,ri,x,ri,y,ti,start,ti,end>(1≤i≤k)。对原始轨迹沿时间维进行拉伸后轨迹信息表示为Rs＝{r1s,r2s,…,rks}，其中ris(1≤i≤k)由轨迹点ri拉伸所得，表示为ris＝<IDR,ri,x,ri,y,ti,end,ti,end+7d>(1≤i≤k)，代表地点(ri,x,ri,y)由于患病节点r的到访，可能在(ti,end,ti,end+7d)内导致其他到访节点感染。此时对于患病节点r而言，其原始轨迹为R，拉伸所得轨迹为Rs。以此类推，对于接触网络中任一节点n，都有对应的原始轨迹N与拉伸轨迹Ns。
可以理解的是，对象之间的接触关系信息与对应多个时空轨迹数据之间具有较高的关联程度，当确定多个时空轨迹数据之间的匹配信息，可以为后续确定多个对象之间的潜在接触关系提供可靠的参考依据。
S308：根据匹配信息，确定多个对象之间的潜在接触关系。
本公开实施例中，在根据匹配信息，确定多个对象之间的潜在接触关系时，可以是将匹配信息输入至预训练的机器学习模型中，以确定多个对象之间的潜在接触关系，或者，还可以根据匹配信息确定多个对象之间的关联程度信息，而后根据关联程度信息确定多个对象之间的潜在接触关系，对此不做限制。
一些实施例中，潜在接触关系，包括：直接接触关系、间接接触关系，以及无接触关系，在根据匹配信息，确定多个对象之间的潜在接触关系时，可以是基于匹配信息，确定部分对象之间存在直接接触关系的第一概率值，基于第一概率值，判断部分对象之间是否存在直接接触关系，由此，所得第一概率值可以量化部分对象之间存在直接接触关系的可能性，从而为直接接触关系的判定过程提供清晰的判定标准，以提升直接接触关系判定过程的合理性。
本公开实施例中，直接接触关系，是指对象与疑似病例、确诊病例和无症状感染者存在接触关系，相应对象可以称为密切接触者。
本公开实施例中，间接接触关系，是指对象与上述密切接触者存在接触关系，相应对象可以称为次级密切接触者。
本公开实施例中，第一概率值，可以被用于描述部分对象之间存在直接接触关系的可能性。
一些实施例中，在基于第一概率值，判断部分对象之间是否存在直接接触关系之后，在部分对象之间不存在直接接触关系的情况下，则基于匹配信息，确定部分对象之间存在间接接触关系的第二概率值，基于第二概率值，判断部分对象之间是否存在间接接触关系，由此，可以在部分对象之间不存在直接接触关系时，基于第二概率值量化部分对象之间是否存在间接接触关系的概率，保证多个对象之间的潜在 接触关系确定过程的全面性。
本公开实施例中，第二概率值，可以被用于描述部分对象之间是否存在间接接触关系的可能性。
可以理解的是，本公开实施例中，当判定部分对象之间不存在间接接触关系时，可以确定部分对象之间无接触关系。
举例而言，对于患病节点r，假设社会接触网络模型G中与其相连的节点集合表示为C，不与其相连的节点集表示为O，其中若某一节点q∈O，则需要根据时空轨迹数据判断两节点之间是否存在潜在接触关系。其中，可以使用第一概率值F(R,Q)判断节点q与节点r直接接触的可能性，F(R,Q)的计算公式可以是：
则可以使用F(Rs,Q)判断节点q与节点r间接接触的可能性，F(Rs,Q)的计算公式可以是：
其中，T(qj)start表示节点q到达原始轨迹点的起始时间，T(rjs)start表示节点r的拉伸轨迹点(ri,s,ri,y)的起始时间，通过T(qj)start-T(rjs)start可以计算得到患病节点r离开(x，y)与节点q到访(x，y)之间的间隔时间。
也即是说，本公开实施例在根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据之后，可以确定多个时空轨迹数据之间的匹配信息，根据匹配信息，确定多个对象之间的潜在接触关系，由此，匹配信息可以有效表征多个时空轨迹数据之间的相似程度，基于匹配信息实现了对多个对象之间的潜在接触关系的准确判定，从而有效提升所得潜在接触关系的可靠性。
S309：基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理。
举例而言，可以采用接触关系推理算法判断社会接触网络模型中的所有孤立节点是否与其余节点存在未被发现的潜在接触关系，该接触关系推理算法主要数据结构类型包括列表和数值。
本公开实施例中，列表类型的数据结构，包括：
孤立节点列表(orphanNodeList)：包含所有孤立节点。
患病节点列表(infectedNodeList)：包含所有患病节点。
孤立节点轨迹列表(orphanNodeTrajectoryList)：包含所有孤立节点的轨迹信息。
患病节点轨迹列表(infectedNodeTrajectoryList)：包含所有患病节点的轨迹信息。
本公开实施例中，数据类型的数据结构包括：
接触因子(contactFactor)：即F(R，Q),根据该值建立对应接触关系。
该接触关系推理算法的主要流程可以包括：遍历孤立节点和其他所有患病节点，每次循环中根据孤立节点和患病节点的轨迹，计算对应的接触因子，并判断两节点的接触类型(直接接触、间接接触或无接触)，对于社会接触网络模型中不存在的接触关系进行补充。
该算法中对于接触形式的判断方法为：1)直接接触：若孤立节点o有原始轨迹点与患病节点i的原始轨迹点位置相等，并且时间维上具有重合关系，则认为两节点之间存在未被发现的直接接触，在社会 接触网络模型G中建立对应边关系，并使用和原始接触关系一致的实线表示；2)间接接触：若孤立节点o的所有原始轨迹点与患病节点i的所有原始轨迹点位置都不相等，但孤立节点有原始轨迹点与患病节点的拉伸轨迹点位置相同，并且时间维上具有重合关系，则认为两节点之间存在间接接触，在社会接触网络模型G中通过虚线建立边关系；3)不存在潜在接触关系。若孤立节点o的任一原始轨迹点与患病节点i的全部原始轨迹点及拉伸轨迹点都不重合，则说明o与i之间不存在潜在接触关系，不对社会接触网络模型G进行处理。
S310：根据多个感染状态信息，从多个对象中确定目标对象。
S310的描述说明可以具体参见上述实施例，在此不再赘述。
本实施例中，通过确定多个时空轨迹数据之间的匹配信息，根据匹配信息，确定多个对象之间的潜在接触关系，由此，匹配信息可以有效表征多个时空轨迹数据之间的相似程度，基于匹配信息实现了对多个对象之间的潜在接触关系的准确判定，从而有效提升所得潜在接触关系的可靠性，通过确定预设传播特征，根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据，由此，可以有效结合预设传播特征灵活获取对应的时空轨迹数据，从而有效提升时空轨迹数据与流行病传播特征之间的适配性，保证所得多个时空轨迹数据的实用性，通过根据预设传播特征，获取与多个时空轨迹数据分别对应的多个轨迹拉伸数据，根据预设传播特征和多个轨迹拉伸数据，确定多个时空轨迹数据之间的匹配信息，由此，可以基于预设传播特征实现对时空轨迹数据的拉伸处理，从而有效提升所得轨迹拉伸数据对相应对象轨迹点的表征效果，而后预设传播特征和多个轨迹拉伸数据确定多个时空轨迹数据之间的匹配信息，可以有效提升所得匹配信息的准确性，通过基于匹配信息，确定部分对象之间存在直接接触关系的第一概率值，基于第一概率值，判断部分对象之间是否存在直接接触关系，由此，所得第一概率值可以量化部分对象之间存在直接接触关系的可能性，从而为直接接触关系的判定过程提供清晰的判定标准，以提升直接接触关系判定过程的合理性，通过在部分对象之间不存在直接接触关系时，基于匹配信息，确定部分对象之间存在间接接触关系的第二概率值，基于第二概率值，判断部分对象之间是否存在间接接触关系，由此，可以在部分对象之间不存在直接接触关系时，基于第二概率值量化部分对象之间是否存在间接接触关系的概率，保证多个对象之间的潜在接触关系确定过程的全面性。
图4是本公开另一实施例提出的流行病学调查中目标对象的识别方法的流程示意图。
如图4所示，该流行病学调查中目标对象的识别方法，包括：S401-S408。
S401：确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据。
S402：确定部分对象之间的接触关系数据。
S403：根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息。
S404：确定社会接触网络模型中的多个子网络，其中，子网络内的对象之间经由一个或多个接触边相连，不同子网络之间不存在接触边。
S401-S404的描述说明可以具体参见上述实施例，在此不再赘述。
S405：根据多个感染状态信息，确定子网络中的参考对象。
本公开实施例中，参考对象，可以是指子网络中最早出现流行病症状的对象。
本公开实施例中，在根据多个感染状态信息，确定子网络中的参考对象时，可以是根据多个感染状态信息，确定子网络中的多个对象的对应的流行病检验信息，而后根据流行病检验信息确定子网络中的 参考对象，或者，还可以根据多个感染状态信息确定子网络中多个对象的症状程度信息，而后根据症状程度信息确定子网络中的参考对象，对此不做限制。
一些实施例中，在根据多个感染状态信息，确定子网络中的参考对象时，可以是根据多个感染状态信息，确定子网络中的多个对象的对应的感染时间信息，根据感染时间信息，确定子网络中的参考对象，由于感染时间信息与流行病溯源过程具有较高的关联程度，当根据感染时间信息，确定子网络中的参考对象时，可以有效降低参考对象与首例病例之间的接触边数量，以基于参考对象快速确定目标对象。
本公开实施例中，感染时间信息，可以是指相应对象流行病症状出现时间、流行病检验结果为阳性时对应的时间等，对此不做限制。
S406：确定参考对象的相邻对象。
本公开实施例中，相邻对象，可以是指与参考对象之间以一条接触边相连的对象，该相邻对象的数量可以是一个或多个。
可以理解的是，相邻对象中可能存在首例病例，当确定参考对象的相邻对象，可以为后续目标对象的确定过程提供可靠的分析对象。
S407：确定相邻对象的特征信息。
本公开实施例中，特征信息，可以被用于描述相邻对象的相关特征，如相邻对象与参考对象的接触时间、相邻对象的流行病症状出现时间等，对此不做限制。
一些实施例中，在确定相邻对象的特征信息时，可以是基于相邻对象满足第一设定条件，则确定相邻对象具有第一特征，基于相邻对象满足第二设定条件，则确定相邻对象具有第二特征，根据第一特征和第二特征，生成特征信息，由此，可以有效结合多维度的相关信息对相邻对象的相关特征进行判定，从而较大程度地丰富了所得特征信息的表征内容。
本公开实施例中，第一设定条件，可以是指预先针对相邻对象所配置的条件，可以被用于判断相邻对象是否具备第一特征。而第二设定条件，可以被用于判断相邻对象是否具备第二特征。
本公开实施例中，第一特征，可以是指相邻对象存在感染候选首例病例的可能性。而第二特征，可以是指参考对象与相邻对象之间的接触关系导致候选首例病例发病的可能性。
举例而言，第一设定条件对应的关系式为：T1-T2<14天，其中T1是指相邻对象出现流行病症状的开始时间，T2是指参考对象与相邻对象之间接触的时间，而14天则是指流行病对应的潜伏期，该数据可以根据流行病的传播特征进行灵活配置。
第二设定条件对应的关系式为：T2-T3<14天，其中，T3是指参考对象出现流行病症状的开始时间。
S408：根据特征信息，确定子网络中的目标对象。
本公开实施例中，在根据特征信息，确定子网络中的目标对象时，可以是预先配置目标对象相应的设定特征信息，而后将特征信息与设定特征信息进行分析对比，以确定子网络中的目标对象，或者，还可以将多个特征信息进行分析对比，并根据对比结果以确定子网络中的目标对象，对此不做限制。
一些实施例中，在根据特征信息，确定子网络中的目标对象时，可以是基于特征信息满足第三设定条件，则根据相邻对象，生成待处理列表，获取待处理列表中多个对象的接触时间信息，根据接触时间信息，确定目标对象，由此，当特征信息满足第三设定条件时，对应相邻对象可能是参考对象的感染源，而接触时间信息与参考对象的感染过程具有较高的关联程度，当根据接触时间信息确定目标对象时，可 以有效提升目标对象确定过程的可靠性。
本公开实施例中，待处理列表，是指基于相邻对象所生成的对象列表。
本公开实施例中，第三设定条件，可以是指预先针对特征信息所配置的条件，例如可以是特征信息中同时包括第一特征和第二特征。
本公开实施例中，接触时间信息，可以是指对象与参考对象之间接触时间的相关信息。
也即是说，本公开实施例在确定社会接触网络模型中的多个子网络之后，可以根据多个感染状态信息，确定子网络中的参考对象，确定参考对象的相邻对象，确定相邻对象的特征信息，根据特征信息，确定子网络中的目标对象，由此，可以基于多个感染状态信息确定子网络中与首例病例之间接触边数量较少的参考对象，而后结合参考对象与相邻对象的相关信息，可以准确、快速的确定目标对象。
举例而言，当特征信息满足第三设定条件时，表征当前相邻节点可能是参考对象的感染源，可以将其作为考对象的感染源备选。对候考对象的所有相邻对象进行判断，获取所有可能的感染源并存储于待处理列表中，该待处理列表中的节点都可能是导致参考对象发病的父节点。而后遍历待处理列表，将与参考对象接触时间最早的对象判定为感染源，在此基础上遍历整个子网络，当无法继续获得参考对象的感染源时，可以将当前参考对象作为当前子网络的目标对象。
本公开实施例中，通过根据多个感染状态信息，确定子网络中的参考对象，确定参考对象的相邻对象，确定相邻对象的特征信息，根据特征信息，确定子网络中的目标对象，由此，可以基于多个感染状态信息确定子网络中与首例病例之间接触边数量较少的参考对象，而后结合参考对象与相邻对象的相关信息，可以准确、快速的确定目标对象，通过根据多个感染状态信息，确定子网络中的多个对象的对应的感染时间信息，根据感染时间信息，确定子网络中的参考对象，由于感染时间信息与流行病溯源过程具有较高的关联程度，当根据感染时间信息，确定子网络中的参考对象时，可以有效降低参考对象与首例病例之间的接触边数量，以基于参考对象快速确定目标对象，通过在相邻对象满足第一设定条件时，确定相邻对象具有第一特征，基于相邻对象满足第二设定条件，则确定相邻对象具有第二特征，根据第一特征和第二特征，生成特征信息，由此，可以有效结合多维度的相关信息对相邻对象的相关特征进行判定，从而较大程度地丰富了所得特征信息的表征内容，通过在特征信息满足第三设定条件时，根据相邻对象，生成待处理列表，获取待处理列表中多个对象的接触时间信息，根据接触时间信息，确定目标对象，由此，当特征信息满足第三设定条件时，对应相邻对象可能是参考对象的感染源，而接触时间信息与参考对象的感染过程具有较高的关联程度，当根据接触时间信息确定目标对象时，可以有效提升目标对象确定过程的可靠性。
图5是本公开一实施例提出的流行病学调查中目标对象的识别装置的结构示意图。
如图5所示，该流行病学调查中目标对象的识别装置50，包括：
第一确定模块501，用于确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据；
第二确定模块502，用于确定部分对象之间的接触关系数据；
第三确定模块503，用于根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息；以及
第四确定模块504，用于根据多个感染状态信息，从多个对象中确定目标对象。
在本公开的一些实施例中，如图6所示，图6是本公开另一实施例提出的流行病学调查中目标对象的识别装置的结构示意图，第三确定模块503，包括：
生成子模块5031，用于根据多个对象属性数据和接触关系数据，构建社会接触网络模型，其中，社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，节点描述对象属性数据，接触边描述接触关系数据；
第一确定子模块5032，用于根据社会接触网络模型，确定各个对象的感染状态信息。
在本公开的一些实施例中，第三确定模块503，还包括：
第二确定子模块5033，用于确定社会接触网络模型中与多个对象分别对应的多个时空轨迹数据；
第三确定子模块5034，用于根据多个时空轨迹数据，确定多个对象之间的潜在接触关系；
处理子模块5035，用于基于潜在接触关系，对社会接触网络模型中的已有接触边进行扩展处理。
在本公开的一些实施例中，第三确定子模块5034，具体用于：
确定多个时空轨迹数据之间的匹配信息；
根据匹配信息，确定多个对象之间的潜在接触关系。
在本公开的一些实施例中，第二确定子模块5033，具体用于：
确定预设传播特征；
根据预设传播特征，获取社会接触网络模型中与多个对象分别对应的多个时空轨迹数据。
在本公开的一些实施例中，第三确定子模块5034，还用于：
根据预设传播特征，获取与多个时空轨迹数据分别对应的多个轨迹拉伸数据；
根据预设传播特征和多个轨迹拉伸数据，确定多个时空轨迹数据之间的匹配信息。
在本公开的一些实施例中，潜在接触关系，包括：直接接触关系、间接接触关系，以及无接触关系；
第三确定子模块5034，还用于：
基于匹配信息，确定部分对象之间存在直接接触关系的第一概率值；
基于第一概率值，判断部分对象之间是否存在直接接触关系。
在本公开的一些实施例中，第三确定子模块5034，还用于：
在部分对象之间不存在直接接触关系的情况下，基于匹配信息，确定部分对象之间存在间接接触关系的第二概率值；
基于第二概率值，判断部分对象之间是否存在间接接触关系。
在本公开的一些实施例中，第四确定模块504，包括：
第四确定子模块5041，用于确定社会接触网络模型中的多个子网络，其中，子网络内的对象之间经由一个或多个接触边相连，不同子网络之间不存在接触边；
第五确定子模块5042，用于根据多个感染状态信息，从子网络中确定目标对象。
在本公开的一些实施例中，第五确定子模块5042，具体用于：
根据多个感染状态信息，确定子网络中的参考对象；
确定参考对象的相邻对象；
确定相邻对象的特征信息；
根据特征信息，确定子网络中的目标对象。
在本公开的一些实施例中，第五确定子模块5042，还用于：
根据多个感染状态信息，确定子网络中的多个对象的对应的感染时间信息；
根据感染时间信息，确定子网络中的参考对象。
在本公开的一些实施例中，第五确定子模块5042，还用于；
基于相邻对象满足第一设定条件，确定相邻对象具有第一特征；
基于相邻对象满足第二设定条件，确定相邻对象具有第二特征；
根据第一特征和第二特征，生成特征信息。
在本公开的一些实施例中，第五确定子模块5042，还用于：
基于特征信息满足第三设定条件，根据相邻对象，生成待处理列表；
获取待处理列表中多个对象的接触时间信息；
根据接触时间信息，确定目标对象。
需要说明的是，前述对流行病学调查中目标对象的识别方法的解释说明也适用于本实施例的流行病学调查中目标对象的识别装置，此处不再赘述。
本公开实施例中，通过确定待流调处理的多个对象，其中，多个对象分别具有对应的多个对象属性数据，确定部分对象之间的接触关系数据，根据多个对象属性数据和接触关系数据，确定各个对象的感染状态信息，以及根据多个感染状态信息，从多个对象中确定目标对象，由此，可以在流行病学调查过程中实现对目标对象的快速确定，从而为流行病溯源提供可靠的参考对象，能够在降低人力成本的同时，有效提升流行病防控工作的执行效率。
图7示出了适于用来实现本公开实施方式的示例性计算机设备的框图。图7显示的计算机设备12仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图7所示，计算机设备12以通用计算设备的形式表现。计算机设备12的组件可以包括但不限于：一个或者多个处理器或者处理单元16，系统存储器28，连接不同系统组件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture；以下简称：ISA)总线，微通道体系结构(Micro Channel Architecture；以下简称：MAC)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association；以下简称：VESA)局域总线以及外围组件互连(Peripheral Component Interconnection；以下简称：PCI)总线。
计算机设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被计算机设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
存储器28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory；以下简称：RAM)30和/或高速缓存存储器32。计算机设备12可以进一步包括其他可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以用于读写不可移动的、非易失性磁介质(图7未显示，通常称为“硬盘驱动器”)。
尽管图7中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及 对可移动非易失性光盘(例如：光盘只读存储器(Compact Disc Read Only Memory；以下简称：CD-ROM)、数字多功能只读光盘(Digital Video Disc Read Only Memory；以下简称：DVD-ROM)或者其他光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线18相连。存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本公开各实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如存储器28中，这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其他程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本公开所描述的实施例中的功能和/或方法。
计算机设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与一个或者多个使得人体能与该计算机设备12交互的设备通信，和/或与使得该计算机设备12能与一个或多个其他计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且，计算机设备12还可以通过网络适配器20与一个或者多个网络(例如局域网(Local Area Network；以下简称：LAN)，广域网(Wide Area Network；以下简称：WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器20通过总线18与计算机设备12的其他模块通信。应当明白，尽管图中未示出，可以结合计算机设备12使用其他硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在系统存储器28中的程序，从而执行各种功能应用以及流行病学调查中目标对象的识别，例如实现前述实施例中提及的流行病学调查中目标对象的识别方法。
为了实现上述实施例，本公开还提出一种非临时性计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本公开前述实施例提出的流行病学调查中目标对象的识别方法。
为了实现上述实施例，本公开还提出一种计算机程序产品，当计算机程序产品中的指令处理器执行时，执行如本公开前述实施例提出的流行病学调查中目标对象的识别方法。
为了实现上述实施例，本公开还提出一种计算机程序，当该计算机程序代码在计算机上运行时，使得计算机执行如本公开前述实施例提出的流行病学调查中目标对象的识别方法。
需要说明的是，前述对流行病学调查中目标对象的识别方法实施例的解释说明也适用于上述实施例中的装置、非瞬时处理器可读存储介质、计算机程序产品和计算机程序，此处不再赘述。
本公开的技术方案中，所涉及的用户个人信息的收集、存储、使用、加工、传输、提供和公开等处理，均符合相关法律法规的规定，且不违背公序良俗。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其他实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。
需要说明的是，在本公开的描述中，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。此外，在本公开的描述中，除非另有说明，“多个”的含义是两个或两个以上。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本公开的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本公开的实施例所属技术领域的技术人员所理解。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本公开各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本公开的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定是指相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
尽管上面已经示出和描述了本公开的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本公开的限制，本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (30)

  1. 一种流行病学调查中目标对象的识别方法，包括：
    确定待流调处理的多个对象，其中，所述多个对象分别具有对应的多个对象属性数据；
    确定部分所述对象之间的接触关系数据；
    根据所述多个对象属性数据和所述接触关系数据，确定各个所述对象的感染状态信息；和
    根据多个所述感染状态信息，从所述多个对象中确定目标对象。
  2. 如权利要求1所述的方法，其中，所述根据所述多个对象属性数据和所述接触关系数据，确定各个所述对象的感染状态信息，包括：
    根据所述多个对象属性数据和所述接触关系数据，构建社会接触网络模型，其中，所述社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，所述节点描述所述对象属性数据，所述接触边描述所述接触关系数据；
    根据所述社会接触网络模型，确定各个所述对象的感染状态信息。
  3. 如权利要求2所述的方法，还包括：
    确定所述社会接触网络模型中与所述多个对象分别对应的多个时空轨迹数据；
    根据所述多个时空轨迹数据，确定所述多个对象之间的潜在接触关系；
    基于所述潜在接触关系，对所述社会接触网络模型中的已有接触边进行扩展处理。
  4. 如权利要求3所述的方法，其中，所述根据所述多个时空轨迹数据，确定所述多个对象之间的潜在接触关系，包括：
    确定多个所述时空轨迹数据之间的匹配信息；
    根据所述匹配信息，确定所述多个对象之间的潜在接触关系。
  5. 如权利要求3或4所述的方法，其中，所述确定所述社会接触网络模型中与所述多个对象分别对应的多个时空轨迹数据，包括：
    确定预设传播特征；
    根据所述预设传播特征，获取所述社会接触网络模型中与所述多个对象分别对应的多个时空轨迹数据。
  6. 如权利要求5所述的方法，其中，所述确定多个所述时空轨迹数据之间的匹配信息，包括：
    根据所述预设传播特征，获取与多个所述时空轨迹数据分别对应的多个轨迹拉伸数据；
    根据所述预设传播特征和所述多个轨迹拉伸数据，确定多个所述时空轨迹数据之间的匹配信息。
  7. 如权利要求6所述的方法，其中，所述潜在接触关系，包括：直接接触关系、间接接触关系和无接触关系；
    所述根据所述匹配信息，确定所述多个对象之间的潜在接触关系，包括：
    基于所述匹配信息，确定部分所述对象之间存在所述直接接触关系的第一概率值；
    基于所述第一概率值，判断部分所述对象之间是否存在所述直接接触关系。
  8. 如权利要求7所述的方法，还包括：
    在所述部分所述对象之间不存在所述直接接触关系的情况下，则基于所述匹配信息，确定部分所述 对象之间存在所述间接接触关系的第二概率值；
    基于所述第二概率值，判断部分所述对象之间是否存在所述间接接触关系。
  9. 如权利要求2所述的方法，其中，所述根据多个所述感染状态信息，从所述多个对象中确定目标对象，包括：
    确定所述社会接触网络模型中的多个子网络，其中，所述子网络内的所述对象之间经由一个或多个所述接触边相连，不同所述子网络之间不存在所述接触边；
    根据多个所述感染状态信息，从所述子网络中确定目标对象。
  10. 如权利要求9所述的方法，其中，所述根据多个所述感染状态信息，从所述子网络中确定目标对象，包括：
    根据多个所述感染状态信息，确定所述子网络中的参考对象；
    确定所述参考对象的相邻对象；
    确定所述相邻对象的特征信息；
    根据所述特征信息，确定所述子网络中的目标对象。
  11. 如权利要求10所述的方法，其中，所述根据多个所述感染状态信息，确定所述子网络中的参考对象，包括：
    根据多个所述感染状态信息，确定所述子网络中的多个所述对象的对应的感染时间信息；
    根据所述感染时间信息，确定所述子网络中的参考对象。
  12. 如权利要求10或11所述的方法，其特征在于，所述确定所述相邻对象的特征信息，包括：
    基于所述相邻对象满足第一设定条件，则确定所述相邻对象具有第一特征；
    基于所述相邻对象满足第二设定条件，则确定所述相邻对象具有第二特征；
    根据所述第一特征和所述第二特征，生成所述特征信息。
  13. 如权利要求12所述的方法，其特征在于，所述根据所述特征信息，确定所述子网络中的目标对象，包括：
    基于所述特征信息满足第三设定条件，则根据所述相邻对象，生成待处理列表；
    获取所述待处理列表中多个对象的接触时间信息；
    根据所述接触时间信息，确定所述目标对象。
  14. 一种流行病学调查中目标对象的识别装置，包括：
    第一确定模块，用于确定待流调处理的多个对象，其中，所述多个对象分别具有对应的多个对象属性数据；
    第二确定模块，用于确定部分所述对象之间的接触关系数据；
    第三确定模块，用于根据所述多个对象属性数据和所述接触关系数据，确定各个所述对象的感染状态信息；和
    第四确定模块，用于根据多个所述感染状态信息，从所述多个对象中确定目标对象。
  15. 如权利要求14所述的装置，其中，所述第三确定模块，包括：
    生成子模块，用于根据所述多个对象属性数据和所述接触关系数据，构建社会接触网络模型，其中，所述社会接触网络模型包括：多个节点，至少部分节点之间具有接触边，所述节点描述所述对象属性数 据，所述接触边描述所述接触关系数据；
    第一确定子模块，用于根据所述社会接触网络模型，确定各个所述对象的感染状态信息。
  16. 如权利要求15所述的装置，还包括：
    第二确定子模块，用于确定所述社会接触网络模型中与所述多个对象分别对应的多个时空轨迹数据；
    第三确定子模块，用于根据所述多个时空轨迹数据，确定所述多个对象之间的潜在接触关系；
    处理子模块，用于基于所述潜在接触关系，对所述社会接触网络模型中的已有接触边进行扩展处理。
  17. 如权利要求16所述的装置，其中，所述第三确定子模块，具体用于：
    确定多个所述时空轨迹数据之间的匹配信息；
    根据所述匹配信息，确定所述多个对象之间的潜在接触关系。
  18. 如权利要求16或17所述的装置，其中，所述第二确定子模块，具体用于：
    确定预设传播特征；
    根据所述预设传播特征，获取所述社会接触网络模型中与所述多个对象分别对应的多个时空轨迹数据。
  19. 如权利要求18所述的装置，其中，所述第三确定子模块，还用于：
    根据所述预设传播特征，获取与多个所述时空轨迹数据分别对应的多个轨迹拉伸数据；
    根据所述预设传播特征和所述多个轨迹拉伸数据，确定多个所述时空轨迹数据之间的匹配信息。
  20. 如权利要求19所述的装置，其中，所述潜在接触关系，包括：直接接触关系、间接接触关系和无接触关系；
    所述第三确定子模块，还用于：
    基于所述匹配信息，确定部分所述对象之间存在所述直接接触关系的第一概率值；
    基于所述第一概率值，判断部分所述对象之间是否存在所述直接接触关系。
  21. 如权利要求20所述的装置，其中，所述第三确定子模块，还用于：
    当所述部分所述对象之间不存在所述直接接触关系时，基于所述匹配信息，确定部分所述对象之间存在所述间接接触关系的第二概率值；
    基于所述第二概率值，判断部分所述对象之间是否存在所述间接接触关系。
  22. 如权利要求15所述的装置，其中，所述第四确定模块，包括：
    第四确定子模块，用于确定所述社会接触网络模型中的多个子网络，其中，所述子网络内的所述对象之间经由一个或多个所述接触边相连，不同所述子网络之间不存在所述接触边；
    第五确定子模块，用于根据多个所述感染状态信息，从所述子网络中确定目标对象。
  23. 如权利要求22所述的装置，其中，所述第五确定子模块，具体用于：
    根据多个所述感染状态信息，确定所述子网络中的参考对象；
    确定所述参考对象的相邻对象；
    确定所述相邻对象的特征信息；
    根据所述特征信息，确定所述子网络中的目标对象。
  24. 如权利要求23所述的装置，其中，所述第五确定子模块，还用于：
    根据多个所述感染状态信息，确定所述子网络中的多个所述对象的对应的感染时间信息；
    根据所述感染时间信息，确定所述子网络中的参考对象。
  25. 如权利要求23或24所述的装置，其中，所述第五确定子模块，还用于：
    基于所述相邻对象满足第一设定条件，确定所述相邻对象具有第一特征；
    基于所述相邻对象满足第二设定条件，确定所述相邻对象具有第二特征；
    根据所述第一特征和所述第二特征，生成所述特征信息。
  26. 如权利要求25所述的装置，其特征在于，所述第五确定子模块，还用于：
    基于所述特征信息满足第三设定条件，根据所述相邻对象，生成待处理列表；
    获取所述待处理列表中多个对象的接触时间信息；
    根据所述接触时间信息，确定所述目标对象。
  27. 一种计算机设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-13中任一项所述的流行病学调查中目标对象的识别方法。
  28. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行权利要求1-13中任一项所述的流行病学调查中目标对象的识别方法。
  29. 一种计算机程序产品，包括计算机程序，其中所述计算机程序在被处理器执行时实现根据权利要求1-13中任一项所述的流行病学调查中目标对象的识别方法的步骤。
  30. 一种计算机程序，其中所述计算机程序包括计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行如权利要求1-13中任一项所述的流行病学调查中目标对象的识别方法。
PCT/CN2023/101457 2022-06-22 2023-06-20 流行病学调查中目标对象的识别方法、装置和计算机设备 WO2023246797A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210710994.0A CN115206543A (zh) 2022-06-22 2022-06-22 流行病学调查中目标对象的识别方法、装置和计算机设备
CN202210710994.0 2022-06-22

Publications (1)

Publication Number Publication Date
WO2023246797A1 true WO2023246797A1 (zh) 2023-12-28

Family

ID=83575582

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/101457 WO2023246797A1 (zh) 2022-06-22 2023-06-20 流行病学调查中目标对象的识别方法、装置和计算机设备

Country Status (2)

Country Link
CN (1) CN115206543A (zh)
WO (1) WO2023246797A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115206543A (zh) * 2022-06-22 2022-10-18 清华大学 流行病学调查中目标对象的识别方法、装置和计算机设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111063449A (zh) * 2020-01-20 2020-04-24 罗晖 一种基于大数据的流行病预测防控系统
AU2020103842A4 (en) * 2020-12-02 2021-02-11 Bimal Kumar Mishra A system and a method for analyzing and forecasting transmission of virus
CN113450923A (zh) * 2020-03-27 2021-09-28 中国科学院深圳先进技术研究院 大规模轨迹数据模拟流感时空传播过程的方法及系统
US20210319910A1 (en) * 2020-04-10 2021-10-14 Dualiti Interactive LLC Contact tracing of epidemic-infected and identification of asymptomatic carriers
CN115206543A (zh) * 2022-06-22 2022-10-18 清华大学 流行病学调查中目标对象的识别方法、装置和计算机设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111063449A (zh) * 2020-01-20 2020-04-24 罗晖 一种基于大数据的流行病预测防控系统
CN113450923A (zh) * 2020-03-27 2021-09-28 中国科学院深圳先进技术研究院 大规模轨迹数据模拟流感时空传播过程的方法及系统
US20210319910A1 (en) * 2020-04-10 2021-10-14 Dualiti Interactive LLC Contact tracing of epidemic-infected and identification of asymptomatic carriers
AU2020103842A4 (en) * 2020-12-02 2021-02-11 Bimal Kumar Mishra A system and a method for analyzing and forecasting transmission of virus
CN115206543A (zh) * 2022-06-22 2022-10-18 清华大学 流行病学调查中目标对象的识别方法、装置和计算机设备

Also Published As

Publication number Publication date
CN115206543A (zh) 2022-10-18

Similar Documents

Publication Publication Date Title
Harris et al. A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis
Kundu et al. How might AI and chest imaging help unravel COVID-19’s mysteries?
Lessler et al. Measuring spatial dependence for infectious disease epidemiology
WO2023246797A1 (zh) 流行病学调查中目标对象的识别方法、装置和计算机设备
Harron et al. Assessing data linkage quality in cohort studies
Raafat et al. Diagnostic accuracy of the WHO clinical definitions for dengue and implications for surveillance: a systematic review and meta-analysis
WO2021120589A1 (zh) 用于3d图像的异常图像筛查方法、装置、设备及存储介质
CN113994351A (zh) 用于动态和增量人脸识别的方法和系统
Smith et al. Comparing the performance of cluster random sampling and integrated threshold mapping for targeting trachoma control, using computer simulation
WO2021217937A1 (zh) 姿态识别模型的训练方法及设备、姿态识别方法及其设备
Souza et al. Detecting spatial clusters of disease infection risk using sparsely sampled social media mobility patterns
Winkler et al. Collective human intelligence outperforms artificial intelligence in a skin lesion classification task
Boscoe et al. Public domain small-area cancer incidence data for New York State, 2005-2009
Cheng et al. A two‐stage multiresolution neural network for automatic diagnosis of hepatic echinococcosis from ultrasound images: A multicenter study
Nopour et al. Performance analysis of data mining algorithms for diagnosing COVID-19
Orel et al. Machine learning to identify socio-behavioural predictors of HIV positivity in East and Southern Africa
Sarac et al. Intelligent diagnosis of coronavirus with computed tomography images using a deep learning model
Shenoy et al. Artificial intelligence in differentiating tropical infections: A step ahead
US20200058038A1 (en) Venue monitoring through sentiment analysis
CN112967814A (zh) 基于深度学习的新型冠状病毒患者行动追踪方法及装置
Wang et al. COVID-19 contact tracking by group activity trajectory recovery over camera networks
Brugh et al. Characterizing and mapping the spatial variability of HIV risk among adolescent girls and young women: A cross-county analysis of population-based surveys in eswatini, haiti, and mozambique
Hemied et al. A COVID‐19 Visual Diagnosis Model Based on Deep Learning and GradCAM
CN113380420A (zh) 一种疫情预测方法、装置、电子设备及存储介质
Osorio et al. Evaluation of remote radiologist-interpreted point-of-care ultrasound for suspected dengue patients in a primary health care facility in Colombia

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23826444

Country of ref document: EP

Kind code of ref document: A1