Information processing device, estimation method, program, storage medium, and health management support system.

An image analysis system identifies individuals at risk of infection by detecting close contact and specific behaviors, facilitating early intervention to prevent disease spread.

JP7577503B2Active Publication Date: 2024-11-05CANON KK
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
JP2020172665
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2020-10-13
Publication Date
2024-11-05
Estimated Expiration
2040-10-13

AI Technical Summary

Technical Problem

It is difficult to identify and prepare for potential infections from individuals who are infected but asymptomatic, leading to challenges in blocking the infection route and preventing the spread of infectious diseases.

Method used

An information processing system that analyzes captured images to identify individuals at risk of infection by detecting close contact and specific behaviors, such as shouting without masks, using imaging devices and risk determination algorithms.

Benefits of technology

Enables early identification of infection risks and reduces the spread of infectious diseases by allowing proactive measures to be taken before symptoms appear.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007577503000001
    Figure 0007577503000001
  • Figure 0007577503000002
    Figure 0007577503000002
  • Figure 0007577503000003
    Figure 0007577503000003
Patent Text Reader

Abstract

To grasp the risk of being infected with an infectious disease to reduce the spread of infection.SOLUTION: An information processing apparatus estimates a person having the risk of being infected with an infectious disease. The information processing apparatus has: acquisition means that acquires a picked-up image photographed by an imaging apparatus that photographs a predetermined area; and estimation means that performs at least one of first estimation processing of extracting image data of a person or a thing having been in contact with an infected person from the picked-up image and estimating a person having the risk of infection by using a result of extraction, and second estimation processing of extracting image data of a person from the picked-up image and estimating a person having the risk of infection based on the motion or the state of the person.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device, an estimation method, a program, a storage medium, and a health management support system for estimating an infection risk holder. [Background technology]

[0002] Every year, there are not a few outbreaks of infectious gastroenteritis and influenza in facilities where people live together. General infections often occur when three elements are present: the source of infection (infected people or animals, and their excrement and environment), the route of infection (pathway), and susceptibility to infection (especially people with weak resistance, the elderly, infants, etc.). Therefore, measures such as removing the source of infection, blocking the route of infection, and improving people's resistance (nutrition, rest, vaccinations, etc.) are effective. Specific examples include hand washing and disinfection, wearing masks and aprons, and regular sterilization of toys. However, it is difficult to prevent infection with the above measures. In such cases, it is necessary to take measures such as removing the source of infection as soon as possible and blocking the route of infection. As an effective technology for this, a technology has been disclosed that uses vital sensors and the like to accurately monitor a large number of people at once and determine their health condition (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-103178 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, for people who are infected but have not yet developed symptoms (latent carriers), they and their families cannot know that they are infected, and therefore cannot adequately prepare for when symptoms appear. This makes it difficult to take measures such as blocking the route of infection from potential carriers or procuring cold medicines in advance.

[0005] The present invention aims to grasp the risk of infection of an infectious disease and reduce the spread of infection. [Means for solving the problem]

[0006] In order to solve the above problem, the present invention provides an image capturing device that captures an image of a predetermined area, an extracting device that extracts image data of an image including a contact person who has come into contact with an infected person from image data of the image captured by the acquiring device that includes an infected person, and Output from Will be The captured image A means for identifying a person who is at risk of infection with an infectious disease based on image data, From the image data of the captured image including the contact person who has come into contact with the infected person, extracting image data that indicates that the infected person is shouting based on information about the shape of the infected person's mouth; It was determined that the infected person was shouting From the image data, image data of a captured image in which the distance between the mouths of the infected person and the contact person who are facing each other is within a specified range is extracted, except when the contact person is wearing a mask. and, except when the contact person is wearing a mask, outputting image data of a captured image in which the distance between the mouths of the infected person and the contact person facing each other is within a specified range to the identification means, and the identification means identifies the contact person included in the image data of a captured image in which the distance between the mouths of the infected person and the contact person facing each other is within a specified range as a person at risk of infection with an infectious disease. The present invention is characterized by the above. Effect of the Invention

[0007] According to the present invention, it is possible to grasp the risk of infection of an infectious disease and reduce the spread of infection. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an overall configuration of a physical condition management support system according to a first embodiment. [Diagram 2] FIG. 2 is a block diagram showing a configuration of an estimation unit according to the first embodiment. [Diagram 3] FIG. 13 is a diagram illustrating an example of table data indicating indexes used for selecting an estimation process. [Figure 4] FIG. 2 is a hardware configuration diagram of an estimation unit. [Diagram 5]4 is a flowchart showing the flow of operations of the physical condition management support system. [Figure 6] FIG. 2 is a block diagram showing an estimation processing unit and its peripheral configuration according to the first embodiment. [Figure 7] FIG. 2 is a diagram illustrating a configuration of a storage unit according to the first embodiment. [Figure 8] FIG. 4 is a block diagram showing a configuration of a second extracted data storage unit according to the first embodiment. [Figure 9] 10 is a flowchart showing an example of the flow of an estimation process according to the first embodiment. [Figure 10] 10 is a flowchart showing an example of the flow of an estimation process according to the first embodiment. [Figure 11] FIG. 11 is a block diagram showing an estimation processing unit and its peripheral configuration according to a second embodiment. [Figure 12] 13 is a flowchart showing an example of the flow of an estimation process according to the second embodiment. [Figure 13] FIG. 11 is a block diagram showing an estimation processing unit and its peripheral configuration according to a third embodiment. [Figure 14] 13 is a flowchart showing an example of the flow of an estimation process according to a third embodiment. [Figure 15] FIG. 13 is a block diagram showing an estimation processing unit and its peripheral configuration according to a fourth embodiment. [Figure 16] FIG. 13 is a block diagram showing an estimation processing unit and its peripheral configuration according to a fifth embodiment. [Figure 17] FIG. 13 is a diagram illustrating an example of a score table stored in a judgment index storage unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the drawings, parts having the same functions are given the same numbers, and repeated explanations are omitted. Note that the configurations shown in the following embodiments are merely examples, and the present invention is not limited to the configurations shown in the drawings.

[0010] <First embodiment> 1 is a block diagram showing the overall configuration of a health management support system 1000 according to a first embodiment. Each block will be briefly described below. Here, as an example, a case where the health management support system 1000 is used in a childcare facility will be described.

[0011] The health condition management support system 1000 includes an estimation system 101, a management terminal 106, and a user terminal 107. The estimation system 101 and the management terminal 106 are connected, for example, via a network. Also, the management terminal 106 and the user terminal 107 are connected, for example, via a network. The network may use wireless communication such as WiFi, or may be a network form using a wired LAN. Note that the user terminal 107 and the estimation system 101 may be connected, and the estimation system 101, the management terminal 106, and the user terminal 107 may be capable of communicating with each other.

[0012] The management terminal 106 is a terminal owned by an administrator who operates the estimation system 101 and operated by the administrator. The administrator may be, for example, a staff member of the facility. The user terminal 107 is a terminal owned by a user, such as a child attending a childcare facility or a family member, and operated by the user. In this specification, the term "terminal" includes, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, and the like.

[0013] The management terminal 106 receives information on the infected person from the user terminal 107, and transmits (outputs) the information on the infected person to the inference system 101. The information on the infected person includes, for example, the name of the infected person, symptoms, and onset date. At this time, the administrator may receive a call from the user and input the information on the infected person into the management terminal 106, thereby transmitting the information on the infected person to the inference system 101. The management terminal 106 then notifies the user terminal 107 of the result of the inference process (processing result) by the inference system 101. The management terminal 106 may notify all user terminals 107 of the processing result, or may notify only some users, such as users who are estimated to be at risk of infection, of the processing result.

[0014] The estimation system 101 includes a data control unit 102 , an estimation unit 103 , a monitoring unit 104 , and an imaging data storage unit 105 .

[0015] The monitoring unit 104 includes one or more imaging devices. The imaging devices, for example, capture images of a predetermined area (target area) in a childcare facility, and capture images of people and objects located in the target area.

[0016] The data control unit 102 uploads or transmits data (captured images) captured by the monitoring unit 104 to the captured image data storage unit 105. Alternatively, based on a request from the estimation unit 103, the data control unit 102 downloads or receives designated captured image data from the captured image data storage unit 105 and transfers it to the estimation unit 103.

[0017] The imaging data storage unit 105 stores (memorizes) data captured by the monitoring unit 104. The imaging data storage unit 105 can be realized by, for example, a hard disk drive (HDD) or a network attached storage (NAS).

[0018] The estimation unit 103 starts the estimation process using an instruction (input) from the management terminal 106 as a trigger, and notifies (outputs) the processing result to the management terminal 106. Note that, in this embodiment, the processing result is set to be notified to the management terminal 106, but a system configuration may be adopted in which the processing result is notified to a device other than the management terminal 106, such as a user terminal 107, for example.

[0019] Hereinafter, the estimation unit 103 of this embodiment will be specifically described. Fig. 2 is a block diagram showing the configuration of the estimation unit 103 according to the first embodiment. The estimation unit 103 is, for example, an information processing device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a server device, or a cloud computing device. The estimation unit 103 includes a notification unit 201, a selection unit 202, a selection index storage unit 203, a transmission / reception unit 204, an estimation processing unit 205, and a storage unit 206.

[0020] The notification unit 201 receives instructions and information on infected individuals from the management terminal 106 described above, or notifies the management terminal 106 of the processing result.

[0021] The selection unit 202 checks the input information from the notification unit 201, i.e., information on the infected person, and selects an appropriate estimation method in the estimation processing unit 205. In addition, the selection unit 202 selects a period of imaging data to be downloaded from the imaging data storage unit 105 based on the information on the infected person.

[0022] The selection index storage unit 203 stores table data that the selection unit 202 refers to as an index used to select an inference process. FIG. 3 is a diagram showing an example of table data indicating the index used to select an inference process. The table data includes information on at least one infectious disease. The table data includes the name of an infectious disease, and information such as the infection route, the number of days of the incubation period, and the characteristics of symptoms (e.g., coughing, infection through the hands) is linked to the infectious disease name. The selection unit 202 selects the inference process to be performed and the period of imaging data to be downloaded from the imaging data storage unit 105 based on the information on the infected person and the index used to select an inference process.

[0023] The estimation processing unit 205 proceeds with the estimation process in accordance with the estimation method instructed by the selection unit 202, in other words, the estimation process selected by the selection unit 202. Details of the estimation process will be described later. The estimation processing unit 205 also transfers the period of the imaging data selected by the selection unit 202 to the transmission / reception unit 204.

[0024] The transmitting / receiving unit 204 requests the imaging data for the date and time specified by the estimation processing unit 205 from the data control unit 102. Thereafter, the data transferred from the data control unit 102 is stored in the storage unit 206.

[0025] The storage unit 206 not only stores the data transferred from the data control unit 102, but also functions as a working memory used by the estimation processing unit 205.

[0026] 4 is a diagram showing a hardware configuration of the estimation unit 103. The estimation unit 103 may include a storage unit 206, a random access memory (RAM) 21, a read only memory (ROM) 22, a central processing unit (CPU) 23, and a communication unit 24.

[0027] The CPU 23 operates based on a program stored in the ROM 22 or the storage unit 206, and controls each unit of the estimation processing unit 205. The ROM 22 stores a boot program executed by the CPU 23 when the estimation processing unit 205 is started, a program dependent on the hardware of the estimation processing unit 205, and the like. The CPU 23 executes a program loaded on the RAM 21, for example, to realize a flow of the estimation process, etc. The CPU 23 may obtain these programs from another device, for example, via a network, and execute them. The communication unit 24 is used, for example, for communication with an external device via a network.

[0028] The estimation unit 103 may include an input unit 25 such as a keyboard or a mouse, and a display unit 26 such as a display.

[0029] 5 is a flowchart showing the flow of operations of the physical condition management support system 1000. In S601 to S602, the operations of the peripheral blocks before the operation of the estimation unit 103 is started are described. First, in S601, the user terminal 107 transmits a message to the management terminal 106 informing the management terminal 106 that Child A will be absent from the daycare center and that the child is ill. Next, in S602, the management terminal 106 that has received the message transmits information about the infected person, including Child A's name, condition, onset date, etc., to the estimation system 101.

[0030] Thereafter, in S603 to S608, specific operations of the estimation unit 103 are described. In S603, the notification unit 201 receives the transmission data of S602. If the notification unit 201 has successfully received the data (Yes), it transfers the received data, i.e., information on infected individuals, to the selection unit 202. If the notification unit 201 has not successfully received the data in S603 (No), it notifies the management terminal 106 of a resend request flag and starts over from S602.

[0031] In S604, the selection unit 202 checks the received data, selects (decides) the image capture date / time of the image capture data to be downloaded from the image capture data storage unit 105 and the estimation process to be executed, and inputs them to the estimation processing unit 205. When selecting the image capture date / time of the image capture data to be downloaded and the estimation process to be executed, the selection unit 202 refers to the table data stored in the selection index storage unit 203. As described above, the table data includes information such as that shown in FIG. 3, and information such as contact infection, droplet infection, or airborne infection, the number of days of the incubation period, and the characteristics of the symptoms are linked to the symptoms. The selection unit 202 selects the estimation process to be executed based on at least one of the infection route and the characteristics of the symptoms included in the table data, for example. The selection unit 202 also selects the period of the image capture data to be downloaded from the image capture data storage unit 105 based on the incubation period included in the table data.

[0032] In S605, the estimation processing unit 205 instructs the transmission / reception unit 204 to download the imaging data of the specified date and time from the imaging data storage unit 105. In response to the instruction from the estimation processing unit 205, the transmission / reception unit 204 downloads the imaging data via the data control unit 102. In S606, the transmission / reception unit 204 stores the imaging data transferred from the data control unit 102 in the storage unit 206. In S607, the estimation processing unit 205 performs estimation processing in accordance with the estimation processing method instructed by the selection unit 202. Detailed operations of the estimation processing will be described later.

[0033] S608 to S609 describe the operation of the peripheral blocks after the operation of the estimation unit 103. In S608, the result of the estimation process by the estimation processing unit 205 is transmitted to the management terminal. Specifically, the estimation unit 103 notifies the management terminal 106 of the name of the child estimated to be at risk of infection and the degree of risk from the notification unit 201. In S609, the management terminal 106, which has received the notification, notifies the user terminal 107 of the family of the child at risk of infection of that fact. The above is the flow of the operation of the estimation unit 103.

[0034] Next, a specific configuration and detailed operation of the estimation processing unit 205 of the estimation unit 103 will be described. FIG. 6 is a block diagram showing the estimation processing unit 205 and its peripheral configuration according to the first embodiment. The estimation processing unit 205 includes a first extraction unit 301, a second extraction unit 302, a third extraction unit 303, a risk level determination unit 304, and a determination index storage unit 305. FIG. 7 is a diagram showing the configuration of the storage unit 206 according to the first embodiment. The storage unit 206 includes an imaging data storage unit 401, a first extracted data storage unit 402, a second extracted data storage unit 403, and a third extracted data storage unit 404. FIG. 8 is a block diagram showing the configuration of the second extracted data storage unit 403 according to the first embodiment. The second extracted data storage unit 403 includes a person data storage unit 501 and an object data storage unit 502.

[0035] The first extraction unit 301 retrieves the captured image data from the captured image data storage unit 401, and extracts image data showing the infected child A. Next, the first extraction unit 301 writes the extracted image data into the first extracted data storage unit 402 to store it.

[0036] The second extraction unit 302 uses the extraction result of the first extraction unit 301 to extract image data of a first contactor who is a person who has come into contact with an infected person or a contact object who is an object who has come into contact with an infected person. Specifically, the second extraction unit 302 takes out image data including Child A from the first extracted data storage unit 402. Then, the second extraction unit 302 extracts image data showing a child (first contactor) who has come into contact with Child A and an object (contact object), and writes and stores the image data in the second extracted data storage unit 403. Note that, as an example, the second extracted data storage unit 403 in this embodiment has a configuration in which a person data storage unit 501 that stores image data including a contactor and an object data storage unit 502 that stores image data including a contact object are separated.

[0037] The third extraction unit 303 extracts image data of a second contactor who is a person who came into contact with the contact object, using the extraction result of the second extraction unit 302. Specifically, the third extraction unit 303 retrieves image data from the object data storage unit 502, extracts image data of the child (second contactor) who touched the contact object, and writes and stores the image data in the third extracted data storage unit 404.

[0038] The risk level determination unit 304 retrieves image data from the person data storage unit 501 and the third extracted data storage unit 404. Then, the name of the child who has been in contact with Child A, i.e., the first contact, is confirmed, and the number of times that child has been in contact with Child A is counted. The name of the child who has been in contact with the contact object, i.e., the second contact, is confirmed, and the number of times that child has been in contact with the contact object is counted. After that, the risk level determination unit 304 determines whether or not there is an infection risk for the child who has been confirmed to have been in contact, according to the risk determination index stored in the determination index storage unit 305. For example, in a case where the number of contacts of the determination index is set to 5 times, it is assumed that Child B has been in contact with Child A 10 times, and Child C has been in contact with Child A 3 times. In this case, the risk level determination unit 304 determines that Child B, who has been in contact more than 5 times, is at risk of infection, and Child C, who has been in contact less than 5 times, is not at risk of infection. That is, Child B is estimated to be an infection risk holder.

[0039] Note that the risk level determination unit 304 may determine the degree of risk of infection (infection risk) of being infected with an infectious disease, for example, based on the number of contacts, instead of the presence or absence of an infection risk. Specifically, in a case where the number of contacts in the determination index is set to 5 times, if the number of contacts exceeds 5 times, it is determined that the "risk of infection is high." On the other hand, if the number of contacts is 5 times or less, it is determined that the "risk of infection is low." By setting multiple thresholds as the determination index, it is also possible to determine the degree of infection risk in more detail, for example, "high," "medium," or "low."

[0040] 9 is a flowchart showing an example of the flow of the estimation process according to the first embodiment. Each operation (step) shown in this flowchart can be executed by the control of each unit by the CPU 23. First, in S704, the first extraction unit 301 retrieves the imaging data from the imaging data storage unit 401 and extracts image data showing an infected person. Then, the first extraction unit 301 writes the extracted image data into the first extracted data storage unit 402 to store it.

[0041] In S705, the second extraction unit 302 retrieves image data including an infected person from the first extracted data storage unit 402, and extracts image data showing a person (first contact person) and an object (contact object) who have been in contact with the infected person. Then, the second extraction unit 302 writes the extracted image data into the second extracted data storage unit 403 to store it.

[0042] In S706, the third extraction unit 303 retrieves image data including the contacted object from the object data storage unit 502, and extracts image data of the person (second contactor) who touched the contacted object. Then, the third extraction unit 303 writes the extracted image data into the third extracted data storage unit 404 to store it.

[0043] In S707, the risk level determination unit 304 retrieves image data from the person data storage unit 501, and counts the names of people who have come into contact with the infected person, i.e., the first contacts, and the number of times each first contact has come into contact with the infected person. Then, in S708, the risk level determination unit 304 reads out the risk determination index stored in the determination index storage unit 305. Then, the risk level determination unit 304 compares the number of contacts of the risk determination index with the count value of each first contact, and determines whether or not each first contact has an infection risk.

[0044] In S709, the risk level determination unit 304 transmits the processing results for each of the first contacts to the notification unit 201. At this time, it is also possible to transmit only the risk level of the first contact determined to be at risk of infection.

[0045] In this flow, the flow for determining the presence or absence of an infection risk of the first contact has been described, but the same flow can be applied to the second contact. When determining the presence or absence of an infection risk of the second contact, in S707, the risk level determination unit 304 retrieves image data from the third extracted data storage unit 404. Then, it counts the names of the people who have come into contact with the contact object, i.e., the second contacts, and the number of times each second contact has come into contact with the contact object. Next, in S708, the risk level determination unit 304 reads out the risk determination index stored in the determination index storage unit 305. Then, it compares the number of contacts of the risk determination index with the count value of each second contact, and determines the risk level of each second contact.

[0046] In addition, if the first contact and the second contact overlap, the total number of times they have come into contact with the infected person and the number of times they have come into contact with the contact object is compared with the number of contacts in the risk assessment index to determine the level of risk.

[0047] In addition, the weighting of the count value of contact with an infected person and contact with a contact object may be changed. Specifically, for example, in a case where the number of contacts in the judgment index is set to 5 times, the weight of contact with an infected person is set to 1, and the weight of contact with a contact object is set to 0.5. Assume that Child D has come into contact with Child A, who is infected, 3 times, and Child D has come into contact with a contact object 3 times. In this case, the count value of the number of contacts is 4.5 times. Therefore, the risk level judgment unit 304 judges Child D to have no risk of infection. The weighting may be changed according to the contact time.

[0048] Furthermore, the risk assessment index may be dynamically changed by reflecting past performance. This makes it possible to improve the estimation accuracy. The risk assessment index may be different between the first contact and the second contact.

[0049] Furthermore, the risk assessment index does not necessarily have to be the number of contacts. For example, it may be the contact time. FIG. 10 is a flowchart showing an example of the flow of the estimation process according to the first embodiment. As an example, FIG. 10 shows an operation flow when the contact time is set as the risk assessment index. Each operation (step) shown in this flowchart can be executed by the control of each part by the CPU 23. Note that S704 to S706 in FIG. 10 are the same operations as those in FIG. 9, and therefore the explanation will be omitted.

[0050] In S801, the risk level determination unit 304 acquires the time that the first contactor contacted the infected person. The contact time is acquired, for example, by converting it from the number of frames of the imaging data. For example, in the case where 20 frames of the image captured at 5 frames / second are continuously in contact, the contact time is 4 seconds. Note that the calculation of the time may be performed in another manner. In S802, the risk level determination unit 304 reads out the risk determination index stored in the determination index storage unit 305. Then, the risk level determination unit 304 compares the contact time of the risk determination index with the acquired contact time between each first contactor and the infected person, and determines whether or not there is an infection risk for each first contactor. If the contact time of the determination index stored in the determination index storage unit 305 exceeds the contact time, it is determined that there is an infection risk, and if it is less than the contact time, it is determined that there is no infection risk.

[0051] For example, in the case where the contact time of the judgment index is 60 seconds, if Child E contacted Child A for 10 minutes and Child F contacted Child A for 30 seconds, the risk level judgment unit 304 judges Child E to be at risk of infection and Child F to be at no risk of infection. In other words, Child E is estimated to be at risk of infection. As with the number of contacts, the risk judgment index may be dynamically changed to reflect past performance.

[0052] The above is a description of the configuration and operation of the first embodiment. According to this embodiment, it is possible to grasp the risk of infection in advance, and to take measures to prepare for onset of the disease before it occurs. As a result, the spread of the infection can be reduced.

[0053] Second Embodiment When the infection route of the infected person is contact infection or droplet infection, the key point is what gesture, posture, or state the infected person made contact with another person. In the second embodiment, contact is determined only when the infected person made contact with another person with a gesture, posture, or state that may cause infection. By adopting this configuration, it is possible to further reduce the estimation processing load with the same estimation accuracy as the first embodiment. In addition, the capacity of the memory unit 206 used in the estimation process can be reduced.

[0054] The configuration and operation of the second embodiment will be specifically described below. Note that blocks having equivalent functions to those of the first embodiment are denoted by the same reference numerals. FIG. 11 is a block diagram showing an estimation processing unit 205 and its peripheral configuration according to the second embodiment. In the second embodiment, the estimation processing unit 205 includes a first detection unit 901. And the storage unit 206 includes a first detection data storage unit 902.

[0055] The first detection unit 901 detects a predetermined movement of an infected person from the imaging data stored in the storage unit 206, and extracts image data at that time. Then, it writes it to the first detection data storage unit 902. The first detection data storage unit 902 stores the image data extracted by the first detection unit 901.

[0056] FIG. 12 is a flowchart showing an example of the flow of the estimation process according to the second embodiment. In S1001, the first detection unit 901 extracts image data when an infected child (infected person) performs a predetermined action from the imaging data stored in the imaging data storage unit 401, and writes the image data to the first detection data storage unit 902. The predetermined action of the infected person here refers to shouting at other children, putting something in the mouth, etc. The extraction of these predetermined actions is performed by analyzing the image data. For example, the first detection unit 901 judges whether or not there has been contact using information on the direction of the infected person's face or the shape of the infected person's mouth. Specifically, for example, the area of ​​the open mouth of the infected person is calculated from the image data, and if the area is equal to or larger than a predetermined area, it is determined that the infected person is shouting. However, when an infected person is detected wearing a mask, the risk of droplet infection is eliminated, so image data is not extracted even in a scene where the infected person is shouting at other children.

[0057] Next, in S1002, the second extraction unit 302 reads image data including an infected person performing a predetermined action from the first detection data storage unit 902, and extracts image data showing a person (first infected person) who has been in contact with the infected person and an object (contact object) from the image data. The subsequent operations of S706 to S709 are almost the same as those in Fig. 9 of the first embodiment, and therefore will not be described.

[0058] As described above, in the second embodiment, the efficiency of the estimation process can be further improved by extracting image data when an infected child comes into contact with another person while making gestures, taking a posture, or being in a state that can cause infection.

[0059] <Third embodiment> The third embodiment is configured to estimate the gestures, posture, or state of a person who has come into contact with an infected person or a contact object when they came into contact with the infected person or the contact object. By adding this configuration to the configuration of the second embodiment, it becomes possible to perform a more efficient estimation process.

[0060] The configuration and operation of the third embodiment will be described below. Note that blocks having the same functions as those of the first and second embodiments are given the same reference numerals. FIG. 13 is a block diagram showing an estimation processing unit 205 according to the third embodiment and its peripheral configuration. Note that in this figure, some configurations in the storage unit 206 are omitted. In the third embodiment, the estimation processing unit 205 further includes a second detection unit 1101 and a third detection unit 1103. And the storage unit 206 further includes a second detection storage unit 1102 and a third detection storage unit 1104.

[0061] FIG. 14 is a flowchart showing an example of the flow of the estimation process according to the third embodiment. S1201 is almost the same as S704 in FIG. 9 of the first embodiment, so the description will be omitted. S1202 is almost the same as S1001 in FIG. 12 of the second embodiment, but in S1202, the first detection unit 901 takes out image data including an infected person from the first extracted data storage unit 402. Then, image data when the infected person performs a predetermined movement is extracted and written to the first detection data storage unit 902. Note that S1201 may be omitted as in the second embodiment.

[0062] In S1203, the second extraction unit 302 retrieves image data of an infected person performing a predetermined movement from the first detection data storage unit 902, and extracts image data showing a person (first contact person) and an object (contact object) who have been in contact with the infected person. Then, the second extraction unit 302 writes the extracted image data into the second extracted data storage unit 403 to store it.

[0063] In S1204, the second detection unit 1101 detects a predetermined movement of the first contact from the image data of the first contact extracted in S1202, and extracts image data at that time. Then, writes it to the second detection storage unit 1102. The predetermined movement of the first contact here refers to the direction of the face toward the infected person, the hand of the infected person touching the face of the first contact, holding hands with the infected person, etc. It should be noted that the determination of whether it is a predetermined movement is performed by analyzing the image data, as in the second embodiment. That is, using information on the movement of the first contact toward the infected person, it is determined whether or not there has been contact. Specifically, for example, the distance between the mouth of the infected person and the first contact who are facing each other is calculated by image analysis, and if the distance is within a specified range (for example, within 1 m), it is determined that the movement is a predetermined movement. However, when the first contact is wearing a mask (state), there is no risk of droplet infection, so image data is not extracted even in a scene where the face of the first contact is facing the infected person.

[0064] In S1205, the third extraction unit 303 retrieves image data including the contacted object from the object data storage unit 502, and extracts image data of the person (second contactor) who touched the contacted object. Then, the third extraction unit 303 writes the extracted image data into the third extracted data storage unit 404 to store it.

[0065] In S1206, the third detection unit 1103 reads the image data extracted in S1205, detects a predetermined action of the second contactor, and extracts image data at that time. Then, the extracted image data is written to the third detection storage unit 1104. The predetermined action of the second contactor here refers to touching a contact object with a hand, or touching a contact object with a mouth or nose, etc.

[0066] After S1206 is completed, the process proceeds to S707 in Fig. 9 of the first embodiment. The subsequent operations S707 to S709 are almost the same as those in Fig. 9 of the first embodiment, and therefore a description thereof will be omitted.

[0067] As described above, according to this embodiment, the efficiency of the estimation process can be further improved.

[0068] <Fourth embodiment> In the above-mentioned embodiment, the configuration was such that infection from an infected person was estimated, but in the fourth embodiment, a configuration is adopted that can estimate whether or not there is a further secondary infection from a person who is determined to be at risk of infection or to have a high degree of risk of infection in the above-mentioned embodiment. Fig. 15 is a block diagram showing an estimation processing unit 205 and its peripheral configuration according to the fourth embodiment.

[0069] In the fourth embodiment, a feedback means 1301 is provided in addition to the configuration of the first embodiment. In this embodiment, the first extraction unit 301 can transmit a command to the risk level determination unit 304 by the feedback means 1301.

[0070] First, a child who has developed symptoms is set as an infected person, and the estimation process described in the first embodiment is performed. Next, the risk level determination unit 304 uses the feedback means 1301 to set the person who is determined to be at risk of infection as an infected person to the first extraction unit 301. Thereafter, the estimation process described in the first embodiment is performed. This makes it possible to estimate a person with a risk of secondary infection.

[0071] Moreover, by repeating the same process thereafter, it is also possible to infer tertiary infection risk holders, quaternary infection risk holders, etc. The number of times the inference process is repeated is up to the discretion of the user.

[0072] According to this embodiment, it is possible to estimate people who are at risk of secondary or tertiary infection.

[0073] <Fifth embodiment> In the first to fourth embodiments, a configuration is adopted in which children who have had direct / indirect contact with an infected child are extracted and the risk level of the child is estimated. In contrast, the fifth embodiment is a configuration in which the risk level of all children except for the infected child is estimated. This embodiment is particularly effective when a child has developed a disease that is airborne, rather than droplet infection or skin contact infection. The configuration and operation of the fifth embodiment will be described below. Note that the same reference numerals are used to denote blocks that perform the same processes as in the first to fourth embodiments.

[0074] 16 is a block diagram showing the estimation processing unit 205 according to the fifth embodiment and its peripheral configuration. The estimation processing unit 205 according to the fifth embodiment has a person extraction unit 1401. The person extraction unit 1401 extracts image data of a person from the imaging data downloaded from the imaging data storage unit 105. In other words, the person extraction unit 1401 extracts image data of a person who was in a target area captured by the imaging device within a period selected by the selection unit 202.

[0075] First, the selection unit 202 selects to perform estimation processing on all children except for the infected child A, that is, all people included in the captured image, based on the symptoms of the sick child (infected, referred to as child A here) obtained from the notifying unit 201 (not shown). Specifically, when the symptoms are of an airborne type such as measles or chickenpox, the selection unit 202 decides to perform estimation processing on all children. In this embodiment, it is assumed that a child has measles.

[0076] After receiving an instruction from the selection unit 202, the person extraction unit 1401 starts the estimation process for all children except for Child A who is infected. First, imaging data from two days before the onset date is downloaded via the transmission / reception unit 204 (not shown) and stored in the storage unit 206. In this embodiment, since the incubation period of measles is set to two days (see FIG. 3), imaging data from two days before the onset date is downloaded. The period of imaging data to be downloaded is preferably determined according to the incubation period. Information on the incubation period is stored in the selection index storage unit 203.

[0077] Next, the person extraction unit 1401 extracts image data when Child B, the person to be estimated, performs a predetermined motion from the imaging data stored in the storage unit, and stores the image data in the storage unit 206. The predetermined motions here refer to actions such as washing hands, touching the face with hands, wearing a mask, and being fussy. Note that, as in the second and third embodiments, the determination of whether or not the motion is a predetermined motion is performed by analyzing the image data. Next, the risk level determination unit 304 reads out the image data when Child B performs a predetermined motion extracted from the storage unit 206, and calculates the risk level using the score table for each predetermined motion stored in the determination index storage unit 305.

[0078] 17 is a diagram showing an example of a score table stored in the judgment index storage unit 305. In the score table, a score value is set for each predetermined action. The risk level judgment unit 304 calculates the infection risk level by adding or subtracting the score value corresponding to each predetermined action. The risk level judgment unit 304 may transmit the calculated infection risk level to the outside as a processing result for child B, or may judge that child B is an infection risk carrier when the infection risk level exceeds a threshold value and transmit the judgment result to the outside as a processing result.

[0079] When the risk estimation process for Child B is completed, the completion notification means 1403 notifies the person extraction unit 1401 that the estimation process for Child B is complete. Upon receiving the notification, the person extraction unit 1401 starts estimation processing for Child C, who is the next person to be estimated. Subsequent processing is the same as that described above. By repeating the above, risk estimation processing is performed for all children. This concludes the explanation of the configuration and operation of the fifth embodiment.

[0080] According to this embodiment, it is possible to grasp the risk of infection in advance even for infectious diseases that are transmitted through the air, thereby reducing the spread of infection.

[0081] <Other embodiments> Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications are possible within the scope of the gist of the present invention. For example, the estimation process of the first to fifth embodiments may be selected based on the infection route and symptoms of the developed infectious disease.

[0082] In the above embodiment, the physical condition management support system 1000 is used in a childcare facility, but the present invention is not limited to this. The system can also be used in welfare facilities, including elderly care facilities, schools, hospitals, and the like.

[0083] The present invention can also be realized by a process in which a program for realizing one or more functions of the above-mentioned embodiment is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) for realizing one or more functions. Furthermore, it is also possible for the imaging device to execute the functions of the present invention by storing the processing of the present invention in the ROM of the imaging device included in the monitoring unit 104. In this case, the processing of the above-mentioned flowchart by the imaging device is realized by the CPU of the imaging device executing the processing based on the program stored in the ROM. In addition, in this case, the imaging device outputs the processing result to an external device by a communication control unit or the like. [Explanation of symbols]

[0084] 101 Estimation System 103 Estimation part 106 Management terminal 107 User terminal 201 Notification Department 202 Selection section 203 Selection index storage unit 205 Estimation processing unit 301 First Extraction Section 302 Second Extraction Section 303 Third Extraction Section 304 Risk Assessment Department

Claims

1. An acquisition means for acquiring an image captured by an imaging device that captures an image of a predetermined area; An extraction means for extracting image data of an image including a contact person who has come into contact with an infected person from image data of an image including an infected person among the captured images acquired by the acquisition means; and a means for identifying a person at risk of infection with an infectious disease based on image data of the captured image output from the extraction means, The extraction means includes: Extracting image data in which it is determined that the infected person is shouting, based on information about the shape of the infected person's mouth, from image data of a captured image including a contact person who has come into contact with the infected person; From the image data in which it is determined that the infected person is shouting, image data of a captured image in which the distance between the mouths of the infected person and the contact person who are facing each other is within a specified range is extracted, except in cases where the contact person is wearing a mask; outputting, to the identification means, image data of a captured image in which the distance between the mouths of the infected person and the contact person who are facing each other is within a specified range, except when the contact person is wearing a mask; The identification means is An information processing device characterized by identifying a contact person included in image data of an captured image in which the distance between the mouths of the infected person and the contact person who are face-to-face is within a specified range as a person at risk of infection with an infectious disease.

2. The information processing apparatus according to claim 1 , further comprising an output unit that outputs to an outside the information on the person who is at risk of infection with the infectious disease and who is identified by the identification unit.

3. 3. The information processing apparatus according to claim 1, wherein the information about the infected person is acquired from an externally connected device.

4. 2. The information processing apparatus according to claim 1, further comprising an estimation unit that estimates an infection risk or a degree of the person identified by the identification unit who is at risk of infection with the infectious disease.

5. The information processing apparatus according to claim 1 , wherein the extracting means extracts image data of the captured images for a period based on an incubation period of the infectious disease which the infected person has developed.

6. A program for causing a computer to function as the information processing device according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Image retrieving device, imaging apparatus, control method of image retrieving device, program, and storage medium

    JP2008178042A

  • Access control system

    JP2010128976A

  • Watch system and wide area watch system

    JP2016103178A

  • Proximity communication device, proximity communication method, and proximity communication program

    JP2017162214A

  • Behavioral analysis device and program

    JP2017207877A