JP6739115B1 - Risk judgment program and system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect a risk level in advance and prevent an incident from occurring. SOLUTION: In a risk determination program for determining the risk of a suspicious person invading a house, reference image information obtained by photographing the outside of the house and reference location information for specifying the location of the house are provided. A combination degree acquisition step of acquiring in advance three or more levels of degree of association between the combination and the degree of risk for the combination, and when newly determining the degree of danger, image information is obtained by newly photographing the outside of the house. With the information acquisition step of acquiring the location information indicating the location of the house together with the acquisition, referring to the degree of association acquired in the association degree acquisition step, the image information and the location information acquired through the information acquisition step Based on the above, the computer is caused to execute a determination step of determining the risk level of the suspicious person entering the house. [Selection diagram] Fig. 4

Description

The present invention relates to a risk determination program and system for determining the risk of suspicious person intrusion into a house.

Conventionally, many attempts have been made to prevent suspicious persons from entering a house. In particular, single-family houses have more intrusion routes than condominiums, so it is necessary to take stronger measures to prevent suspicious persons from entering in order to protect the safety of residents.

Japanese Patent Application No. 2016-210848

In the technology disclosed in Patent Document 1 described above, a technology for identifying a person from a face image by artificial intelligence is described, but artificial intelligence is utilized to quantitatively determine the risk of suspicious person intrusion into an actual house. It is not possible. By actually predicting the degree of danger with high accuracy, when the resident is in danger, he/she will contact the security company and the police as soon as possible. It was necessary to prevent unintentional mobilization of guards and police officers by security companies. Such a point of view is not specifically described in the disclosed technique of the cited document 1.

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose thereof is to detect the risk of a suspicious person invading a house in advance and to protect the safety of the resident. The purpose of the present invention is to provide a risk discriminating program and system for discriminating the risk automatically using artificial intelligence.

The risk level determination program according to the present invention is a risk level determination program for determining the risk level of a suspicious person entering a house, and is used to identify the reference image information of the outside of the house and the location of the house. A combination acquisition step of acquiring in advance three or more levels of association between the combination having the reference location information and the degree of risk for the combination, and when newly determining the degree of risk, a new image of the exterior of the house is taken. By acquiring the image information by doing the information acquisition step of acquiring the location information indicating the location of the house and the association degree acquired in the association degree acquisition step, the image obtained through the information acquisition step The computer is caused to execute a determination step of determining the risk level of a suspicious person entering the house based on the information and the location information.

A risk level determination system according to the present invention is a risk level determination system for determining a risk level of a suspicious person intruding a house, in which reference image information of the outside of the house and a location of the house are specified. A combination having a combination of reference location information and a degree of risk associated with the combination, and a degree-of-relationship acquiring unit that acquires in advance three or more levels of degree of correlation, and when newly determining the degree of danger, a new image of the outside of the house is taken. By obtaining the image information by doing so, the information obtaining means for obtaining the location information indicating the location of the house and the association degree obtained by the association degree obtaining means are referred to and obtained through the information obtaining means. It is characterized by further comprising: a discriminating means for discriminating a risk level of a suspicious person entering the house based on the image information and the location information.

In order to detect the risk of a suspicious person invading a house in advance and prevent an incident in advance, the risk can be automatically and highly accurately determined using artificial intelligence.

It is a block diagram which shows the whole structure of the risk determination system in which the risk determination program to which this invention is applied is mounted. It is a figure which shows the specific structural example of a discrimination device. It is a figure for demonstrating operation|movement in the risk determination program to which this invention is applied. It is a figure which shows the example which set the connection degree of 3 steps or more including the reference location information. It is a figure which shows the example which set the degree of association of three steps or more including the in-home reference pattern information. It is a figure which shows the example which set the connection degree of 3 steps or more including the reference time zone information. It is a figure which shows the example which set the connection degree of 3 steps or more including the reference person information. It is a figure which shows the example which set the connection degree of 3 steps or more including the reference audio|voice information. It is a figure which shows the example which set the connection degree of three steps or more including the security service for reference.

Hereinafter, a risk level determination program to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an overall configuration of a risk level determination system 1 in which a risk level determination program according to the present invention is installed. The risk determination system 1 includes an information acquisition unit 9, a determination device 2 connected to the information acquisition unit 9, and a database 3 connected to the determination device 2.

The information acquisition unit 9 is a device for a person who uses the system to input various commands and information, and is specifically configured by a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be a device such as a microphone capable of detecting a voice and converting the voice into text information. In addition, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be composed of a scanner having a function of recognizing a character string from a paper document. The information acquisition unit 9 may be integrated with the determination device 2 described below. The information acquisition unit 9 outputs the detected information to the determination device 2.

The database 3 stores information about the risk of intruding a suspicious person into a house, such as a case that occurred before the suspicious person invading the house, or a case where the risk was high, although the case did not occur. The database 3 includes reference image information previously captured by a camera that actually configures the information acquisition unit 9, reference house structure information including structure information about the house, reference location information for specifying a house location, Reference at-home pattern information indicating the in-home pattern of the resident of the house, reference time zone information indicating the time zone at the time of shooting of the reference image information, and a reference person who has extracted the person by analyzing the reference image information. Information, reference voice information recorded when the reference image information is captured, reference security service information indicating the contract status of the security service of the security company, etc. are stored.

The discriminating device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet type terminal, a wearable terminal, etc. in addition to the PC. It may be a materialized product. The user can determine the degree of danger of a suspicious person invading the house by obtaining the search solution by the determination device 2.

FIG. 2 shows a specific configuration example of the discrimination device 2. The discriminating device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire discriminating device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard or the like. A communication unit 26, a determination unit 27 that makes various determinations, and a storage unit 28, which is represented by a hard disk or the like and stores a program for performing a search to be executed, are connected to the internal bus 21. .. Further, the internal bus 21 is connected to a display unit 23 as a monitor that actually displays information.

The control unit 24 is a so-called central control unit for controlling each component installed in the discrimination device 2 by transmitting a control signal via the internal bus 21. The control unit 24 also transmits various control commands via the internal bus 21 in response to an operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input by the user. When the user inputs the execution command, the operation unit 25 notifies the control unit 24 of the input. The control unit 24, which has received this notification, executes the desired processing operation in cooperation with each component including the determination unit 27. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The determination unit 27 is responsible for various determinations regarding the risk of intrusion of a suspicious person into the house. The determination unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the estimation operation. The determination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is configured by a graphic controller that creates a display image under the control of the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is configured by a hard disk, under the control of the control unit 24, predetermined information is written to each address and is read out as needed. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation of the risk determination system 1 having the above-described configuration will be described.

In the risk discriminating system 1, for example, as shown in FIG. 3, it is premised that a combination of reference image information and reference house structure information is formed. The reference image information is an image of the outside of the house, taken by a camera installed in the house, the gate of the house, the entrance, the garden, the exterior, the fence, the fence, the parking space, the doorway, etc., for example, Various images such as images of pedestrians passing by roads outside the house, images of resident residents entering the house through the gate, and images of suspicious individuals attempting to invade the fence of the house. Is.

The reference house structure information is data indicating the structure of the house, and includes, for example, a photo of the entire house taken from the air, a photo of the house taken from the road side, electronic data of a completed house drawing, and the house shown on the map. It is electronic data such as an overall structural drawing.

In the example of FIG. 3, the reference image information is, for example, reference image information P11 to P13 obtained by photographing the outside of the house for each place or for each time series, and as the reference house structure information, structures F to I. And so on.

As input data, such reference image information and reference house structure information are arranged. A combination of the reference image information as such input data and the reference house structure information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the risk level of a suspicious person entering a house as an output solution is displayed as a percentage.

Each combination (intermediate node) of the reference image information and the reference house structure information is associated with each other through the association degree of three or more levels with respect to the risk degree as the output solution. The reference image information and the reference housing structure information are arranged on the left side through the degree of association, and the respective risk degrees are arranged on the right side through the degree of association. The degree of association indicates the degree of risk to which the reference image information and the reference house structure information arranged on the left side are highly related. In other words, this degree of association is an index that indicates what degree of danger each of the reference image information and the reference house structure information is likely to be associated with, and the reference image information and the reference house structure information. It shows the accuracy in selecting the most probable risk level from. In the example of FIG. 3, w13 to w22 are shown as the degree of association. These w13 to w22 are shown in 10 levels as shown in Table 1 below, and the closer to 10 points, the higher the degree of association between each combination as an intermediate node and the degree of danger as an output. On the contrary, the closer to one point, the lower the degree of association between each combination as an intermediate node and the degree of danger as an output.

The determination device 2 acquires in advance the association degrees w13 to w22 of three or more levels shown in FIG. In other words, the discrimination device 2 accumulates the reference image information, the reference approach information, and the data indicating the degree of danger in that case in analyzing the actual degree of danger, and analyzes these. , By analyzing, the association degree shown in FIG. 3 is created.

For example, assume that the reference image information P11 is an image in which a resident of the house enters the house through the gate. In addition, when it is assumed that the structure F of the house to be discriminated is used, whether or not there is a case in which damage to residents of the house has occurred in the previous data, and whether or not the case has occurred It is extracted whether or not the degree of danger is not unusual, or whether or not it is particularly safe. These data can be obtained from the record of the image data taken by the past camera for the reference image information, and the reference structure information is the completion drawing and the map data recorded in the house maker or the government office, Alternatively, the image may be extracted from an aerial image or image data of a house previously imaged from a road. The digitization of the risk level may be performed by visually recognizing the reference image information by a plurality of people and totaling a questionnaire survey or the like regarding the risk level.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P11 and the structure F, past data such as whether or not an incident actually occurred, or whether or not the incident was not reached but the risk was high, etc. Analyze from. The higher the degree of association that leads to high-risk output, the higher the number of cases in which an incident occurs, and the higher the risk of an incident, and the higher the degree of association that leads to low-risk output, as the number of cases in which an incident occurs. Set. In the example of the intermediate node 61a linked in the case of the reference image information P11 and the structure H, the output is linked to 90% risk and 30% risk, but the risk is extremely high compared to the previous case. Since this is a high case, the degree of association of w13 leading to 90% risk is set to 7 points, and the degree of association of w14 leading to 30% risk is set to 2 points.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence.

In the example of the degree of association shown in FIG. 3, the node 61b is a node of a combination of the reference image information P11 and the structure F of the reference house structure information, and the degree of association of 60% risk is w15, and the risk degree is The degree of association of 0% is w16. The node 61c is a node which is a combination of the reference image information P12 with the structure G (for example, the structure information regarding the layout of the garden) of the reference house structure information and the structure I (for example, the structural information regarding the layout of the fence). Yes, the degree of association of 30% risk is w17, and the degree of association of 70% risk is w18.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data, when actually determining a new risk from now on, the risk is determined using the learned data described above. In such a case, the image information is newly acquired and the housing structure information is acquired. The image information corresponds to the reference image information, and the house structure information corresponds to the reference house structure information.

The image information to be newly acquired is captured by the camera of the information acquisition unit 9 described above. This shooting is the same as the image outside the house taken to obtain the above-mentioned reference image information. Further, the shooting conditions are not necessarily required to the same shooting conditions (shooting angle, angle of view, resolution) for obtaining the reference image information described above.

The acquisition of the housing structure information accesses a database in which the housing structure information of the house whose risk is to be determined is recorded. For example, when the house structure information is recorded in the database in association with the address, the house structure information linked to the address may be read by inputting the address.

Based on the image information newly acquired in this way and the approach information of the train, the degree of risk at the time when the new image information is actually acquired is obtained. In such a case, the pre-acquired association degree shown in FIG. 3 (Table 1) is referred to. For example, when the newly acquired image information is the same as or similar to P12 and the acquired housing structure information is structure I, the node 61d is associated through the association degree. In this node 61d, "risk level 60%" is associated with w19, and "risk level 70%" is associated with the association level w20. In such a case, “the risk level of 60%” having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimal solution, and “the risk 70%” in which the degree of association is low but the degree of association is recognized may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.
In this way, the selection of these optimum solutions uses the learned model shown in FIG. 3, and when the input data (image information, housing structure information) for which the solution is actually desired is input, the output solution (risk level) is output. It can be realized through artificial intelligence. However, in the present invention, it is not essential to utilize artificial intelligence, and a combination of the reference image information and the reference housing structure information and the degree of association with the risk for the combination are used in three or more stages. It may be realized in any form.

Table 2 below shows examples of the association degrees w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the association degrees w1 to w12 extending from this input. That is, the greater the association degrees w1 to w12, the heavier the weighting in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all be the same value, and the weighting in the selection of the intermediate node 61 may be all the same.

FIG. 4 illustrates an example in which a combination of the above-described reference image information and reference location information and the degree of association with the risk for the combination is set in three or more stages.

As input data, such reference image information and reference location information are arranged. A combination of the reference image information as the input data and the reference location information is the intermediate node shown in FIG.
The reference location information includes all information for identifying the location of the house. The reference location information includes not only address information and map information but also an image of the surrounding environment including the house. This reference location information also includes the situation of the building adjacent to the house and what purpose the adjacent land is used for, such as shops, buildings, restaurants, vacant lots, parking lots, and schools. In other words, if the adjacent land is a vacant land, it is likely that the vacant land will easily enter the house.

The discriminator 2 acquires in advance the degrees of association w13 to w22 of three or more levels shown in FIG. In other words, the discrimination device 2 accumulates the reference image information, the reference location information, and the data indicating the degree of danger in that case in analyzing the actual degree of danger, and analyzes them. , The association degree shown in FIG. 4 is created by analysis.

In the example of the degree of association shown in FIG. 4, the node 61b is a node in which the reference location information is the location J with respect to the reference image information P11, the degree of association of 60% is w15, and the degree of risk is 0. The degree of association of% is w16.

Similarly, when such a degree of association is set, image information is newly acquired and location information is acquired. The image information corresponds to the reference image information, and the location information corresponds to the reference location information.

The location information is accessed by accessing a database in which the house structure information of the house whose risk is to be determined is recorded. For example, when the location information is recorded in the database in association with the address, the location information linked to the address (neighboring place is relatively bright in a restaurant, or neighboring place is relatively bright) is entered by entering the address. (For example, a suspicious person is likely to intrude at the parking lot).

In obtaining the degree of risk, reference is made to the degree of association acquired in advance and shown in FIG. For example, when the acquired image is the same as or similar to the reference image information P12 and the location information is the location M, the combination is associated with the node 61c, and the node 61c has a risk degree of 30% and the association degree w17. And the risk level 70% is associated with the association level w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

FIG. 5 shows an example in which a combination of the above-described reference image information and reference home pattern information and the degree of risk of the combination is set in three or more levels.

As input data, such reference image information and reference in-home pattern information are arranged. A combination of the reference image information as the input data and the reference location information is the intermediate node shown in FIG.

The in-home reference pattern information for reference includes all information for identifying the in-home pattern of a resident who lives in the house. As the reference home-use pattern information, for example, based on the amount of electric power used in the house and the image of the resident's entrance and exit taken by a camera installed at the entrance or the gate, the time when the resident is at home and going out It is a pattern of the time zone in which it is present. From Monday to Sunday, the resident's at-home time zone and out-of-home time zone are patterned for each time zone on each day of the week based on the above-described power consumption and images. At this time, the above-described power consumption amount and image may be machine-learned in advance to determine the pattern.

The discriminating device 2 acquires in advance the association degrees w13 to w22 of three or more stages shown in FIG. That is, the discrimination device 2 stores reference image information, reference home patterns, and data indicating the degree of risk in that case in analyzing the actual risk, and analyzes them. By analyzing, the association degree shown in FIG. 5 is created.

In the example of the degree of association shown in FIG. 5, the node 61b is a node in which the reference location information is the location J with respect to the reference image information P11, the degree of association of 60% is w15, and the degree of risk is 0. The degree of association of% is w16.

Similarly, when such a degree of association is set, image information is newly acquired and at-home pattern information is also acquired. The image information corresponds to the reference image information, and the at-home pattern information corresponds to the reference-at-home pattern information.

In order to obtain the in-home pattern information, a database in which in-home pattern information of a house whose risk level is to be determined is recorded is accessed. For example, when the home-at-home pattern information is associated with an address and recorded in the database, the home-at-home pattern information linked to the address by entering the address (Monday-Friday, 9:00 to 21:00 is It is also possible to read out when the user is out and at home other than that, and on Saturdays and Sundays, when he is out from 10:00 to 15:00 and otherwise stays at home.

In obtaining the degree of risk, reference is made to the degree of association acquired in advance and shown in FIG. For example, when the acquired image is the same as or similar to the reference image information P12 and the in-home pattern information is the in-home pattern R, the combination is associated with the node 61c, and the node 61c is associated with the risk degree of 30%. The degree w17 is associated with the degree of risk 70%, and the risk degree 70% is associated with the degree of association w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

In FIG. 6, a combination of three or more levels of the combination of the above-described reference image information and the reference time zone information indicating the time zone at the time of shooting of the reference image information, and the risk degree for the combination is set. It shows an example.

As the input data, such reference image information and reference time zone information are arranged. A combination of the reference image information as such input data and the reference time zone information is the intermediate node shown in FIG.

The reference time zone information means the time zone at the time of shooting of the reference image information, and not only the time at the temporary point but also the time such as 10:10 to 10:20. It may have a width.

The discriminator 2 acquires in advance the degree of association w13 to w22 of three or more levels shown in FIG. That is, the discrimination device 2 stores reference image information, reference home patterns, and data indicating the degree of risk in that case in analyzing the actual risk, and analyzes them. By analyzing, the association degree shown in FIG. 6 is created.

In the example of the degree of association shown in FIG. 6, the node 61b is a node in which the reference time zone information is the combination of the time zone S with respect to the reference image information P11. The degree of association of 0% is w16. In other words, there are times when crime is less likely to be intruded by suspicious persons and times when it is greater. Especially, when the number of suspicious persons intrudes in the daytime is small and the number of suspicious persons in the nighttime is large, the degree of risk is analyzed in advance in relation to the reference image information for each of the time zones S to V,... Are stored in association with each other.

Similarly, when such a degree of association is set, image information is newly acquired and at-home time zone information is acquired. The image information corresponds to the reference image information, and the time zone information corresponds to the reference at-home time zone information.

The time zone information is acquired by extracting the time zone at the time of shooting the image information in the house whose risk level is to be determined. Then, the extracted time zone information is compared with the reference time zone information to make a determination. In such a case, the database in which the reference time zone information is recorded is accessed. For example, when the time zone information is from 9:20 to 9:30 (time zone V), the degree of risk is determined via the time zone V (9:20 to 9:30) of the same reference time zone information. To seek.

In obtaining the risk level, the pre-acquired association level shown in FIG. 6 is referred to. For example, when the acquired image is the same as or similar to the reference image information P12 and the time zone information is the time zone V, the combination is associated with the node 61c, and the node 61c is associated with the risk degree of 30%. The degree w17 is associated with the degree of risk 70%, and the risk degree 70% is associated with the degree of association w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

FIG. 7 shows an example in which, in addition to the above-mentioned reference image information and reference housing structure information, a combination of reference person information and a degree of risk for the combination are set in three or more levels. Is shown.

The reference person information is information obtained by extracting the person shown in the reference image information. The person information includes facial features (face contour, conspicuousness, hairstyle, presence/absence of glasses, wrinkles, scratches, etc.), age and gender estimated from facial features, and the like. A neural network may be used as the method for extracting the facial features. In such a case, (1) edge extraction is performed from the image data of the facial portion. (2) A skin color region is extracted from the image data of the face portion, (3) A region corresponding to the skin color region extracted in (2) is extracted from the edge image generated in (1), (4) Corresponding to the skin color region A well-known method is used, such as calculating cumulative histograms in the vertical direction and the horizontal direction from the edge image, and (5) using the number of pixels in the cumulative histogram in which the brightness is equal to or greater than a predetermined threshold value as NN (neural network) input data. You may do so. Further, (6) NN may be used to estimate the age and sex of the visitor based on the input data and the teacher data.

In such a case, as shown in FIG. 7, the degree of association is such that the set of combinations of the reference image information, the reference house structure information, and the reference person information is the intermediate nodes 61a to 61e as described above. Will be expressed.

For example, in FIG. 7, in the node 61c, the reference image information P12 has the association degree w3, the reference house structure information “structure G” has the association degree w7, and the reference person information “person β (for example, person information For a wife who often visits next door)” is associated with a degree of association of w11. Similarly, in the node 61e, the reference image information P13 has the association degree w5, the reference house structure information “structure G” has the association degree w8, and the reference person information “person α (for example There is no male in his 40's” with a relevance of w10. Even when the reference person information is not registered, the fact that it is not registered may be treated as one piece of reference person information.

Similarly, when such a degree of association is set, the degree of risk at the time when the new image information is actually acquired is calculated based on the newly acquired image information, the housing structure information, and the person information. .. The personal information referred to here is extracted from the actually acquired image information by performing image analysis by the same method as the extraction of the reference personal information.

The degree of association shown in FIG. 7, which is acquired in advance, is referred to when the degree of risk is calculated. For example, when the acquired image is the same as or similar to the reference image information P12, the reference house structure information “structure G”, and the extracted person information is the person β, the combination is associated with the node 61c, The node 61c is associated with a degree of risk of 30% with the degree of association w17 and with a degree of risk of 70% with the degree of association w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

If the person is not registered in the reference person information, it is assumed to be the person β, and even if the extracted person information is a person who is not registered in the reference person information, the person β is regarded as being input and the solution search is performed. Becomes

It should be noted that this reference person is also used for the combination of the reference image information and the reference location information, the combination of the reference image information and the reference home pattern information, and the combination of the reference image information and the reference time information. The degree of association may be defined by further including a combination with information. Further, the degree of association may be defined by a combination of the reference image information and the reference person information.

FIG. 8 is an example in which, in addition to the above-described reference image information and reference housing structure information, a combination of reference audio information and the degree of risk for the combination are set in three or more levels. Is shown.

The reference audio information is audio that is actually recorded through a microphone or the like at the time of shooting the reference image information (or a predetermined time before and after the shooting). The analysis of the voice information may be performed by well-known means or may be finely analyzed by using the NN. Alternatively, the audio information may be analyzed on the frequency axis.

In such a case, as shown in FIG. 8, the degree of association is such that the set of the combination of the reference image information, the reference house structure information, and the reference voice person information is the intermediate nodes 61a to 61e, as described above. Will be expressed as.

For example, in FIG. 8, in the node 61c, the reference image information P12 has a relevance degree w3, the reference house structure information “structure G” has a relevance degree w7, and the reference voice information “voice X” has a relevance degree w11. Are associated with each other.

Similarly, even when such a degree of association is set, the degree of risk at the time when the new image information is actually acquired is calculated based on the newly acquired image information, the housing structure information, and the audio information. .. The audio information mentioned here is the audio actually recorded through a microphone or the like at the time of shooting the image information (or a predetermined time before and after the shooting). The analysis of the voice information may be performed by well-known means or may be finely analyzed by using the NN. Further, the audio information may be analyzed on the frequency axis.

To obtain this risk, reference is made to the degree of association acquired in advance and shown in FIG. For example, when the acquired image is the same as or similar to the reference image information P12, the reference house structure information “structure G”, and the extracted voice information is the voice X, the combination is associated with the node 61c, The node 61c is associated with a degree of risk of 30% with the degree of association w17 and with a degree of risk of 70% with the degree of association w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

It should be noted that this reference voice is also applied to the combination of the reference image information and the reference location information, the combination of the reference image information and the reference home pattern information, and the combination of the reference image information and the reference time information. The degree of association may be defined by further including a combination with information. Further, the degree of association may be defined by a combination of the reference image information and the reference audio information.

FIG. 8 is an example in which, in addition to the above-described reference image information and reference housing structure information, a combination of reference audio information and the degree of risk for the combination are set in three or more levels. Is shown.

The reference audio information is audio that is actually recorded through a microphone or the like at the time of shooting the reference image information (or a predetermined time before and after the shooting). The analysis of the voice information may be performed by well-known means or may be finely analyzed by using the NN. Alternatively, the audio information may be analyzed on the frequency axis.

In such a case, as shown in FIG. 8, the degree of association is such that the set of the combination of the reference image information, the reference house structure information, and the reference voice person information is the intermediate nodes 61a to 61e, as described above. Will be expressed as.

For example, in FIG. 8, in the node 61c, the reference image information P12 has a relevance degree w3, the reference house structure information “structure G” has a relevance degree w7, and the reference voice information “voice X” has a relevance degree w11. Are associated with each other.

Similarly, even when such a degree of association is set, the degree of risk at the time when the new image information is actually acquired is calculated based on the newly acquired image information, the housing structure information, and the audio information. .. The audio information mentioned here is the audio actually recorded through a microphone or the like at the time of shooting the image information (or a predetermined time before and after the shooting). The analysis of the voice information may be performed by well-known means or may be finely analyzed by using the NN. Further, the audio information may be analyzed on the frequency axis.

To obtain this risk, reference is made to the degree of association acquired in advance and shown in FIG. For example, when the acquired image is the same as or similar to the reference image information P12, the reference house structure information “structure G”, and the extracted voice information is the voice X, the combination is associated with the node 61c, The node 61c is associated with a degree of risk of 30% with the degree of association w17 and with a degree of risk of 70% with the degree of association w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.

It should be noted that this reference voice is also applied to the combination of the reference image information and the reference location information, the combination of the reference image information and the reference home pattern information, and the combination of the reference image information and the reference time information. The degree of association may be defined by further including a combination with information. Further, the degree of association may be defined by a combination of the reference image information and the reference audio information.

In FIG. 9, in addition to the reference image information and the reference house structure information described above, a combination of reference security service information and the degree of risk of the combination are set in three or more levels. An example is shown.

The reference security service information is whether or not the house has a contract with the security service of a security company, or the contract status regarding the specific contract content. The contract is, for example, when a door is broken or a window glass is broken, a security company comes to patrol a house from a security company.

In such a case, as shown in FIG. 8, the degree of association is such that the set of the combination of the reference image information, the reference house structure information, and the reference security service information is the intermediate node nodes 61a to 61e as described above. Will be expressed as.

For example, in FIG. 8, in the node 61c, the reference image information P12 has the association degree w3, the reference house structure information “structure G” has the association degree w7, and the “uncontracted” as the reference security service information has the association degree. It is linked with w11.

Even when such a degree of association is set, similarly, based on the newly acquired image information, the house structure information, and the security service information, the degree of risk at the time when the new image information is actually acquired is set. Ask. The security service information mentioned here relates to whether or not the house to be discriminated is actually contracted for security service of a security company, or the contract status regarding specific contract contents.

The degree of association shown in FIG. 9 which is acquired in advance in obtaining the degree of risk is referred to. For example, when the acquired image is the same as or similar to the reference image information P12, the reference house structure information “structure G”, and the extracted security service information is “uncontracted”, the combination is associated with the node 61c. In this node 61c, the risk level of 30% is associated with the association level w17, and the risk level of 70% is associated with the association level w18. As a result of such a degree of association, the degree of risk at the time when the new image information and approach information are actually acquired is obtained based on w17 and w18.
It should be noted that this reference security is also applied to the combination of the reference image information and the reference location information, the combination of the reference image information and the reference home pattern information, and the combination of the reference image information and the reference time information. The degree of association may be defined by further including a combination with service information. Further, the association degree may be defined by a combination of the reference image information and the reference security service information.

According to the present invention having the above-described configuration, it is possible to easily determine the risk of intrusion of a suspicious person in a house with a small amount of labor without requiring special skill. Further, according to the present invention, it is possible to make the determination of the degree of risk with higher accuracy than a human. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Further, the present invention is characterized in that the optimum physical properties and the generation mechanism are searched for through the association degrees set in three or more stages. The degree of association can be described by a numerical value from 0 to 100%, for example, in addition to the above-mentioned five levels, but is not limited to this, and at any level as long as it can be described by a numerical value of three or more levels. It may be configured.

By searching for the most probable risk based on the degree of association represented by three or more levels, the degree of association is high in situations where there are multiple possible candidates for higher risk. It is also possible to search and display in order. If it is possible to display to the user in the descending order of the degree of association, it is possible to preferentially display the more probable risk, and it is possible to call attention to the higher risk.

When the degree of risk is high, the danger can be escaped by contacting the security service company or the police, or by prompting the resident of the house to be alerted immediately. Especially when the degree of risk is higher, it is possible to protect the safety by alerting residents through voices or the like or by generating a voice outside to discourage a suspicious person from intruding. Further, according to the present invention, since the accuracy of detecting the degree of risk is high, it is only necessary to carry out the operation of calling the police only when it is really necessary without calling the police unnecessarily.

In addition to this, according to the present invention, it is possible to make a determination without missing the determination result of an output having an extremely low degree of association such as 1%. Remind users that even output discrimination results with a very low degree of association are connected as slight signs, and may be useful as the discrimination results once every tens or hundreds of times. can do.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is set low, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but there is a low possibility that a more appropriate discrimination result can be suitably detected, and a lot of noise may be picked up. is there. On the other hand, if the threshold value is set high, it is highly possible that the optimal risk can be detected with high probability, but normally, the degree of association is low, and although it is passed through, it appears once every tens or hundreds of times. In some cases, the solution may be overlooked. It is possible to decide which is to be emphasized based on the idea of the user side and the system side, but it is possible to increase the degree of freedom in selecting such a point to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. Further, based on the camera image captured in the house and the acquired reference image information, reference location information, reference at-home pattern information, reference time information, reference voice information, reference security service information, etc., and input parameters, When new knowledge about the relationship with the output solution (risk level) is discovered, the degree of association is increased or decreased according to the knowledge.
In other words, this update is equivalent to learning in artificial intelligence. This is a learning act because new data is acquired and reflected in the learned data.
Further, not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, etc. may be used for the process of first creating a learned model and the above-mentioned update. In the case of unsupervised learning, instead of reading a data set of input data and output data for learning, information corresponding to the input data (reference image information, reference location information, reference home pattern information, reference (Time information, reference voice information, reference security service information, etc.) may be read and learned, and the degree of association related to output data may be self-formed therefrom.

This update of the degree of association is not based on the information that can be acquired from the public communication network, but is also artificial on the system side or the user side based on the contents of research data and papers by academic experts, academic conference presentations, newspaper articles, books, etc. Alternatively, it may be automatically updated. You may make it utilize artificial intelligence in these update processes.

1 Danger Level Discrimination System 2 Discrimination Device 21 Internal Bus 23 Display Unit 24 Control Unit 25 Operating Unit 26 Communication Unit 27 Estimating Unit 28 Storage Unit 61 Node

Claims (9)

In the risk judgment program for judging the risk of suspicious person intrusion into the house,
A combination having pre-acquired three or more levels of association between a combination having reference image information obtained by photographing the outside of the house and reference location information for specifying the location of the house, and a risk level for the combination. Steps,
When newly determining the degree of risk, an information acquisition step of acquiring image information by newly photographing the outside of the house and acquiring location information indicating the location of the house,
A discriminating step for discriminating the risk of intrusion of a suspicious person into the house based on the image information and the location information obtained through the information obtaining step by referring to the degree of association obtained in the obtaining step. A risk level determination program that is executed by the. In the association degree acquisition step, a combination having reference person information in which a person is extracted by further analyzing the reference image information, and a degree of association of three or more levels with a risk degree for the combination are acquired in advance,
In the information acquisition step, when newly determining the degree of risk, the person information in which the person is extracted is further acquired by analyzing the image information acquired by photographing the outside of the house,
The risk determination program according to claim 1, wherein the determination step further determines the risk based on the personal information acquired through the information acquisition step. In the association degree acquisition step, a combination having the reference voice information recorded when the reference image information is captured and the degree of risk of the combination are acquired in advance in three or more levels.
In the information acquisition step, when newly determining the degree of risk, the outside of the house is photographed and the voice information recorded at the same time is further acquired,
The risk discriminating program according to claim 1 or 2, wherein in the discriminating step, the risk is discriminated based on voice information acquired through the information acquiring step. In the association degree acquisition step, the house further obtains in advance a degree of association of three levels or more between the combination having the reference security service information indicating the contract status of the security service of the security company and the risk degree for the combination,
In the information acquisition step, when newly determining the degree of risk, security service information indicating the contract status of the security service in the house is further acquired,
The risk determination program according to any one of claims 1 to 3, wherein the determination step further determines the risk based on the security service information. In the association degree obtaining step, further to the above combination, the three or more stages of association degree between the risk for the combination obtained in advance and a reference housing structure information containing structural information about the housing,
In the information acquisition step, when the risk level is newly determined, the housing structure information of the house is acquired,
The determination step further determines the risk level of a suspicious person intruding into the house based on the housing structure information acquired through the information acquisition step. The risk determination program described in the section. In the association degree obtaining step further and the combination and a reference home pattern information indicating a home pattern resident of the house, previously obtained three or more stages association degree between the risk for the combination,
In the information acquisition step, when newly determining the degree of risk, in-home pattern information indicating the in-home pattern of the house is acquired,
The determining step further determines a risk level of a suspicious person intruding into the house based on the at-home pattern information acquired through the information acquiring step. The risk determination program described in the section. In the association degree acquisition step, further , three or more levels of association degree between the combination having the reference time zone information indicating the time zone at the time of capturing the reference image information and the risk degree for the combination are acquired in advance. ,
In the information acquisition step, when newly determining the degree of risk, the time zone information in the time zone at the time of the shooting is further acquired,
In the above determination step, further based on the time zone information, suspicious person entering any one risk determination program according one of claims 1 to 6, characterized in that to determine the risk of the above housing. 9. The risk determination according to claim 1, wherein the association degree obtaining step uses the association degree corresponding to a weighting coefficient of each output of a node of a neural network in artificial intelligence. program. In the risk determination system for determining the risk of suspicious persons entering a house,
A combination having pre-acquired three or more levels of association between a combination having reference image information obtained by photographing the outside of the house and reference location information for specifying the location of the house, and a risk level for the combination. Means and
When newly determining the degree of risk, an information acquisition unit that acquires image information by newly photographing the outside of the house and also acquires location information indicating the location of the house,
With reference to the degree of association obtained by the degree-of-association obtaining means, based on the image information and the location information obtained through the information obtaining means, a determining means for determining the risk of intruding a suspicious person into the house is provided. A risk determination system characterized by being equipped.

Images