CN114758787A

CN114758787A - Regional epidemic situation information processing method, device and system

Info

Publication number: CN114758787A
Application number: CN202011573119.XA
Authority: CN
Inventors: 陈宁; 尹义; 邹博
Original assignee: Shenzhen Intellifusion Technologies Co Ltd
Current assignee: Shenzhen Intellifusion Technologies Co Ltd
Priority date: 2020-12-25
Filing date: 2020-12-25
Publication date: 2022-07-15

Abstract

The embodiment of the application discloses a method, a device and a system for processing regional epidemic situation information, wherein the method comprises the following steps: acquiring multi-dimensional information of a target object in a first area, wherein the multi-dimensional information comprises at least one of the following: identity information, physical sign information, residence information and travel information; determining label information of each person in the target object according to sign information in the multi-dimensional information; determining an epidemic situation network distribution diagram according to the target object, the multi-dimensional information and the label information of each person; and carrying out predictive analysis processing on the epidemic situation of the first area through the epidemic situation network distribution diagram. Therefore, the embodiment of the application is beneficial to ensuring that the epidemic situation network distribution map effectively reflects the incidence relation among the target object, the multidimensional information and the label information, so that the epidemic situation network distribution map has higher timeliness, accuracy and efficiency when the overall epidemic situation of the first area is subjected to prediction analysis, prevention and control and management.

Description

Regional epidemic situation information processing method, device and system

Technical Field

The application relates to the technical field of computers, in particular to a method, a device and a system for processing regional epidemic situation information.

Background

Outbreaks and spread of epidemic situations can have serious impact on regional economy and the daily life of people in the region. In order to effectively reduce the above influence caused by the epidemic situation, not only newly added diagnosis, doubtful situation, floating population, travel track and other epidemic situation data in the area need to be collected in real time, but also the epidemic situation of the area needs to be predicted and analyzed in real time through the epidemic situation data, so that the prevention, control and management of the regional epidemic situation are realized.

However, because the collected epidemic situation data often has the characteristics of large quantity, high dimensionality and the like, the process of predicting and analyzing the regional epidemic situation through the epidemic situation data is time-consuming and serious, and the prediction analysis result also has the problem of low accuracy. How to utilize effective technical means to realize rapid and accurate prediction and analysis of regional epidemic situation and realize timely and accurate prevention, control and management of regional epidemic situation becomes a problem to be solved urgently.

Disclosure of Invention

The embodiment of the application provides a method, a device and a system for processing regional epidemic situation information, and aims to realize higher timeliness, accuracy and efficiency when an epidemic situation network distribution diagram is used for carrying out prediction analysis, prevention control and management on the overall epidemic situation of a first region.

In a first aspect, an embodiment of the present application provides a method for processing regional epidemic situation information, including:

obtaining multidimensional information of a target object in a first area, wherein the multidimensional information comprises at least one of the following: identity information, physical sign information, residence information and travel information;

determining label information of each person in the target object according to the sign information in the multi-dimensional information, wherein the label information is used for indicating whether the person in the target object has an epidemic representation phenomenon or not;

determining an epidemic situation network distribution diagram according to the target object, the multidimensional information and the label information of each person; wherein each node of the epidemic situation network distribution map is used for representing one person in the target object; each edge of the epidemic situation analysis network graph is used for indicating that nodes at two ends of each edge meet at least one relation in preset relations, and the preset relations are determined by the multi-dimensional information and/or the label information of each person; the weight corresponding to each edge is used for representing the number of the nodes at the two ends of each edge which simultaneously meet the relationship in the preset relationship;

and carrying out predictive analysis, prevention and control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

In a second aspect, an embodiment of the present application provides a regional epidemic situation information processing apparatus, including:

an information obtaining module, configured to obtain multidimensional information of a target object in a first area, where the multidimensional information includes at least one of: identity information, physical sign information, residence information and travel information;

the information processing module is used for determining label information of each person in the target object according to the sign information in the multi-dimensional information, wherein the label information is used for indicating whether the person in the target object has an epidemic representation phenomenon or not;

the network construction module is used for determining an epidemic situation network distribution map according to the target object, the multidimensional information and the label information of each person; wherein each node in the epidemic situation network distribution map is used for representing one person in the target object; each edge of the epidemic situation analysis network graph is used for indicating that nodes at two ends of each edge meet at least one relation in preset relations, and the preset relations are determined by the multi-dimensional information and/or the label information of each person; the weight corresponding to each edge is used for representing that the nodes at the two ends of each edge simultaneously meet the relationship number in the preset relationship;

and the analysis and prediction module is used for carrying out prediction analysis, prevention control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

In a third aspect, an embodiment of the present application provides a regional epidemic situation information processing system, including a server and an electronic device, where a communication connection is established between the server and the electronic device; the server is configured to perform the steps of the first aspect; the electronic equipment is used for acquiring multi-dimensional information of a target object in a first area and sending the multi-dimensional information to the server.

In a fourth aspect, embodiments of the present application provide a server, including a processor, a memory and a communication interface, the memory storing one or more programs, and the one or more programs being executed by the processor, the one or more programs being for executing the instructions of the steps in the first aspect of the embodiments of the present application.

In a fifth aspect, embodiments of the present application provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application.

In a sixth aspect, the present application provides a computer program product, where the computer program product includes a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package.

It can be seen that in the embodiment of the application, the label information of each person in the target object is determined by acquiring the multi-dimensional information of the target object in the first region and according to the sign information in the multi-dimensional information; then, determining an epidemic situation network distribution diagram according to the target object, the multi-dimensional information and the label information of each person; finally, the epidemic situation of the first area is subjected to prediction analysis processing through the epidemic situation network distribution diagram. Because a corresponding relation is established between the nodes of the epidemic situation network distribution diagram and the personnel in the target object, a relevant relation is established between the edges of the epidemic situation network distribution diagram and the preset relation determined by the multidimensional information and/or the label information, and a relevant relation is established between the weight corresponding to the edges of the epidemic situation network distribution diagram and the number of the edges meeting the relation in the preset relation at the same time, the epidemic situation network distribution diagram is determined according to the target object, the multidimensional information and the label information of each personnel, the incidence relation among the target object, the multidimensional information and the label information can be effectively reflected by the epidemic situation network distribution diagram, and the overall epidemic situation of the first area is predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution diagram, so that higher timeliness, accuracy and efficiency are achieved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be expressly understood that the drawings described below are only illustrative of some embodiments of the invention. It is also possible for a person skilled in the art to derive other figures from these figures without inventive effort.

Fig. 1 is a schematic diagram of an architecture of a regional epidemic situation information processing system according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of another regional epidemic situation information processing system provided in the embodiment of the present application;

fig. 3 is a schematic structural diagram of a server provided in an embodiment of the present application;

fig. 4 is a schematic flowchart of a method for processing regional epidemic situation information according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an epidemic situation network distribution diagram according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of another epidemic situation network distribution diagram provided in the embodiment of the present application;

fig. 7 is a block diagram illustrating functional units of a regional epidemic situation information processing apparatus according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of another server provided in the embodiment of the present application.

Detailed Description

In order to better understand the technical solutions of the present application, the following description is given for clarity and completeness in conjunction with the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the description of the embodiments of the present application without inventive step, are within the scope of the present application.

Before describing the technical solution of the embodiment of the present application, the regional epidemic situation information processing system, the server, the electronic device, and the like that may be involved in the present application will be described below.

For example, please refer to fig. 1, wherein fig. 1 is a schematic diagram of an architecture of a regional epidemic situation information processing system according to an embodiment of the present application. The regional epidemic situation information processing system 10 can include a data acquisition module 110, a data transmission module 120, a data processing module 130, an analysis prediction module 140, and an algorithm module 150, and each functional module in the regional epidemic situation information processing system 10 can be connected and accessed to each other.

Specifically, the data acquisition module 110 may include multiple types of data sensing or acquisition devices, such as a portrait acquisition device for confirmed or suspected case finding and tracking; a license plate collection device for license plate analysis; intelligent acquisition equipment to identity information acquisition.

Specifically, the data collection module 110 may be a two-dimensional code channel or an applet, etc. which is declared autonomously. The autonomous declaration system can collect identity information (such as names, identification cards, mobile phone numbers, social account numbers, license plates, face images, fingerprints and other data), sign information (such as body temperature, pulse, blood pressure, heart rate and other data), residence information (such as residential addresses and other data), travel information (such as daily travel track and other data) and epidemic prevention information (such as presence of an epidemic representation phenomenon, presence of a serious epidemic area travel history, presence of contact diagnosis/suspected case and other data) and the like for target objects in a first area (such as a cell, a community, an enterprise, a garden and the like) in real time or according to a certain period (such as time, day, week and the like).

Specifically, the data acquisition module 110 may be an epidemic propagation acquisition system, which utilizes the internet of things technology to realize data interaction recording by using near field communication or contact modes (such as Bluetooth, ultra wideband UWB, near field communication NFC, Zigbee, laser or visible light, etc.), so as to acquire data of specific people in a target area during mutual contact.

Specifically, the data collecting module 110 may be a body temperature, face or fingerprint detecting system, including a gate/gate control system for temperature measurement, face or fingerprint control, a temperature or face camera, an attendance machine, a temperature measuring witness comparing machine for identity registration, and the like, so as to collect body temperature, face or fingerprint of specific people in the target area.

Specifically, the data transmission module 120 may be configured to transmit the collected data, which is a highway for uploading data or instructions. In addition, the data transmission module 120 may be adapted according to different collected data, and the data transmission module 120 may support a wired transmission mode or a wireless transmission mode. The wired transmission mode can be a transmission mode such as a coaxial cable, an optical fiber line and the like; the wireless transmission mode may be a transmission mode such as a mobile cellular network (e.g., a fourth generation 4G or a fifth generation 5G mobile communication network), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), Bluetooth (Bluetooth), wireless fidelity (Wi-Fi), Zigbee (Zigbee), Near Field Communication (NFC), or Ultra Wide Band (UWB).

Specifically, the data processing module 130 may have functions of a multidimensional data application system, a crowd relation analysis system, and the like. The multidimensional data application system can be used for data archiving or classification processing of data acquired by the data acquisition module 110, and can realize archive data with artificial cores, such as one person for one file, one vehicle for one file, and one code for one file. The crowd relation analysis system can be used for carrying out data association processing on the data processed by the multidimensional data application system to obtain an epidemic situation network distribution map, and realizing holographic files of the data, so that the overall epidemic situation of the first area is analyzed, prevented, controlled and managed by the epidemic situation network distribution map. For example, the epidemic situation network distribution map is used for analyzing and mining the people who are exposed to confirmed/suspected cases, so that the possible risks of the exposed people can be checked at the first time; reverse tracing is carried out on the infection source by utilizing the epidemic situation network distribution diagram; and positioning and tracking the key personnel in the epidemic period by using the epidemic situation network distribution map.

Specifically, the analysis and prediction module 140 may include an epidemic prevention big data analysis middlebox, and may perform prediction analysis, prevention and control, management, and the like on the overall epidemic situation of the first area by using the epidemic situation network distribution map; the data collected by the data collection module 110 can be labeled to obtain a training sample set, the constructed semi-supervised network model is trained by using the training sample set, and finally, the overall epidemic situation of the first area is subjected to prediction analysis, prevention and control, management and the like through the trained semi-supervised network model. For example, relevant information of confirmed patients, public place crowd data, enterprise rework data, community personnel trip data and the like are input into the trained semi-supervised network module to predict population in an epidemic situation risk area or epidemic situation risk level and the like which may appear next step.

Specifically, the algorithm module 150 may be an Artificial Intelligence (Artificial Intelligence) operating system. The algorithm module 150 can provide the data acquisition module 110 with relevant algorithms for acquiring information such as body temperature, fingerprints, faces, license plates, travel tracks, social account numbers, mobile phone numbers, signs, residences and the like; the data processing module 130 can be provided with a correlation algorithm for data archiving or classification processing and a correlation algorithm for data association processing to obtain an epidemic situation network distribution map; the analysis prediction module 140 may be provided with relevant algorithms for data label labeling, semi-supervised network model iteration, semi-supervised network model training, semi-supervised network model deployment and upgrade, and the like; a face recognition algorithm, a fingerprint recognition algorithm, a mask recognition algorithm, a face aggregation algorithm, and the like required by the regional epidemic situation information processing system 10 may be provided.

For example, please refer to fig. 2, fig. 2 is a schematic diagram of an architecture of another regional epidemic situation information processing system according to an embodiment of the present application. The regional epidemic information processing system 20 can include a server 210 and an electronic device 220. The server 210 and the electronic device 220 are connected in communication, and may transmit a series of operation instructions and data to each other. Secondly, the electronic device 220 may be configured to collect multidimensional information of the target object in the first area, and send the multidimensional information to the server 210; the server 210 can be used to process the multidimensional information from the electronic device 220 and execute the regional epidemic situation information processing method of the present application. It should be noted that, the server 210 and the electronic device 220 may communicate with each other in a wired or wireless manner, and the method is not limited in particular.

Further, the regional epidemic situation information processing system 20 can also include other number of electronic devices, which is not limited in this regard.

Embodiments of the present application describe various embodiments in connection with a server and an electronic device. Each will be described in detail below.

Specifically, the server in the embodiment of the present application may be an independent physical server, may also be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), big data, and an artificial intelligence platform, which is not specifically limited to this.

Specifically, the electronic device in the embodiment of the present application may be a handheld device, a wearable device, a body temperature detection device, a heartbeat detection device, a face recognition device, a fingerprint recognition device, a physical sign monitoring device, or an on-vehicle device, and may also be various specific User Equipment (UE), terminal equipment (terminal device), a mobile phone (smart phone), a smart watch, a smart band, a thermometer, a vital sign monitor, a camera, a Personal Digital Assistant (PDA), or a personal computer (personal computer), and the like, which is not limited specifically.

The following describes an example of the structure of the server in the embodiment of the present application with reference to fig. 3, and it is understood that the structure illustrated in fig. 3 does not constitute a specific limitation to the server. In other embodiments of the present application, the server may also include more or fewer components than illustrated in FIG. 3, or combine certain components, or split certain components, or a different arrangement of components. In addition, the components illustrated in fig. 3 may be implemented by hardware, software, or a combination of software and hardware.

Referring to fig. 3, the server may include a processor 310, a communication module 320, a power management module 330, and a storage module 340. The processor 310 is connected to and controls the communication module 320, the power management module 330, and the storage module 340 in the form of corresponding buses. The processor 310 is a control center of the server, and is connected to each module of the server through various interfaces and lines.

Specifically, the processor 310 invokes the stored data in the memory by running or executing the software programs and/or modules in the storage module 340 to perform various functions of the server and process the data, and monitor the overall operation of the server. Alternatively, the processor 310 may include an Application Processor (AP), a modem processor, a Graphic Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a memory, a video codec, a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a baseband processor and/or a neural Network Processor (NPU), and the like.

The wireless communication function of the server may be implemented by the communication module 320, the modem processor, the baseband processor, and the like.

Specifically, the communication module 320 may provide functions of a second generation 2G mobile communication technology network, a third generation 3G mobile communication technology network, a fourth generation 4G mobile communication technology network, and a fifth generation 5G mobile communication technology network to perform receiving and transmitting of communication data; solutions for wireless communication applied to the server may be provided, including Bluetooth (BT), Wireless Local Area Network (WLAN), wireless fidelity (Wi-Fi) network, Near Field Communication (NFC), Infrared (IR), and the like.

Further, the communication module 320 has the same function as the data transmission module 120 in fig. 1.

Specifically, the power management module 330 may include a power management chip, and may provide management functions such as power conversion, distribution, or detection for the server.

In particular, the storage module 340 may be used to store computer-executable program code, which includes instructions. The processor 310 executes various functional applications of the server and data processing by executing instructions stored in the storage module 340. In one possible example, the internal storage module 340 stores program codes for executing the technical solutions of the embodiments of the present application.

The acquired epidemic situation data often has the characteristics of large quantity, high dimensionality and the like, so the process of carrying out prediction analysis on the epidemic situation of the region through the epidemic situation data consumes a lot of time, and the prediction analysis result also has the problem of low accuracy. How to utilize effective technical means to realize rapid and accurate prediction and analysis of regional epidemic situation and realize timely and accurate prevention, control and management of regional epidemic situation becomes the problem to be solved urgently.

With reference to the above description, the steps of the regional epidemic situation information processing method will be described below in terms of method examples, and refer to fig. 4. Fig. 4 is a schematic flowchart of a regional epidemic situation information processing method provided in an embodiment of the present application, and is applied to a server in a regional epidemic situation information processing system; the method comprises the following steps:

s410, multi-dimensional information of the target object in the first area is obtained.

Wherein the multi-dimensional information may include at least one of: identity information, physical sign information, residence information and travel information.

Specifically, the identity information may be used to indicate various identity conditions of each person in the target object, the sign information may be used to indicate various vital sign conditions of each person in the target object, the residence information may be used to indicate a residence condition of each person in the target object, and the travel information may be used to indicate a travel trajectory condition of each person in the target object.

The target object in the first area may be understood as a group of people in a certain area. For example, a particular crowd in city a, a particular household in cell B, a particular worker in factory C, an employee of a particular business in campus D, or a particular student in school E, etc. Therefore, the method and the device collect the multi-dimensional information of the target object in the first area, and perform prediction analysis, prevention and control, management and the like on the overall epidemic situation of the first area according to the processing result of the multi-dimensional information. For example, the processing result of the multi-dimensional information is utilized to analyze and mine the people who are contacted with confirmed/suspected cases, so that the contacted people can be checked at the first time, and the epidemic situation spreading risk is avoided; the infection source is reversely traced by using the processing result of the multidimensional information, so that the infection source can be known at the first time; positioning and tracking the key personnel in the first area by using the processing result of the multi-dimensional information; and predicting the epidemic situation risk level which is possibly generated in the next step of the first area by using the processing result of the multidimensional information.

In addition, the embodiment of the application considers that the multidimensional information of the target object in the first area is obtained from multiple dimensions (such as identity, vital signs, residence place, travel track and the like), so that higher accuracy can be achieved when the overall epidemic situation of the first area is subjected to prediction analysis, prevention and control and management by the processing result of the multidimensional information.

It should be further noted that the target object in the first area may acquire the multidimensional information through an electronic device in the area epidemic situation information processing system, and the data acquisition module 110 and the data transmission module 120 shown in fig. 1 may be installed in the electronic device, that is, the data acquisition module 110 acquires the multidimensional information, and then the electronic device transmits the acquired multidimensional information to the server through the data transmission module 120. For example, when the electronic device is a handheld device, a mobile phone number, a social account number and a phone book of a target object can be acquired through the handheld device and uploaded to a server; when the electronic equipment is vehicle-mounted equipment, the license plate number of the target object can be acquired through the vehicle-mounted equipment and uploaded to the server; when the electronic device is a wearable device, the physical sign information and the like of the target object can be acquired through the wearable device and uploaded to the server. Alternatively, the target object in the first area may collect the multidimensional information through a server, and the data collection module 110 shown in fig. 1 may be installed in the server at this time, which is not limited in this respect.

Specifically, the identity information may include at least one of: face image information, fingerprint information, social account information, communication information and license plate information.

It should be noted that, when the face image information is acquired, the server may identify the identity of the person in the target object through a face recognition algorithm, compare and enter the face, and identify whether to wear a mask or not; the relationship spectrum of the personnel in the target object can be calculated and tracked through a face clustering algorithm, so that whether the personnel wear the mask or not is detected through face image information, key personnel in the first area are positioned and tracked through the face image information, and the like.

When the fingerprint information is acquired, the server can identify the identity of the personnel in the target object through a fingerprint identification algorithm, and compare and input the fingerprint and the like, so that the key personnel in the first area are positioned and tracked through the fingerprint information and the like.

When the social account information is obtained, the server can perform tag processing on whether a friend relationship or a relative relationship exists between people in the target object through chat data or name remarks in the social account information.

When the communication information is acquired, the server can perform label processing on whether the friend relationship or the relative relationship exists between the persons in the target object through the mobile phone number or the telephone book in the communication information.

When the license plate information is obtained, the server can identify the identity of the personnel in the target object through the license plate number in the communication information, and obtain corresponding data such as travel tracks through the license plate number.

The following embodiment of the present application will describe an example of how to identify face image information by a face recognition algorithm and how to identify fingerprint information by a fingerprint recognition algorithm.

In one possible example, the recognition of the face image information by the face recognition algorithm comprises the following steps: determining the three-family five-eye proportion information of a target person (the target person is one of all persons in the target object) according to the face image information; determining a first characteristic vector corresponding to reference image information from a preset image information base according to the three-family five-eye proportion information, wherein the preset image information base comprises the reference image information; inputting the face image information into a feature extraction model to obtain a second feature vector; calculating to obtain a first ratio according to the similarity measurement of the first feature vector and the second feature vector; obtaining a first detection result according to the first ratio and a preset ratio range; under the condition that the first ratio is within the preset ratio range, the first detection result is that the face image information is matched with the reference image information (namely the identification and the matching are successful); or, in a case that the first ratio is not within the preset ratio range, the first detection result is that the face image information does not match the reference image information (i.e., the recognition and matching fails).

The preset image information base may be a face image database photographed in advance, for example, a face database photographed and stored in advance for an employee by an enterprise. The reference image information may be a plurality of face images extracted from a preset image information base.

Further, determining the three-family five-eye proportion information of the target person according to the face image information may include the following steps: acquiring left eye hairline point information, right eye hairline point information, forehead hairline information, eyebrow information, nose bottom information and jaw information of a target person from the face image information; determining the five-eye proportion information of the target person according to the left eye hairline point information, the right eye hairline point information and the preset five-eye segmentation points; and determining the tribential proportion information of the target person according to the forehead hairline information, the eyebrow information, the nose bottom information and the jaw information of the target person. It is understood that the pentaocular scale information is used to indicate the width scale of the face and to divide the width of the face into five equal parts in units of eye-shaped length. That is, the left hairline of the eye to the right hairline of the eye is five eyes, there is a space between two eyes, and the outer sides of two eyes to the lateral hairline are a space between one eye, 1/5 in proportion. The three-family scale information is used for indicating the length scale of the human face. That is, the length of the face is divided into three equal parts, 1/3, which are respectively in proportion from the forehead hairline to the eyebrow bone, from the eyebrow bone to the bottom of the nose, and from the bottom of the nose to the chin.

Further, the feature extraction model may include a pre-trained Convolutional Neural Network (CNN) model, a Local Binary Pattern (LBP), a Histogram of Oriented Gradients (HOG), a scale-invariant feature transform (SIFT), and the like. The convolutional neural network can be obtained by training a preset image information base, and a feature vector corresponding to the face image information is extracted through a trained deep neural network model. The LBP marks the difference between the pixel of the central point and the pixel of the adjacent domain through a preset threshold value; the HOG is a feature descriptor for object detection, and is used for constructing features by calculating and counting a gradient direction histogram of a local area of an image; the SIFT obtains features by solving feature points in the image and descriptors of the feature points and the related sizes and directions, and performs image feature point matching.

Further, the similarity measure between the first feature vector and the second feature vector may be calculated by a preset ratio formula to obtain a first ratio.

Further, the preset ratio formula may be:

B₁＝min(D(V_a,V_b))；

wherein, B₁Expressing the first ratio, the function D is Euclidean distance calculation formula, V_aRepresenting a first feature vector, V_bThe second feature vector is shown. It can be understood that the euclidean distance between the first feature vector corresponding to the reference image information and the second feature vector corresponding to the face image information of the target person is calculated, and the minimum euclidean distance is obtained. Then, a first detection result is determined by judging whether the minimum euclidean distance is within a preset ratio range.

Further, the preset ratio formula may also be:

B₂＝(V_cV_d)/(||V_c||²+||V_d||²-V_cV_d)；

wherein, B₂Denotes a first ratio, V_cRepresenting a first feature vector, V_dRepresenting the second feature vector. It can be understood that the first ratio is obtained by calculating a first feature vector corresponding to the reference image information and a second feature vector corresponding to the face image information of the target person. Then, a first detection result is determined by judging whether the first ratio is within a preset ratio range.

In one possible example, the identification of fingerprint information by a fingerprint identification algorithm comprises the steps of: performing fingerprint preprocessing and feature dimension reduction processing on the fingerprint information, wherein the fingerprint preprocessing comprises at least one of the following steps: fingerprint segmentation, fingerprint enhancement, binarization and refinement, wherein the characteristic dimension reduction comprises at least one of the following steps: variance selection method, correlation coefficient method, chi-square test, principal component analysis method and linear discriminant analysis method; extracting fingerprint characteristic information in the fingerprint information after fingerprint preprocessing and characteristic dimension reduction processing through a pre-trained image segmentation model, wherein the fingerprint characteristic information comprises end points and branch points of fingerprint ridge lines; detecting the fingerprint characteristic information and reference fingerprint information in a preset fingerprint information base to obtain a second detection result; wherein, the second detection result may include that the fingerprint feature information matches the reference fingerprint information, and the fingerprint feature information does not match the reference fingerprint information.

It should be noted that, due to various reasons, the fingerprint information collected is a gray scale image containing noise. The purpose of fingerprint preprocessing is to improve the quality of fingerprint information and enhance the contrast of ridges and valleys to facilitate feature extraction. The fingerprint segmentation is to separate a background area of a fingerprint from an image, so that the calculation amount of processing fingerprint information is reduced; the fingerprint enhancement is to filter the input gray level image with more noise, remove the cross connection, break points and fuzzy parts in the fingerprint information and obtain a clearer gray level image; binarization is to change a gray level image into a binary image with a value of 0-1, so that the data quantity needing to be stored and processed is reduced; the thinning means that edge pixels of fingerprint lines are deleted, so that only one pixel broadband is provided, the data quantity required to be stored and processed is further reduced, and the fingerprint information detection is favorably improved.

In addition, the fingerprint information usually has multi-dimensional features, and the time complexity and dimension of the algorithm exponentially increase. Therefore, the feature dimension reduction processing can ensure that the fingerprint information is easier to use, the calculation overhead of the algorithm is reduced, noise is removed, overfitting of a training model is reduced, and the like. The feature dimension reduction process may include a feature selection process and a feature extraction process. The feature selection processing comprises a variance selection method, a correlation coefficient method, chi-square test, a mutual information method, a recursive feature elimination method, a feature selection method based on penalty terms and a feature selection method based on a tree model; the feature extraction process includes Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). The PCA maps high-dimensional image data to a low-dimensional space for representation through linear projection processing, and ensures that the variance of the image data on the projected low-dimensional space is maximum, so as to reduce the dimensionality of the image data and retain more original data of the image data; LDA is a supervised linear dimension reduction algorithm, and can make the image data after dimension reduction easily distinguishable.

Further, the image segmentation model includes a CNN model, a Full Convolution Network (FCN), a U-net convolution network, a Recurrent Neural Network (RNN), a deep lab network, and the like. Wherein the deplab network is a model combining Deep Convolutional Neural Networks (DCNNs) and probabilistic graphical models (DenseCRFs), and may include deplab v1, deplab v2, deplab v3, deplab v3+, etc.

Specifically, the physical sign information may include at least one of the following: body temperature information, pulse information, blood pressure information, heart rate information.

It should be noted that the body temperature information may be used to indicate the body temperature value of each person in the target subject. Wherein, the normal body temperature range of adults is 36-37.4 ℃, and the abnormal body temperature is mainly in a range of high body temperature or lower than the normal body temperature. The range of the body temperature higher than the normal body temperature comprises a low heat range of 37.4-38 ℃, a moderate heat range of 38-39 ℃, a high heat range of 39-41 ℃ and an ultrahigh heat range above 41 ℃. Therefore, the embodiment of the application can judge whether the person in the target object has the epidemic representation phenomenon (namely, whether the body temperature is normal) through the body temperature information.

The pulse information may be used to indicate a pulse value of each person in the target subject. Wherein different age groups or different sexes have different pulse values for arterial pulsation. For example, the normal pulse range of infants is 130-150 bpm, the normal pulse range of children is 110-120 bpm, the normal pulse range of adults is 60-100 bpm, and the normal pulse range of the elderly can be as slow as 55-75 bpm. Therefore, the embodiment of the application can judge whether the person in the target object has the epidemic representation phenomenon (namely whether the pulse is normal) through the pulse information.

The blood pressure information may be used to indicate a blood pressure value for each person in the target subject. Wherein different age groups or different sexes have different blood pressure values for the pressure at which blood flows in the blood vessel. For example, the systolic pressure of a normal adult is between 90-140 mmHg, and the diastolic pressure is between 60-90 mmHg. Therefore, the embodiment of the application can judge whether the person in the target object has the epidemic representation phenomenon (namely whether the blood pressure is normal) through the blood pressure information.

The heart rate information may be used to indicate a heart rate value for each person in the target subject. Wherein different age groups or different sexes have different heart rate values for the number of heart beats. For example, the normal heart rate for an adult ranges from 60 to 100 beats/minute. Therefore, the embodiment of the application can judge whether the person in the target object has the epidemic representation phenomenon (namely whether the heart rate is normal) through the heart rate information.

The following embodiment of the present application will describe how to acquire body temperature information.

In one possible example, the acquisition of body temperature information comprises the steps of: acquiring first temperature information of a target part of a target person (the target person is one of all persons in a target object), second temperature information of an environment where the target person is currently located, and first distance information (the first distance information is a distance from the target person to an acquisition point, which may be an electronic device or a data acquisition module 110 shown in fig. 1), wherein the target part comprises one of the following: forehead, wrist and neck; inputting the first distance information and the second temperature information into a preset temperature compensation formula to obtain the compensation temperature of the target part, wherein the preset temperature compensation formula is as follows:

wherein Δ T represents a compensation temperature, β represents a preset constant of the target portion, α represents an adjustable parameter, T represents second temperature information, and d1 is used for representing first distance information; and calculating the sum of the compensation temperature and the first temperature information to obtain the body temperature information.

And S420, determining label information of each person in the target object according to the sign information in the multi-dimensional information.

Wherein, the label information can be used for indicating whether the person in the target object has the epidemic representation phenomenon.

It should be noted that, in the embodiment of the present application, it is considered that sign information is used to perform tagging processing on whether each person in the target object has an epidemic disease characterization phenomenon (such as a normal sign, a suspected case, or a confirmed case), so that higher efficiency and accuracy can be achieved when performing prediction analysis, prevention control, and management on the overall epidemic situation of the first area through the tagging processing.

Specifically, the label types of the label information may include a normal label, a suspected label, and a confirmed label. The normal label can be used for indicating that the person in the target object does not have the disease characterization phenomenon, the suspected label can be used for indicating that the person in the target object is suspected to have the disease characterization phenomenon, and the confirmed label can be used for indicating that the person in the target object has the disease characterization phenomenon. Meanwhile, the label types of the label information can be obtained through multiple times of big data analysis and statistics, that is, the embodiment of the application considers that the normal label, the suspected label and the confirmed label are obtained through multiple times of big data analysis and statistics.

It should be noted that, in the embodiment of the present application, the tag types of the tag information are considered to be divided into three categories (i.e., a normal tag, a suspected tag, and a confirmed tag), and it can be understood that the tag information of each person in the target object is one of the three categories, so that whether each person in the target object has an epidemic disease characterization phenomenon is tagged through the three categories, and higher efficiency can be achieved when the overall epidemic situation of the first area is subjected to prediction analysis, prevention control, and management.

Specifically, the embodiment of the application considers that the sign information is input into a pre-trained preset classification model to determine the label information of each person in the target object. The following is a detailed description.

In one possible example, determining the label information of each person in the target object according to the sign information in the multi-dimensional information may include the following steps: determining the proportion of various types of information in the physical sign information to obtain first proportion information; extracting a characteristic vector of the sign information according to the first proportion information to obtain a first characteristic matrix; inputting the first characteristic matrix into a pre-trained preset classification model to obtain score information aiming at each label type; and taking the label corresponding to the highest score in the score information as label information.

It should be noted that, because the sign information of the embodiment of the present application may include various types of information (e.g., body temperature, pulse, blood pressure, and/or heart rate), the embodiment of the present application needs to consider the proportion of the various types of information when influencing the epidemic representation phenomenon of the person in the target object (i.e., regarding the various types of information as the influencing factors and the weight of the influencing factors), and then perform feature extraction on the sign information according to the respective proportion, so that the proposed first feature matrix can reflect the respective proportion (i.e., the weight) of the information, thereby being beneficial to improving the accuracy of the score information obtained by the preset classification model for each label type, and subsequently ensuring that the accuracy of the prediction analysis, prevention and control, and management on the overall epidemic situation of the first region can be higher.

It should be further noted that the first feature matrix is input into a pre-trained preset classification model to obtain score information for each label type, which can be understood that the preset classification model scores the physical sign information according to three types of labels, namely a normal label, a suspected label and a confirmed label, and obtains scores (i.e. weights) corresponding to the three types of labels, so that the label corresponding to the highest score is used as the label information of the person in the target object.

Specifically, determining the proportion of each type of information in the physical sign information to obtain the first proportion information may include the following steps: and determining the proportion of various types of information in the physical sign information according to a preset proportion table to obtain first proportion information. The preset proportion table can be obtained through multiple times of big data analysis and statistics.

Illustratively, when the physical sign information includes body temperature information, pulse information, blood pressure information and heart rate information, collecting a large amount of physical sign data corresponding to the persons who have confirmed diagnosis, suspected cases and normal physical signs, analyzing and counting the proportion of the body temperature, the pulse, the blood pressure and the heart rate in the physical sign data respectively when the body temperature, the pulse, the blood pressure and the heart rate influence the representation phenomenon of the plague by using big data, and finally obtaining the preset proportion table shown in table 1. Wherein, the body temperature accounts for the largest proportion when influencing the representation phenomenon of the epidemic diseases, and the proportion reaches 50 percent.

TABLE 1

Type (B)	Body temperature	Pulse rate	Blood pressure	Heart rate
					Ratio (%)	50％	10％	20％	20％

Specifically, the extracting the feature vector of the sign information may include at least one of the following modes: one-hot (one-hot) encoding, term-frequency inverse text frequency (TF-IDF).

Specifically, the preset classification model in the embodiment of the present application may include a CNN model and a classifier. The classifier may include a bayesian classifier (negative bases classifier), a Support Vector Machine (SVM), and the like. In addition, the bayesian classifier may include a naive bayes classifier (negative bayesian classifier), a tree-augmented bayesian classifier (TAN), a bayesian network-augmented bayesian classifier (BAN), a semi-naive bayesian classifier (SNBC), and the like.

An example of the training process of the preset classification model is described below.

In one possible example, the training process of the preset classification model may include the following steps: acquiring a training sample set, wherein the training sample set consists of sign information marked with a normal label corresponding to the sign information, sign information marked with a suspected label corresponding to the sign information and sign information marked with a confirmed label corresponding to the sign information; extracting the feature vectors of the training sample set to obtain a second feature matrix; and training a preset classification model through the second feature matrix.

It should be noted that, in the embodiment of the present application, a training sample set is formed by obtaining sign information corresponding to three types of labels, namely, a normal label, a suspected label, and a confirmed label, so that it is ensured that a preset classification model trained by the training sample set is more accurate.

And S430, determining an epidemic situation network distribution diagram according to the target object, the multi-dimensional information and the label information of each person.

Each node of the epidemic situation network distribution diagram is used for representing one person in the target object; each edge of the epidemic situation analysis network graph is used for indicating that nodes at two ends of each edge meet at least one of preset relations; the weight corresponding to each edge is used for representing the number of the relationship that the nodes at the two ends of each edge simultaneously meet the preset relationship.

It should be noted that, the nodes of the epidemic situation network distribution diagram in the embodiment of the present application and the people in the target object are established with a corresponding relationship, the edges of the epidemic situation network distribution diagram and the preset relationship determined by the multidimensional information and/or the label information establish a relationship, and a correlation relationship is established between the weight corresponding to the edge of the epidemic situation network distribution diagram and the number of the relationship of the edge simultaneously meeting the preset relationship, thereby realizing the determination of the epidemic situation network distribution map according to the target object, the multi-dimensional information and the label information of each person, ensuring that the epidemic situation network distribution map can effectively reflect the incidence relation among the target object, the multi-dimensional information and the label information, therefore, the overall epidemic situation of the first area is predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution map, and the method has higher timeliness, accuracy and efficiency.

It should be further noted that, in the embodiment of the present application, an association relationship is established between the weight corresponding to the edge of the epidemic situation network distribution diagram and the number of relationships that the edge simultaneously satisfies the preset relationship, so that the embodiment of the present application may analyze the closeness of the connection between the nodes at the two ends of the edge (corresponding to the people in the target object) according to the size of the weight corresponding to the edge. If the weight corresponding to the edge is larger, the higher the contact tightness between the nodes at the two ends of the edge is (the more the relation is), namely the edge is a strong link; if the corresponding weight of the edge is smaller, the lower the contact tightness between the nodes at two ends of the edge is (the farther the relationship is), namely the edge is a weak link. Therefore, the embodiment of the application has higher accuracy and efficiency when the epidemic situation of the first area is subjected to prediction analysis, prevention and control and management through the strong link or the weak link of each edge in the epidemic situation network distribution diagram.

Illustratively, the server obtains multidimensional data for the target objects within the region H. The target object comprises 3 persons, namely a person A, a person B, a person C and a person D, and the multidimensional data comprise face information, social account information, a mobile phone number, a phone book, body temperature information, residence information, travel information and the like of the 4 persons. Secondly, the server determines the label information of the 4 persons according to the body temperature information. Wherein, the label information of the personnel A is a suspected label, and the rest personnel are normal labels. And thirdly, the server determines the epidemic situation network distribution diagram according to the 4 persons, the multi-dimensional information and the label information of the 4 persons. The epidemic situation network distribution graph is composed of a node A (corresponding to a person A), a node B (corresponding to a person B), a node C (corresponding to a person C) and a node D (corresponding to a person D), the weight corresponding to the edge between the node A and the node B is 4, the weight corresponding to the edge between the node A and the node C is 1, and the weight corresponding to the edge between the node A and the node D is 1. Because the edge between node a and node B corresponds to the highest weight, the relationship between person a and person B is the closest. Finally, when the server carries out positioning tracking on the person A suspected to be ill through the epidemic situation network distribution diagram, the server can preferentially carry out troubleshooting on the person B at the first time, and therefore higher accuracy and efficiency are achieved when prediction analysis, prevention control and management are carried out on the region H.

Specifically, the preset relationship may include a friend relationship determined by the identity information, a relative relationship determined by the identity information, the same tag relationship determined by the tag information of each person, the same residential place relationship determined by the residence information, and the same travel track relationship determined by the travel information.

It should be noted that, for the friend relationship determined by the identity information, it may be understood that the server may determine whether a friend relationship exists between people in the target object according to chat data, name notes, and the like in the social account information included in the identity information, and may also determine whether a friend relationship exists between people in the target object according to a mobile phone number, a phone book, and the like in the communication information included in the identity information. Similarly, for the relationship determined by the identity information, it can be understood that the server may determine whether the relationship exists between the persons in the target object according to chat data or name notes and the like in the social account information included in the identity information, and may also determine whether the relationship exists between the persons in the target object according to a mobile phone number or a phone book and the like in the communication information included in the identity information.

In addition, with respect to the same tag relationship determined by the tag information of each person, it is understood that the server may determine whether the same tag exists between the persons in the target object according to the tag information of each person. Similarly, for the same place relationship determined by the residence information, it is understood that the server may determine whether the same place of residence exists among the persons in the target object from the residence information. Wherein the same residence may be the same cell, the same floor, the same street, etc. Similarly, for the same travel track relationship determined by the travel information, it can be understood that the server may determine whether the same travel track exists between the persons in the target object according to the travel information.

Therefore, the preset relationship is determined according to the identity information, the label information of each person, the residence information and/or the travel information, so that each side in the epidemic situation network distribution diagram is constructed according to various relationships in the preset relationship, and the weight corresponding to each side in the epidemic situation network distribution diagram is constructed according to the number of the relationships in the preset relationship.

In the following, an example of how the server determines the epidemic situation network distribution map according to the target object, the multidimensional information, and the label information of each person will be described in the embodiments of the present application.

In one possible example, the determining the epidemic network distribution map according to the target object, the multidimensional information and the tag information of each person may include the following steps: acquiring N nodes, wherein each node in the N nodes corresponds to one person in the target object, and N is equal to the number of all the persons in the target object; connecting two nodes meeting at least one relation in the preset relations in the N nodes to obtain M edges, wherein M is a positive integer; taking the number of the M edges which simultaneously satisfy the relationship in the preset relationship as the weight corresponding to each edge in the M edges; and constructing an epidemic situation network distribution diagram through the N nodes, the M edges and the weight corresponding to each edge in the M edges.

It should be noted that, in the epidemic situation network distribution diagram of the embodiment of the present application, a correspondence relationship is established between N nodes and all people in the target object, a relationship is established between the M edges in the epidemic situation network distribution diagram and at least one of the preset relationships, and a relational relationship is established between the weight corresponding to the M edges in the epidemic situation network distribution diagram and the number of the relationship of the edges simultaneously meeting the preset relationship, thereby realizing the determination of the epidemic situation network distribution map according to the target object, the multidimensional information and the label information of each person, ensuring that the epidemic situation network distribution map can effectively reflect the incidence relation among the target object, the multidimensional information and the label information, therefore, the overall epidemic situation of the first area can be predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution map, and higher timeliness, accuracy and efficiency can be achieved.

Specifically, in the embodiment of the present application, the epidemic situation network distribution diagram is regarded as an undirected graph, and therefore the definition of the wireless graph constructed according to the target object, the multidimensional data, and the lability of each person is as follows:

the undirected graph is defined as G (V, E, W). Wherein V ═ { V ═ V₁,v₂,...,v_NThe node set is represented and contains N nodes; e ═ E₁,e₂,...,e_MRepresents a set of edges, and the set of edges contains M edges; w ═ W_i,jI, j ∈ V and<i,j>e represents the set of weights corresponding to each edge in the edge set, and the weight w_i,jThe following formula is satisfied:

wherein the parameters

Whether a friend relationship exists between the node i and the node j is represented, and the friend relationship satisfies the following formula:

parameter(s)

Whether the relationship between the node i and the node j exists is represented, and the relationship satisfies the following formula:

parameter(s)

Whether the same label relationship exists between the node i and the node j is represented, and the same label relationship satisfies the following formula:

parameter(s)

Representing whether the same residence relationship exists between the node i and the node j, and the same residence relationship satisfies the following formula:

parameter(s)

Whether the same travel track relationship exists between the node i and the node j is represented, and the same travel track relationship satisfies the following formula:

illustratively, the server obtains multidimensional data for the target objects within the region G. The target object comprises 12 persons, and the multidimensional data comprise face information, social account information, a mobile phone number, a phone book, body temperature information, residence information, travel information and the like of the 12 persons. Secondly, the server determines the label information of the 12 persons according to the body temperature information. Wherein, the label information of the person K in the 12 persons is a suspected label, and the rest persons are normal labels. Thirdly, the server determines the epidemic situation network distribution diagram as shown in fig. 5 according to the 12 persons, the multidimensional information and the tag information of the 12 persons. The epidemic situation network distribution graph is composed of 12 nodes, 22 edges and weights corresponding to the 22 edges, a node 501 of the 12 nodes corresponds to a person K, a node 502 of the 12 nodes corresponds to a person L of the 12 persons, and the rest of the same principles are known. Meanwhile, since a friend relationship, the same residence relationship, and the same travel trajectory relationship exist between the person K and the person L, the weight corresponding to the edge connecting the node 501 and the node 502 is 3. Finally, the server performs positioning tracking on the person K suspected to be ill through the epidemic situation network distribution diagram, and performs troubleshooting and the like on direct contact persons (such as the node 502, the node 503, the node 504, the node 505 and the node 506) and indirect contact persons (such as the node 510 associated with the node 502, the node 507 associated with the node 505 and the like) of the person K at the first time, so as to realize prediction analysis, prevention control, management and the like on the epidemic situation of the area G.

It should be noted that, since the epidemic situation network distribution diagram is essentially a network diagram, the embodiment of the present application introduces a community (community) concept in the network diagram. The communities refer to a subgraph composed of a plurality of nodes in a network graph, the nodes in the subgraph have close connection (similar to a complete subgraph), and the connection between every two communities is relatively sparse.

In addition, Modularity (Modularity) can be used to measure whether the partitioning result of a community is good or not, and a good partitioning result is expressed by: the similarity is high between nodes inside the community, and the similarity is low between nodes outside the community. Meanwhile, the modularity is a measurement method for evaluating the network division quality, and the physical meaning is the difference between the number of connected edges between nodes in the community and the number of edges under the random condition. It can be seen that the modularity is a relative index, which has a value range of [ -1/2,1), and is defined as follows:

wherein Q represents modularity; a. the_ijRepresenting the weight corresponding to the edge between the node i and the node j; k is a radical of_i＝∑_jA_ijRepresenting all edges connected to node iThe sum (i.e., degrees) of the corresponding weights; c. C_iRepresenting the community to which the node i belongs; c. C_jRepresenting the community to which the node j belongs;

representing the sum of the weights of all edges (i.e., the number of edges).

The following embodiment of the present application further introduces how to update and optimize each community in the epidemic situation network distribution diagram to ensure that the epidemic situation network distribution diagram has higher timeliness and accuracy when performing predictive analysis, prevention control and management on the overall epidemic situation of the first region.

In one possible example, after S430, the method further includes the steps of: determining communities to which each node of the epidemic situation network distribution diagram belongs according to the magnitude relation between the weights corresponding to all edges connected with the same node in the epidemic situation network distribution diagram to obtain P communities, wherein P is a positive integer larger than 1; acquiring target nodes from all nodes of an epidemic situation network distribution map, and acquiring Q communities adjacent to communities to which the target nodes belong from P communities, wherein Q is smaller than P; calculating the modularity of the target node sequentially distributed to each of the Q communities to obtain Q modularity variables, wherein the modularity variables are used for representing the variable quantity of the modularity of the target node between before and after the target node is distributed; if the maximum value of the Q modularity variables is larger than a preset threshold value, distributing the target node to a community corresponding to the maximum value; or if the maximum value of the Q modularity degree variables is smaller than or equal to a preset threshold value, the target node is not distributed to the community corresponding to the maximum value.

It should be noted that, in the epidemic situation network distribution diagram in the embodiment of the present application, there are different situations between the weights corresponding to all the edges connected to the same node. Meanwhile, if the weight corresponding to the edge is larger, the higher the contact tightness between the nodes at the two ends of the edge is, that is, the edge is a strong link; if the weight corresponding to the edge is smaller, the lower the contact tightness between the nodes at the two ends of the edge is, that is, the edge is a weak link. Based on this, the embodiment of the application considers that the communities to which each node of the epidemic situation network distribution diagram belongs are divided according to the magnitude relation among the weights corresponding to all the edges connected with the same node in the epidemic situation network distribution diagram, that is, which nodes belong to the same community.

Secondly, the modularity variable is used to represent a variable amount of the modularity between the target node before and after the target node is allocated, and may be understood as a variable amount between the modularity corresponding to the community to which the target node belongs before and after the target node is allocated. Wherein, the modularity variable satisfies the following formula:

wherein m represents the sum of the weights corresponding to each edge of the epidemic situation network distribution diagram; k₁Representing the sum of weights corresponding to edges between a target node and all nodes in a first community, wherein the first community is a community to be allocated to the target node in all communities adjacent to the community to which the target node belongs; k₂Representing a sum of all weights corresponding to edges connected to each node within the first community; k is₃Representing the sum of the weights corresponding to all edges connected to the target node.

And finally, determining whether the target node is distributed to the community corresponding to the maximum value or not by judging the relation between the maximum value in the Q modularity variables and a preset threshold value, thereby updating and optimizing each community in the epidemic situation network distribution diagram, ensuring that the epidemic situation network distribution diagram reflects the incidence relation among the target object, the multi-dimensional information and the label information in real time, and ensuring that the overall epidemic situation in the first area is predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution diagram to have higher timeliness and accuracy.

The above embodiment is exemplified below with reference to fig. 6.

Illustratively, in fig. 6, first, the epidemic situation network distribution graph includes 8 nodes, 12 edges and weights corresponding to the 12 edges. Wherein, in the epidemic situation network distribution diagram, there are two edges connected with the node 601, that is, the node 601 and the nodeEdges between 602, edges between

nodes

601 and 603. Since the difference between the weights corresponding to the two edges is small (for example, the difference is 1), the node 601, the node 602, and the node 603 may belong to the same community. Similarly, there are three edges connecting to node 603, namely the edge between node 603 and node 601, the edge between node 603 and node 602, and the edge between node 603 and node 605. Because the difference between the weights corresponding to the edge between the node 603 and the node 605 and the other two edges is large (for example, the difference is more than 2), the node 605 and the node 603 do not belong to the same community. By analogy, the node 601, the node 602, and the node 603 belong to the same community (i.e., community a), the node 604, the node 605, and the node 606 belong to the same community (i.e., community B), and the node 607 and the node 608 belong to the same community (i.e., community C). Second, the node 602 (i.e., the target node) is obtained from all the nodes of the epidemic situation network distribution graph, and two communities (i.e., community B and community C) adjacent to the community (i.e., community a) to which the node 602 belongs are obtained. Third, the modularity of the node 602 to be assigned to community B is computed to obtain a modularity variable Δ Q₁：

Similarly, the modularity of the node 602 to be assigned to community C is calculated to obtain a modularity variable Δ Q₂：

Finally, due to Δ Q₂Is maximum and the preset threshold is 0.03. Therefore, the target node is distributed to the equipment C, and the epidemic situation network distribution diagram is optimized.

In one possible example, after S430, the method further includes the steps of: and optimizing the epidemic situation network distribution diagram by a community discovery algorithm based on modularity.

It should be noted that the community discovery algorithm based on modularity aims to maximize the modularity. The community discovery algorithm based on modularity considered in the embodiments of the present application includes a fast modularity maximum algorithm (Louvain algorithm). The Louvain algorithm is better in efficiency and effect, a hierarchical community structure can be found, and the optimization aim is to maximize the modularity of the whole network.

Therefore, the embodiment of the application considers that each community in the epidemic situation network distribution map is updated and optimized through the community discovery algorithm based on the modularity degree, the incidence relation among the target object, the multi-dimensional information and the label information is guaranteed to be reflected by the epidemic situation network distribution map in real time, and the overall epidemic situation of the first area is predicted, analyzed, prevented, controlled and managed through the epidemic situation network distribution map, and timeliness and accuracy are high.

S440, performing prediction analysis, prevention control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

It should be noted that, the performing, predicting, analyzing, controlling and managing the epidemic situation of the first area through the epidemic situation network distribution map may include at least one of the following: the method comprises the steps of utilizing the epidemic situation network distribution diagram to carry out positioning tracking on people with confirmed or suspected cases in a first area, utilizing the epidemic situation network distribution diagram to carry out timely investigation on target people contacted with the people with confirmed or suspected cases in the first area, utilizing the epidemic situation network distribution diagram to carry out reverse tracing on an infection source in the first area, and utilizing the epidemic situation network distribution diagram to carry out prediction and evaluation on epidemic situation risk levels in the first area.

It can be seen that in the embodiment of the application, the label information of each person in the target object is determined by acquiring the multi-dimensional information of the target object in the first region and according to the sign information in the multi-dimensional information; then, determining an epidemic situation network distribution diagram according to the target object, the multi-dimensional information and the label information of each person; finally, the epidemic situation of the first area is subjected to prediction analysis processing through the epidemic situation network distribution diagram. Because a corresponding relation is established between the nodes of the epidemic situation network distribution diagram and the personnel in the target object, a relevant relation is established between the edges of the epidemic situation network distribution diagram and a preset relation determined by the multidimensional information and/or the label information, and a relevant relation is established between the weight corresponding to the edges of the epidemic situation network distribution diagram and the number of the edges meeting the relation in the preset relation at the same time, the epidemic situation network distribution diagram is determined according to the target object, the multidimensional information and the label information of each personnel, the incidence relation among the target object, the multidimensional information and the label information can be effectively reflected by the epidemic situation network distribution diagram, and the overall epidemic situation of the first area is predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution diagram, so that higher timeliness, accuracy and efficiency are achieved.

The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It is understood that the server includes hardware structures and/or software modules for performing the respective functions in order to implement the above-described functions. Those of skill in the art will readily appreciate that the present application is capable of hardware or a combination of hardware and computer software implementing the various illustrative elements and algorithm steps described in connection with the embodiments provided herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the server may be divided into the functional modules according to the above method example, for example, each functional module may be divided corresponding to each function, or two or more functional modules may be integrated into one processing unit. Wherein the processing unit may be a processor or controller, such as a CPU, general purpose processor, DSP, ASIC, FPGA, transistor logic, hardware component, or any combination thereof. Or a combination of both implementing computing functionality, e.g., a combination of one or more microprocessors, DSPs, and microprocessors, such that the processing unit may implement or execute the various illustrative logical blocks, modules, and circuits described in connection with the above description. In addition, the processing unit may be configured to perform any one of the steps performed by the server in the above method embodiments, and when performing data transmission such as sending, optionally call a communication unit to complete the corresponding operation, where the communication unit may be a communication interface, a transceiver circuit, and the like.

Furthermore, the integrated functional module may be implemented in a form of hardware or software. It should be noted that the division of the units in the embodiment of the present application is illustrative, and is only one division of the logic functions, and there may be another division in actual implementation.

In the case of using the integrated function module, fig. 7 shows a block diagram of the function module composition of a regional epidemic situation information processing device. The regional epidemic situation information processing device 700 is applied to a server, and specifically comprises: an information acquisition module 710, an information processing module 720, a network construction module 730, and an analysis prediction module 740.

Wherein,

an obtaining information module 710, configured to obtain multidimensional information of the target object in the first area, where the multidimensional information includes at least one of: identity information, physical sign information, residence information and travel information;

the information processing module 720 is configured to determine, according to the sign information in the multidimensional information, tag information of each person in the target object, where the tag information is used to indicate whether a person in the target object has an epidemic representation phenomenon;

the network construction module 730 is used for determining an epidemic situation network distribution map according to the target object, the multi-dimensional information and the label information of each person; each node in the epidemic situation network distribution diagram is used for representing one person in the target object; each edge in the epidemic situation analysis network diagram is used for indicating that nodes at two ends of each edge meet at least one of preset relations, and the preset relations are determined by multi-dimensional information and/or label information of each person; the weight corresponding to each edge is used for representing the relation quantity of each edge which simultaneously meets the preset relation;

and the analysis and prediction module 740 is used for performing prediction analysis, prevention control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

It should be noted that, for specific implementation of each operation executed by each module in the regional epidemic situation information processing apparatus 700, reference may be made to the corresponding description of the method embodiment shown in fig. 4, and details are not described here again.

It can be seen that in the embodiment of the application, the label information of each person in the target object is determined by acquiring the multi-dimensional information of the target object in the first region and according to the sign information in the multi-dimensional information; then, determining an epidemic situation network distribution map according to the target object, the multi-dimensional information and the label information of each person; finally, the epidemic situation of the first area is subjected to prediction analysis processing through the epidemic situation network distribution diagram. Because a corresponding relation is established between the nodes of the epidemic situation network distribution diagram and the personnel in the target object, a relevant relation is established between the edges of the epidemic situation network distribution diagram and the preset relation determined by the multidimensional information and/or the label information, and a relevant relation is established between the weight corresponding to the edges of the epidemic situation network distribution diagram and the number of the edges meeting the relation in the preset relation at the same time, the epidemic situation network distribution diagram is determined according to the target object, the multidimensional information and the label information of each personnel, the incidence relation among the target object, the multidimensional information and the label information can be effectively reflected by the epidemic situation network distribution diagram, and the overall epidemic situation of the first area is predicted, analyzed, prevented, controlled and managed by the epidemic situation network distribution diagram, so that higher timeliness, accuracy and efficiency are achieved.

In one possible example, the preset relationship includes a friend relationship determined by the identity information, a relative relationship determined by the identity information, the same tag relationship determined by the tag information of each person, the same place of residence relationship determined by the residence information, and the same travel trajectory relationship determined by the travel information.

In one possible example, in determining the epidemic network distribution map according to the target object, the multidimensional information, and the tag information of each person, the network construction module 730 is specifically configured to: acquiring N nodes, wherein each node in the N nodes corresponds to one person in the target object, and N is equal to the number of all the persons in the target object; connecting two nodes meeting at least one relation in the preset relations in the N nodes to obtain M edges, wherein M is a positive integer; taking the number of the M edges which simultaneously satisfy the relationship in the preset relationship as the weight corresponding to each edge in the M edges; and constructing an epidemic situation network distribution diagram through the N nodes, the M edges and the weight corresponding to each edge in the M edges.

In one possible example, the tag types of the tag information include a normal tag, a suspected tag, and a confirmed tag; the normal label is used for indicating that the person in the target object does not have the epidemic disease characterization phenomenon, the suspected label is used for indicating that the person in the target object is suspected to have the epidemic disease characterization phenomenon, and the confirmed label is used for indicating that the person in the target object has the epidemic disease characterization phenomenon.

In one possible example, in determining the tag information of each person in the target object according to the sign information in the multi-dimensional information, the information processing module 720 is specifically configured to: determining the proportion of various types of information in the physical sign information to obtain first proportion information; extracting a feature vector of the sign information according to the first proportion information to obtain a first feature matrix; inputting the first characteristic matrix into a pre-trained preset classification model to obtain score information aiming at each label type; and taking the label corresponding to the highest score in the score information as label information.

In one possible example, the training process of the preset classification model includes the following steps: acquiring a training sample set, wherein the training sample set consists of sign information marked with a normal label corresponding to the sign information, sign information marked with a suspected label corresponding to the sign information and sign information marked with a confirmed label corresponding to the sign information; extracting the feature vectors of the training sample set to obtain a second feature matrix; and training a preset classification model through the second feature matrix.

In one possible example, after determining the epidemic network distribution map according to the target object, the multidimensional information and the label information of each person, the device further comprises a network optimization module; the network optimization module is used for determining communities to which each node of the epidemic situation network distribution diagram belongs according to the magnitude relation among the weights corresponding to all edges connected with the same node in the epidemic situation network distribution diagram so as to obtain P communities, wherein P is a positive integer larger than 1; acquiring a target node from all nodes of an epidemic situation network distribution diagram, and acquiring Q communities adjacent to the community to which the target node belongs from P communities, wherein Q is smaller than P; calculating the modularity of the target node to be sequentially distributed to each of the Q communities to obtain Q modularity variables, wherein the modularity variables are used for representing the variable quantity of the modularity of the target node between before and after distribution; if the maximum value of the Q modularity variables is larger than a preset threshold value, distributing the target node to a community corresponding to the maximum value; or if the maximum value of the Q modularity degree variables is smaller than or equal to a preset threshold value, the target node is not distributed to the community corresponding to the maximum value.

A schematic structural diagram of another server provided in the embodiment of the present application is described below, as shown in fig. 7. The server 800 includes a processor 810, a memory 820, a communication interface 830, and at least one communication bus connecting the processor 810, the memory 820, and the communication interface 830.

The processor 810 may be one or more central processing units CPU. In the case where the processor 810 is a CPU, the CPU may be a single core CPU or a multi-core CPU. The Memory 820 includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), or a portable Read-Only Memory (CD-ROM), and the Memory 820 is used for related instructions and data. Communication interface 830 is used for receiving and transmitting data.

The processor 810 in the server 800 is configured to read one or more programs 821 stored in the memory 820 for performing the following steps: acquiring multi-dimensional information of a target object in a first area, wherein the multi-dimensional information comprises at least one of the following: identity information, physical sign information, residence information and travel information; determining label information of each person in the target object according to the sign information in the multi-dimensional information, wherein the label information is used for indicating whether the person in the target object has an epidemic representation phenomenon or not; determining an epidemic situation network distribution diagram according to the target object, the multi-dimensional information and the label information of each person; each node of the epidemic situation network distribution diagram is used for representing one person in the target object; each edge of the epidemic situation analysis network diagram is used for indicating that nodes at two ends of each edge meet at least one of preset relations, and the preset relations are determined by multi-dimensional information and/or label information of each person; the weight corresponding to each edge is used for representing the number of the nodes at the two ends of each edge which simultaneously meet the relationship in the preset relationship; and carrying out predictive analysis, prevention and control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

It should be noted that, for specific implementation of each operation performed by the server 800, reference may be made to the corresponding description of the method embodiment shown in fig. 4, and details are not described here again.

Embodiments of the present application also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, the computer program being operable to cause a computer to perform part or all of the steps of any of the methods as set forth in the above method embodiments.

Embodiments of the present application also provide a computer program product, where the computer program product includes a computer program operable to cause a computer to perform part or all of the steps of any one of the methods as described in the above method embodiments. The computer program product may be a software installation package.

For simplicity of description, each of the above method embodiments is described as a series of combinations of operations. It will be appreciated by those of skill in the art that the present application is not limited by the order of acts described, as some steps in the embodiments of the present application may occur in other orders or concurrently. Moreover, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that acts and modules referred to are not necessarily required to implement the embodiments of the application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood by those skilled in the art that the described apparatus can be implemented in other ways. It will be appreciated that the above described apparatus embodiments are merely illustrative. For example, the division of the modules is only one logical function division, and actually, there may be another division manner. That is, multiple modules or components may be combined or integrated into another software, and some features may be omitted or not implemented. In addition, the shown or discussed mutual coupling, direct coupling or communication connection and the like can be an indirect coupling or communication connection through some interfaces, devices, modules or units, and can also be an electric or other form.

The above modules or units, if implemented in the form of software functions and sold or used as independent products, may be stored in a computer-readable storage medium. It will be appreciated that the solution of the present application (which form a part of or all or part of the prior art) may be embodied in the form of a computer software product. The computer software product is stored in a memory and includes several instructions for causing a computer device (personal computer, server, network device, etc.) to perform all or part of the steps of the embodiments of the present application. The computer-readable storage medium may be stored in various memories such as a usb disk, a ROM, a RAM, a removable hard disk, a magnetic disk, or an optical disk.

While the embodiments of the present application have been described in detail, it should be understood by those skilled in the art that the embodiments of the present application are only used for assisting understanding of the core concept of the technical solutions of the present application, and therefore, the embodiments of the present application may be changed in terms of the specific implementation and the application scope. The contents described in the present specification should not be construed as limiting the scope of the present application. In addition, any modification, equivalent replacement, improvement and the like made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A regional epidemic situation information processing method is characterized by comprising the following steps:

determining an epidemic situation network distribution diagram according to the target object, the multidimensional information and the label information of each person; wherein each node of the epidemic network distribution map is used for representing one person in the target object; each edge of the epidemic situation analysis network graph is used for indicating that nodes at two ends of each edge meet at least one relation in a preset relation, and the preset relation is determined by the multi-dimensional information and/or the label information of each person; the weight corresponding to each edge is used for representing that the nodes at the two ends of each edge simultaneously meet the relationship number in the preset relationship;

and carrying out predictive analysis, prevention and control and management on the epidemic situation of the first area through the epidemic network distribution map.

2. The method of claim 1, wherein said determining an epidemic network profile based on said target object, said multidimensional information, and said tag information for each individual comprises:

acquiring N nodes, wherein each node in the N nodes corresponds to one person in the target object, and N is equal to the number of all persons in the target object;

connecting two nodes which meet at least one of the preset relations in the N nodes to obtain M edges, wherein M is a positive integer;

taking the number of the M edges which simultaneously satisfy the relationship in the preset relationship as the weight corresponding to each edge in the M edges;

and constructing the epidemic situation network distribution map according to the weight corresponding to the N nodes, the M edges and each edge in the M edges.

3. The method of claim 1, wherein the tag types of the tag information include a normal tag, a suspected tag, and a confirmed tag; the normal label is used for indicating that the person in the target object does not have the disease characterization phenomenon, the suspected label is used for indicating that the person in the target object is suspected to have the disease characterization phenomenon, and the confirmed label is used for indicating that the person in the target object has the disease characterization phenomenon.

4. The method of claim 3, wherein determining label information for each person in the target subject from the vital sign information in the multi-dimensional information comprises:

determining the proportion of various types of information in the physical sign information to obtain first proportion information;

extracting a feature vector of the sign information according to the first proportion information to obtain a first feature matrix;

inputting the first characteristic matrix into a pre-trained preset classification model to obtain score information aiming at each label type;

and taking the label corresponding to the highest score in the score information as the label information.

5. The method according to claim 4, wherein the training process of the preset classification model comprises the following steps:

acquiring a training sample set, wherein the training sample set consists of the sign information marked with the normal label corresponding to the normal label, the sign information marked with the suspected label corresponding to the suspected label and the sign information marked with the confirmed label corresponding to the confirmed label;

extracting a feature vector of the training sample set to obtain a second feature matrix;

and training the preset classification model through the second feature matrix.

6. The method of claim 1, wherein the preset relationships include a friend relationship determined by the identity information, a relative relationship determined by the identity information, a same tag relationship determined by tag information of each person, a same place of residence relationship determined by the place of residence information, and a same travel trajectory relationship determined by the travel information.

7. The method according to any one of claims 1 to 6, wherein after said determining an epidemic situation network profile from said target object, said multidimensional information and said tag information for each person, said method further comprises:

determining communities to which each node of the epidemic situation network distribution diagram belongs according to the size relation between the weights corresponding to all edges connected with the same node in the epidemic situation network distribution diagram to obtain P communities, wherein P is a positive integer larger than 1;

acquiring target nodes from all nodes of the epidemic situation network distribution diagram, and acquiring Q communities adjacent to the community to which the target nodes belong from the P communities, wherein Q is smaller than P;

calculating the modularity of the target node to be sequentially distributed to each of the Q communities to obtain Q modularity variables, wherein the modularity variables are used for representing the variable quantity of the modularity of the target node between before and after distribution;

if the maximum value of the Q modularity degree variables is larger than a preset threshold value, distributing the target node to a community corresponding to the maximum value; or,

if the maximum value of the Q modularity degree variables is smaller than or equal to the preset threshold value, the target node is not distributed to the community corresponding to the maximum value.

8. A regional epidemic situation information processing device is characterized by comprising:

the network construction module is used for determining an epidemic situation network distribution map according to the target object, the multidimensional information and the label information of each person; wherein each node in the epidemic network distribution map is used for representing one person in the target object; each edge of the epidemic situation analysis network graph is used for indicating that nodes at two ends of each edge meet at least one relation in preset relations, and the preset relations are determined by the multi-dimensional information and/or the label information of each person; the weight corresponding to each edge is used for representing that the nodes at the two ends of each edge simultaneously meet the relationship number in the preset relationship;

and the analysis and prediction module is used for carrying out prediction analysis, prevention and control and management on the epidemic situation of the first area through the epidemic situation network distribution map.

9. The system for processing the regional epidemic situation information is characterized by comprising a server and electronic equipment, wherein the server is in communication connection with the electronic equipment; the server is configured to perform the method of any of claims 1-7; the electronic equipment is used for acquiring multi-dimensional information of a target object in a first area and sending the multi-dimensional information to the server.

10. A computer-readable storage medium, characterized in that it stores a computer program for electronic data exchange, wherein the computer program causes a computer to perform the method according to any one of claims 1-7.