Analysis information frequency analysis device, detection information characteristic determination device, analysis information frequency analysis method, detection information characteristic determination method, program and storage medium

Abstract

To provide an analysis information frequency analysis device which analyzes the combination of states by combining the detected states and a detection information characteristic determination device using the same.SOLUTION: An analysis information frequency analysis device 10 according to the present invention includes an analysis information acquisition unit 11, an analysis target generation unit 12, a frequency analysis unit 13, and an analysis result output unit 14. The analysis information acquisition unit 11 acquires analysis information. The analysis information is the information on the analysis result related to information detected within a certain period of time. The analysis target generation unit 12 extracts multiple pieces of individual state information for each analysis information and generates analysis target information by combining the pieces of individual state information. The individual state information is the information on the state in any time zone included in the analysis information. The frequency analysis unit 13 analyzes the analysis target information and generates analysis result information on the analysis target information whose frequency of occurrence matches a specification condition. The analysis result output unit 14 outputs the analysis result information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an analysis information frequency analysis device, a detection information characteristic determination device, an analysis information frequency analysis method, a detection information characteristic determination method, a program, and a recording medium. [Background technology]

[0002] Artificial intelligence is being used to detect fraudulent activities. A technology that analyzes images to analyze abnormal behavior has been disclosed (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-17939 A Summary of the Invention [Problem to be solved by the invention]

[0004] The technology in Patent Document 1 can define one behavior based on image analysis. However, there is a problem in that some normal behaviors and fraudulent behaviors are similar, and it may be difficult to distinguish between them based on only one behavior.

[0005] SUMMARY OF THE PRESENT EMBODIMENTS Accordingly, an object of the present invention is to provide an analytical information frequency analysis device that combines detected states and analyzes the state combinations, and a detection information feature determination device that utilizes the same. [Means for solving the problem]

[0006] In order to achieve the above object, the analysis information frequency analysis device of the present invention comprises: The present invention includes an analysis information acquisition unit, an analysis target generation unit, a frequency analysis unit, and an analysis result output unit, The analysis information acquisition unit acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, the analysis target generation unit extracts a plurality of pieces of individual state information for each of the analysis information, and generates analysis target information by combining the individual state information; The individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis unit analyzes the analysis target information and generates analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output unit outputs the analysis result information.

[0007] The detection information characteristic determination device of the present invention comprises: The apparatus includes an information acquisition unit, a judgment target generation unit, a feature judgment unit, and an information output unit, The feature determination unit includes the analysis information frequency analysis device of the present invention, The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The information acquisition unit acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, the judgment target generation unit extracts a plurality of individual state target information for each of the detection information, and generates judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; Alternatively, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is no matching selection condition information, generates determination result information regarding the determination, the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output unit outputs the determination result information.

[0008] The analysis information frequency analysis method of the present invention includes the steps of: The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, Each of the above steps is executed by a computer.

[0009] The detection information feature determination method of the present invention includes the steps of: The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination step includes an analysis information frequency analysis method, The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquiring step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and combining the individual state target information to generate judgment target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination, Alternatively, the feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination, the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, Each of the above steps is executed by a computer.

[0010] The first program of the present invention is The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, The program causes a computer to execute each of the above procedures.

[0011] The second program of the present invention is The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; Alternatively, the feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, The program causes a computer to execute each of the above procedures.

[0012] The first recording medium of the present invention is The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, A computer-readable recording medium records a program for causing a computer to execute each of the above procedures.

[0013] The second recording medium of the present invention is The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; Alternatively, the feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, A computer-readable recording medium records a program for causing a computer to execute each of the above procedures. Effect of the Invention

[0014] According to the present invention, it is possible to analyze a combination of states based on the frequency of occurrence, and to automatically determine whether or not a detected state corresponds to fraudulent activity or the like, using the analysis results. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram illustrating an example of a configuration of the analysis information frequency analysis device according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of the analysis information frequency analysis device according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart illustrating an example of processing in the analytical information frequency analysis device of the first embodiment. [Figure 4] FIG. 4 is a reference diagram for explaining an example of the process of the analysis information frequency analysis method according to the first embodiment. [Diagram 5] FIG. 5 is a reference diagram for explaining another example of the process of the analysis information frequency analysis method according to the first embodiment. [Figure 6] FIG. 6 is a block diagram illustrating an example of a configuration of a detected information characteristic determining device according to the second embodiment. [Figure 7] FIG. 7 is a block diagram illustrating an example of a hardware configuration of a detected information characteristic determining device according to the second embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of processing in the detected information characteristic determining device according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] The embodiments of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiments. In each of the drawings, the same parts are given the same reference numerals. In addition, the explanations of each embodiment can be mutually incorporated unless otherwise specified, and the configurations of each embodiment can be combined unless otherwise specified.

[0017] [Embodiment 1] Fig. 1 is a block diagram showing an example of the configuration of an analysis information frequency analysis device 10 (hereinafter also referred to as "this analysis device") according to this embodiment. As shown in Fig. 1, this analysis device 10 includes an analysis information acquisition unit 11, an analysis target generation unit 12, a frequency analysis unit 13, and an analysis result output unit 14. In addition, although not shown, this analysis device 10 may include, for example, an input unit, an output unit, a display unit, and / or a storage unit.

[0018] The present analysis device 10 may be, for example, a single device including each of the above-mentioned units, or may be a device to which each of the above-mentioned units can be connected via a communication line network. The present analysis device 10 may also be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and a known network may be used, for example, wired or wireless. Examples of the communication line network include an Internet line, a World Wide Web (WWW), a telephone line, a Local Area Network (LAN), a Storage Area Network (SAN), a Delay Tolerant Networking (DTN), a Low Power Wide Area (LPWA), and a Local 5G (L5G). Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), a Local 5G, and a LPWA. Examples of the wireless communication may include a form in which each device directly communicates with each other (Ad Hoc communication), an infrastructure (infrastructure communication), and an indirect communication via an access point. The present analysis device 10 may be incorporated into, for example, a server of a system. The analytical device 10 may be, for example, a personal computer (PC, for example, desktop type or notebook type) on which the program of the present invention is installed, a smartphone, a tablet terminal, etc. Furthermore, the analytical device 10 may be in the form of cloud computing or edge computing, for example, in which at least one of the units is on a server and the other units are on a terminal.

[0019] 2 shows an example of a block diagram of the hardware configuration of the present analytical device 10. The present analytical device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, an output device 106, a communication device 107, etc. Each part of the present analytical device 10 is connected to each other via the bus 103 by each interface (I / F).

[0020] The central processing unit 101 cooperates with other components through a controller (system controller, I / O controller, etc.) and controls the entire analysis device 10. In the analysis device 10, the central processing unit 101 executes, for example, the program of the present invention and other programs, and reads and writes various information. Specifically, for example, the central processing unit 101 functions as an analysis information acquisition unit 11, an analysis target generation unit 12, a frequency analysis unit 13, and an analysis result output unit 14. In the case where the analysis device 10 includes the output unit, the central processing unit 101 may function as the output unit. The analysis device 10 may include, as a calculation device, other calculation devices such as a CPU, a GPU (Graphics Processing Unit), an APU (Accelerated Processing Unit), etc., or may include a combination of a CPU and these.

[0021] The bus 103 can also be connected to, for example, an external device. Examples of the external device include a user terminal, an external storage device (external database, etc.), a printer, an external input device, an external display device, an external imaging device, etc. The present analysis device 10 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0022] An example of the memory 102 is a main memory (primary storage device). When the central processing unit 101 performs processing, the memory 102 reads various operation programs, such as the program of the present invention, stored in the storage device 104 described below, and the central processing unit 101 receives data from the memory 102 and executes the program. The main memory is, for example, a RAM (random access memory). The memory 102 may also be, for example, a ROM (read only memory).

[0023] The storage device 104 is also called an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operation program including the program of the present invention. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing from and to the recording medium. The recording medium is not particularly limited, and may be, for example, an internal or external type, such as a HD (hard disk), a CD-ROM, a CD-R, a CD-RW, an MO, a DVD, a flash memory, or a memory card. The storage device 104 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD). When the present analysis device 10 includes the storage unit, for example, the storage device 104 functions as the storage unit. The storage unit can store, for example, analysis information, analysis target information, analysis result information, detection information, judgment target information, and judgment result information, which will be described later.

[0024] In the present analysis device 10, the memory 102 and the storage device 104 can also store various information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present analysis device 10, and information used when the present analysis device 10 executes processing. In this case, the memory 102 and the storage device 104 may store, for example, the analysis information. Note that at least a part of the information may be stored, for example, in an external server other than the memory 102 and the storage device 104, or may be stored in a distributed manner in multiple terminals using block chain technology or the like.

[0025] The present analysis device 10 further includes, for example, an input device 105 and an output device 106. Examples of the input device 105 include pointing devices such as a touch panel, a track pad, and a mouse; a keyboard; an imaging means such as a camera and a scanner; a card reader such as an IC card reader and a magnetic card reader; and an audio input means such as a microphone. Examples of the output device 106 include a display device such as an LED display and a liquid crystal display; an audio output device such as a speaker; a printer; and the like. In the present embodiment 1, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated device, such as a touch panel display.

[0026] Next, an example of the analyzed information frequency analysis method of this embodiment will be described with reference to the flowchart of Fig. 3. The analyzed information frequency analysis method of this embodiment is carried out as follows, for example, using the present analysis device 10 of Fig. 1 or Fig. 2. Note that the analyzed information frequency analysis method of this embodiment is not limited to use of the present analysis device 10 of Fig. 1 or Fig. 2.

[0027] First, the analysis information acquisition unit 11 acquires analysis information (S1, analysis information acquisition step). The analysis information is information on the analysis result related to information detected within a certain period of time. The detected information is, for example, an image captured by a camera, a video camera, or the like, and may be a video or a still image, and may be captured continuously or intermittently. The analysis result targeted by this analysis device may be, for example, any analysis result of behavior analysis by behavior analysis AI or object analysis by object detection AI. The certain period of time may be, for example, a period of time that is continuously acquired at intervals of 5 minutes, and the method of designation is not limited, such as 1 minute before and after the time when a certain specific state is detected. The behavior analysis allows the behavior of the detected image to be analyzed based on changes in state over time. The analyzed behavior is, for example, a behavior such as picking up a product or crouching down on the spot. The object analysis allows the detected image to be analyzed for the shape, presence, and other states of a specific object. The analyzed state is, for example, the state of whether or not a worker is wearing a helmet. As described above, the behavior can be considered as a change in state, and therefore, hereinafter, the analyzed behavior and the analyzed state are collectively referred to as a state. The analysis information acquisition unit 11 acquires the analysis information from, for example, a database that stores the analysis results of an image captured by an imaging device, but is not limited to this. The method of acquiring the analysis results may be any method, such as directly acquiring the analysis results from an imaging device having an analysis function.

[0028] Next, the analysis target generating unit 12 extracts a plurality of individual state information for each of the analysis information, and generates analysis target information by combining the individual state information (S2, analysis target generating step). The individual state information is information on a state in an arbitrary time period included in the analysis information. In the case of behavior analysis, the arbitrary time period is, for example, a time period related to the passage of time required to grasp a behavior, such as the time from reaching for a product, grabbing the product, and bringing the product to one's hand. In the case of object analysis, the arbitrary time period is, for example, an arbitrary time period for confirming the state of an object. Thus, the arbitrary time period may be, for example, a specific moment, or may have a certain width. The analysis information acquired by the analysis information acquiring unit 11 includes, for example, a plurality of actions within a certain period of time. For example, a plurality of actions may be performed within a period of three minutes, such as picking up a product, crouching down on the spot, putting the product in a bag, and standing up on the spot. In addition, as for the change in the state of an object, for example, a helmet may be put on or taken off within a period of three minutes, and there is a state progression, such as a state with a helmet and a state without a helmet, depending on the passage of time. Therefore, the individual state information is information on the contents of the analyzed state, such as picking up a product. The analysis target generation unit 12 extracts a plurality of states from the analysis information within a certain period of time, combines the extracted plurality of states, and generates the analysis target information to be analyzed. Since there are individual differences in the speed of movements, the combination of the extracted plurality of states does not necessarily have to be combined in the same time unit, and for example, the combination may be based only on the changed state. The method of combination is, for example, a combination of consecutive actions such as picking up a product and crouching down on the spot, but is not limited to this, and consecutive actions within a certain period of time do not necessarily have to be combined in order, and any setting may be used.

[0029] Next, the frequency analysis unit 13 analyzes the analysis target information and generates analysis result information on the analysis target information whose occurrence frequency matches a specified condition (S3, frequency analysis step). The specified condition is, for example, how many times it occurred within the last month, and an upper limit and a lower limit may be set in the condition setting. The upper limit and the lower limit may be the same value. In addition to setting a threshold value for the upper limit and the lower limit, for example, the frequency is tallied and the highest frequency is set as "those that exceed the frequency upper limit" and the rest as "those that do not meet the frequency lower limit", or conversely, the lowest frequency is set as "those that do not meet the frequency lower limit" and the rest as "those that exceed the frequency upper limit", and any other method for setting the upper limit and the lower limit may be used. Furthermore, the specified condition is not limited to this, and a time period such as 5:00 p.m. to 7:00 p.m. may be specified, or any other setting may be used according to the purpose of the analysis. The analysis result information may include at least one of normal state information and exception state information. The normal state information is information on the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, and can be said to be a combination of states that is usually seen often. The exceptional state information is information on the analysis result information whose occurrence frequency does not meet a specified lower frequency limit, and can be said to be a combination of states that does not occur often, and can be used as a criterion for judging, for example, abnormal behavior. Therefore, the frequency analysis unit 13 can be said to analyze the analysis target information generated by the analysis target generation unit 12 by combining states, based on the occurrence frequency, and extract a combination of states with a specified frequency. In addition, the frequency analysis unit 13 can extract information on a normal state, which is a combination of states that usually occurs often, and extract a state related to an exceptional state, which is a combination of states that does not occur often. Note that the analysis result information extracted as a result of the analysis may be managed, for example, by attaching an identification number to it, or by attaching information on characteristics such as behavior, or may have necessary information added thereto.

[0030] Next, the analysis result output unit outputs the analysis result information (S3, analysis result output step). The analysis result information is output to, for example, a dedicated database or the like, but is not limited thereto, and may be arbitrarily set according to the purpose, for example, to be displayed on a dedicated monitor.

[0031] Hereinafter, an example of a specific process of the analysis information frequency analysis method using the present analysis device 10 will be described. Note that the following explanation is an example of a specific flow, and as described above, the present analysis device 10 and the analysis information frequency analysis method of the present embodiment are not limited to the following explanation. Furthermore, the analysis information frequency analysis method of the present embodiment is not limited to the use of the present analysis device 10.

[0032] First, the analysis information acquisition unit 11 acquires the analysis information. The upper part of FIG. 4 is an example of the analysis information. In FIG. 4, the analysis result of the behavior of two people, A and B, for three minutes from 10 o'clock is shown. Among the analyzed behaviors, there is one that is analyzed as "inventory taking or shoplifting", but the specific behavior is unknown, but it is an analysis result that it is impossible to distinguish which behavior it is. Next, the analysis target generation unit 12 combines behaviors based on the analysis information as shown in the lower part of FIG. 4, and generates analysis target information. Among the behaviors of A shown in FIG. 4, (a) to (c) and among the behaviors of B shown in FIG. 4, (d) to (f) are examples of analysis target information. Next, the frequency analysis unit 13 analyzes each analysis target information. As (a) and (d) are common, they are behaviors that are frequently performed in other cases, and the same is true for (b) and (e). (c) is a behavior that is often performed by employees and is also a behavior that is frequently performed in other cases. (f) is a behavior that is not often seen in other cases. From the above, the frequency analysis unit 13 generates analysis result information with the behavior of (f) as exception state information. Then, the analysis result output unit 14 outputs the analysis result information to a dedicated database, where the analysis results are accumulated.

[0033] FIG. 5 is an example of object detection regarding wearing of helmets at a work site. The flow of processing is the same as that of the above-mentioned behavior analysis. The upper part of FIG. 5 shows the analysis result, which is reconfigured as the analysis target information as shown in the lower part. As a result, the change in state is divided into four modes: wearing a helmet to wearing it, not wearing it to wearing it, wearing it to not wearing it, and not wearing it to not wearing it. For two people A and B in the time period of FIG. 5, it can be analyzed that wearing it to wearing it four times, not wearing it to wearing it two times, wearing it to not wearing it once, and not wearing it to not wearing it once, and it is possible to analyze the frequency. It can be analyzed that it is normal to continue wearing a helmet during the time period of FIG. 5.

[0034] The analysis information frequency analysis device of this embodiment can analyze a combination of states based on the occurrence frequency and classify the characteristic states. Therefore, by using the analysis device 10 of this embodiment, it is possible to analyze the detected states with higher accuracy.

[0035] [Embodiment 2] The second embodiment is a detection information characteristic determination device of the present invention.

[0036] The detection information characteristic judgment device 20 (hereinafter, also referred to as "this judgment device") of this embodiment will be described with reference to FIG. 6. FIG. 6 is a block diagram showing an example of the configuration of this judgment device 20 of this embodiment. As shown in FIG. 6, this judgment device 20 of this embodiment includes an information acquisition unit 21, a judgment target generation unit 22, a characteristic judgment unit 23, and an information output unit 24, and the characteristic judgment unit 23 includes the configuration of this analysis device 10 of embodiment 1 (analysis information acquisition unit 11, analysis target generation unit 12, frequency analysis unit 13, and analysis result output unit 14). The configuration of this analysis device 10 of embodiment 1 included in this judgment device 20 is similar to that of this device 10 of embodiment 1, and the description thereof can be used.

[0037] The present determination device 20 may be, for example, a single device including each of the above-mentioned units, or each of the above-mentioned units may be a device that can be connected via a communication line network. The present determination device 20 may also be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and a known network may be used, for example, wired or wireless. Examples of the communication line network include an Internet line, a World Wide Web (WWW), a telephone line, a Local Area Network (LAN), a Storage Area Network (SAN), a Delay Tolerant Networking (DTN), a Low Power Wide Area (LPWA), and a Local 5G (L5G). Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), a Local 5G, and a LPWA. Examples of the wireless communication may include a form in which each device directly communicates with each other (Ad Hoc communication), an infrastructure (infrastructure communication), and an indirect communication via an access point. The present determination device 20 may be incorporated into, for example, a server of a system. The determination device 20 may be, for example, a personal computer (PC, for example, desktop type or notebook type) on which the program of the present invention is installed, a smartphone, a tablet terminal, etc. Furthermore, the determination device 20 may be in the form of cloud computing or edge computing, for example, in which at least one of the units is on a server and the other units are on a terminal.

[0038] 7 illustrates a block diagram of the hardware configuration of the present determination device 20. The hardware configuration of the present determination device 20 is similar to that of the present analysis device 10 of the first embodiment, except that the feature determination unit 23 includes the configuration of the present analysis device 10 of the first embodiment, and therefore the description thereof can be used.

[0039] Next, an example of the detection information characteristic determination method of this embodiment will be described with reference to the flowchart of Fig. 8. The detection information characteristic determination method of this embodiment is implemented as follows, for example, using the present determination device 20 shown in Figs. 6 and 7. Note that the detection information characteristic determination method of this embodiment is not limited to use of the present determination device 20 shown in Figs. 6 and 7.

[0040] Each step of the analyzed information frequency analysis method included in the present determination device 20 of this embodiment is similar to each step (S1 to S4) of the analyzed information frequency analysis method of embodiment 1, and therefore the explanations thereof can be cited.

[0041] The information acquisition unit 21 of the present judgment device 20 of this embodiment acquires detection information (S1B, information acquisition step). The detection information is information on the analysis result related to information detected within a certain period of time regarding the judgment target. The certain period of time and the analysis result correspond to the analysis information in the present analysis device 10 of embodiment 1, and the setting contents are the same as those in the case of the analysis information, so the explanation thereof can be used. Furthermore, the method of acquiring the detection information is also the same as that in the case of the analysis information acquisition unit 11 of the present analysis device 10, so the explanation thereof can be used.

[0042] Next, the judgment target generating unit 22 extracts a plurality of pieces of individual state target information for each piece of detection information, and generates judgment target information by combining the individual state target information (S2B, judgment target generating step). The individual status target information is information on a status at any time period included in the detection information. The judgment target information is contrasted with the analysis result information of the present analysis device 10, and the content of the information corresponds to the analysis target information of the present analysis device 10, so the explanation thereof can be used.

[0043] Next, the characteristic judgment unit 23 judges whether there is selection condition information that matches the judgment target information, and if there is matching selection condition information, generates judgment result information regarding the judgment (S3B, characteristic judgment step). The characteristic judgment unit 23 may also judge whether there is selection condition information that matches the judgment target information, and if there is no matching selection condition information, generate judgment result information regarding the judgment. The selection condition information is information within an arbitrarily selected range from the normal state information and the exceptional state information.

[0044] Specifically, the feature determination unit 23 may select the normal state information as the selection condition information, and generate the determination result information when the selection condition information matches the normal state information. This makes it possible to determine whether the detection information to be determined corresponds to a normal state. The determination result information may include necessary information, such as an indication that the state is normal, an indication of the content of the behavior, etc. As a result, the determination result can be used, for example, not only to confirm whether the work is being performed as normal, but also to confirm the normal state and consider the layout of the store or the layout of objects in the work place.

[0045] Furthermore, the characteristic determination unit 23 may, for example, select the exceptional state information as the selection condition information, and generate the determination result information when the selection condition information matches. This makes it possible to detect abnormal behavior, etc. The normal state information may be selected as the selection condition information, and generate the determination result information when the selection condition information does not match. This makes it possible to detect anything that deviates from the normal state information as an abnormal state, even if it does not fall under the exceptional state information.

[0046] The selection condition information may be based on a selection of both the exceptional state information and the exceptional state information, and the selection range may be set to a condition, such as excluding those wearing employee uniforms. In addition, the conditions for judgment may be set arbitrarily, whether or not they match the selection condition information.

[0047] The characteristic determination unit 23 may generate the determination result information including control information. For example, when generating the determination result information, information for controlling an external device, such as sounding an alarm or turning on a lamp, may be generated.

[0048] Next, the information output unit 24 outputs the judgment result information (S4B, information output step). The output of the judgment result information is similar to that of the present analysis device 10, and therefore the description thereof can be used. Note that, if the judgment result information includes the control information, the control information is output to, for example, an alarm device, a lamp, etc., in accordance with the control information.

[0049] Hereinafter, an example of a specific process of the detection information feature determination method using the present determination device 20 will be described. Note that the following explanation is an example of a specific flow, and as described above, the present determination device 20 and the detection information feature determination method of the present embodiment are not limited to the following explanation. In addition, the detection information feature determination method of the present embodiment is not limited to the use of the present determination device 20.

[0050] First, the information acquisition unit 21 acquires the detection information. Next, the judgment target generation unit 22 generates judgment target information from the detection information. Then, the feature judgment unit 23 compares the judgment target information with the analysis result information generated by the present analysis device 10, and judges whether the specified condition is met. Note that, for example, if the purpose is to detect fraudulent activity, each process up to this point is performed continuously. As a result, if it is judged that something satisfies the specified condition, such as abnormal behavior, the feature judgment unit 23 generates judgment result information. Then, the information output unit 24 outputs the judgment result information, such as displaying it on a dedicated monitor.

[0051] The detected information characteristic determination device of this embodiment can automatically determine whether a combination of detected states is an unusual state by using the analysis result by the analyzed information frequency analysis device of embodiment 1. Therefore, for example, it is possible to detect fraudulent acts with higher accuracy.

[0052] [Embodiment 3] The first program of the present embodiment is a program for making a computer execute each step of the above-mentioned analysis information frequency analysis method. Specifically, the program of the present embodiment is a program for making a computer execute, for example, an analysis information acquisition procedure, an analysis target generation procedure, a frequency analysis procedure, and an analysis result output procedure.

[0053] The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information.

[0054] The first program of the present embodiment can also be said to be a program that causes a computer to function as, for example, an analysis information acquisition procedure, an analysis target generation procedure, a frequency analysis procedure, and an analysis result output procedure.

[0055] The second program of this embodiment is a program for causing a computer to execute each step of the above-mentioned detection information characteristic determination method. Specifically, the program of this embodiment is a program for causing a computer to execute, for example, an information acquisition step, a determination target generation step, a characteristic determination step, an information output step, and each step of the analysis information frequency analysis method included in the characteristic determination step.

[0056] The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting individual state target information from the detection information and generating judgment target information constituted by the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; Alternatively, a determination is made as to whether or not there is selection condition information that matches the judgment target information, and if there is no matching selection condition information, judgment result information regarding the judgment is generated; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information.

[0057] In addition, the second program of this embodiment can also be said to be a program that causes a computer to function, for example, as an information acquisition procedure, a judgment target generation procedure, a feature judgment procedure, and an information output procedure, as well as each step of the analysis information frequency analysis method included in the feature judgment procedure.

[0058] The program of this embodiment can be implemented by using the descriptions in the analysis information frequency analysis device and analysis information frequency analysis method, and the detection information feature determination device and detection information feature determination method of the present invention. In each of the steps, for example, the "step" can be read as "processing". In addition, the program of this embodiment may be recorded in a computer-readable recording medium. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples thereof include random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (for example, SSD (Solid State Drive), USB flash memory, SD / SDHC card, etc.), optical disk (for example, CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy (registered trademark) disk (FD), etc. In addition, the program of this embodiment (for example, also referred to as a programming product or program product) may be in a form distributed from an external computer, for example. The "distribution" may be, for example, distribution via a communication network or distribution via a device connected by a wire. The program of the present embodiment may be installed and executed in the device to which it is distributed, or may be executed without being installed.

[0059] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0060] <Additional Notes> A part or all of the above-described embodiments can be described as follows, but is not limited to the following. (Appendix 1) The present invention includes an analysis information acquisition unit, an analysis target generation unit, a frequency analysis unit, and an analysis result output unit, The analysis information acquisition unit acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, the analysis target generation unit extracts a plurality of pieces of individual state information for each of the analysis information, and generates analysis target information by combining the individual state information; The individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis unit analyzes the analysis target information and generates analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output unit outputs the analysis result information. Analytical information frequency analysis device. (Appendix 2) The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency. 2. The analysis information frequency analysis apparatus of claim 1. (Appendix 3) The apparatus includes an information acquisition unit, a judgment target generation unit, a feature judgment unit, and an information output unit, The feature determination unit includes the analysis information frequency analysis device according to claim 2; The information acquisition unit acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, the judgment target generation unit extracts a plurality of individual state target information for each of the detection information, and generates judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output unit outputs the determination result information. Detected information characteristic determination device. (Appendix 4) The apparatus includes an information acquisition unit, a judgment target generation unit, a feature judgment unit, and an information output unit, The feature determination unit includes the analysis information frequency analysis device according to claim 2; The information acquisition unit acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, the judgment target generation unit extracts a plurality of individual state target information for each of the detection information, and generates judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is no matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output unit outputs the determination result information. Detected information characteristic determination device. (Appendix 5) The feature determination unit generates the determination result information including control information. 5. The detection information characteristic determination device according to claim 3 or 4. (Appendix 6) The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, Each of the steps is executed by a computer. Analysis information frequency analysis method. (Appendix 7) The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency. The analysis information frequency analysis method described in Appendix 6. (Appendix 8) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination step includes an analysis information frequency analysis method, The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquiring step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and combining the individual state target information to generate judgment target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination, the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, Each of the steps is executed by a computer. A method for determining characteristics of detected information. (Appendix 9) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination step includes an analysis information frequency analysis method, The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquiring step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and combining the individual state target information to generate judgment target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination, the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, Each of the steps is executed by a computer. A method for determining characteristics of detected information. (Appendix 10) The characteristic determination step generates the determination result information including control information, Each of the steps is executed by a computer. 10. A method for determining characteristics of detected information as described in appendix 8 or 9. (Appendix 11) The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, A program for causing a computer to execute each of the above procedures. (Appendix 12) The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency. 12. The program according to claim 11. (Appendix 13) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, A program for causing a computer to execute each of the above procedures. (Appendix 14) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, A program for causing a computer to execute each of the above procedures. (Appendix 15) The feature determination procedure generates the determination result information including control information; 15. The program according to claim 13 or 14, for causing a computer to execute each of the steps. (Appendix 16) The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step. The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the above procedures. (Appendix 17) The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency. 17. A recording medium as described in appended claim 16. (Appendix 18) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the above procedures. (Appendix 19) The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination procedure includes an analysis information frequency analysis method; The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information of an analysis result related to information detected within a certain period of time, The analysis target generating step includes extracting a plurality of pieces of individual state information for each of the analysis information, and combining the individual state information to generate analysis target information; The individual state information is information on a state at an arbitrary time period included in the analysis information, The frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result information includes at least one of normal state information and exception state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information on the analysis result information whose occurrence frequency does not meet a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquisition step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding a subject to be determined, The judgment target generating step includes extracting a plurality of individual state target information for each of the detection information, and generating judgment target information by combining the individual state target information; The individual state object information is information on a state at an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no selection condition information that matches, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the above procedures. (Appendix 20) The feature determination procedure generates the determination result information including control information; 20. A computer-readable recording medium according to claim 18 or 19, having a program recorded thereon for causing a computer to execute each of the procedures. [Industrial Applicability]

[0061] According to the present invention, a combination of states is analyzed based on the frequency of occurrence, and the results of the analysis are used to automatically determine whether a detected combination of states is an unusual state, which is useful for detecting fraudulent activities, for example. [Explanation of symbols]

[0062] 10 Analysis information frequency analysis device 11 Analysis information acquisition section 12 Analysis target generation section 13 Frequency Analysis Section 14 Analysis result output section 20. Detection information characteristic judgment device 21 Information Acquisition Department 22 Judgment target generation unit 23 Feature determination section 24 Information output section 101 Central Processing Unit 102 Memory 103 Bus 104 Storage device 105 Input Device 106 Output Device 107 Communication Devices

Claims

1. The analysis information acquisition unit, the analysis target generation unit, the frequency analysis unit, and the analysis result output unit are included. the analysis information acquisition unit acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generation unit extracts a plurality of pieces of individual state information for each piece of analysis information, and combines the individual state information to generate analysis target information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis unit analyzes the analysis target information and generates analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; the analysis result output unit outputs the analysis result information. Analysis information frequency analysis device.

2. the analysis result information includes at least one of normal state information and exceptional state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, The exception state information is information about the analysis result information whose occurrence frequency is less than a specified lower limit of frequency. The analysis information frequency analysis device according to claim 1.

3. The apparatus includes an information acquisition unit, a judgment target generation unit, a feature judgment unit, and an information output unit, The feature determination unit includes the analysis information frequency analysis device according to claim 2, The information acquisition unit acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding the object to be determined, the judgment target generation unit extracts a plurality of pieces of individual state target information for each of the detection information, and generates judgment target information by combining the individual state target information; The individual status target information is status information for an arbitrary time period included in the detection information, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output unit outputs the determination result information. Detection information characteristic determination device.

4. The apparatus includes an information acquisition unit, a judgment target generation unit, a feature judgment unit, and an information output unit, The feature determination unit includes the analysis information frequency analysis device according to claim 2, The information acquisition unit acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding the object to be determined, the judgment target generation unit extracts a plurality of pieces of individual state target information for each of the detection information, and generates judgment target information by combining the individual state target information; The individual status target information is status information for an arbitrary time period included in the detection information, the feature determination unit determines whether or not there is selection condition information that matches the determination target information, and if there is no matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output unit outputs the determination result information. Detection information characteristic determination device.

5. the feature determination unit generates the determination result information including control information.

5. The detection information characteristic determination device according to claim 3 or 4.

6. The method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generating step extracts a plurality of pieces of individual state information for each of the pieces of analysis information, and combines the pieces of individual state information to generate analysis target information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; The analysis result output step outputs the analysis result information, Each step is performed by a computer. Analysis information frequency analysis method.

7. The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination step includes an analysis information frequency analysis method, The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generating step extracts a plurality of pieces of individual state information for each of the pieces of analysis information, and combines the pieces of individual state information to generate analysis target information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; the analysis result information includes at least one of normal state information and exceptional state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, the exception state information is information about the analysis result information whose occurrence frequency is less than a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquiring step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding the object to be determined, The determination target generating step extracts a plurality of pieces of individual state target information for each piece of detection information, and generates determination target information by combining the individual state target information; The individual status target information is status information for an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is the matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, Each step is performed by a computer. Detection information feature determination method.

8. The method includes an information acquisition step, a judgment target generation step, a feature judgment step, and an information output step, The feature determination step includes an analysis information frequency analysis method, The analysis information frequency analysis method includes an analysis information acquisition step, an analysis target generation step, a frequency analysis step, and an analysis result output step, The analysis information acquisition step acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generating step extracts a plurality of pieces of individual state information for each of the pieces of analysis information, and combines the pieces of individual state information to generate analysis target information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency matches a specified condition; the analysis result information includes at least one of normal state information and exceptional state information, The normal state information is information about the analysis result information whose occurrence frequency exceeds a specified upper frequency limit, the exception state information is information about the analysis result information whose occurrence frequency is less than a specified lower limit of frequency, The analysis result output step outputs the analysis result information, The information acquiring step acquires detection information, The detection information is information of an analysis result related to information detected within a certain period of time regarding the object to be determined, The determination target generating step extracts a plurality of pieces of individual state target information for each piece of detection information, and generates determination target information by combining the individual state target information; The individual status target information is status information for an arbitrary time period included in the detection information, The feature determination step determines whether or not there is selection condition information that matches the determination target information, and if there is no matching selection condition information, generates determination result information regarding the determination; the selection condition information is information of a range arbitrarily selected from the normal state information and the exceptional state information, The information output step outputs the determination result information, Each step is performed by a computer. Detection information feature determination method.

9. A method comprising: an analysis information acquisition step; an analysis target generation step; a frequency analysis step; and an analysis result output step; The analysis information acquisition step acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generating step extracts a plurality of pieces of individual state information for each of the analysis information, and generates analysis target information by combining the individual state information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency meets a specified condition; the analysis result output step outputs the analysis result information; A program that causes a computer to execute each step.

10. A method comprising: an analysis information acquisition step; an analysis target generation step; a frequency analysis step; and an analysis result output step; The analysis information acquisition step acquires analysis information, The analysis information is information on an analysis result related to information detected within a certain period of time, the analysis target generating step extracts a plurality of pieces of individual state information for each of the analysis information, and generates analysis target information by combining the individual state information; the individual state information is information on a state at an arbitrary time period included in the analysis information, the frequency analysis step includes analyzing the analysis target information and generating analysis result information regarding the analysis target information whose occurrence frequency meets a specified condition; the analysis result output step outputs the analysis result information; A computer-readable recording medium that records a program for causing a computer to execute each procedure.

Images