KR102265617B1 - Method for predicting potential confirmator of epidemic through analysis of cctv video - Google Patents

Abstract

Provided is a method for predicting a probable case of epidemic through analysis of a CCTV video. The method of the present invention comprises the following steps of: receiving CCTV standard data, user location information and movement path information on a newly confirmed case; extracting a list of CCTVs adjacent to the movement path of the confirmed case and a list of users around the movement path of the confirmed case from the CCTV standard data and the user location information, based on the movement path information on a newly confirmed case; analyzing a plurality of CCTV videos included in the list of CCTVs adjacent to the movement path of the confirmed case; and predicting probable cases of endemic, based on an analysis result, wherein the step of analyzing a plurality of CCTV videos included in the list of CCTVs adjacent to the movement path of the confirmed case is to measure distances between the newly confirmed case and a plurality of first citizens located within a given distance from the newly confirmed case for each CCTV video and the step of predicting probable cases of endemic includes a step of calculating an infection rate of each of the first citizens, based on the measured distance and a step of predicting the first citizen having an infection rate no less than a given reference percentage as a probable case.

Description

Method for predicting potential confirmed cases for infectious diseases through CCTV image analysis {METHOD FOR PREDICTING POTENTIAL CONFIRMATOR OF EPIDEMIC THROUGH ANALYSIS OF CCTV VIDEO}

The present invention relates to a method of predicting a potential confirmed person for an infectious disease through CCTV image analysis.

In general, an infectious disease refers to diseases that are contagious among diseases. Such an infectious disease is a disease caused by a specific pathogen or a toxic substance of a pathogen, and refers to a disease that is transmitted from an infected person to a susceptible host (human).

And most of these infectious diseases are transmitted through person-to-person contact.

It is ideal to block an infectious disease before it spreads, but in reality, it is almost impossible to prevent a new infectious disease in advance. Therefore, once the spread of a new infectious disease has begun, if it is discovered, the best course of action is to prevent further spread.

Therefore, in order to prevent the further spread of a new infectious disease, it is essential not only to quarantine the confirmed person, but also to quickly identify people who have come into contact with the confirmed person so that quarantine measures are taken for those who have come in contact.

However, in the case of the conventional epidemiological investigation of an infectious disease, the accuracy of the investigation is poor because the investigation was conducted by inquiring the payment information of the confirmed person, identifying the movement route of the confirmed person, and finding each person who came into contact with the confirmed person on the movement route. There is a problem that takes time.

In addition, there is a problem that prevention of n-th infection is not performed at all because only those who have been in direct contact with the confirmed person are identified, and those who have indirectly contacted the confirmed person are not identified.

Laid-open Patent Publication No. 10-2017-0035145, 2017.05.15.

The problem to be solved by the present invention is to provide a method of predicting a potential confirmed person for an infectious disease through CCTV image analysis.

However, the problems to be solved by the present invention are not limited to the problems described above, and other problems may exist.

A method for predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an aspect of the present invention for solving the above-mentioned problem includes the steps of receiving CCTV standard data, user location information, and new confirmed patient movement information about the infectious disease , extracting a CCTV list around the confirmed person's movement line and a user list around the confirmed person's movement line from the CCTV standard data and user location information, respectively, based on the new confirmed person movement line information, a plurality of included in the confirmed person's movement line area CCTV list Analyzing the CCTV images of and estimating a potential confirmed person for the infectious disease based on the analysis result, and analyzing a plurality of CCTV images included in the CCTV list surrounding the movement of the confirmed person includes: With respect to the CCTV image, the distance between a new confirmed patient and a plurality of first neighbors located within a predetermined distance from the new confirmed patient is respectively measured, and the step of predicting a potential confirmed person for the infectious disease is based on the measured distance. , calculating an infection rate of each of the plurality of first surrounding people, and predicting a first surrounding person having an infection rate of a predetermined reference percentage or higher as a potential confirmed patient.

In some embodiments of the present invention, the step of extracting the CCTV list around the confirmed person's movement line and the user list around the confirmed person's movement line from the CCTV standard data and user location information, respectively, comprises: It may be to identify the user and extract the CCTV list around the confirmed person's movement line and the user list around the confirmed person's movement line for each location.

In some embodiments of the present invention, the analyzing of the plurality of CCTV images included in the CCTV list around the movement line of the confirmed person includes analyzing the CCTV images without the first neighbor located within a predetermined distance from the new confirmed person. may not

In some embodiments of the present invention, the calculating of the infection rate for each of the plurality of first neighbors based on the measured distance comprises: when the distance to the new confirmed patient is less than the first length, the infection rate is set to a first value , and when the distance to the new confirmed patient is greater than or equal to the first length and less than the second length, the infection rate is calculated as a second value, and when the distance to the new confirmed patient is greater than or equal to the second length, the infection rate is calculated as the third value can be calculated.

In some embodiments of the present invention, the method may further include grouping the potential confirmed cases based on the user list around the confirmed cases.

In some embodiments of the present invention, the grouping of the potential confirmed patients based on the list of users around the movement of the confirmed patient includes the location information of the potential confirmed person in the CCTV image and the user list included in the list of users around the movement of the confirmed patient. By comparing the location information of each of a plurality of users, from among a plurality of users included in the user list surrounding the movement line of the confirmed patient, the user corresponding to the location information in the CCTV image of the potential confirmed patient is extracted and grouped.

In some embodiments of the present invention, the method calculates the infection rate of each of a plurality of second neighbors located within a predetermined distance from the potential confirmed person based on the analysis result and the step of analyzing the CCTV image based on the potential confirmed person It may further include the step of

In some embodiments of the present invention, the analyzing of the CCTV image targeting the potential confirmed patient may include measuring a distance between the potential confirmed patient and the second surrounding person, respectively.

In some embodiments of the present invention, the calculating of the infection rate of each of the plurality of second neighbors may be calculated based on the measured distance, but multiplied by a predetermined ratio.

A computer program according to another aspect of the present invention for solving the above problems is combined with a computer that is hardware to execute a method of predicting a potential confirmed person for an infectious disease through the CCTV image analysis, and stored in a computer readable recording medium do.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention described above, it is possible to prevent secondary infection by predicting a potential confirmed person according to the infection rate of the first neighbors who were at a predetermined distance from the confirmed person. In addition, it is possible to prevent tertiary infection by calculating the infection rate for the second neighbors who were at a predetermined distance from the potential confirmed person.

Accordingly, government agencies or local governments can take appropriate administrative actions immediately, shorten the time required for each procedure, and, as a result, detect national public health crises at an early stage and respond in a timely manner. can do.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a conceptual diagram for explaining a system for predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an embodiment of the present invention.
2 is a flowchart of a method of predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an embodiment of the present invention.
3 is an exemplary diagram for explaining information on the movement of a new confirmed patient according to an embodiment of the present invention.
4 is an exemplary diagram for explaining that a CCTV list and a user list around the movement of a confirmed patient are extracted for each location according to an embodiment of the present invention.
5 is an exemplary diagram for explaining a first neighbor within a predetermined distance according to an embodiment of the present invention.
6 is a flowchart of a specific method of step S140 of FIG. 3 .
7 is a flowchart of a method of calculating an infection rate of a second neighbor based on a potential confirmed person according to an embodiment of the present invention.
8 is an exemplary diagram illustrating extracting a user list by grouping potential confirmed patients according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. As used herein, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram for explaining a system for predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an embodiment of the present invention.

Referring to FIG. 1 , a system for predicting a potential confirmed patient for an infectious disease through CCTV image analysis (hereinafter, a potential confirmed patient prediction system) is a user terminal 10, an external institution 20, a server 30, and an administrator terminal. (40) may be included.

Here, the server 30 may transmit/receive data by being synchronized in real time with the user terminal 10 , the external institution 20 , and the manager terminal 40 using a wireless communication network. The wireless communication network may support various long-distance communication methods, for example, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), and Wimax (World Interoperability for Microwave Access: Wimax). ), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA) , HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), IEEE 802.16, Long Term Evolution (LTE), LTEA (Long Term Evolution-Advanced), broadband wireless mobile communication service (Wireless Mobile) Broadband Service: Various communication methods such as WMBS), BLE (Bluetooth Low Energy), Zigbee, RF (Radio Frequency), LoRa (Long Range), etc. may be applied, but are not limited thereto, and various well-known wireless or mobile communications method may be applied.

In this embodiment, the user terminal 10 and the manager terminal 40 may include various portable electronic communication devices supporting communication with the server 30 . For example, as a separate smart device, a smart phone, a personal digital assistant (PDA), a tablet, a wearable device, for example, a watch type terminal (Smartwatch), a glass type terminal (including Smart Glass), HMD (Head Mounted Display), etc.) and various Internet of Things (IoT) terminals, but are not limited thereto.

The user terminal 10 may provide location information to the server 30 through a web page for providing real-time location information provided by the server 30 .

When the user accesses the real-time location information providing webpage through the user terminal 10 and inputs consent to provide location information, the server 30 may receive the user's location information in real time through the user terminal 10 . .

According to an embodiment, the user terminal 10 may update the user's location information every predetermined time (eg, 30 minutes) and provide it to the server 30 .

Here, the location information may include latitude/longitude and time of the corresponding location.

The external institution 20 means a public institution managed by the state, and may transmit publicly provided data to the server 30 . The external organization 20 may provide the server 30 with CCTV standard data and information on the movement of new confirmed patients for infectious diseases.

For example, CCTV standard data can be provided from the public data portal (data.go.kr), and information on the movement of new confirmed cases can be provided from the National Disaster Safety Portal (safekorea.go.kr).

According to the embodiment, the external agency 20 may temporarily update the CCTV standard data and provide it to the server 30 .

Here, the CCTV standard data may include a location number address, number of cameras, latitude/longitude, etc.

According to an embodiment, the external institution 20 may update the movement information of the new confirmed patient in real time and provide it to the server 30 .

Here, the new confirmed patient movement information may include the detailed address of the location where the new confirmed patient was exposed and the date and time the new confirmed patient was exposed.

The server 30 may include a collection unit 31 , a processing unit 32 , and a transmission unit 33 .

The collection unit 31 collects the user's location information provided from the user terminal 10 and collects CCTV standard data and new confirmed patient movement information provided from the external organization 20 .

The processing unit 32 calculates the infection rate of people around the new confirmed patient using the collected user location information, CCTV standard data, and new confirmed patient movement information, and predicts potential confirmed cases based on this. In addition, the infection rate of people around the predicted potential confirmed patient is calculated.

The transmitting unit 33 transmits potential patient group information, infection rate information of each potential patient, and the number and infection rate information of each potential patient to the manager terminal 40 .

The manager terminal 40 receives potential patient group information, infection rate information of each potential patient, the number of people around each potential patient, infection rate information, and the like.

The administrator can check the possibility of secondary and tertiary infections for new infectious diseases through the potential patient group information received by the administrator terminal 40, the infection rate information of each potential patient, the number of people around each potential patient and the infection rate information, etc. By understanding it, it is possible to effectively establish countermeasures against secondary and tertiary infections.

2 is a flowchart of a method of predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an embodiment of the present invention. 3 is an exemplary diagram for explaining information on the movement of a new confirmed patient according to an embodiment of the present invention. 4 is an exemplary diagram for explaining that a CCTV list and a user list around the movement of a confirmed patient are extracted for each location according to an embodiment of the present invention. 5 is an exemplary diagram for explaining a first neighbor within a predetermined distance according to an embodiment of the present invention. 6 is a flowchart of a specific method of step S140 of FIG. 3 . 7 is a flowchart of a method of calculating an infection rate of a second neighbor based on a potential confirmed person according to an embodiment of the present invention. 8 is an exemplary diagram illustrating extracting a user list by grouping potential confirmed patients according to an embodiment of the present invention.

Referring to FIG. 2 , the server 30 receives CCTV standard data, user location information, and new confirmed patient movement information for infectious diseases ( S110 ). Since step S110 is the same as described above, a detailed description thereof will be omitted.

Next, the server 30 extracts a CCTV list around the confirmed person's movement line and a user list around the confirmed person's movement line from the standard CCTV data and user location information, respectively, based on the new confirmed patient movement line information (S120).

Information on the movement of new confirmed patients is accumulated and stored according to the movement of new confirmed patients. That is, when it is determined that the new confirmed patient A was exposed to the location A, only the information about the location A is included in the new confirmed patient movement information. After that, if it is determined that the new confirmed person A was also exposed to location B, the new confirmed person's movement information includes information about location B as well as information about location A.

Referring to FIG. 3 , the movement route information of the new confirmed patient A includes the detailed address and exposure date of each location, and the detailed address and exposure date for each location may be accumulated and stored according to the movement of the new confirmed patient.

According to an embodiment, it is possible to identify CCTVs and users existing in one or more locations of the movement of a new confirmed patient, and extract a list of CCTVs and a list of users around the movement of the confirmed person for each location.

At this time, based on the location information of each CCTV included in the CCTV standard data and the location information of the user included in the user location information, the CCTV list around the movement line of the confirmed patient and the user list around the movement line of the confirmed person can be extracted for each location.

Referring to FIG. 4 , if it is determined that the new confirmed person is exposed to the location A and the location B according to the movement information of the new confirmed person, the server 30 extracts the CCTV list and the user list surrounding the location A, and the location B Extracts the surrounding CCTV list and the surrounding user list. At this time, the CCTV included in the surrounding CCTV list of the location A and the CCTV included in the surrounding CCTV list of the location B may be different from or overlapped with each other. Similarly, the user included in the nearby user list of the location A and the user included in the nearby user list of the location B may be different from or overlapped with each other.

According to another embodiment, the server 30 extracts the local CCTV list and the local user list corresponding to the location where the new confirmed person is exposed from the CCTV standard data and user location information, and then the confirmed person from the local CCTV list and the local user list It is possible to extract the CCTV list around the movement line and the user list around the confirmed person's movement line.

On the other hand, the server 30 may provide the extracted CCTV list around the confirmed person's movement line and the user list around the confirmed person's movement line to the manager terminal 40 .

The manager checks the CCTV list around the confirmed person's movement line received through the manager terminal 40 and acquires each CCTV image included in the CCTV list around the confirmed person's movement line. Specifically, each CCTV image may be provided from a local institution or company that manages each CCTV included in the CCTV list around the movement line of the confirmed person.

Next, the server 30 analyzes a plurality of CCTV images included in the CCTV list around the movement line of the confirmed patient (S130).

The server 30 analyzes the distance from people (hereinafter, first neighbors) around the new confirmed person in the CCTV image based on the new confirmed person.

According to an embodiment, for each CCTV image, the server 30 measures a distance between a new confirmed patient and a plurality of first surrounding persons located within a predetermined distance from the new confirmed patient, respectively.

Referring to FIG. 5 , there are 8 people excluding new confirmed cases in the CCTV image. At this time, only 6 people who exist within a predetermined distance from the new confirmed cases are measured at distances from the new confirmed cases and exist within a predetermined distance. For the two who do not, the distance to the new confirmed patient is not measured.

In this case, the predetermined distance may be determined at an interval enough to not be able to contact a new confirmed patient in any way. For example, the predetermined distance may be determined to be 10 m, but is not limited thereto.

According to another embodiment, the server 30 does not analyze the CCTV image without the first surrounding person located within a predetermined distance from the new confirmed patient.

In other words, since there is no person (the first neighbor) located within a certain distance that may have come into contact with a new confirmed person, even if there is a person outside the prescribed distance in the CCTV video (people outside the prescribed distance can contact the new confirmed person) There is no need to analyze the CCTV images because there is no possibility of doing so).

According to another embodiment, the server 30 may analyze the CCTV images in the order of the number of people after calculating the number of people included in each CCTV image included in the CCTV list around the movement line of the confirmed person.

For example, the server 30 may calculate the number of people using a deep learning-based crowd counting method, but is not limited thereto, and all methods of estimating the number of people in the video are applicable.

Next, the server 30 predicts a potential confirmed person for an infectious disease based on the analysis result (S140).

Referring to FIG. 6 , the server 30 calculates an infection rate of each of the plurality of first neighbors based on the measured distance ( S141 ).

The shorter the distance to the new confirmed person, the higher the infection rate of the first person in the vicinity is calculated.

According to an embodiment, the server 30 calculates the infection rate as the first value when the distance to the new confirmed patient is less than the first length, and when the distance to the new confirmed patient is greater than the first length and less than the second length, The infection rate may be calculated as the second value, and when the distance to the new confirmed patient is greater than or equal to the second length, the infection rate may be calculated as the third value.

For example, if the first length is 2m, the second length is 4m, the first value is 70%, the second value is 30%, and the third value is 10%, the server 30 is a new The infection rate of the first neighbor who is less than 2m from the confirmed person is calculated as 70%, the infection rate of the first neighbor who is more than 2m and less than 4m from the new confirmed patient is 30%, and the distance from the new confirmed person is 30%. It is possible to calculate the infection rate of the first neighbor who is 4m or more as 10%. Although it has been described that the infection rate is calculated by dividing the three cases, according to an embodiment, the infection rate may be calculated more accurately by dividing the unit into smaller length units.

Next, the server 30 predicts the first surrounding person whose infection rate is greater than or equal to a predetermined reference percentage as a potential confirmed patient (S142).

For example, when the predetermined reference percentage is 70%, the server 30 may predict a first nearby person having an infection rate of 70% or more as a potential confirmed patient.

That is, the server 30 determines that among the plurality of first surrounding people, the first surrounding person who was located closer to the new confirmed person is more likely to be infected, and classifies it as a potential confirmed person and manages it. Accordingly, it is possible to more efficiently and systematically prepare for a secondary infection for a new infectious disease.

Furthermore, the server 30 can prepare for tertiary infection for a new infectious disease by calculating the infection rate even for people around the potential confirmed person (hereinafter referred to as the second neighbor) and managing even indirect contact with the new confirmed person.

Referring to FIG. 7 , the server 30 analyzes the CCTV image based on the potential confirmed person (S210).

The server 30 analyzes each CCTV image included in the CCTV list around the movement line of the confirmed person based on the potential confirmed person, not the standard of the new confirmed person.

For example, when potential confirmed cases A and B are predicted from a specific CCTV image, the server 30 analyzes the specific CCTV image based on the potential confirmed patient A, and analyzes the specific CCTV image based on the potential confirmed patient B.

Specifically, the server 30 measures the distance between the potential confirmed person and the people in the vicinity (hereinafter referred to as the second neighbor) based on the potential confirmed person in the CCTV image.

According to an embodiment, with respect to the CCTV image, the server 30 measures a distance between a potential confirmed patient and a plurality of second neighbors located within a predetermined distance from the potential confirmed patient, respectively.

Since the method of measuring the distance between the potential confirmed patient and the second nearby person is the same as the above-described method of measuring the distance between the new confirmed patient and the first surrounding person, a detailed description thereof will be omitted.

Next, the server 30 calculates an infection rate of each of the plurality of second neighbors located within a predetermined distance from the potential confirmed patient based on the analysis result ( S220 ).

Specifically, the server 30 calculates the infection rate of the second neighbor based on the measured distance, but multiplies it by a predetermined ratio. Here, the predetermined ratio is a value less than 1.

According to an embodiment, when the distance to the potential confirmed patient is less than the first length, the server 30 calculates the infection rate by multiplying the first value by a predetermined ratio, and when the distance to the potential confirmed patient is greater than the first length and the second length If the length is less than 2, the infection rate can be calculated by multiplying the second value by a predetermined ratio, and when the distance to the potential confirmed patient is greater than or equal to the second length, the infection rate can be calculated by multiplying the third value by the predetermined ratio.

For example, when the first length is 2 m, the second length is 4 m, the first value is 70 percent, the second value is 30 percent, the third value is 10 percent, and the predetermined ratio is 0.5. , the server 30 calculates the infection rate of the second neighbor who is less than 2m away from the potential confirmed patient as 70% x 0.5 = 35%, and the infection rate of the second nearby person who is 2m or more and less than 4m from the potential confirmed patient can be calculated as 30%x0.5=15%, and the infection rate of the second neighbor who is more than 4m away from a potential confirmed patient can be calculated as 10%x0.5=5%. Although it has been described that the infection rate is calculated by dividing the three cases, according to an embodiment, the infection rate may be calculated more accurately by dividing the unit into smaller length units.

When calculating the infection rate of the second neighbor, multiplying by a predetermined ratio is because the second neighbor did not have direct contact with the new confirmed person. That is, even if the distance measured for the first neighbor and the distance measured for the second neighbor through the CCTV image analysis are the same, the first neighbor is in direct contact with the new confirmed person, and the second neighbor is directly with the new confirmed person. It is not appropriate to calculate the infection rate equally because it is not through contact. Therefore, the infection rate of the second neighbor is calculated to be lower than the infection rate of the first neighbor by multiplying the predetermined ratio.

Meanwhile, although not clearly shown in FIG. 2 , the present invention may further include grouping potential confirmed patients based on a list of users around the confirmed patient movement line.

The server 30 compares the location information in the CCTV image of the potential confirmed patient with the location information of each of a plurality of users included in the user list around the confirmed person's movement line, and among the plurality of users included in the user list around the confirmed person's movement line, It is possible to extract and group users corresponding to the location information in the CCTV images of potential confirmed patients.

With reference to FIG. 8, three CCTV images included in the CCTV list around the movement line of the confirmed person are analyzed to describe the case of predicting 3, 2, and 1 potential confirmed cases, respectively.

The server 30 identifies the location information of each of the three potential confirmed patients from the first CCTV image, and compares each location information with the location information of each of the 100 users included in the user list around the confirmed person's movement. As a result of the comparison, potential confirmed patient 1 is matched with user 1, potential confirmed patient 2 is matched with user 2, and potential confirmed patient 3 is matched with user 10. Accordingly, user 1, user 2, and user 10 are included in the list of users predicted as potential confirmed cases (grouped as potential confirmed cases).

The server 30 identifies the location information of each of the two potential confirmed patients in the second CCTV image, and compares each location information with the location information of each of the 100 users included in the user list around the confirmed person's movement line. As a result of the comparison, potential confirmed patient 4 matches user 20, and potential patient 5 matches user 50. Accordingly, user 20 and user 50 are included in the user list predicted as a potential confirmed patient (grouped as a potential confirmed patient).

The server 30 identifies the location information of one potential confirmed person from the third CCTV image, and compares the location information with the location information of each of the 100 users included in the user list around the confirmed person's movement line. As a result of the comparison, potential confirmed case 5 matches user 55. Accordingly, user 55 is included in the user list predicted as a potential confirmed patient (grouped as a potential confirmed patient).

Although it has been described above that the predicted potential confirmed cases in each CCTV image match different users, the matching users may overlap. For example, a list of users predicted as Potential Case 3 and Potential Case 5 because Potential Case 3 and Potential Case 5 match the same user (eg, User 10) (i.e. Potential Case 3 and Potential Case 5 are the same person). User 1, User 2, User 10, User 20, and User 55 will be included.

According to an embodiment, the list of users predicted to be potential confirmed cases may also include information on the infection rate of the second nearby people calculated for each user predicted as potential confirmed cases.

For example, when the infection rate of 3 second surrounding people is calculated for the potential confirmed patient 1, the user list predicted as the potential confirmed patient may include information on the infection rate of the 3 second surrounding people for the user 1 together.

The server 30 provides a list of users predicted as potential confirmed cases to the manager terminal 40, so that the manager can check potential patient group information, infection rate information of each potential patient, the number of people around each potential patient, infection rate information, etc. let it be

According to an embodiment, when the location information of the user predicted to be a potential confirmed person is updated, the server 30 may analyze the CCTV image based on the updated location information. That is, by analyzing the CCTV images in the vicinity of the location corresponding to the updated location information, it is possible to calculate the infection rate of the second neighbor in each CCTV image.

That is, similar to calculating the infection rate of the first surrounding person according to the movement information of the new confirmed person, the infection rate of the second nearby person can be calculated for each location according to the movement information of the potential confirmed person.

The method for predicting a potential confirmed person for an infectious disease through CCTV image analysis according to an embodiment of the present invention described above may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. have.

The above-mentioned program, in order for the computer to read the program and execute the methods implemented as a program, C, C++, JAVA, Ruby, which the processor (CPU) of the computer can read through the device interface of the computer; It may include code coded in a computer language such as machine language. Such code may include functional code related to a function defining functions necessary for executing the methods, etc., and includes an execution procedure related control code necessary for the processor of the computer to execute the functions according to a predetermined procedure. can do. In addition, the code may further include additional information necessary for the processor of the computer to execute the functions or code related to memory reference for which location (address address) in the internal or external memory of the computer to be referenced. have. In addition, when the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code uses the communication module of the computer to determine how to communicate with any other computer or server remotely. It may further include a communication-related code for whether to communicate and what information or media to transmit and receive during communication.

The storage medium is not a medium that stores data for a short moment, such as a register, a cache, a memory, etc., but a medium that stores data semi-permanently and can be read by a device. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program may be stored in various recording media on various servers that the computer can access or in various recording media on the computer of the user. In addition, the medium may be distributed in a computer system connected by a network, and a computer readable code may be stored in a distributed manner.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

10: user terminal
20: external organs
30 : server
31: collection unit
32: processing unit
33: transmission unit
40: administrator terminal

Claims (10)

A method performed by a server, comprising:
Receiving CCTV standard data, user location information, and new confirmed patient movement information for infectious diseases;
extracting a CCTV list and a user list around the confirmed patient's movement line from the CCTV standard data and user location information, respectively, based on the new confirmed patient movement line information;
analyzing a plurality of CCTV images included in the CCTV list around the movement line of the confirmed patient; and
Predicting a potential confirmed person for the infectious disease based on the analyzed result,
The step of analyzing a plurality of CCTV images included in the CCTV list around the movement line of the confirmed patient is,
For each CCTV image, the distance between a new confirmed patient and a plurality of first neighbors located within a predetermined distance from the new confirmed patient is measured, respectively,
The step of predicting a potential confirmed person for the infectious disease includes:
Calculating an infection rate of each of the plurality of first neighbors based on the measured distance;
Predicting a first nearby person whose infection rate is greater than or equal to a predetermined reference percentage as a potential confirmed patient;
Calculating the infection rate of each of the plurality of first neighbors based on the measured distance comprises:
If the distance to the new confirmed patient is less than the first length, the infection rate is calculated as the first value,
If the distance to the new confirmed patient is greater than or equal to the first length and less than the second length, the infection rate is calculated as a second value,
If the distance to the new confirmed patient is greater than or equal to the second length, the infection rate is calculated as a third value,
The method is
Analyzing CCTV images based on potential confirmed cases; and
The method further comprises calculating an infection rate of each of a plurality of second neighbors located within a predetermined distance from the potential confirmed patient based on the analyzed result,
In the step of analyzing the CCTV image for the potential confirmed patient, the distance between the potential confirmed patient and the second surrounding person is measured,
Calculating the infection rate of each of the plurality of second neighbors is calculated based on the measured distance, and is calculated by multiplying a predetermined ratio,
A method of predicting potential confirmed cases of infectious diseases through CCTV image analysis. According to claim 1,
The step of extracting a CCTV list and a user list around the confirmed person's movement line from the CCTV standard data and user location information, respectively,
Identifying CCTVs and users present in one or more locations of the movement of a new confirmed patient, and extracting a list of CCTVs around the movement of the confirmed patient and a list of users around the movement of the confirmed patient for each location,
A method of predicting potential confirmed cases for infectious diseases through CCTV image analysis. According to claim 1,
The step of analyzing a plurality of CCTV images included in the CCTV list around the movement line of the confirmed patient is,
The analysis is not performed on the CCTV image without the first surrounding person located within a predetermined distance from the new confirmed patient,
A method of predicting potential confirmed cases for infectious diseases through CCTV image analysis. delete According to claim 1,
The method further includes grouping the potential confirmed patients based on the user list around the confirmed patient movement line.
A method of predicting potential confirmed cases for infectious diseases through CCTV image analysis. 6. The method of claim 5,
The step of grouping the potential confirmed cases based on the user list around the confirmed cases includes:
By comparing the location information in the CCTV image of the potential confirmed patient with the location information of each of a plurality of users included in the user list around the confirmed person's movement line, among a plurality of users included in the user list around the confirmed person's movement line, the potential Extracting and grouping users corresponding to the location information in the CCTV image of the confirmed patient,
A method of predicting potential confirmed cases for infectious diseases through CCTV image analysis. delete delete delete A computer readable record to perform a method of predicting a potential confirmed person for an infectious disease through CCTV image analysis of any one of paragraphs 1, 2, 3, 5 and 6 in combination with a computer A computer program stored on a medium.

Images