WO2023246705A1 - 流行病学调查数据处理方法、装置和计算机设备 - Google Patents
流行病学调查数据处理方法、装置和计算机设备 Download PDFInfo
- Publication number
- WO2023246705A1 WO2023246705A1 PCT/CN2023/101102 CN2023101102W WO2023246705A1 WO 2023246705 A1 WO2023246705 A1 WO 2023246705A1 CN 2023101102 W CN2023101102 W CN 2023101102W WO 2023246705 A1 WO2023246705 A1 WO 2023246705A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- contact
- attribute data
- data
- node
- risk value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
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
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Definitions
- the present disclosure relates to the field of data processing technology, and specifically to an epidemiological survey data processing method, device and computer equipment.
- epidemiological survey processing may be affected by human resources and medical resources, resulting in lower accuracy of the obtained survey data processing results.
- 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 an epidemiological survey data processing method, device, computer equipment and storage medium, which can quantitatively assess the disease risk of multiple objects based on object attribute data and contact relationship data, so that the obtained
- the target risk value can clearly represent the disease probability of the corresponding subject, which can effectively improve the practicality and accuracy of the survey data processing results in the epidemic prevention and control process.
- the epidemiological survey data processing method proposed by the embodiment of the first aspect of the present disclosure includes: determining multiple objects to be processed for epidemiological investigation, wherein the multiple objects respectively have corresponding multiple object attribute data; determining as described in the part Contact relationship data between objects; determining a target risk value of each object based on the plurality of object attribute data and the contact relationship data; and generating a survey data processing result based on a plurality of the target risk values.
- the epidemiological survey data processing method proposed by the embodiment of the first aspect of the present disclosure determines the contacts between some objects by determining multiple objects to be processed, wherein each of the multiple objects has corresponding multiple object attribute data.
- Relational data determines the target risk value of each object based on multiple object attribute data and contact relationship data, and generates survey data processing results based on multiple target risk values. It can perform evaluation of multiple objects based on object attribute data and contact relationship data.
- the disease risk is quantitatively assessed so that the obtained target risk value can clearly represent the disease probability of the corresponding subject, which can effectively improve the practicality and accuracy of the survey data processing results in the process of epidemic prevention and control.
- the epidemiological survey data processing device 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 multiple corresponding objects. 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 the contact relationship data of each of the objects according to the multiple object attribute data and the contact relationship data. a target risk value; and a generating module configured to generate survey data processing results according to a plurality of the target risk values.
- the epidemiological survey data processing device determines the contact between some objects by determining multiple objects to be processed, wherein the multiple objects respectively have multiple corresponding object attribute data.
- Relational data determines the target risk value of each object based on multiple object attribute data and contact relationship data, and generates survey data processing results based on multiple target risk values. It can perform evaluation of multiple objects based on object attribute data and contact relationship data.
- the disease risk is quantitatively assessed so that the obtained target risk value can clearly represent the disease probability of the corresponding subject, which can effectively improve the practicality and accuracy of the survey data processing results in the process of epidemic prevention and control.
- 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 epidemiological survey data processing method proposed in the embodiment includes: a memory, a processor, and a computer program stored in the memory and executable on the processor.
- the fourth embodiment of the present disclosure provides a non-transitory computer-readable storage medium on which a computer program is stored.
- the program is executed by a processor, the epidemiological survey data as proposed in the first embodiment of the present disclosure is realized. Approach.
- the fifth embodiment of the present disclosure provides a computer program product.
- instructions in the computer program product are executed by a processor, the epidemiological survey data processing method proposed in the first embodiment of the present disclosure is executed.
- Figure 1 is a schematic flow chart of an epidemiological survey data processing method proposed by an embodiment of the present disclosure
- Figure 2 is a schematic flow chart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- Figure 3 is a schematic flow chart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- Figure 4 is a schematic structural diagram of a contact type proposed by an embodiment of the present disclosure.
- Figure 5 is a schematic flow chart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- Figure 6 is a schematic flow diagram of an epidemiological survey simulation calculation proposed by an embodiment of the present disclosure.
- Figure 7 is a schematic structural diagram of an epidemiological survey data processing device proposed by an embodiment of the present disclosure.
- Figure 8 is a schematic structural diagram of an epidemiological survey data processing device proposed by another embodiment of the present disclosure.
- FIG. 9 illustrates a block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure.
- Figure 1 is a schematic flowchart of an epidemiological survey data processing method proposed by an embodiment of the present disclosure.
- the execution subject of the epidemiological survey data processing method in this embodiment is an epidemiological survey data processing device.
- the device can be implemented by software and/or hardware.
- the device can be configured on a computer device.
- computer equipment may include but is not limited to terminals, servers, etc., for example, the terminal may be a mobile phone, a handheld computer, etc.
- the epidemiological survey data processing method includes steps S101 to S104.
- S101 Determine multiple objects to be processed by the flow adjustment, wherein the multiple objects respectively have multiple corresponding object attribute data.
- epidemic investigation which can also be called epidemiological investigation, refers to the 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 users who are 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 flow control.
- the contact information between the objects can be obtained in advance, and then combined with the contact information corresponding to the epidemic patients to determine the multiple objects to be processed by the flow control.
- reliable processing objects can be provided for the epidemiological survey data processing process, which can effectively reduce the epidemiological survey data processing effect while ensuring the epidemiological survey data processing effect.
- 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 multiple trip information can be matched to determine contact relationship data between some objects.
- determining the contact relationship data between some objects can subsequently determine the target risk value of each object. Provide reliable analysis basis.
- S103 Determine the target risk value of each object based on multiple object attribute data and contact relationship data.
- the risk value can be used to describe the probability of each subject being infected with the epidemic.
- the target risk value refers to the risk value of each object determined based on multiple object attribute data and contact relationship data.
- the target object attribute data and target contact relationship data corresponding to different target risk values may be determined in advance, and the object attribute data Match the target object attribute data to obtain the first risk value, match the contact relationship data with the target contact relationship data to obtain the second risk value, and then combine the first risk value and the second risk value to determine the target risk value.
- any other possible method may be used to determine the target risk value of each object based on multiple object attribute data and contact relationship data.
- the obtained target risk value can effectively represent the corresponding disease probability of each object, so as to facilitate the epidemic control process. Based on different target risk values, flexible processing for each object is achieved.
- S104 Generate survey data processing results based on multiple target risk values.
- the survey data processing results may refer to relevant information describing the corresponding target risk values of multiple objects.
- the risk threshold when generating survey data processing results based on multiple target risk values, the risk threshold may be determined in advance, and then the multiple target risk values and risk thresholds may be compared to obtain the comparison results, and the comparison results may be obtained based on the comparison.
- the results generate corresponding survey data processing results, or multiple target risk values can also be input into the pre-trained machine learning model to obtain survey data processing results.
- the contact relationship data between some objects is determined, and based on the multiple object attribute data and contact Relational data, determine the target risk value of each object, and generate survey data processing results based on multiple target risk values.
- the disease risk of multiple objects can be quantitatively assessed based on object attribute data and contact relationship data, so that the obtained target risk value can clearly represent the disease probability of the corresponding object, which can effectively improve the investigation data processing results in epidemic diseases. Practicality and accuracy in the prevention and control process.
- Figure 2 is a schematic flowchart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- the epidemiological survey data processing method includes steps S201 to S205.
- 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 can refer to a real contact network generated based on multiple object attribute data and contact relationship data, and can be used to describe contact information between multiple objects as well as the attribute information of each object itself.
- 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 target risk value of each object based on the social contact network model.
- the target risk value of the corresponding object of each node when determining the target risk value of each object according to the social contact network model, may be determined based on the location information of the node in the social contact network model, or it may also be based on The number of contact edges of each node determines the target risk value of each object.
- the topological structure information corresponding to the social contact network model may be determined, and a risk transfer model may be generated based on the contact relationship data and topological structure information, And predict the target risk value of each object based on the object attribute data, contact relationship data, and risk transfer model. Therefore, the risk transfer model based on the contact relationship data and topological structure information can more accurately simulate the epidemic in the social contact network.
- the transfer process in the model can reduce human risk when predicting the target risk value of each object based on object attribute data, contact relationship data, and risk transfer model. While reducing labor costs, the target risk value can be quickly determined.
- topological structure refers to a network structure that does not depend on the position of the nodes and the shape of the contact edges.
- topological structure information refers to the relevant information corresponding to the topological structure in the social contact network model, such as: degree, degree distribution, path, network diameter, network average path length, betweenness, agglomeration coefficient, degree-degree correlation, etc.
- the degree k i of node i in the network can refer to the number of contact edges directly connected to node i, and the degree of a node can measure the importance of the node in the network.
- the calculation formula of k i can be:
- the average degree ⁇ k> refers to the average degree of all nodes in the network.
- the calculation formula can be:
- the calculation formula for average degree ⁇ k> can also be:
- N represents the number of nodes in the social contact network model
- L represents the number of contact edges in the network.
- Degree distribution refers to the proportion of the number of nodes with node degree k in the social contact network model to the total number of nodes in the network. If it is a discrete variable, the probability of a node with degree k can be expressed as P(k), and the calculation formula is:
- N k represents the number of nodes with degree value k
- N represents the number of nodes.
- the degree distribution can be expressed as the distribution of P(k) under different k values in the social contact network model. If P(k) is a discrete variable, it satisfies:
- K min represents the minimum value of all node degree values in the social contact network model.
- a path refers to a sequence of nodes where every pair of adjacent nodes is connected by an edge. If a path P passes through nodes ⁇ 0,1,2,...,n ⁇ in order, then there are n+1 nodes and n edges on the path.
- the path with the least number of contact edges is the shortest path.
- the number of connected edges on this path is the shortest distance between the two nodes, expressed as d ij .
- the average value of the shortest distance between any two points is the average path length of the network ⁇ d>, and the calculation formula is:
- Betweenness refers to the number of times that the shortest path between any pair of nodes passes through a certain point/contact edge. If it passes through a point, it is called point betweenness. If it passes through a contact edge, it is called edge betweenness. It can characterize the location of the corresponding node or contact edge. Importance in social contact network models. The calculation formula of betweenness can be:
- g jk represents the number of shortest paths from node j to node k, Indicates the number of nodes passing through node i in the shortest path.
- the aggregation coefficient can represent the aggregation of nodes around node i.
- the ratio of the actual number of edges between the k adjacent nodes of node i and the number of all possible edges is the aggregation coefficient.
- the calculation formula is:
- k i represents the number of adjacent nodes of node i (that is, the degree value of node i), and e i is the actual number of edges between adjacent nodes of node i.
- the agglomeration coefficient can be calculated through geometric triangles, as shown in the formula:
- the calculation formula of the average clustering coefficient ⁇ C> can be:
- Degree-degree correlation can be used to describe the connection tendencies of nodes with different degree values in the social contact network model.
- the social contact network model is said to be homogeneous.
- nodes with large degrees are associated with other degree nodes. Large nodes are more likely to be connected; conversely, if nodes with small degrees are more likely to be connected with other nodes with small degrees, then the degrees of nodes in the social contact network model are negatively correlated, and the social contact network model is heterogeneous; the rest of the situation shows The social contact network model is neutral.
- the joint probability e jk is used to express the probability that the two endpoint degree values of a randomly selected edge in the social contact network model are m and n respectively.
- the calculation formula Can be:
- e jk also has normalization:
- e jk can be expressed as:
- the change of the average value k nn of the average neighbor degree of a node in the social contact network model with the degree value k can be used to quantitatively describe the degree-degree correlation, which is denoted as k nn (k).
- the average neighbor degree of node i is recorded as k nn,i , which represents the average degree value of all adjacent nodes of node i.
- the calculation formula can be:
- k i represents the degree of node i
- a ij represents the elements in the adjacency matrix A.
- N represents the total number of nodes in the social contact network model
- P(k) represents the degree distribution function of the social contact network model
- a is a constant
- the social contact network model is an assortative network
- reflects the strength or weakness of the social contact network model with assortment or assortment.
- the risk transmission model refers to the model used to determine the information related to risk transmission between nodes in the social contact network model.
- multiple objects with contact relationships may be determined based on the risk transfer model, and then the objects with contact relationships will be determined.
- the object attribute data and contact relationship data corresponding to multiple objects are input into the pre-trained machine learning model to obtain the target risk value corresponding to each object.
- a relationship table can be used to obtain the target risk value corresponding to each object.
- the relationship The mapping relationship between object attribute data, contact relationship data, and target risk values can be recorded in the table.
- the initial risk value of the first node corresponding to the first object may be obtained, where the first The object belongs to multiple objects.
- the second node that forms a parent-child relationship with the first node is determined.
- the second node describes the object attribute data of the second object.
- the object attribute data and the contact relationship data between the first object and the second object process the initial risk value to obtain the target risk value. From this, the second node that forms a parent-child relationship with the first node can be quickly determined based on the risk transfer model. , and effectively combine the multi-dimensional relevant information of the first node and the second node to achieve comprehensive consideration of the corresponding target risk value of the first object, effectively improving the reliability in the process of determining the target risk value.
- the first object refers to one object among multiple objects.
- multiple objects can be traversed, and the multiple objects are sequentially used as the first object.
- the second object refers to an object among multiple objects that has a contact relationship with the first object.
- the first node refers to the node corresponding to the first object in the social contact network model.
- the second node refers to the node corresponding to the second object in the social contact network model.
- the initial risk value refers to the risk value of the first object in the initial state.
- the number of second nodes corresponding to the first node may be multiple.
- 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.
- the target risk value of each object is determined. From this, the obtained social contact network model can be clear and accurate It can effectively represent the contact information between each object, thereby effectively improving the flow control processing effect and ensuring the reliability of the obtained target risk value.
- S205 Generate survey data processing results based on multiple target risk values.
- 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.
- the contact edge describes the contact relationship data, and then determines the target risk value of each object based on the social contact network model.
- the processing effect ensures the reliability of the obtained target risk value by determining the topological structure information corresponding to the social contact network model, generating a risk transfer model based on the contact relationship data and topological structure information, and based on the object attribute data, contact relationship data, and The risk transfer model predicts the target risk value of each object. Therefore, the risk transfer model based on contact relationship data and topological structure information can more accurately simulate the transfer process of the epidemic in the social contact network model.
- it can quickly determine the target risk value while reducing labor costs, by obtaining the initial risk value of the first node corresponding to the first object.
- the second node that forms a parent-child relationship with the first node is determined, where the second node describes the object attribute data of the second object, and according to the object attributes of the first object
- the data, the object attribute data of the second object, and the contact relationship data between the first object and the second object process the initial risk value to obtain the target risk value.
- the parent-child relationship with the first node can be quickly determined based on the risk transfer model.
- the second node of the relationship and effectively combines the multi-dimensional relevant information of the first node and the second node to achieve comprehensive consideration of the corresponding target risk value of the first object, effectively improving the reliability in the process of determining the target risk value.
- Figure 3 is a schematic flowchart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- the epidemiological survey data processing method includes steps S301 to 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.
- S304 Determine topological structure information corresponding to the social contact network model.
- S305 Generate a risk transfer model based on contact relationship data and topological structure information.
- S306 Obtain the initial risk value of the first node corresponding to the first object, where the first object belongs to multiple objects.
- S307 According to the risk transfer model, determine the second node that forms a parent-child relationship with the first node, where the second node describes the object attribute data of the second object.
- S308 Determine the risk transfer value between the second object and the first object based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- the risk transmission value may refer to a value describing the risk of epidemic transmission between the second object and the first object.
- the calculation formula for the target risk value of each node can be:
- the distance between the second object and the first object is determined based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- the contact relationship data between the second objects is used to obtain the risk transfer value, and there is no restriction on this.
- the distance between the second object and the first object is determined based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- the risk transfer value can be a parameter that determines the second object Consider the risk value, and determine the risk correction factor between the second object and the first object based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object. , correct the reference risk value according to the risk correction factor to obtain the risk transfer value, because the reference risk value can represent the corresponding epidemic infection risk of the second object, and the obtained risk correction factor can effectively represent the impact of the second object on the corresponding risk value of the first object.
- the adaptability of the risk transfer value determination process to the first object and the second object can be effectively improved, ensuring that the resulting risk transfer value is suitable for the first object and the second object. Accuracy of characterization of information between risks.
- the reference risk value refers to the corresponding risk value of the second object.
- the risk correction factor may refer to a correction factor used to correct the reference risk value.
- node f is the parent node of node i
- F is a correction factor related to the object attribute data, contact type and contact time information of node f and node i.
- the distance between the second object and the first object is determined based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object may be input into the pre-trained risk modification factor generation model, To determine the risk modification factor between the second object and the first object, or a communication link between the execution subject of the embodiment of the present disclosure and the big data server can be established in advance, and then the big data server based on the object attribute data of the first object , object attribute data of the second object, and contact relationship data between the first object and the second object, to determine the risk modification factor between the second object and the first object.
- the distance between the second object and the first object is determined based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- the node type correction factor may be determined based on the object attribute data of the first object and the object attribute data of the second object
- the contact type and contact time information may be determined based on the contact relationship data
- the contact corresponding to the contact type may be determined.
- Type correction factor determine the contact time correction factor corresponding to the contact time information, and generate a risk correction factor based on the node type correction factor, contact type correction factor, and contact time correction factor.
- the obtained node type correction factor, contact type correction factor and contact time correction factors can effectively represent the impact of corresponding factors on the reference risk value.
- risk correction factors are generated based on node type correction factors, contact type correction factors, and contact time correction factors, the effectiveness of multi-dimensional correction factors can be achieved. Fusion, thereby effectively improving the correction effect of the obtained risk correction factors on the reference risk value.
- the node type correction factor refers to a correction factor generated based on the object attribute data of the first object and the object attribute data of the second object, and can be used to describe the object attribute data of the first object and the object attributes of the second object. The impact of the data on the reference risk value.
- the contact type refers to the way of contact between objects. For example, it can be divided into “family”, “living together”, “dining together”, “close contact”, “closed space exposure” and “open space exposure” 6 kind.
- the exposure type correction factor refers to the correction factor determined based on the exposure type, which can be used to describe the impact of the exposure type on the reference risk value.
- Figure 4 is a schematic structural diagram of a contact type proposed by an embodiment of the present disclosure.
- the contact time information refers to relevant information describing the contact time between the first object and the second object.
- the contact time correction factor refers to a correction factor generated based on contact time information, which can be used to describe the impact of contact time information on the reference risk value.
- the calculation formula of the risk modification factor F can be:
- F n refers to the node type correction factor
- F c refers to the contact type correction factor
- F t refers to the contact time correction factor
- risk levels can be divided into five levels from high to low, namely "high”, “higher”, “medium”, “lower” and “low”.
- the division process can be determined by the user based on relevant information, or it can also be determined using an artificial intelligence model, and there is no limit to this.
- S309 Obtain the target risk value based on the risk transfer value and the initial risk value.
- the embodiment of the present disclosure can determine the object attribute data of the first object, the object attribute data of the second object, and the first node.
- the contact relationship data between the object and the second object determines the risk transfer value between the second object and the first object.
- the target risk value is obtained. Therefore, the obtained risk transfer value can be effective Quantifying the impact of multi-dimensional factors in the social contact network model on the risk value of the first node, and then determining the target risk value based on the initial risk value corresponding to the first node, can effectively improve the clarity of the target risk value determination process.
- the relationship between the second object and the first object is determined based on the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object.
- Risk transfer value based on the risk transfer value and the initial risk value, the target risk value is obtained. Therefore, the obtained risk transfer value can effectively quantify the impact of multi-dimensional factors in the social contact network model on the risk value of the first node, and then combined with the third Determining the target risk value based on the initial risk value corresponding to a node can effectively improve the clarity of the target risk value determination process.
- the reference risk value of the second object By determining the reference risk value of the second object, based on the object attribute data of the first object and the object attribute data of the second object , and the contact relationship data between the first object and the second object, determine the risk correction factor between the second object and the first object, correct the reference risk value according to the risk correction factor, and obtain the risk transfer value, because the reference risk value can Characterizes the corresponding epidemic infection risk of the second object, and the obtained risk modification factor can effectively characterize the impact of the second object on the corresponding risk value of the first object.
- the compatibility of the transfer value determination process with the first object and the second object ensures that the obtained risk transfer value accurately represents the risk transfer information between the first object and the second object, by based on the object attribute data of the first object and The object attribute data of the second object determines the node type correction factor, determines the contact type and contact time information according to the contact relationship data, determines the contact type correction factor corresponding to the contact type, and determines the contact time correction factor corresponding to the contact time information, The risk correction factor is generated based on the node type correction factor, contact type correction factor, and contact time correction factor.
- the obtained node type correction factor, contact type correction factor, and contact time correction factor can effectively represent the impact of the corresponding factors on the reference risk value.
- the risk correction factor is generated based on the node type correction factor, contact type correction factor, and contact time correction factor, the effective fusion of multi-dimensional correction factors can be achieved, thereby effectively improving the correction effect of the obtained risk correction factor on the reference risk value.
- Figure 5 is a schematic flowchart of an epidemiological survey data processing method proposed by another embodiment of the present disclosure.
- the epidemiological survey data processing method includes steps S501 to S507.
- S501 Determine multiple objects to be processed by the flow adjustment, where the multiple objects respectively have multiple corresponding object attribute data.
- S502 Determine contact relationship data between some objects.
- S503 Determine the target risk value of each object based on multiple object attribute data and contact relationship data.
- S504 Generate a to-be-processed list according to multiple target risk values, where the to-be-processed list includes: multiple nodes respectively corresponding to multiple objects, and the multiple nodes respectively have multiple corresponding processing orders.
- the pending list refers to the node list generated based on multiple target risk values.
- the processing order refers to the order information of each node in the to-be-processed list during processing.
- the flow adjustment is performed from large to small according to the corresponding target risk value of the node.
- the flow adjustment is performed from early to late according to the time when it was added to the list of nodes to be processed.
- Epidemic control the social contact network model G is dynamically changing.
- the node set V only contains nodes corresponding to the currently indicated cases, and the edge relationship set E_(i,j) is empty. The epidemic control ends for a certain node. Only then can its adjacent nodes and contact relationships be added or updated in the contact network G. Each object in the flow adjustment needs to occupy the flow adjustment team for a certain period of time.
- This duration is a variable that can reflect the business capabilities of the flow adjustment team.
- Each simulation The number of transfer teams is limited during the process, and its number is equal to the number of transfer teams that have been formed in the area when the epidemic broke out. When all transfer teams are occupied by individuals to be transferred, you need to wait for a certain transfer team to be released. Conduct flow adjustment for new individuals to be transferred.
- the processing order can be determined by the object attribute data corresponding to the node, or can be determined by the node's social contact Determination of location information in network models.
- the processing order is determined by the target risk value and contact relationship data of the corresponding object, or the processing order is determined by the target risk value, contact relationship data, and object attribute data of the corresponding object.
- the contact relationship data corresponding to the object may be determined, where other objects with contact relationship data that have contact relationship data with the object satisfy the first setting condition, and the contact type is determined based on the contact relationship data, If the contact type is the first contact type, the processing order is determined based on the target risk value of the object. If the contact type is the second contact type, the processing order is determined based on the target risk value of the object and the object attribute data. Since different contact types correspond to objects There are differences in epidemic infection risks. When different strategies are used to determine the processing order of objects based on contact types, the rationality of the resulting processing order can be effectively improved.
- the first set condition may refer to the subject being diagnosed with an epidemic.
- the first contact type can refer to a close contact, that is, a close contact, that is, the subject has a relatively close contact with the epidemic patient.
- the second contact type can refer to secondary close contacts, that is, secondary contacts, that is, the subject has a close relationship with the close contact.
- the contact time range in the determination process can be from 2 days before the patient's symptoms appear to At the current time point, or from 2 days before specimen sampling to the current time point, the contact methods can include living in the same room, diagnosis and treatment care, close contact in the diagnosis and treatment place, close contact on the same means of transportation, dining or entertainment in a confined space, and exposure to epidemics Infection points, etc.; objects that have contact relationships with close contacts can be called secondary close contacts.
- the time range selected in the determination process can be from the first contact between the close contact and the case or asymptomatic infected person to isolation During the period between management, contact methods may include living together, working in a closed environment, close contact without effective protection, etc.
- the processing order based on the object's target risk value and the object attribute data it may be that if it is determined based on the object attribute data that the object satisfies the second set condition, and the target risk value is greater than or equal to the set threshold, then Determine the processing order is the priority processing order. If it is determined based on the object attribute data that the object does not meet the second set condition, or the target risk value is less than the set threshold, the node corresponding to the object is deleted from the to-be-processed list. Since different objects have different effects on the epidemic There may be differences in resistance capabilities.
- the personalized attribute data of different objects can be effectively adapted during the process of determining the processing order, thereby ensuring that the obtained While ensuring the practicality of the processing sequence, it also effectively improves resource utilization during the processing of epidemiological survey data.
- the second set condition can be used to perform comparative analysis in combination with the object attribute data of the object to determine whether the object is a high-risk person.
- the set threshold refers to the threshold value configured in advance for the target risk value.
- the relative object can be edited as a general contact.
- S505 According to the processing order, generate the survey data processing result corresponding to the third node in the to-be-processed list, where the third node is the node corresponding to the first processing order among the multiple nodes.
- the node corresponding to the first processing order has the highest epidemic infection probability in the to-be-processed list.
- Generating the survey data processing results corresponding to the third node in the to-be-processed list can promptly determine whether high-risk personnel are infected with the epidemic. Disease diagnosis.
- the embodiment of the present disclosure can generate a to-be-processed list based on the multiple target risk values, where the to-be-processed list includes: Multiple nodes respectively correspond to multiple objects, and the multiple nodes respectively have multiple corresponding processing orders.
- the processing order a survey data processing result corresponding to the third node in the to-be-processed list is generated, where the third node is a plurality of nodes.
- the survey data processing result corresponding to the third node in the to-be-processed list is generated. , which can effectively improve the clarity of representation of the obtained survey data processing results.
- the relevant data in the social contact network model may change accordingly.
- the data of the contact relationship with the third object is obtained.
- the fourth object can provide accurate processing objects for subsequent update processing.
- S507 Update the target risk values of the objects among the plurality of objects except the third object according to the object attribute data of the fourth object.
- the target risk values of the multiple objects may change accordingly.
- the multiple objects are evaluated based on the object attribute data of the fourth object.
- the target risk value of other objects except the third object is updated, which can effectively improve the accuracy of the target risk value.
- the embodiment of the present disclosure after the embodiment of the present disclosure generates the survey data processing result corresponding to the third node in the to-be-processed list according to the processing order, if the survey data processing result indicates that the third object satisfies the first setting condition, then the data processing result corresponding to the third node in the to-be-processed list is obtained.
- the third object has a fourth object with contact relationship data, and the target risk values of the other objects among the multiple objects except the third object are updated based on the object attribute data of the fourth object. Since the object in the social contact network model is diagnosed with an epidemic time, it may cause the target risk values of other objects to change. Based on the survey data processing results, multiple target risk values can be updated in a timely manner, thereby effectively improving the timeliness of the target risk values.
- Figure 6 is a schematic flowchart of an epidemiological survey simulation calculation proposed by an embodiment of the present disclosure, in which when the infected node list infectedNodeList, the pending list needInvestigation and the epidemic investigation list underInvestigation are not When it is empty, the flow adjustment work has not yet ended, and loop processing is performed; if a sick node has been diagnosed and flow adjustment processing has been performed, the sick node will be put into the needInvestigation to be processed list, and the subsequent processing method for this node is as follows "Update the entire network risk"; if there is a node that needs to be investigated, that is, the pending list needInvestigation is not empty, and there is an available investigation team, the node will be added to the node list underInvestigation; the node list underInvestigation will be added to the investigation team.
- the header node is subjected to flow adjustment, and its close nodes and sub-close nodes are obtained through flow adjustment. After updating the disease risk of the above nodes, they are added to the pending list needInvestigation and reordered. After the loop exits, the nodes and their flow adjustment are output. Time nodeInvestigatedTime, the simulation flow adjustment process ends.
- list type data structures include:
- Infected NodeList Contains all infected nodes, sorted by the time when the node was diagnosed or initially tested positive from small to large.
- To-be-processed node list (needInvestigation): Contains all nodes that need to be flow tuned, sorted from large to small according to the current risk of the nodes.
- Node list in flow adjustment (underInvestigation): Contains all nodes that are in flow adjustment.
- Node and its flow adjustment time (nodeInvestigatedTime): If the node is flow adjusted, the node and its flow adjustment completion time are recorded.
- TeamNumber The number of local flow investigation teams that can perform epidemiological investigation tasks.
- T inv The average time required for node flow investigation
- the factors that affect the effectiveness of epidemic prevention and control during the epidemiological investigation process include: the number of flow investigation subjects, the time of individual flow transfer, and the resources of the flow transfer team.
- the number of flow transfer objects determines the workload in the flow transfer work.
- the time cost of the flow transfer team for each flow transfer object is determined when individual flow calls are made.
- the resources of the flow transfer team represent the main tasks of the current epidemic prevention and control work.
- the number of available draft teams By changing the "Limit of flow investigation objects (Limit)", "Average time required for node flow investigation T inv " and "Number of flow investigation teams (Team)", the epidemiological investigation process under different strategies can be simulated.
- “Limit of flow investigation objects (Limit)” stipulates the types of nodes that require epidemiological investigation.
- the node types are divided into “sick", “close contacts”, “sub-close contacts” and “higher-risk sub-close contacts”.
- the reason for conducting flow control on the disease node and the "close contact” node is because the current flow control objects specified in the current flow control work include these two types of objects.
- the reason for conducting flow control on the "sub-close contact” node is because there is a certain disease risk in the sub-close contact of the sick individual. Risk of disease; on the other hand, since the disease probability of sub-close nodes is not high during the spread of epidemics, in order to achieve better prevention and control results with limited flow control resources, you can choose not to flow all sub-close nodes.
- Adjustment is performed, and only the nodes with higher disease risk in the secondary close contacts are adjusted, that is, it is assumed that the disease risk value of a certain close contact node exceeds the close contact with the smallest disease risk among all known nodes in the current contact network G
- the closely connected node can be considered as a "higher risk secondary close connection", and it needs to be flow adjusted as well.
- the average time required for node flow adjustment T inv is the average flow adjustment time consumed by the flow adjustment team on all the individuals to be flow adjustment. In actual flow adjustment work, this value is set to 4 hours. However, affected by changes in the epidemic form and the professional capabilities of the migration team, T inv in an epidemic often differs greatly from the specified value. Therefore, this variable can be changed to study the impact of the professional capabilities of the migration team on epidemic prevention and control. effect.
- “Number of flow control teams (Team)” is a reflection of the available flow control resources in epidemic prevention and control. The greater the number of flow control teams, the more flow control resources are currently available. By changing the number of teams, epidemic prevention and control can be analyzed The income situation when different numbers of transfer teams are invested in the work.
- the flow confirmation time T inv,sim (i) if node i is a diseased node, the diagnosis time T confirm (i) of the object can also be obtained through the object attribute data.
- T in_advance T inv,act (i)-T confirm (i), when T in_advance is greater than 0, N in_advance increases by 1.
- T in_advance The average duration of advance flow adjustment of diseased nodes.
- T in_advance reflects the length of time before the node is diagnosed because the node risk is too high, reflecting the ability and speed to grasp key information in the spread of the epidemic in advance.
- N in_advance The number of diseased nodes N in_advance that are transferred in advance. If T in_advance > 0, N in_advance increases by 1. Isolating all sick nodes early and grasping the contact relationships of sick nodes has a great impact on epidemic prevention and control. This indicator can be used to measure the impact of the epidemic in the simulation flow control process. Stay on top of the situation.
- a to-be-processed list is generated based on multiple target risk values, where the to-be-processed list includes: multiple nodes respectively corresponding to multiple objects, and the multiple nodes respectively have multiple corresponding processing orders.
- the processing order generates the survey data processing results corresponding to the third node in the to-be-processed list, where the third node is the node corresponding to the first processing order among multiple nodes. Therefore, the obtained processing order can effectively characterize the correspondence between each node.
- the processing priority when generating the survey data processing result corresponding to the third node in the to-be-processed list according to the processing order, can effectively improve the clarity of the representation of the obtained survey data processing result, by indicating the third object in the survey data processing result
- a fourth object having contact relationship data with the third object is obtained, and the target risk values of other objects among the plurality of objects except the third object are updated according to the object attribute data of the fourth object, Because when an object in the social contact network model is diagnosed with an epidemic, it may cause changes in the target risk values of other objects.
- multiple target risk values can be updated in a timely manner, thereby effectively improving the timeliness of the target risk values.
- the processing order is determined by the target risk value and contact relationship data of the corresponding object, or the processing order is determined by the target risk value, contact relationship data and object attribute data of the corresponding object.
- the processing order can be flexibly determined in different application scenarios. Acquire the strategy, thereby effectively improving the applicability of the obtained processing sequence, by determining the contact relationship data corresponding to the object, wherein other objects with contact relationship data that meet the first set condition, determine the contact type based on the contact relationship data, If the contact type is the first contact type, the processing order is determined based on the target risk value of the object. If the contact type is the second contact type, the processing order is determined based on the target risk value of the object and the object attribute data.
- the processing order is determined to be the priority processing order.
- the object is deleted from the to-be-processed list.
- Figure 7 is a schematic structural diagram of an epidemiological survey data processing device proposed by an embodiment of the present disclosure.
- the epidemiological survey data processing device 70 includes:
- the first determination module 701 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 702 is used to determine the contact relationship data between some objects
- the third determination module 703 is used to determine the target risk value of each object based on multiple object attribute data and contact relationship data;
- the generation module 704 is used to generate survey data processing results according to multiple target risk values.
- the third determination module 703 includes:
- Generating sub-module 7031 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 between them, and the nodes describe the object attribute data , the contact edge describes the contact relationship data;
- the determination sub-module 7032 is used to determine the target risk value of each object according to the social contact network model.
- the determination sub-module 7032 is specifically used for:
- Predict the target risk value of each object based on object attribute data, contact relationship data, and risk transfer model.
- the determination sub-module 7032 is also used to:
- the risk transfer model determine a second node that forms a parent-child relationship with the first node, wherein the second node describes object attribute data of the second object;
- the initial risk value is processed according to the object attribute data of the first object, the object attribute data of the second object, and the contact relationship data between the first object and the second object, and a target risk value is obtained.
- the determination sub-module 7032 is also used to:
- the target risk value is obtained.
- the determination sub-module 7032 is also used to:
- the reference risk value is corrected according to the risk correction factor to obtain the risk transfer value.
- the determination sub-module 7032 is also used to:
- the generation module 704 is specifically used to:
- to-be-processed list includes: multiple nodes respectively corresponding to multiple objects, and the multiple nodes respectively have multiple corresponding processing orders;
- the survey data processing result corresponding to the third node in the to-be-processed list is generated, where the third node is the node corresponding to the first processing order among the plurality of nodes.
- the third node describes object attribute data of the third object
- the target risk values of the other objects among the plurality of objects except the third object are updated according to the object attribute data of the fourth object.
- the order of processing is determined by the target risk value and exposure relationship data of the corresponding object.
- the processing sequence is determined by the target risk value of the corresponding object, contact relationship data, and object attribute data.
- the generation module 704 is also used to:
- the processing sequence is determined based on the target risk value of the object
- the processing order is determined based on the target risk value of the object and the object attribute data.
- the generation module 704 is also used to:
- the processing order is determined to be the priority processing order
- the node corresponding to the object is deleted from the to-be-processed list.
- the contact relationship data between some objects is determined, and based on the multiple object attribute data and contact relationship data, determine the target risk value of each object, and generate survey data processing results based on multiple target risk values.
- the disease risk of multiple objects can be quantitatively assessed based on the object attribute data and contact relationship data, so that the obtained The target risk value can clearly represent the disease probability of the corresponding subject, which can effectively improve the practicality and accuracy of the survey data processing results in the epidemic prevention and control process.
- FIG. 9 illustrates a block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure.
- the computer device 12 shown in FIG. 9 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 9, commonly referred to as a "hard drive").
- a disk drive for reading and writing a removable non-volatile disk may be provided, as well as a disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disk read-only memory).
- Disc Read Only Memory hereinafter referred to as: CD-ROM
- DVD-ROM Digital Video Disc Read Only Memory
- 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.) and may Communicates with one or more devices that enable human interaction with the computer device 12, and/or with any device (e.g., network card, modem, etc.) that enables the computer device 12 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 (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 (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 epidemiological survey data processing by running programs stored in the system memory 28, for example, implementing the epidemiological survey data processing method mentioned in the previous embodiment.
- 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 epidemiological survey data processing as proposed in the previous embodiments of the present disclosure is implemented. method.
- the present disclosure also proposes a computer program product.
- the instruction processor in the computer program product is executed, the epidemiological survey data processing method proposed in the previous embodiments of the present disclosure is executed.
- 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.
- the program can be stored in a computer-readable storage medium.
- the program can be stored in a computer-readable storage medium.
- 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
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本公开提出一种流行病学调查数据处理方法、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,确定各个对象的目标风险值,以及根据多个目标风险值,生成调查数据处理结果。
Description
相关申请的交叉引用
本申请基于申请号为202210712545.X、申请日为2022年06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。
本公开涉及数据处理技术领域,具体涉及一种流行病学调查数据处理方法、装置和计算机设备。
在流行病防控过程中,为了及时发现并隔离流行病感染人员,通常采取流行病学调查的方法对流行病所在地的人员进行调查处理。
相关技术中,在流行病学调查处理时,可能会受到流调人力资源和医疗资源的影响,导致所获取的调查数据处理结果准确性较低。
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数据处理方法、装置、计算机设备和存储介质,可以基于对象属性数据和接触关系数据对多个对象的患病风险进行量化评估,使所得目标风险值可以清晰表征相应对象的患病概率,从而可以有效提升调查数据处理结果在流行病防控过程中的实用性和准确性。
本公开第一方面实施例提出的流行病学调查数据处理方法,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目标风险值;以及根据多个所述目标风险值,生成调查数据处理结果。
本公开第一方面实施例提出的流行病学调查数据处理方法,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,确定各个对象的目标风险值,以及根据多个目标风险值,生成调查数据处理结果,可以基于对象属性数据和接触关系数据对多个对象的患病风险进行量化评估,使所得目标风险值可以清晰表征相应对象的患病概率,从而可以有效提升调查数据处理结果在流行病防控过程中的实用性和准确性。
本公开第二方面实施例提出的流行病学调查数据处理装置,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目标风险值;以及生成模块,用于根据多个所述目标风险值,生成调查数据处理结果。
本公开第二方面实施例提出的流行病学调查数据处理装置,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,确定各个对象的目标风险值,以及根据多个目标风险值,生成调查数据处理结果,可以基于对象属性数据和接触关系数据对多个对象的患病风险进行量化评估,使所得目标风险值可以清晰表征相应对象的患病概率,从而可以有效提升调查数据处理结果在流行病防控过程中的实用性和准确性。
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数据处理方法。
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数据处理方法。
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数据处理方法。
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。
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数据处理方法的流程示意图;
图2是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图;
图3是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图;
图4是本公开实施例提出的一接触类型结构示意图;
图5是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图;
图6是本公开实施例提出的一流行病学调查模拟计算流程示意图;
图7是本公开一实施例提出的流行病学调查数据处理装置的结构示意图;
图8是本公开另一实施例提出的流行病学调查数据处理装置的结构示意图;
图9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。
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数据处理方法的流程示意图。
其中,需要说明的是,本实施例的流行病学调查数据处理方法的执行主体为流行病学调查数据处理装置,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,该流行病学调查数据处理方法,包括步骤S101至步骤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。
其中,流调,也可以被称为流行病学调查,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。
其中,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。
本公开实施例中,通过确定待流调处理的多个对象,可以为流行病学调查数据处理过程提供可靠的处理对象,在保证流行病学调查数据处理效果的同时,有效降低流行病学调查数据处理过程对社会秩序造成的影响。
S102:确定部分对象之间的接触关系数据。
其中,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。
本公开实施例中,由于流行病的感染风险与对象之间的接触关系数据具有较高的关联程度,由此,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目标风险值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,确定各个对象的目标风险值。
其中,风险值,可以被用于描述各个对象自身感染流行病的概率。而目标风险值,则是指基于多个对象属性数据和接触关系数据所确定的各个对象的风险值。
一些实施例中,在根据多个对象属性数据和接触关系数据,确定各个对象的目标风险值时,可以是预先确定不同目标风险值对应的目标对象属性数据和目标接触关系数据,将对象属性数据与目标对象属性数据进行匹配处理,以得到第一风险值,将接触关系数据与目标接触关系数据进行匹配处理,以得到第二风险值,而后结合第一风险值和第二风险值确定目标风险值。
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,确定各个对象的目标风险值时,
还可以是采用第三方风险评估装置基于多个对象属性数据和接触关系数据对各个对象的风险值进行评估,以确定各个对象的目标风险值。
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,确定各个对象的目标风险值。
本公开实施例中,当根据多个对象属性数据和接触关系数据,确定各个对象的目标风险值时,所得目标风险值可以有效表征各个对象相应的患病概率,以便于在流行病管控过程中基于不同目标风险值,实现针对各个对象的灵活处理。
S104:根据多个目标风险值,生成调查数据处理结果。
其中,调查数据处理结果,可以是指描述多个对象相应目标风险值的相关信息。
可以理解的是,上述调查数据处理结果可以有效表征多个对象相应的流行病感染风险,能够在流行病管控过程中提供可靠的执行依据,从而有效提升流行病管控过程中的管控效率和管控准确性。
本公开实施例中,在根据多个目标风险值,生成调查数据处理结果时,可以是预先确定风险阈值,而后将多个目标风险值与风险阈值进行对比处理,从而获得对比结果,并根据对比结果生成对应的调查数据处理结果,或者,还可以将多个目标风险值输入至预训练的机器学习模型中,以得到调查数据处理结果。
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,确定各个对象的目标风险值,以及根据多个目标风险值,生成调查数据处理结果。由此,可以基于对象属性数据和接触关系数据对多个对象的患病风险进行量化评估,使所得目标风险值可以清晰表征相应对象的患病概率,从而可以有效提升调查数据处理结果在流行病防控过程中的实用性和准确性。
图2是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图。
如图2所示,该流行病学调查数据处理方法,包括步骤S201至步骤S205。
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。
其中,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,确定各个对象的目标风险值。
本公开实施例中,在根据社会接触网络模型,确定各个对象的目标风险值时,可以是基于节点在社会接触网络模型中的位置信息确定各个节点相应对象的目标风险值,或者,还可以基于各个节点的接触边数量,确定各个对象的目标风险值。
在一些实施例中,在根据社会接触网络模型,确定各个对象的目标风险值时,可以是确定与社会接触网络模型对应的拓扑结构信息,根据接触关系数据和拓扑结构信息,生成风险传递模型,以及根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值,由此,基于接触关系数据和拓扑结构信息所得到的风险传递模型可以较为准确地模拟流行病在社会接触网络模型中的传递过程,当根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值时,可以在降低人
工成本的同时,实现对目标风险值的快速确定。
可以理解的是,若干节点和连接节点的边关系组成了网络,而拓扑结构,是指不依赖于节点位置和接触边形态的网络结构。
其中,拓扑结构信息,是指社会接触网络模型中拓扑结构对应的相关信息,例如:度、度分布、路径、网络直径、网络平均路径长度、介数、集聚系数以及度-度相关性等。
举例而言,对于用邻接矩阵A表示的社会接触网络模型,网络中节点i的度ki可以是指与节点i直接相连的接触边的数量,节点的度可以衡量节点在网络中的重要程度,ki的计算公式可以为:
将社会接触网络模型的度计作L,则L的计算公式为:
平均度<k>是指网络中所有节点的度的平均值,计算公式可以为:
或者,平均度<k>的计算公式也可以是:
其中,N表示社会接触网络模型中节点的数量,L表示网络中接触边的数量。
度分布是指社会接触网络模型中节点度为k的节点个数占网络中节点总数的比例,若是离散型变量,一个节点度值为k的概率可以表示为P(k),计算公式为:
其中,Nk表示度值为k的节点个数,N表示节点个数。
度分布可以表示为社会接触网络模型中不同k值下P(k)的分布情况,若P(k)为离散型变量则满足:
若P(k)为连续性变量则满足:
其中Kmin表示社会接触网络模型中全部节点度值的最小值。
一条路径是指一组每一对相邻节点都有连边的节点序列。若一条路径P按顺序穿过节点{0,1,2,...,n},则该路径上共有n+1个节点和n条边,可以将路径P表示为P_(0,n)={0,1,2,...,n}或P_(0,n)={(0,1),(1,2),...,(n-1,n)}。
从一个节点到另一个节点的所有路径中,接触边数最少的路径即为最短路径,这条路径上的连边数就是这两节点的最短距离,表示为dij。网络直径是指网络中两节点之间最短路径的最大值,表示为:D=(max)┬(i,j)dij。
任意两点间最短距离的平均值就是网络的平均路径长度<d>,计算公式为:
介数是指任意一对节点间最短路径经过某一点/接触边的次数,若经过点则称为点介数,若经过接触边则称为边介数,它可以表征对应节点或接触边在社会接触网络模型中的重要程度。介数的计算公式可以为:
其中,gjk表示节点j到节点k最短路径的数量,表示最短路径中经过节点i的数量。
集聚系数可以表示节点i周围节点的聚集情况,节点i的k个邻接节点之间实际连边数与所有可能连边数的比值就是集聚系数,计算公式为:
其中,ki表示节点i的邻接节点的个数(即节点i的度值),ei是节点i的邻接节点之间实际存在的边数。
对于以图形式表示的网络G,可以通过几何三角形对集聚系数进行计算,如式:
其中,集聚系数平均值<C>的计算公式,可以为:
度-度相关性可以用来描述社会接触网络模型中不同度值节点的连接倾向,社会接触网络模型的度呈正相关性时称社会接触网络模型是同配的,此时度大节点与其他度大节点连接的可能性大;反之若度小节点更倾向于与其他度小节点连接,则社会接触网络模型中节点的度呈负相关性,社会接触网络模型是异配的;其余情况则说明社会接触网络模型是中性的。为将社会接触网络模型的度相关性通过可视化的方式表示出来,用联合概率ejk表示社会接触网络模型中随机选择的某一条边的两个端点度值分别为m和n的概率,计算公式可以为:
其中n(j,k)表示端点度值分别为j和k的边数,N表示网络的总边数;当j=k时,μ(j,k)=2,其他情况μ(j,k)=1。ejk还具有归一性:
用qk表示从社会接触网络模型中随机选择一个节点含有度值为k的邻接节点的概率,则ejk可以表示为:
其中,qk的计算公式可以为:
如果社会接触网络模型不具有度相关性,即社会接触网络模型中两节点间的是否存在接触边与它们的度值无关,则有:ejk=qjqk。
本公开实施例中,可以使用社会接触网络模型中节点的平均邻居度的平均值knn随度值k的变化以定量描述度-度相关性,记为knn(k)。将节点i的平均邻居度记为knn,i,表示节点i所有邻接节点的平均度值,计算公式可以为:
其中,ki表示节点i的度,aij表示邻接矩阵A中的元素。对于社会接触网络模型中度值为k的所有节点的平均邻居度的均值knn(k)可以表示为:
其中,N表示社会接触网络模型中的节点总数,P(k)表示社会接触网络模型的度分布函数,a是一常数;当μ>0时,社会接触网络模型是同配网络;μ=0时,社会接触网络模型是中性网络;μ<0时,社会接触网络模型是异配网络,|μ|反映了社会接触网络模型同配或异配的强弱性。
其中,风险传递模型,是指被用于确定社会接触网络模型中节点之间风险传递相关信息的模型。
本公开实施例中,在根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值时,可以是基于风险传递模型确定存在接触关系的多个对象,而后将存在接触关系的多个对象相应的对象属性数据和接触关系数据输入至预训练的机器学习模型中,以得到各个对象相应的目标风险值,或者,还可以采用关系表获取各个对象相应的目标风险值,该关系表中可以记载对象属性数据、接触关系数据以及目标风险值之间的映射关系。
在一些实施例中,在根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值时,可以是获取与第一对象所对应第一节点的初始风险值,其中,第一对象属于多个对象,根据风险传递模型,确定与第一节点形成父子关系的第二节点,其中,第二节点描述第二对象的对象属性数据,根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据处理初始风险值,得到目标风险值,由此,可以基于风险传递模型快速确定与第一节点形成父子关系的第二节点,并有效结合第一节点和第二节点多维度的相关信息,实现对第一对象相应目标风险值的综合考量,有效提升该目标风险值确定过程中的可靠性。
其中,第一对象是指多个对象中的一个对象,本公开实施例中可以遍历多个对象,依次将多个对象分别作为第一对象。而第二对象,是指多个对象中与第一对象具有接触关系的对象。
其中,第一节点,是指第一对象在社会接触网络模型中对应的节点。而第二节点,是指第二对象在社会接触网络模型中对应的节点。
其中,初始风险值,是指初始状态下,第一对象所存在的风险值。
可以理解的是,同一对象可能存在多个接触对象,由此,与第一节点对应的第二节点的数量可能是多个。
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,而后根据社会接触网络模型,确定各个对象的目标风险值,由此,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信息,从而有效提升流调处理效果,保证所得目标风险值的可靠性。
S205:根据多个目标风险值,生成调查数据处理结果。
S205的描述说明可以具体参见上述实施例,在此不再赘述。
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,而后根据社会接触网络模型,确定各个对象的目标风险值,由此,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信息,从而有效提升流调处理效果,保证所得目标风险值的可靠性,通过确定与社会接触网络模型对应的拓扑结构信息,根据接触关系数据和拓扑结构信息,生成风险传递模型,以及根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值,由此,基于接触关系数据和拓扑结构信息所得到的风险传递模型可以较为准确地模拟流行病在社会接触网络模型中的传递过程,当根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值时,可以在降低人工成本的同时,实现对目标风险值的快速确定,通过获取与第一对象所对应第一节点的初始风险值,其中,第一对象属于多个对象,根据风险传递模型,确定与第一节点形成父子关系的第二节点,其中,第二节点描述第二对象的对象属性数据,根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据处理初始风险值,得到目标风险值,由此,可以基于风险传递模型快速确定与第一节点形成父子关系的第二节点,并有效结合第一节点和第二节点多维度的相关信息,实现对第一对象相应目标风险值的综合考量,有效提升该目标风险值确定过程中的可靠性。
图3是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图。
如图3所示,该流行病学调查数据处理方法,包括步骤S301至步骤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。
S304:确定与社会接触网络模型对应的拓扑结构信息。
S305:根据接触关系数据和拓扑结构信息,生成风险传递模型。
S306:获取与第一对象所对应第一节点的初始风险值,其中,第一对象属于多个对象。
S307:根据风险传递模型,确定与第一节点形成父子关系的第二节点,其中,第二节点描述第二对象的对象属性数据。
S301-S307的描述说明可以具体参见上述实施例,在此不再赘述。
S308:根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值。
其中,风险传递值,可以是指描述第二对象与第一对象之间流行病传递风险的数值。
举例而言,在风险传递模型中,各个节点的目标风险值计算公式可以为:
其中,节点i的患病风险使用γ_i进行表示,若节点i是患病节点,则γi=1,表示患病风险为1;若它是有n个父节点的正常节点,则风险值为“1-(1-γ1,i)(1-γ2,i)…(1-γn,i)”,表示节点i受n个父节点影响的患病风险;γf,i表示父节点f传递给子节点i的风险,即风险传递值。
本公开实施例中,在根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值时,可以是获取第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据分别对应的三个参考风险传递值,而后对所得三个参考风险传递值加权处理,以得到风险传递值,或者,还可以使用第三方风险传递值确定装置处理第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,以得到风险传递值,对此不做限制。
在一些实施例中,在根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值时,可以是确定第二对象的参
考风险值,根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子,根据风险修正因子修正参考风险值,得到风险传递值,由于参考风险值可以表征第二对象相应的流行病感染风险,而所得风险修正因子可以有效表征第二对象对第一对象相应风险值所造成的影响,当根据风险修正因子修正参考风险值时,可以有效提升该风险传递值确定过程与第一对象和第二对象的适配性,保证所得风险传递值对第一对象和第二对象之间风险传递信息的表征准确性。
其中,参考风险值,是指第二对象相应的风险值。
其中,风险修正因子,可以是指被用于修正参考风险值的修正因子。
举例而言,风险传递值γf,i的计算公式可以为:
γf,i=γf*F;
γf,i=γf*F;
其中,节点f是节点i的父节点,F是一个与节点f和节点i的对象属性数据、接触类型和接触时间信息有关的修正因子。
本公开实施例中,在根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子时,可以是将第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据输入至预训练的风险修正因子生成模型中,以确定第二对象与第一对象之间的风险修正因子,或者,还可以预先建立本公开实施例的执行主体与大数据服务器的通信链接,而后由大数据服务器基于第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子。
在一些实施例中,在根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子时,可以是根据第一对象的对象属性数据和第二对象的对象属性数据,确定节点类型修正因子,根据接触关系数据,确定接触类型和接触时间信息,确定与接触类型对应的接触类型修正因子,确定与接触时间信息对应的接触时间修正因子,根据节点类型修正因子、接触类型修正因子,以及接触时间修正因子生成风险修正因子,由此,所得节点类型修正因子、接触类型修正因子以及接触时间修正因子可以分别有效表征相应因素对参考风险值产生的影响,当根据节点类型修正因子、接触类型修正因子,以及接触时间修正因子生成风险修正因子时,可以实现多维度修正因子的有效融合,从而有效提升所得风险修正因子对参考风险值的修正效果。
其中,节点类型修正因子,是指基于第一对象的对象属性数据和第二对象的对象属性数据所生成的修正因子,可以被用于描述第一对象的对象属性数据和第二对象的对象属性数据对参考风险值产生的影响。
其中,接触类型,是指对象之间的接触方式,例如可以分为“家庭”、“同住”、“同餐”、“近距离接触”、“封闭空间暴露”和“开放空间暴露”6类。而接触类型修正因子,是指基于接触类型所确定的修正因子,可以被用于描述接触类型对参考风险值的影响。
举例而言,如图4所示,图4是本公开实施例提出的一接触类型结构示意图,其中,6类接触类型之间存在包含或交集的关系,因此在应用场景中,可以基于相关信息灵活确定对象相应的接触类型,例如“家庭”包含了“同住”和“同餐”,若个体间既有同餐接触关系,又为家庭成员,则将该接触关系的接触类型设置为“家庭”即可。
其中,接触时间信息,是指描述第一对象与第二对象之间接触时间的相关信息。而接触时间修正因子,是指基于接触时间信息所生成的修正因子,可以被用于描述接触时间信息对参考风险值所产生的影响。
举例而言,风险修正因子F的计算公式可以为:
其中,Fn是指节点类型修正因子、Fc是指接触类型修正因子,Ft是指接触时间修正因子。
在应用场景中,针对不同类型的修正因子,可以将其风险等级从高到低划分为5级,分别为“高”、“较高”、“中等”、“较低”和“低”,其划分过程可以由用户基于相关信息进行确定,或者,也可以采用人工智能模型进行确定,对此不做限制。
S309:根据风险传递值和初始风险值,得到目标风险值。
也即是说,本公开实施例在根据风险传递模型,确定与第一节点形成父子关系的第二节点之后,可以根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值,根据风险传递值和初始风险值,得到目标风险值,由此,所得风险传递值可以有效量化社会接触网络模型中多维度因素对第一节点风险值所产生的影响,而后结合第一节点对应的初始风险值确定目标风险值,可以有效提升目标风险值确定过程的清晰性。
S310:根据多个目标风险值,生成调查数据处理结果。
S310的描述说明可以具体参见上述实施例,在此不再赘述。
本公开实施例中,通过根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值,根据风险传递值和初始风险值,得到目标风险值,由此,所得风险传递值可以有效量化社会接触网络模型中多维度因素对第一节点风险值所产生的影响,而后结合第一节点对应的初始风险值确定目标风险值,可以有效提升目标风险值确定过程的清晰性,通过确定第二对象的参考风险值,根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子,根据风险修正因子修正参考风险值,得到风险传递值,由于参考风险值可以表征第二对象相应的流行病感染风险,而所得风险修正因子可以有效表征第二对象对第一对象相应风险值所造成的影响,当根据风险修正因子修正参考风险值时,可以有效提升该风险传递值确定过程与第一对象和第二对象的适配性,保证所得风险传递值对第一对象和第二对象之间风险传递信息的表征准确性,通过根据第一对象的对象属性数据和第二对象的对象属性数据,确定节点类型修正因子,根据接触关系数据,确定接触类型和接触时间信息,确定与接触类型对应的接触类型修正因子,确定与接触时间信息对应的接触时间修正因子,根据节点类型修正因子、接触类型修正因子,以及接触时间修正因子生成风险修正因子,由此,所得节点类型修正因子、接触类型修正因子以及接触时间修正因子可以分别有效表征相应因素对参考风险值产生的影响,当根据节点类型修正因子、接触类型修正因子,以及接触时间修正因子生成风险修正因子时,可以实现多维度修正因子的有效融合,从而有效提升所得风险修正因子对参考风险值的修正效果。
图5是本公开另一实施例提出的流行病学调查数据处理方法的流程示意图。
如图5所示,该流行病学调查数据处理方法,包括步骤S501至S507。
S501: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。
S502:确定部分对象之间的接触关系数据。
S503:根据多个对象属性数据和接触关系数据,确定各个对象的目标风险值。
S501-S503的描述说明可以具体参见上述实施例,在此不再赘述。
S504:根据多个目标风险值,生成待处理列表,其中,待处理列表包括:与多个对象分别对应的多个节点,多个节点分别具有对应的多个处理次序。
其中,待处理列表,是指基于多个目标风险值所生成的节点列表。
其中,处理次序,是指待处理列表中各个节点在处理过程中的次序信息。
本公开实施例中,对于所有待处理节点,均按照节点相应目标风险值从大到小进行流调,当目标风险值大小相等时,则按照它加入待处理节点列表的时间从早到晚进行流调,社会接触网络模型G是动态变化的,模拟流调开始时节点集V只包含当前已指示病例对应的节点,边关系集E_(i,j)为空,对某一节点流调结束之后才能在接触网络G中增加或更新其邻接节点和接触关系,每个流调中的对象需要占用流调队伍一定的时长,该时长是一个可以反映流调队伍业务能力的变量,每次模拟的过程中流调队伍数量是有限的,其数量等于流行病暴发时所在地区已组建的流调队伍数量,当所有流调队伍都被待流调个体占用时需要等待某一流调队伍释放后才可以对新的待流调个体进行流调。
本公开实施例中,处理次序,可以由节点对应的对象属性数据确定,或者,可以由节点在社会接触
网络模型中的位置信息确定。
在一些实施例中,处理次序由相应对象的目标风险值和接触关系数据确定,或处理次序由相应对象的目标风险值、接触关系数据以及对象属性数据确定,由此,可以在不同应用场景中灵活确定处理次序的获取策略,从而有效提升所得处理次序的适用性。
在一些实施例中,在确定处理次序时,可以是确定与对象对应的接触关系数据,其中,与对象存在接触关系数据的其他对象满足第一设定条件,根据接触关系数据,确定接触类型,如果接触类型是第一接触类型,则根据对象的目标风险值确定处理次序,如果接触类型是第二接触类型,则根据对象的目标风险值和对象属性数据确定处理次序,由于不同接触类型对应对象的流行病感染风险存在差异,当基于接触类型采用不同的策略确定对象的处理次序时,可以有效提升所得处理次序的合理性。
其中,第一设定条件,可以是指对象确诊流行病。
其中,第一接触类型,可以是指密切接触者,即密接,即该对象与流行病患者的接触方式较为紧密。而第二接触类型,可以是指次级密切接触者,即次密,即该对象与密接人员存在密接关系。
举例而言,在判定接触类型时,与疑似病例、确诊病例和无症状感染者存在接触关系的对象,可以称为密切接触者,判定过程中的接触时间范围可以是患者症状出现前2天至当前时间点,或标本采样前2天至当前时间点,接触方式可以为包括同室生活、诊疗护理、诊疗场所近距离接触、同一交通工具上近距离接触、密闭空间同餐或娱乐、暴露于流行病感染点等;与密切接触者存在接触关系的对象,可以称为次级密切接触者,判定过程中所选取的时间范围可以是在密切接触者与病例或无症状感染者的首次接触至隔离管理之间的时间段,接触方式可以包括共同生活、密闭环境工作、近距离接触但未采取有效防护等。
在一些实施例中,在根据对象的目标风险值和对象属性数据确定处理次序时,可以是如果根据对象属性数据确定对象满足第二设定条件,且目标风险值大于或等于设定阈值,则确定处理次序是优先处理次序,如果根据对象属性数据确定对象不满足第二设定条件,或者目标风险值小于设定阈值,则从待处理列表中删除对象对应的节点,由于不同对象对流行病的抵抗能力可能存在差异,当基于对象属性数据和第二设定条件的对比结果确定相应的处理次序时,可以在处理次序确定过程中有效适配不同对象的个性化属性数据,从而在保证所得处理次序实用性的同时,有效提升该流行病学调查数据处理过程中的资源利用率。
其中,第二设定条件,可以被用于结合对象的对象属性数据进行对比分析,以判断对象是否属于高风险人员。
其中,设定阈值,是指预先针对目标风险值所配置的门限值。
举例而言,如果根据对象属性数据确定对象不满足第二设定条件,或者目标风险值小于设定阈值,则可以将相对对象编辑为一般接触者。
可以理解的是,当对象不满足第二设定条件或者目标风险值小于设定阈值时,相应对象的流行病感染风险较低,此时从待处理列表中删除对象对应的节点,可以有效提升待处理列表的实用性,避免造成流行病防控资源的浪费。
S505:根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果,其中,第三节点是多个节点中第一位处理次序对应的节点。
可以理解的是,第一位处理次序对应的节点在待处理列表中的流行病感染概率最高,生成与待处理列表中第三节点对应的调查数据处理结果,可以及时对高风险人员是否感染流行病进行判定。
也即是说,本公开实施例在根据多个对象属性数据和接触关系数据,确定各个对象的目标风险值之后,可以根据多个目标风险值,生成待处理列表,其中,待处理列表包括:与多个对象分别对应的多个节点,多个节点分别具有对应的多个处理次序,根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果,其中,第三节点是多个节点中第一位处理次序对应的节点,由此,所得处理次序可以有效表征各个节点对应的处理优先级,当根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果时,可以有效提升所得调查数据处理结果的表征清晰性。
S506:如果调查数据处理结果指示第三对象满足第一设定条件,则获取与第三对象存在接触关系数据的第四对象。
本公开实施例中,当调查数据处理结果指示第三对象满足第一设定条件时,社会接触网络模型中的相关数据可能会随之产生变化,此时获取与第三对象存在接触关系数据的第四对象,可以为后续的更新处理过程提供准确的处理对象。
S507:根据第四对象的对象属性数据对多个对象中除第三对象的其他对象的目标风险值进行更新处理。
可以理解的是,当调查数据处理结果指示第三对象满足第一设定条件时,多个对象的目标风险值可能会随之产生变化,此时根据第四对象的对象属性数据对多个对象中除第三对象的其他对象的目标风险值进行更新处理,可以有效提升该目标风险值的准确性。
也即是说,本公开实施例在根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果之后,如果调查数据处理结果指示第三对象满足第一设定条件,则获取与第三对象存在接触关系数据的第四对象,根据第四对象的对象属性数据对多个对象中除第三对象的其他对象的目标风险值进行更新处理,由于社会接触网络模型中对象确诊流行病时,可能会导致其余对象的目标风险值产生变化,基于调查数据处理结果,可以及时对多个目标风险值进行更新,从而有效提升目标风险值的时效性。
举例而言,如图6所示,图6是本公开实施例提出的一流行病学调查模拟计算流程示意图,其中,当患病节点列表infectedNodeList、待处理列表needInvestigation和流调中列表underInvestigation都不为空时,流调工作尚未结束,进行循环处理;如果有患病节点已经确诊并进行了流调处理,则将该患病节点放入待处理列表needInvestigation中,后续针对该节点的处理方式为“更新整个网络风险”;如果有节点需要进行流调,即待处理列表needInvestigation不为空,同时有可用流调队伍,则将该节点加入流调中节点列表underInvestigation;对流调中节点列表underInvestigation的表头节点进行流调,并通过流调该节点获得其密接节点和次密接节点,更新上述节点患病风险后将其加入待处理列表needInvestigation中并重新排序,循环退出后输出节点及其流调时间nodeInvestigatedTime,模拟流调过程结束。
在该流行病学调查模拟计算过程中,主要数据结构可以分为列表和数值两种类型,其中,列表类型的数据结构,包括:
患病节点列表(infectedNodeList):包含所有患病节点,按节点确诊或初检阳性时间从小到大排序。
待处理节点列表(needInvestigation):包含所有需要进行流调的节点,按照节点当前风险从大到小进行排序。
流调中节点列表(underInvestigation):包含所有正在流调中的节点。
已流调节点列表(hasInvestigated):包含所有已完成流调的节点。
节点及其流调时间(nodeInvestigatedTime):若节点进行了流调,则记录节点及它流调完成的时间。
而数值类型的数据结构,包括:
流调队伍数量(teamNumber:当地可执行流行病学调查任务的流调队伍数量。
节点流调所需平均时长(avgInvestigationTime),记为Tinv:流调队伍完成一起流行病学调查任务的平均时长。
当前时间(currentTime):模拟流行病学调查过程中的系统时间。
可以理解的是,在流行病学调查过程中影响流行病防控效果的因素包括:流调对象的数量、个体流调用时和流调队伍资源。流调对象的数量确定了流调工作中的工作量,个体流调用时确定了流调队伍针对每个流调对象所消耗的时间成本,流调队伍资源代表了本起流行病防控工作中可用的流调队伍数量。通过改变“流调对象限制(Limit)”、“节点流调所需平均时长Tinv”和“流调队伍数量(Team)”,可以模拟不同策略下的流行病学调查过程。
“流调对象限制(Limit)”规定了需要进行流行病学调查的节点类型,节点类型分为“患病”、“密接”、“次密接”和“较高风险次密接”,对“患病”节点和“密接”节点进行流调是因为当前流调工作规定的流调对象包括了这两类对象,对“次密接”节点进行流调是因为患病个体的次密接存在一定的患病风险;另一方面,由于在流行病传播过程中次密接的患病概率并不高,故为在有限流调资源下取得更好的防控效果,可以选择不对所有次密接节点都进行流调,而仅对次密接中具有较高患病风险的节点进行流调,即假设某次密接节点的患病风险值超过了当前接触网络G中所有已知节点中具有最小患病风险的密接节点的风险值时,可以认为此次密接节点是“较高风险次密接”,需要对它也进行流调。
“节点流调所需平均时长Tinv”是流调队伍在所有待流调个体上平均消耗的流调时长,在实际流调工作中这一值被规定为4小时。但受流行病形式变化和流调队伍专业能力的影响,一起疫情中的Tinv往往和规定值有较大出入,故可以通过改变这一变量以研究流调队伍的业务能力对流行病防控效果的影响。
“流调队伍数量(Team)”是流行病防控中可用流调资源的体现,流调队伍的数量越多,表明当前可用的流调资源越多,通过改变Team的数量可以分析疫情防控工作中投入不同流调队伍数量时的收益情况。
本公开实施例在在模拟一次流行病学调查之后,通过输出结果nodeInvestigatedTime可获得已完成流调的节点集Vinv(Vinv={1,2,…,i,…,m})及对应节点的流调时间Tinv,sim(i),若节点i为患病节点,还可以通过对象属性数据获得该对象的确诊时间Tconfirm(i)。通过以上数据可以计算得到患病节点模拟流调结束时间相较于患病节点确诊时间提前的平均值“患病节点提前流调时长Tin_advance”以及“提前完成流调的患病节点数量Nin_advance”,其中Tin_advance=Tinv,act(i)-Tconfirm(i),当Tin_advance大于0时Nin_advance加1。
通过采用不同模拟策略模拟流行病学调查,对于防控效果可以从以下几个方面进行定量分析:
1.患病节点的提前流调平均时长Tin_advance。对于每一患病节点,Tin_advance反映了因为节点风险过高而在其确诊前就对其进行流调的提前时长,反映了提前掌握流行病传播中关键信息的能力和速度。
2.提前流调的患病节点数量Nin_advance。Tin_advance>0则Nin_advance加1,较早隔离所有患病节点并掌握患病节点的接触关系对于流行病防控具有较大影响,可以通过这一指标衡量模拟流调过程中对于流行病的掌握情况。
3.患病节点在所有已流调节点Vinv中的分布情况。通过分析患病节点在所有已流调节点Vinv的分布情况可以反映流调模拟算法的效益,患病节点位置越靠前,说明其效益越好,对于流调资源的利用率越高。
4.模拟流调结束时已流调节点的数量Ninv。该值反映了模拟流行病学调查过程中的工作量。
本公开实施例中,通过根据多个目标风险值,生成待处理列表,其中,待处理列表包括:与多个对象分别对应的多个节点,多个节点分别具有对应的多个处理次序,根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果,其中,第三节点是多个节点中第一位处理次序对应的节点,由此,所得处理次序可以有效表征各个节点对应的处理优先级,当根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果时,可以有效提升所得调查数据处理结果的表征清晰性,通过在调查数据处理结果指示第三对象满足第一设定条件时,获取与第三对象存在接触关系数据的第四对象,根据第四对象的对象属性数据对多个对象中除第三对象的其他对象的目标风险值进行更新处理,由于社会接触网络模型中对象确诊流行病时,可能会导致其余对象的目标风险值产生变化,基于调查数据处理结果,可以及时对多个目标风险值进行更新,从而有效提升目标风险值的时效性,处理次序由相应对象的目标风险值和接触关系数据确定,或处理次序由相应对象的目标风险值、接触关系数据以及对象属性数据确定,由此,可以在不同应用场景中灵活确定处理次序的获取策略,从而有效提升所得处理次序的适用性,通过确定与对象对应的接触关系数据,其中,与对象存在接触关系数据的其他对象满足第一设定条件,根据接触关系数据,确定接触类型,如果接触类型是第一接触类型,则根据对象的目标风险值确定处理次序,如果接触类型是第二接触类型,则根据对象的目标风险值和对象属性数据确定处理次序,由于不同接触类型对应对象的流行病感染风险存在差异,当基于接触类型采用不同的策略确定对象的处理次序时,可以有效提升所得处理次序的合理性,通过在根据对象属性数据确定对象满足第二设定条件,且目标风险值大于或等于设定阈值时,确定处理次序是优先处理次序,在根据对象属性数据确定对象不满足第二设定条件,或者目标风险值小于设定阈值时,从待处理列表中删除对象对应的节点,由于不同对象对流行病的抵抗能力可能存在差异,当基于对象属性数据和第二设定条件的对比结果确定相应的处理次序时,可以在处理次序确定过程中有效适配不同对象的个性化属性数据,从而在保证所得处理次序实用性的同时,有效提升该流行病学调查数据处理过程中的资源利用率。
图7是本公开一实施例提出的流行病学调查数据处理装置的结构示意图。
如图7所示,该流行病学调查数据处理装置70,包括:
第一确定模块701,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702,用于确定部分对象之间的接触关系数据;
第三确定模块703,用于根据多个对象属性数据和接触关系数据,确定各个对象的目标风险值;以及
生成模块704,用于根据多个目标风险值,生成调查数据处理结果。
在本公开的一些实施例中,如图8所示,图8是本公开另一实施例提出的流行病学调查数据处理装置的结构示意图,第三确定模块703,包括:
生成子模块7031,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;
确定子模块7032,用于根据社会接触网络模型,确定各个对象的目标风险值。
在本公开的一些实施例中,确定子模块7032,具体用于:
确定与社会接触网络模型对应的拓扑结构信息;
根据接触关系数据和拓扑结构信息,生成风险传递模型;以及
根据对象属性数据、接触关系数据,以及风险传递模型预测各个对象的目标风险值。
在本公开的一些实施例中,确定子模块7032,还用于:
获取与第一对象所对应第一节点的初始风险值,其中,第一对象属于多个对象;
根据风险传递模型,确定与第一节点形成父子关系的第二节点,其中,第二节点描述第二对象的对象属性数据;以及
根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据处理初始风险值,得到目标风险值。
在本公开的一些实施例中,确定子模块7032,还用于:
根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险传递值;
根据风险传递值和初始风险值,得到目标风险值。
在本公开的一些实施例中,确定子模块7032,还用于:
确定第二对象的参考风险值;
根据第一对象的对象属性数据、第二对象的对象属性数据,以及第一对象与第二对象之间的接触关系数据,确定第二对象与第一对象之间的风险修正因子;
根据风险修正因子修正参考风险值,得到风险传递值。
在本公开的一些实施例中,确定子模块7032,还用于:
根据第一对象的对象属性数据和第二对象的对象属性数据,确定节点类型修正因子;
根据接触关系数据,确定接触类型和接触时间信息;
确定与接触类型对应的接触类型修正因子;
确定与接触时间信息对应的接触时间修正因子;
根据节点类型修正因子、接触类型修正因子,以及接触时间修正因子生成风险修正因子。
在本公开的一些实施例中,生成模块704,具体用于:
根据多个目标风险值,生成待处理列表,其中,待处理列表包括:与多个对象分别对应的多个节点,多个节点分别具有对应的多个处理次序;
根据处理次序,生成与待处理列表中第三节点对应的调查数据处理结果,其中,第三节点是多个节点中第一位处理次序对应的节点。
在本公开的一些实施例中,第三节点描述第三对象的对象属性数据;
生成模块704,还用于:
在调查数据处理结果指示第三对象满足第一设定条件时,获取与第三对象存在接触关系数据的第四对象;
根据第四对象的对象属性数据对多个对象中除第三对象的其他对象的目标风险值进行更新处理。
在本公开的一些实施例中,其中,
处理次序由相应对象的目标风险值和接触关系数据确定;或
处理次序由相应对象的目标风险值、接触关系数据以及对象属性数据确定。
在本公开的一些实施例中,生成模块704,还用于:
确定与对象对应的接触关系数据,其中,与对象存在接触关系数据的其他对象满足第一设定条件;
根据接触关系数据,确定接触类型;
在接触类型是第一接触类型时,根据对象的目标风险值确定处理次序;
在接触类型是第二接触类型时,根据对象的目标风险值和对象属性数据确定处理次序。
在本公开的一些实施例中,生成模块704,还用于:
在根据对象属性数据确定对象满足第二设定条件,且目标风险值大于或等于设定阈值时,确定处理次序是优先处理次序;
在根据对象属性数据确定对象不满足第二设定条件,或者目标风险值小于设定阈值时,从待处理列表中删除对象对应的节点。
需要说明的是,前述对流行病学调查数据处理方法的解释说明也适用于本实施例的流行病学调查数据处理装置,此处不再赘述。
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,确定各个对象的目标风险值,以及根据多个目标风险值,生成调查数据处理结果,由此,可以基于对象属性数据和接触关系数据对多个对象的患病风险进行量化评估,使所得目标风险值可以清晰表征相应对象的患病概率,从而可以有效提升调查数据处理结果在流行病防控过程中的实用性和准确性。
图9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9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9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9未显示,通常称为“硬盘驱动器”)。
尽管图9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数据处理,例如实现前述实施例中提及的流行病学调查数据处理方法。
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数据处理方法。
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数据处理方法。
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 (27)
- 一种流行病学调查数据处理方法,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目标风险值;以及根据多个所述目标风险值,生成调查数据处理结果。
- 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目标风险值,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目标风险值。
- 如权利要求2所述的方法,其中,所述根据所述社会接触网络模型,确定各个所述对象的目标风险值,包括:确定与所述社会接触网络模型对应的拓扑结构信息;根据所述接触关系数据和所述拓扑结构信息,生成风险传递模型;以及根据所述对象属性数据、所述接触关系数据,以及所述风险传递模型预测各个所述对象的目标风险值。
- 如权利要求3所述的方法,其中,所述根据所述对象属性数据、所述接触关系数据,以及所述风险传递模型预测各个所述对象的目标风险值,包括:获取与第一对象所对应第一节点的初始风险值,其中,所述第一对象属于多个所述对象;根据所述风险传递模型,确定与所述第一节点形成父子关系的第二节点,其中,所述第二节点描述第二对象的对象属性数据;以及根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据处理所述初始风险值,得到所述目标风险值。
- 如权利要求4所述的方法,其中,所述根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据处理所述初始风险值,得到所述目标风险值,包括:根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险传递值;根据所述风险传递值和所述初始风险值,得到所述目标风险值。
- 如权利要求5所述的方法,其中,所述根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险传递值,包括:确定所述第二对象的参考风险值;根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险修正因子;根据所述风险修正因子修正所述参考风险值,得到所述风险传递值。
- 如权利要求6所述的方法,其中,所述根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险修正因子,包括:根据所述第一对象的对象属性数据和所述第二对象的对象属性数据,确定节点类型修正因子;根据所述接触关系数据,确定接触类型和接触时间信息;确定与所述接触类型对应的接触类型修正因子;确定与所述接触时间信息对应的接触时间修正因子;根据所述节点类型修正因子、所述接触类型修正因子,以及所述接触时间修正因子生成所述风险修 正因子。
- 如权利要求1所述的方法,其中,所述根据多个所述目标风险值,生成调查数据处理结果,包括:根据多个所述目标风险值,生成待处理列表,其中,所述待处理列表包括:与所述多个对象分别对应的多个节点,所述多个节点分别具有对应的多个处理次序;根据所述处理次序,生成与所述待处理列表中第三节点对应的所述调查数据处理结果,其中,所述第三节点是所述多个节点中第一位处理次序对应的节点。
- 如权利要求8所述的方法,其中,所述第三节点描述第三对象的对象属性数据;在所述根据所述处理次序,生成与所述待处理列表中第三节点对应的所述调查数据处理结果之后,还包括:响应于所述调查数据处理结果指示所述第三对象满足第一设定条件,获取与所述第三对象存在接触关系数据的第四对象;根据所述第四对象的对象属性数据对所述多个对象中除所述第三对象的其他对象的目标风险值进行更新处理。
- 如权利要求8所述的方法,其中,所述处理次序由相应所述对象的目标风险值和所述接触关系数据确定;或所述处理次序由相应所述对象的目标风险值、所述接触关系数据以及所述对象属性数据确定。
- 如权利要求10所述的方法,还包括:确定与所述对象对应的接触关系数据,其中,与所述对象存在所述接触关系数据的其他对象满足第一设定条件;根据所述接触关系数据,确定接触类型;响应于所述接触类型是第一接触类型,根据所述对象的目标风险值确定所述处理次序;响应于所述接触类型是第二接触类型,根据所述对象的目标风险值和所述对象属性数据确定所述处理次序。
- 如权利要求11所述的方法,其中,所述根据所述对象的目标风险值和所述对象属性数据确定所述处理次序,包括:响应于根据所述对象属性数据确定所述对象满足第二设定条件,且所述目标风险值大于或等于设定阈值,确定所述处理次序是优先处理次序;响应于根据所述对象属性数据确定所述对象不满足所述第二设定条件,或者所述目标风险值小于所述设定阈值,从所述待处理列表中删除所述对象对应的节点。
- 一种流行病学调查数据处理装置,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目标风险值;以及生成模块,用于根据多个所述目标风险值,生成调查数据处理结果。
- 如权利要求13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;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目标风险值。
- 如权利要求14所述的装置,其中,所述确定子模块用于:确定与所述社会接触网络模型对应的拓扑结构信息;根据所述接触关系数据和所述拓扑结构信息,生成风险传递模型;以及根据所述对象属性数据、所述接触关系数据,以及所述风险传递模型预测各个所述对象的目标风险值。
- 如权利要求15所述的装置,其中,所述确定子模块,还用于:获取与第一对象所对应第一节点的初始风险值,其中,所述第一对象属于多个所述对象;根据所述风险传递模型,确定与所述第一节点形成父子关系的第二节点,其中,所述第二节点描述第二对象的对象属性数据;以及根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据处理所述初始风险值,得到所述目标风险值。
- 如权利要求16所述的装置,其中,所述确定子模块,还用于:根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险传递值;根据所述风险传递值和所述初始风险值,得到所述目标风险值。
- 如权利要求17所述的装置,其中,所述确定子模块,还用于:确定所述第二对象的参考风险值;根据所述第一对象的对象属性数据、所述第二对象的对象属性数据,以及所述第一对象与所述第二对象之间的所述接触关系数据,确定所述第二对象与所述第一对象之间的风险修正因子;根据所述风险修正因子修正所述参考风险值,得到所述风险传递值。
- 如权利要求18所述的装置,其中,所述确定子模块,还用于:根据所述第一对象的对象属性数据和所述第二对象的对象属性数据,确定节点类型修正因子;根据所述接触关系数据,确定接触类型和接触时间信息;确定与所述接触类型对应的接触类型修正因子;确定与所述接触时间信息对应的接触时间修正因子;根据所述节点类型修正因子、所述接触类型修正因子,以及所述接触时间修正因子生成所述风险修正因子。
- 如权利要求13所述的装置,其中,所述生成模块用于:根据多个所述目标风险值,生成待处理列表,其中,所述待处理列表包括:与所述多个对象分别对应的多个节点,所述多个节点分别具有对应的多个处理次序;根据所述处理次序,生成与所述待处理列表中第三节点对应的所述调查数据处理结果,其中,所述第三节点是所述多个节点中第一位处理次序对应的节点。
- 如权利要求20所述的装置,其中,所述第三节点描述第三对象的对象属性数据;所述生成模块,还用于:在所述调查数据处理结果指示所述第三对象满足第一设定条件时,获取与所述第三对象存在接触关系数据的第四对象;根据所述第四对象的对象属性数据对所述多个对象中除所述第三对象的其他对象的目标风险值进行更新处理。
- 如权利要求20所述的装置,其中,所述处理次序由相应所述对象的目标风险值和所述接触关系数据确定;或所述处理次序由相应所述对象的目标风险值、所述接触关系数据以及所述对象属性数据确定。
- 如权利要求22所述的装置,其中,所述生成模块,还用于:确定与所述对象对应的接触关系数据,其中,与所述对象存在所述接触关系数据的其他对象满足第一设定条件;根据所述接触关系数据,确定接触类型;在所述接触类型是第一接触类型的情况下,根据所述对象的目标风险值确定所述处理次序;在所述接触类型是第二接触类型的情况下,根据所述对象的目标风险值和所述对象属性数据确定所述处理次序。
- 如权利要求23所述的装置,其中,所述生成模块,还用于:在根据所述对象属性数据确定所述对象满足第二设定条件,且所述目标风险值大于或等于设定阈值的情况下,确定所述处理次序是优先处理次序;在根据所述对象属性数据确定所述对象不满足所述第二设定条件,或者所述目标风险值小于所述设定阈值的情况下,从所述待处理列表中删除所述对象对应的节点。
- 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1-12中任一项所述的方法。
- 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,其中,所述计算机指令用于使所述计算机执行权利要求1-12中任一项所述的方法。
- 一种计算机程序产品,包括计算机程序,所述计算机程序在被处理器执行时实现根据权利要求1-12中任一项所述方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210712545.XA CN115440388A (zh) | 2022-06-22 | 2022-06-22 | 流行病学调查数据处理方法、装置和计算机设备 |
| CN202210712545.X | 2022-06-22 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023246705A1 true WO2023246705A1 (zh) | 2023-12-28 |
Family
ID=84240748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/101102 Ceased WO2023246705A1 (zh) | 2022-06-22 | 2023-06-19 | 流行病学调查数据处理方法、装置和计算机设备 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115440388A (zh) |
| WO (1) | WO2023246705A1 (zh) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115440388A (zh) * | 2022-06-22 | 2022-12-06 | 清华大学 | 流行病学调查数据处理方法、装置和计算机设备 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091287A (zh) * | 2019-12-13 | 2020-05-01 | 南京三百云信息科技有限公司 | 风险对象识别方法、装置以及计算机设备 |
| CN112786210A (zh) * | 2021-01-15 | 2021-05-11 | 华南师范大学 | 一种疫情传播追踪方法及系统 |
| CN113871023A (zh) * | 2021-07-07 | 2021-12-31 | 厦门市美亚柏科信息股份有限公司 | 基于社会行为的传染病追踪方法、装置、设备及介质 |
| US20220172211A1 (en) * | 2020-11-30 | 2022-06-02 | International Business Machines Corporation | Applying machine learning to learn relationship weightage in risk networks |
| CN115440388A (zh) * | 2022-06-22 | 2022-12-06 | 清华大学 | 流行病学调查数据处理方法、装置和计算机设备 |
-
2022
- 2022-06-22 CN CN202210712545.XA patent/CN115440388A/zh active Pending
-
2023
- 2023-06-19 WO PCT/CN2023/101102 patent/WO2023246705A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091287A (zh) * | 2019-12-13 | 2020-05-01 | 南京三百云信息科技有限公司 | 风险对象识别方法、装置以及计算机设备 |
| US20220172211A1 (en) * | 2020-11-30 | 2022-06-02 | International Business Machines Corporation | Applying machine learning to learn relationship weightage in risk networks |
| CN112786210A (zh) * | 2021-01-15 | 2021-05-11 | 华南师范大学 | 一种疫情传播追踪方法及系统 |
| CN113871023A (zh) * | 2021-07-07 | 2021-12-31 | 厦门市美亚柏科信息股份有限公司 | 基于社会行为的传染病追踪方法、装置、设备及介质 |
| CN115440388A (zh) * | 2022-06-22 | 2022-12-06 | 清华大学 | 流行病学调查数据处理方法、装置和计算机设备 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115440388A (zh) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abueg et al. | Modeling the effect of exposure notification and non-pharmaceutical interventions on COVID-19 transmission in Washington state | |
| Gething et al. | Estimating the number of paediatric fevers associated with malaria infection presenting to Africa's public health sector in 2007 | |
| CN113161006A (zh) | 密接人员感染风险评估方法、装置、电子设备及存储介质 | |
| Pung et al. | Using high-resolution contact networks to evaluate SARS-CoV-2 transmission and control in large-scale multi-day events | |
| Zhu et al. | Measuring electronic communication networks in virtual care teams using electronic health records access-log data | |
| Zhao et al. | Threshold analyses on combinations of testing, population size, and vaccine coverage for COVID-19 control in a university setting | |
| CN113593713A (zh) | 疫情防控方法、装置、设备和介质 | |
| Sun et al. | Recurrent events analysis with data collected at informative clinical visits in electronic health records | |
| Johnson et al. | Quantifying efficiency gains of innovative designs of two-arm vaccine trials for COVID-19 using an epidemic simulation model | |
| CN114783580A (zh) | 一种医疗数据质量评估方法及系统 | |
| Schneider et al. | Cost impact analysis of novel host-response diagnostic for patients with community-acquired pneumonia in the emergency department | |
| Tuschhoff et al. | Detecting and quantifying heterogeneity in susceptibility using contact tracing data | |
| 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 | |
| CN115440388A (zh) | 流行病学调查数据处理方法、装置和计算机设备 | |
| Jerome et al. | An assessment of mass casualty triage systems using the Alberta trauma registry | |
| Reyes et al. | Modelling patient trajectories in emergency department simulations using retrospective patient cohorts | |
| US20220384054A1 (en) | Tool to quantify airborne-disease transmission risk in a workplace setting | |
| Koutsellis et al. | A predictive model and country risk assessment for COVID-19: an application of the limited failure population concept | |
| Vittinghoff et al. | Survival analysis | |
| JP6094996B2 (ja) | 動物感染症対策のための意思決定を支援する装置、方法およびプログラム | |
| Saraee et al. | Literature review on epidemiological modelling, spatial modelling and artificial intelligence for COVID-19 | |
| Borsboom et al. | The lighting of the BECONs: A behavioral data science approach to tracking interventions in COVID-19 research | |
| CN118588319A (zh) | 一种传染病感染风险检测模型的构建方法及应用 | |
| Preuss et al. | Improving patient flow in a primary care clinic | |
| CN110349006A (zh) | 基于活跃度来度量交易风险的方法、装置和电子设备 |
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: 23826353 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23826353 Country of ref document: EP Kind code of ref document: A1 |