Information provision device, information provision method, and information provision program

Abstract

To provide an information provision device, an information provision method, and an information provision program for effectively grasping an event occurring in a monitored target area.SOLUTION: A server device 10-1 collects monitoring data acquired by monitoring apparatuses 30 (30-1, 30-2,...) installed at each of a plurality of monitoring target locations included in a monitoring target area, detects, on the basis of the collected monitoring data, events that occur at the respective monitoring target locations, and generates a monitoring report including text data using a generation model that outputs text data indicating contents of the event that has occurred in the monitoring target area when the detected result is input.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information providing device, an information providing method, and an information providing program. [Background technology]

[0002] A technology is known that manages the progress of a work schedule corresponding to a work object based on work data corresponding to the process during work on the work object and image data capturing the state of the work object corresponding to that process, and automatically generates a work report that manages the state of the work object according to the progress. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-12312 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when implementing facility security or equipment management, it is difficult to effectively grasp events that occur in the monitored area. For example, when there are multiple monitored locations within the monitored area that need to be monitored regularly, it is difficult to automatically generate a monitoring report that explains events that occur within the monitored area in a way that is easy for administrators to read and understand.

[0005] The present invention has been made in view of the above, and has an object to effectively grasp events that occur in a monitored area. [Means for solving the problem]

[0006] An information providing device according to one embodiment of the present invention comprises a collection unit that collects monitoring data acquired by monitoring equipment installed at each of a plurality of monitored locations included in a monitored area; an analysis unit that detects events that have occurred at each of the plurality of monitored locations based on the collected monitoring data; and a generation unit that, when the detection results are input, generates a monitoring report including the text data using a machine learning model that outputs text data indicating the content of the events that have occurred in the monitored area.

[0007] An information provision method according to one embodiment of the present invention involves a computer collecting monitoring data acquired by monitoring equipment installed at each of a plurality of monitored locations included in a monitored area, detecting events that have occurred at each of the plurality of monitored locations based on the collected monitoring data, and generating a monitoring report including the text data using a machine learning model that, when the detection results are input, outputs text data indicating the content of the events that have occurred in the monitored area.

[0008] An information provision program according to one embodiment of the present invention causes a computer to execute a process of collecting monitoring data acquired by monitoring equipment installed at each of a plurality of monitored locations included in a monitored area, detecting events that have occurred at each of the plurality of monitored locations based on the collected monitoring data, and generating a monitoring report including the text data using a machine learning model that, when the detection results are input, outputs text data indicating the content of the events that have occurred in the monitored area. [Effects of the Invention]

[0009] According to the present invention, it is possible to effectively grasp events that occur in a monitored area. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of the configuration and processing of a patrol surveillance system according to a first embodiment. [Figure 2]1 is a block diagram showing an example of the configuration of each device in a patrol surveillance system according to a first embodiment. [Figure 3] 3 is a diagram illustrating an example of a monitoring data storage unit of the server device according to the first embodiment. FIG. [Figure 4] 4 is a diagram illustrating an example of a monitoring report storage unit of the server device according to the first embodiment. FIG. [Figure 5] FIG. 3 is a diagram illustrating an example of an analysis model storage unit of the server device according to the first embodiment. [Figure 6] FIG. 3 is a diagram illustrating an example of a generation model storage unit of the server device according to the first embodiment. [Figure 7] 4 is a flowchart showing an example of the overall flow of the patrol monitoring system according to the first embodiment. [Figure 8] 10 is a diagram illustrating an example of the configuration and processing of a patrol surveillance system according to a second embodiment. FIG. [Figure 9] FIG. 10 is a block diagram showing an example of the configuration of each device in the patrol surveillance system according to the second embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of an analysis model storage unit of a server device according to a second embodiment. [Figure 11] FIG. 10 is a diagram illustrating an example of a candidate information storage unit of a server device according to a second embodiment. [Figure 12] FIG. 10 is a diagram illustrating an example of a setting information storage unit of a server device according to a second embodiment. [Figure 13] FIG. 10 is a diagram showing a specific example 1 of a display screen of an operator terminal according to the second embodiment. [Figure 14] FIG. 10 is a diagram showing a specific example 2 of a display screen of an operator terminal according to the second embodiment. [Figure 15] 10 is a flowchart showing an example of the overall flow of the patrol surveillance system according to the second embodiment. [Figure 16] FIG. 1 is a diagram illustrating an example of a hardware configuration according to the first and second embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0011] An information providing device, an information providing method, and an information providing program according to a first embodiment and a second embodiment of the present invention will be described in detail below with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.

[0012] [Embodiment 1] The configuration and processing of the patrol monitoring system 100-1 according to the first embodiment, the configuration and processing of each device of the patrol monitoring system 100-1, and the processing flow of the patrol monitoring system 100-1 will be described below in order, and finally the effects of the embodiment will be described.

[0013] 1. Configuration and Processing of Patrol Monitoring System 100-1 The configuration and processing of a patrol monitoring system 100-1 according to an embodiment will be described in detail using FIG. 1. FIG. 1 is a diagram showing an example of the configuration and processing of the patrol monitoring system 100-1 according to an embodiment. Below, an example of the overall configuration of the patrol monitoring system 100-1, an example of the processing of the patrol monitoring system 100-1, and the effects of the patrol monitoring system 100-1 will be described. Note that in the embodiment, person identification, behavior detection, and abnormal state detection in facility security and equipment management will be described as an example, but the field of use is not limited thereto, and the system can also be applied to monitoring parks, roads, rivers, etc., and the analysis targets for behavior detection can be applied not only to people but also to construction machinery, robots, and animals.

[0014] (1-1. Example of the overall configuration of the patrol monitoring system 100-1) The patrol monitoring system 100-1 includes a server device 10-1, an operator terminal 20, and monitoring equipment 30. The server device 10-1, the operator terminal 20, and the monitoring equipment 30 are connected to each other via a predetermined communication network (not shown) so as to be able to communicate with each other by wire or wirelessly. The predetermined communication network may be any of various communication networks such as the Internet or a dedicated line.

[0015] (1-1-1. Server device 10-1) The server device 10-1 is an information providing device that analyzes monitoring data (image data, measurement data) collected from the monitoring devices 30 and generates a monitoring report. For example, the server device 10-1 may be realized in a cloud environment, an on-premise environment, an edge environment, or the like. Note that the patrol monitoring system 100-1 shown in FIG. 1 may include multiple server devices 10-1.

[0016] (1-1-2. Operator terminal 20) The operator terminal 20 is a manager terminal used by an operator O who is the manager of the area to be monitored. Note that the patrol monitoring system 100-1 shown in FIG.

[0017] (1-1-3. Monitoring equipment 30) The monitoring devices 30 are imaging devices and measuring devices installed at each monitored location within the monitored area, and are realized by cameras 30A, sensors 30B, etc. Here, the cameras 30A are imaging devices such as security cameras and monitoring cameras installed at each monitored location. The sensors 30B are measuring devices such as thermometers, hygrometers, sound level meters, intrusion detection sensors, human presence sensors, gas detectors, etc. installed at each monitored location.

[0018] Here, the monitored area is a predetermined range including multiple monitored locations monitored by the patrol monitoring system 100-1, and may be, but is not limited to, a building or house including multiple rooms, a plant or factory including multiple equipment, a park, road or river structure including multiple structures, or farmland or sea area including multiple monitoring points.

[0019] In the example of FIG. 1, monitoring device 30-1 (camera 30A-1, sensor 30B-1) is installed at monitored location 1, and monitoring device 30-2 (camera 30A-2, sensor 30B-2) is installed at monitored location 2.

[0020] (1-2. Example of overall processing of the patrol monitoring system 100-1) The overall processing of the above-described patrol surveillance system 100-1 will be described. Note that the processing of the following steps S1 to S4 may be executed in a different order. Also, some of the processing of the following steps S1 to S4 may be omitted.

[0021] (1-2-1. Monitoring data collection process) First, server device 10-1 collects monitoring data from monitoring devices 30 (step S1). For example, server device 10-1 collects image data of still images taken every second from cameras 30A (30A-1, 30A-2, ...) installed at each monitored location. Server device 10-1 also collects temperature measurement data measured every second from sensors 30B (30B-1, 30B-2, ...) installed at each monitored location.

[0022] At this time, the server device 10-1 stores the collected monitoring data together with the shooting time and measurement time. The image data may be image data of a moving image or data including audio data. The measurement data may be data on humidity, noise, an intrusion detection signal, a motion detection signal, a gas detection signal, etc.

[0023] (1-2-2. Event detection processing) Second, the server device 10-1 detects events (step S2). For example, the server device 10-1 analyzes image data and detects, as events, a person who appears at a monitored location, the person's behavior, etc. The server device 10-1 also analyzes measurement data and detects, as events, abnormal conditions such as room temperature and noise that occur at a monitored location. At this time, the server device 10-1 can also detect each event that occurs at each monitored location using an analysis model AM, which is a machine learning model that outputs an event when monitoring data is input.

[0024] (1-2-3. Monitoring report generation process) Third, the server device 10-1 generates a monitoring report (step S3). For example, the server device 10-1 generates a monitoring report including text data indicating the details of events that have occurred in the monitored area. At this time, the server device 10-1 generates the monitoring report including text data (e.g., event details, event summary, event statistics) indicating the details of each event that has occurred in the monitored area using a generation model GM, which is a machine learning model that outputs text data indicating the details of events that have occurred in the monitored base when an event detection result is input.

[0025] As a specific example 1, the server device 10-1 generates a monitoring report including details of each event that occurred at each monitored location. For example, the server device 10-1 generates a monitoring report for "Building A," which is a monitored area, including details of each event that occurred at each monitored location, such as "In Room A-1, one person entered at t1, three people entered at t2, and four people left at t3," and "In Room A-2, the room temperature exceeded the specified value T degrees at t4, and fell below the specified value T degrees at t5."

[0026] As a specific example 2, the server device 10-1 generates a monitoring report including a summary of each event that occurred at each monitored location. For example, the server device 10-1 generates a monitoring report for the monitored area "Building A" including a summary of each event that occurred at each monitored location, such as "A total of four people entered and left Room A-1," and "In Room A-2, the room temperature temporarily exceeded the specified value."

[0027] As a specific example 3, the server device 10-1 generates a monitoring report including statistics of each event that occurred at each monitored location. For example, the server device 10-1 generates a monitoring report for "Building A," which is a monitored area, including the number of occurrences, frequency of occurrence, etc. of each event that occurred at each monitored location, such as "Room A-1: ​​Total of 4 people entered and left the room, Room A-2: Room temperature exceeded the specified value once."

[0028] The server device 10-1 can also identify the importance associated with the event and generate a monitoring report including text data indicating the content of each event according to the conditions assigned to the importance.

[0029] Here, importance indicates the degree of urgency, priority, seriousness, etc. of a response to an occurring event, and is expressed, for example, on an 11-point scale from 0 to 10. Note that importance may also be expressed as a score from 0 to 100%, or as a rank of A, B, C, high, medium, low, etc.

[0030] For example, when the importance of an event is "high," server device 10-1 generates an event summary with no character limit and generates a monitoring report in which the event summary precedes the event details for each monitored location. When the importance of an event is "medium," server device 10-1 generates an event summary or event statistics within a specified character limit and generates a monitoring report in which the event summary or event statistics precedes the event details for each monitored location. When the importance of an event is "low," server device 10-1 generates event statistics and generates a monitoring report in which the event statistics precede the event details for each monitored location.

[0031] Furthermore, the server device 10-1 can generate a monitoring report that includes text data and audio data indicating the content of each event.The server device 10-1 can also generate a monitoring report that includes text data and video data synchronized with the audio data indicating the content of each event.

[0032] (1-2-4. Monitoring report notification processing) Fourth, the server device 10-1 notifies the operator O of the monitoring report (step S4). For example, the server device 10-1 transmits the generated monitoring report to the operator terminal 20 and causes a sentence indicating the content of each event to be displayed on the monitor of the operator terminal 20. Furthermore, the server device 10-1 can cause the operator terminal 20 to not only display the sentence indicating the content of each event, but also read out the sentence or display a synchronized video.

[0033] At this time, the server device 10-1 can also notify the operator terminal 20 of an alarm if the importance of the detected event is equal to or greater than a predetermined value.

[0034] (1-3. Effects of Patrol Monitoring System 100-1) Below, the problems with the patrol surveillance system 100P according to the reference technology will be explained, and then the effects of the patrol surveillance system 100-1 will be explained.

[0035] (1-3-1. Problems with the 100P Patrol Surveillance System) The patrol monitoring system 100P according to the reference technology is a technology for generating reports on work performed on a work object. It inputs work data according to the work process for the work object, generates image data capturing the state of the work object corresponding to the process, and automatically generates a work report that manages the progress of the work schedule for the work object based on the work data and image data, and manages the state of the work object according to the progress. However, the automatically generated work reports of the patrol monitoring system 100P are not always written in easy-to-read and understandable language. Furthermore, the patrol monitoring system 100P assumes that workers will actually visit each location, making it difficult to automatically generate work reports without workers personally visiting each location.

[0036] (1-3-2. Overview of Patrol Monitoring System 100-1) The following processes are executed in the patrol monitoring system 100-1. First, the server device 10-1 collects monitoring data such as image data and measurement data from the monitoring devices 30 installed at the monitored locations. Second, the server device 10-1 analyzes the collected monitoring data and detects events that have occurred at the monitored locations. Third, the server device 10-1 generates a monitoring report that includes text, audio, and video of details, summaries, and statistical values ​​of the events. At this time, the server device 10-1 can also generate the monitoring report according to the importance of the event. Fourth, the server device 10-1 notifies the operator O of the generated monitoring report.

[0037] (1-3-3. Effects of Patrol Monitoring System 100-1) The patrol monitoring system 100-1 has the following advantages. First, the patrol monitoring system 100-1 can create monitoring reports containing text using the generative model GM, making it easy for the operator O, who is the administrator, to provide text that is easy to read and understand. Second, the patrol monitoring system 100-1 can analyze collected monitoring data and detect events that occur at monitored locations, making it possible for the operator O to automatically create monitoring reports without having to personally visit each monitored location. Third, the patrol monitoring system 100-1 can create monitoring reports containing text, audio, and video of event details, summaries, and statistical values, making it easy to create multimedia reports that provide information in various formats. Fourth, the patrol monitoring system 100-1 can create monitoring reports that contain different details and summaries depending on the importance of the event, making it easier for the operator O to quickly understand the situation in the monitored area.

[0038] As described above, the patrol monitoring system 100-1 can effectively grasp events that occur in the monitored area.

[0039] 2. Configuration and Processing of Each Device in the Patrol Monitoring System 100-1 The configuration and processing of each device included in the patrol monitoring system 100-1 shown in Fig. 1 will be described using Fig. 2. Fig. 2 is a block diagram showing an example configuration of each device of the patrol monitoring system 100-1 according to embodiment 1. Below, an example configuration of the entire patrol monitoring system 100-1 according to embodiment 1 will be described, followed by detailed descriptions of an example configuration and processing of the server device 10-1, an example configuration and processing of the operator terminal 20, and an example configuration and processing of the monitoring device 30.

[0040] (2-1. Example of the overall configuration of the patrol monitoring system 100-1) An example of the overall configuration of the patrol monitoring system 100-1 shown in Fig. 1 will be described using Fig. 2. As shown in Fig. 2, the patrol monitoring system 100-1 has a server device 10-1, an operator terminal 20, and monitoring equipment 30. The server device 10, the operator terminal 20, and the monitoring equipment 30 are communicatively connected via a communication network N realized by the Internet, a dedicated line, or the like.

[0041] The server device 10-1 is installed in a cloud environment, an on-premise environment, an edge environment, etc. The operator terminal 20 is installed in a monitoring room or the like of a facility, equipment, or section managed by an operator O. The monitoring device 30 is installed at a monitored base, which is the monitoring site of the facility, equipment, or section.

[0042] (2-2. Configuration Example and Processing Example of Server Device 10-1) An example of the configuration and processing of server device 10-1 will be described with reference to Fig. 2. Server device 10-1 is an information providing device, and includes input unit 11, output unit 12, communication unit 13, storage unit 14-1, and control unit 15-1.

[0043] (2-2-1. Input section 11) The input unit 11 controls input of various information to the server device 10-1. For example, the input unit 11 is realized by a mouse, a keyboard, etc., and accepts input of various information to the server device 10-1.

[0044] (2-2-2. Output section 12) The output unit 12 controls the output of various information from the server device 10-1. For example, the output unit 12 is realized by a display or the like, and displays various information stored in the server device 10-1.

[0045] (2-2-3. Communications Department 13) The communication unit 13 controls data communication with other devices. For example, the communication unit 13 performs data communication with each communication device via a router, etc. The communication unit 13 can also perform data communication with an operator's terminal (not shown).

[0046] (2-2-4. Storage section 14-1) The storage unit 14-1 stores various pieces of information referenced by the control unit 15-1 when it operates and various pieces of information acquired when the control unit 15-1 operates. The storage unit 14-1 includes a monitoring data storage unit 14a, a monitoring report storage unit 14b, an analytical model storage unit 14c-1, and a generative model storage unit 14d. Here, the storage unit 14-1 may be realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. Note that, in the example of FIG. 2, the storage unit 14-1 is installed inside the server device 10-1, but it may also be installed outside the server device 10-1, or multiple storage units may be installed.

[0047] (2-2-4-1. Monitoring data storage unit 14a) The monitoring data storage unit 14a stores monitoring data. For example, the monitoring data storage unit 14a stores monitoring data collected by a collection unit 15a of the control unit 15-1, which will be described later. Here, an example of data stored in the monitoring data storage unit 14a will be described with reference to FIG. 3. FIG. 3 is a diagram showing an example of the monitoring data storage unit 14a of the server device 10 according to the first embodiment. In the example of FIG. 3, the monitoring data storage unit 14a has items such as "monitoring device," "monitoring target location," "time," and "monitoring data."

[0048] "Monitoring equipment" refers to identification information for identifying the photographing equipment or measuring equipment, such as the identification number or symbol of camera 30A or sensor 30B. "Monitored location" refers to identification information for identifying the facility, equipment, or section in the monitored area where the photographing equipment or measuring equipment is installed, such as the identification number or symbol of the facility, equipment, or section. "Time" refers to the time of photographing or measurement, and is expressed, for example, in years, months, days, hours, minutes, and seconds. "Monitoring data" refers to the monitoring data acquired during the photographing or measurement time, such as image data of still images, image data of moving images, image data of moving images including audio data, temperature measurement data, humidity measurement data, noise measurement data, intrusion detection signal measurement data, motion detection signal measurement data, and gas detection signal measurement data, all acquired every second.

[0049] That is, Figure 3 shows an example in which data such as {time: "time #1", monitoring data: "monitoring data #1-1"}, {time: "time #2", monitoring data: "monitoring data #1-2"}, {time: "time #3", monitoring data: "monitoring data #1-3"} is stored in the monitoring data storage unit 14a for the monitoring device 30 identified by "monitoring device #1" and the monitored location within the monitored area identified by "monitoring location #1".

[0050] (2-2-4-2. Monitoring report storage unit 14b) The monitoring report storage unit 14b stores monitoring reports. For example, the monitoring report storage unit 14b stores monitoring reports generated by a generation unit 15c of the control unit 15-1, which will be described later. An example of data stored in the monitoring report storage unit 14b will now be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the monitoring report storage unit 14b of the server device 10-1 according to the first embodiment. In the example of FIG. 4, the monitoring report storage unit 14b has items such as "monitored area," "monitored device," "monitored location," "time," and "monitoring report."

[0051] The "monitored area" refers to identification information for identifying the facilities, equipment, or sections where the imaging or measuring equipment is installed, such as the identification number or symbol of the facility, equipment, or section. The "monitoring equipment" refers to identification information for identifying the imaging or measuring equipment, such as the identification number or symbol of camera 30A or sensor 30B. The "monitored location" refers to identification information for identifying the facilities, equipment, or sections where the imaging or measuring equipment is installed in the monitored area, such as the identification number or symbol of the facility, equipment, or section. The "time" refers to the time period covered by the monitoring report, such as the year, month, day, hour, minute, and second. The "monitoring report" is text data describing the events that occurred in the monitored area during the time period, such as text data showing details of the event, text data showing an overview of the event, text data showing event statistics, audio data played along with the text data describing the event, and audio and video data played along with the text data describing the event.

[0052] That is, Figure 4 shows an example in which data {time: "times #1 to #3", monitoring report: "monitoring report #1"} is stored in the monitoring report memory unit 14b in a monitored area identified by "monitored area #1", which includes {monitoring device: "monitoring device #1", monitored location: "monitored location #1"}, {monitoring device: "monitoring device #2", monitored location: "monitored location #2"}, ...

[0053] (2-2-4-3. Analysis model storage unit 12c-1) The analytical model storage unit 14c-1 stores an analytical model AM. For example, the learning model storage unit 12c stores the analytical model AM, which is a machine learning model used by the analysis unit 15b of the control unit 15-1, which will be described later. Here, an example of data stored in the analytical model storage unit 14c-1 will be described with reference to FIG. 5. FIG. 5 is a diagram illustrating an example of the analytical model storage unit 14c-1 of the server device 10-1 according to the first embodiment. In the example of FIG. 5, the analytical model storage unit 14c-1 has an item such as "analysis model."

[0054] An "analysis model" is model data for a machine learning model, and includes, for example, execution data for executing the algorithms of the analysis model AM, such as image analysis for detecting events from image data and sensor analysis for detecting events from measurement data, model parameters which are setting values, hyperparameters, etc.

[0055] FIG. 5 shows an example in which a plurality of trained machine learning models, namely "analysis model #1", "analysis model #2", . . . , are stored in the analysis model storage unit 14c-1.

[0056] (2-2-4-4. Generative model storage unit 14d) The generative model storage unit 14d stores a generative model GM. For example, the generative model storage unit 14d stores the generative model GM, which is a machine learning model used by the generation unit 15c of the control unit 15-1, which will be described later. Here, an example of data stored in the generative model storage unit 14d will be described with reference to FIG. 6. FIG. 6 is a diagram illustrating an example of the generative model storage unit 14d of the server device 10-1 according to the first embodiment. In the example of FIG. 6, the generative model storage unit 14d has an item such as "generative model."

[0057] A "generative model" is model data of a trained machine learning model, and is data that includes, for example, execution data for executing the algorithm of a language generation model, model parameters that are setting values, hyperparameters, etc.

[0058] FIG. 6 shows an example in which a plurality of trained machine learning models, namely "Generation Model #1", "Generation Model #2", . . . , are stored in the generation model storage unit 14d.

[0059] (2-2-5. Control unit 15-1) The control unit 15-1 controls the entire server device 10-1. The control unit 15-1 has a collection unit 15a, an analysis unit 15b, a generation unit 15c, and a notification unit 15d. Here, the control unit 15-1 can be realized by, for example, an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0060] (2-2-5-1. Collection unit 15a) The collection unit 15a collects various types of information. The collection unit 15a may store the collected various types of information in the storage unit 14-1. The monitoring data collection process (image data collection process, measurement data collection process) will be described below.

[0061] (Monitoring data collection process) The collection unit 15a executes a monitoring data collection process, for example, by collecting monitoring data acquired by the monitoring devices 30 installed at each of a plurality of monitored locations included in a monitored area.

[0062] To explain a specific example, the collection unit 15a collects monitoring data such as {time: "time #1", monitoring data: "monitoring data #1-1"}, {time: "time #2", monitoring data: "monitoring data #1-2"}, and {time: "time #3", monitoring data: "monitoring data #1-3"} as monitoring data acquired by the monitoring device 30-1 installed at the monitored site 1 and transmitted to the server device 10-1, and stores the collected data in the monitoring data storage unit 14a. The collection unit 15a also collects monitoring data such as {time: "time #1", monitoring data: "monitoring data #2-1"}, {time: "time #2", monitoring data: "monitoring data #2-2"}, and {time: "time #3", monitoring data: "monitoring data #2-3"} as monitoring data acquired by the monitoring device 30-2 installed at the monitored site 2 and transmitted to the server device 10-1, and stores the collected data in the monitoring data storage unit 14a.

[0063] (Image data collection and processing) The collection unit 15a executes an image data collection process as the monitoring data collection process. For example, the collection unit 15a collects, as monitoring data, image data acquired by photographing devices installed at multiple monitored locations. At this time, the collection unit 15a collects, for example, image data of still images, image data of moving images, image data of moving images including audio data, etc., acquired every second by the camera 30A.

[0064] (Measurement data collection processing) The collection unit 15a executes a measurement data collection process as the monitoring data collection process. For example, the collection unit 15a collects, as monitoring data, measurement data acquired by measuring devices installed at multiple monitored locations. At this time, the collection unit 15a collects, for example, temperature measurement data, humidity measurement data, noise measurement data, intrusion detection signal measurement data, human presence signal measurement data, gas detection signal measurement data, etc., acquired every second by the sensor 30B.

[0065] (2-2-5-2. Analysis section 15b) The analysis unit 15b analyzes various types of information. The analysis unit 15b may acquire the various types of information from the storage unit 14-1. The analysis unit 15b may store the analysis results in the storage unit 14-1. The event detection process (image data analysis process, measurement data analysis process) will be described below.

[0066] (Event detection processing) The analysis unit 15b executes an event detection process, for example, to detect an event that has occurred at each of a plurality of monitored locations based on the collected monitoring data.

[0067] To explain a specific example, the analysis unit 15b analyzes the monitoring data {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", monitoring data: "monitoring data #1-1"} collected from monitoring device 30-1 installed at monitored location 1, detects an event that occurred at monitored location 1, and outputs the detection result {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", event: "event #1-1"}. In addition, the analysis unit 15b analyzes the monitoring data {monitoring device: "monitoring device #2", monitored location: "monitored location #2", time: "time #3", monitoring data: "monitoring data #2-3"} collected from the monitoring device 30-2 installed at the monitored location 2, detects an event that occurred at the monitored location 2, and outputs the detection result {monitoring device: "monitoring device #2", monitored location: "monitored location #2", time: "time #3", event: "event #2-3"}.

[0068] At this time, the analysis unit 15b may acquire the detection result output by inputting {monitoring device: "monitoring device #1", monitored site: "monitored site #1", time: "time #1", monitoring data: "monitoring data #1-1"} as the monitoring data collected from the monitoring device 30-1 installed at the monitored site 1 into "analysis model #1" as the analysis model AM stored in the analysis model storage unit 14c. Furthermore, the analysis unit 15b may acquire the detection result output by inputting {monitoring device: "monitoring device #2", monitored site: "monitored site #2", time: "time #3", monitoring data: "monitoring data #2-3"} as the monitoring data collected from the monitoring device 30-2 installed at the monitored site 2 into "analysis model #2" as the analysis model AM stored in the analysis model storage unit 14c.

[0069] (Image data analysis processing) The analysis unit 15b executes an image data analysis process as the event detection process. For example, the analysis unit 15b detects an event based on the collected image data. In this case, the analysis unit 15b analyzes image data of still images acquired every second by the camera 30A, and detects events such as people entering or leaving a room, people's behavior, and the movement of objects installed in the room based on differences in the image data. The analysis unit 15b can also detect an event that has occurred using an analysis model AM that outputs an event when image data of still images acquired every second by the camera 30A is input.

[0070] (Measurement data analysis processing) The analysis unit 15b executes a measurement data analysis process as the event detection process. For example, the analysis unit 15b detects an event based on the collected measurement data. At this time, the analysis unit 15b analyzes measurement data such as temperature, humidity, noise, intrusion detection signal, human presence signal, and gas detection signal acquired every second by the sensor 30B, and detects an abnormal state of the room as an event based on a specified value of each measurement data. The analysis unit 15b can also detect an event that has occurred using an analysis model AM that outputs an event when measurement data such as temperature, humidity, noise, intrusion detection signal, human presence signal, and gas detection signal acquired every second by the sensor 30B is input.

[0071] (2-2-5-3. Generation unit 15c) The generation unit 15c generates various types of information. The generation unit 15c may acquire the various types of information from the storage unit 14-1. The generation unit 15c may also store the various types of information in the storage unit 14-1. The monitoring report generation process (event detail generation process, event summary generation process, event statistic value generation process, importance identification process, and multimedia report generation process) will be described below.

[0072] (Monitoring report generation process) The generation unit 15c executes a monitoring report generation process. For example, the generation unit 15c uses a generation model GM, which is a machine learning model that outputs text data indicating the content of an event that has occurred in a monitored area when a detection result is input, to generate a monitoring report including the output text data.

[0073] To explain a specific example, the generation unit 15c acquires the text data output by inputting {monitoring device: "monitoring device #1", monitored location: "monitoring location #1", time: "time #1", event: "event #1-1"}, {monitoring device: "monitoring device #2", monitored location: "monitoring location #2", time: "time #3", event: "event #2-3"}, etc. as the detection results of events that have occurred within the monitored area into the "generative model #1" as the generative model GM stored in the generative model memory unit 14d, and generates a monitoring report "monitoring report #1" that includes the acquired text data.

[0074] At this time, the generation unit 15c can also generate a monitoring report corresponding to the specified content and format by inputting into the generation model GM prompts that specify the type of monitoring report (e.g., event details, event summary, statistical values, multimedia report), the maximum character length for the event summary and statistical values, the classification of operator O (e.g., skill level "high," "medium," "low"), language (e.g., Japanese, English, Chinese), etc., along with the detection results of events that have occurred within the monitored area.

[0075] (Event details generation process) The generation unit 15c executes an event detail generation process as the monitoring report generation process. For example, the generation unit 15c generates a monitoring report using a generative model GM that outputs text data indicating a detailed description of the event when a detection result is input.

[0076] Here, a specific example of a description (event details) showing details of an event will be described. For example, when outputting only the event details as a monitoring report, the generation unit 15c generates a monitoring report including event details such as, "The events that occurred at monitoring point A from 6:00 AM to 6:00 PM on XX / XX day are as follows: (1) At 10:00 AM, three employees entered XX conference room, sat down and engaged in an activity, and all three employees left the room at 11:05 PM. (2) At 12:05 PM, two employees entered XX conference room through the main entrance, sat down and had a meal, and all two employees left the room at 12:50 PM. (3) At 3:15 PM, one employee and three unregistered individuals entered XX conference room through the employee side entrance, sat down and held a meeting, and all employees left the room at 4:25 PM. (4) At 3:50 PM, the noise level on floor 401 exceeded the specified value of □ dB."

[0077] (Event summary generation process) The generation unit 15c executes an event summary generation process as the monitoring report generation process. For example, the generation unit 15c generates a monitoring report using a generative model GM that outputs text data indicating an explanatory sentence of the summary of an event when a detection result is input.

[0078] Here, a specific example of an explanatory text (event summary) showing an overview of an event will be described. For example, when outputting only the event summary as a monitoring report, the generation unit 15c generates a monitoring report including an event summary such as "From 6:00 AM to 6:00 PM on XX month and XX day, there were three usage events in XX conference room, with a total of 10 people entering and leaving the room. The noise level on floor 401 exceeded the specified value once."

[0079] Furthermore, when outputting both the event summary and the event details as a monitoring report, the generation unit 15c writes an event summary at the beginning such as "From 6:00 AM to 6:00 PM on XX / XX, there were three usage events in XX conference room, and a total of 10 people entered the room. The noise level on the 401 floor exceeded the specified value once." after the event summary, and writes a message such as "The events that occurred at monitoring point A from 6:00 AM to 6:00 PM on XX / XX are as follows. (1) At 10:00 AM, three employees entered XX conference room, and 10 people arrived. (1) At 12:05 PM, two employees entered the XX conference room through the main entrance, sat down and had a meal, and all three left at 11:50 PM. (2) At 12:05 PM, two employees entered the XX conference room through the main entrance, sat down and had a meal, and all two left at 12:50 PM. (3) At 3:15 PM, one employee and three unregistered employees entered the XX conference room through the employee side entrance, sat down and held a meeting, and all left at 4:25 PM. (4) At 3:50 PM, the noise level on the 401 floor exceeded the specified value by □ dB. Generate a monitoring report with details of such events.

[0080] (Event statistics generation process) The generation unit 15c executes an event statistical value generation process as the monitoring report generation process. For example, the generation unit 15c generates a monitoring report using a generative model GM that outputs sentence data indicating the statistical value of an event when a detection result is input.

[0081] Here, a specific example of the event statistical value (event statistical value) will be described. For example, when outputting only the event statistical value as a monitoring report, the generation unit 15c generates a monitoring report including an event statistical value such as "The total number of users from 6 AM to 6 PM on XX month XX day was 10, 1 abnormal noise was detected, and 0 abnormal temperature was detected."

[0082] Furthermore, when outputting both the event statistics and the event details as a monitoring report, the generation unit 15c writes the event statistics such as "The total number of users from 6:00 AM to 6:00 PM on XX / XX was 10, 1 abnormal noise was detected, and 0 abnormal temperature was detected" at the beginning of the report, and adds the following after the event statistics: "The events that occurred at monitoring point A from 6:00 AM to 6:00 PM on XX / XX were as follows: (1) At 10:00 AM, three employees entered XX conference room, sat down and performed an activity, and at 11:05 AM, three employees left the room. (2) At 12:05 PM, two employees entered XX Conference Room through the main entrance, sat down and had a meal, and both left the room at 12:50 PM. (3) At 3:15 PM, one employee and three unregistered people entered XX Conference Room through the employee side entrance, sat down and held a meeting, and all left the room at 4:25 PM. (4) At 3:50 PM, the noise level on floor 401 exceeded the specified value by □ dB. Generate a monitoring report with details of such events.

[0083] (Importance identification process) The generation unit 15c executes an importance level identification process as the monitoring report generation process. For example, the generation unit 15c identifies the importance level associated with an event and generates a monitoring report including text data indicating the content of the event according to the condition assigned to the importance level.

[0084] At this time, when the importance associated with the event is equal to or greater than a first threshold, the generation unit 15c generates a monitoring report including, as text data, a description of the event with no upper limit on the number of characters. In other words, when the importance is high, the generation unit 15c generates, as text data, a monitoring report including event details and an event summary, regardless of the total number of characters specified in advance, for the purpose of clearly conveying the content of the event to the operator O.

[0085] Furthermore, when the importance associated with an event is less than the first threshold and equal to or greater than the second threshold, the generation unit 15c generates a monitoring report including, as text data, at least one of an event description and event statistical values ​​within the upper limit of the number of characters. That is, when the importance is medium, the generation unit 15c generates, as text data, a monitoring report including event details, an event summary, event statistical values ​​such as the number of event occurrences and the frequency of event occurrences, and the like, within a pre-specified total number of characters, for the purpose of clearly conveying the content of the event to the operator O and concisely conveying the content of the event to the operator O. Furthermore, the generation unit 15c can also generate a monitoring report including event details, an event summary, event statistical values ​​such as the number of event occurrences and the frequency of event occurrences, and the like, within the playback time when played back as audio data, rather than within a pre-specified total number of characters.

[0086] Furthermore, when the importance associated with an event is less than a second threshold, the generation unit 15c generates a monitoring report including text data indicating the statistical values ​​of the event. That is, when the importance is low, the generation unit 15c generates a monitoring report including event statistical values ​​such as the number of event occurrences and the frequency of event occurrences as text data, for the purpose of concisely conveying the content of the event to the operator O.

[0087] Here, a specific example of text data showing the content of an event taking into consideration the importance level will be described. For example, when the generation unit 15c considers the importance levels "high" (e.g., importance levels 7 to 9), "medium" (e.g., importance levels 4 to 6), and "low" (e.g., importance levels 0 to 3) in a monitoring report, the generation unit 15c generates the following data: "The events that occurred at monitoring point A from 6:00 AM to 6:00 PM on △ month △ day are as follows. (1) The following events occurred as events of "high" importance: (1-1) At 10:00 AM, six people, exceeding the capacity of XX conference room, entered the room and held a meeting. Three were employees and three were non-registered people. They remained seated and held the meeting until 11:00 PM, and then left the room. (1-2) At 10:30 AM and 2:20 PM, the cashier opened and closed the safe in the vault. (1-3) At 5:40 PM, a PC alarm sounded on floor 301, and continued for 10 minutes until 5:50 PM." (2) An event of "medium" importance will be reported. Excluding events reported with "high" importance, there were a total of eight users at monitoring point A today. (3) Regarding events of "low" importance, 16 events occurred during this period." A monitoring report is generated that includes event details, an event summary, and event statistics. Note that when considering the "highest" importance (e.g., importance 10), the generation unit 15c can generate an alarm to notify operator O in addition to generating the monitoring report.

[0088] (Multimedia report generation process) The generation unit 15c executes a multimedia report generation process as the monitoring report generation process. For example, the generation unit 15c generates a monitoring report that includes text data indicating the content of an event as well as audio data indicating the content of the event. The generation unit 15c also generates a monitoring report that includes text data indicating the content of the event as well as audio data indicating the content of the event and video data synchronized with the audio data.

[0089] To explain a specific example, the generation unit 15c acquires, as a monitoring report output from the "generative model #1" as the generative model GM, a "monitoring report #1" including "text data #1" which is text data and "audio data #1" which is audio data obtained by converting the text data into a reproducible form. Furthermore, the generation unit 15c acquires, as a monitoring report output from the "generative model #1" as the generative model GM, a "monitoring report #1" including "text data #1" which is text data, "audio data #1" which is audio data obtained by converting the text data into a reproducible form, and "video data #1" which is video data at the time an event occurs.

[0090] (2-2-5-4. Notification section 15d) The notification unit 15d notifies various types of information. Note that the notification unit 15d may acquire the various types of information from the storage unit 14-1. The monitoring report notification process will be described below.

[0091] (Monitoring report notification processing) The notification unit 15d executes the monitoring report generation process, for example, the notification unit 15d notifies the operator O of the monitoring report generated by the generation unit 15c.

[0092] To explain a specific example, the notification unit 15d obtains "Monitoring Report #1" from the monitoring report storage unit 14b as a monitoring report to be notified to the operator O, specifies the operator terminal 20 as the destination of the monitoring report, transmits "Monitoring Report #1" to the operator terminal 20, and displays text data "Text Data #1" included in "Monitoring Report #1" on the display of the operator terminal 20. At this time, the notification unit 15d may play audio data "Audio Data #1" and video data "Video Data #1" included in "Monitoring Report #1". Furthermore, when an event with a "highest" importance level occurs, the notification unit 15d may display an alarm on the display of the operator terminal 20.

[0093] (2-3. Configuration Example and Processing Example of Operator Terminal 20) 2 again, a description will be given of an example of the configuration and processing of the operator terminal 20. The operator terminal 20 is a posting device and a viewing device, and includes an input / output unit 21, a transmitting / receiving unit 22, and a communication unit .

[0094] (2-3-1. Input / output section 21) The input / output unit 21 controls the input of various information to the operator terminal 20. For example, the input / output unit 21 is realized by a mouse, a keyboard, a touch panel, or the like, and accepts input of various information to the operator terminal 20. The input / output unit 21 also controls the display of various information from the operator terminal 20. For example, the input / output unit 21 is realized by a display, or the like, and displays various information stored in the operator terminal 20.

[0095] The input / output unit 21 also displays text data included in the monitoring report transmitted from the server device 10-1, which is an information providing device, and plays back audio data and video data included in the monitoring report transmitted from the server device 10-1.

[0096] (2-3-2. Transmitter / receiver 22) The transmitting / receiving unit 22 transmits various types of information. For example, the transmitting / receiving unit 22 transmits setting information input by the operator O via a setting screen to the server device 10-1.

[0097] The transmitting / receiving unit 22 receives various types of information. For example, the transmitting / receiving unit 22 receives a monitoring report transmitted from the server device 10-1. The transmitting / receiving unit 22 also receives an alarm transmitted from the server device 10-1.

[0098] (2-3-3. Communications Department 23) The communication unit 23 controls data communication with other devices. For example, the communication unit 23 performs data communication with each communication device via a router, etc. The communication unit 23 can also perform data communication with an operator's terminal (not shown).

[0099] (2-4. Configuration and Processing Examples of Monitoring Device 30) 2 again, a description will be given of an example of the configuration and processing of the monitoring device 30. For example, the monitoring device 30 is realized by a camera 30A which is an imaging device such as a security camera or a monitoring camera installed in a facility managed by the operator O, and a sensor 30B which is a measuring device such as a thermometer, a hygrometer, a sound level meter, an intrusion detection sensor, a human presence sensor, or a gas detector installed in a facility managed by the operator O, and has an acquisition unit 31 and a communication unit 32.

[0100] (2-4-1. Acquisition part 31) The acquisition unit 31 acquires monitoring data. For example, the acquisition unit 31 acquires image data of still images and moving images, audio data, etc. by photographing the inside of the facility every second. The acquisition unit 31 also acquires measurement data such as humidity, noise, intrusion detection signals, human detection signals, and gas detection signals by measuring the inside of the facility every second.

[0101] The acquisition unit 31 transmits the acquired monitoring data to the server device 10-1. For example, the acquisition unit 31 transmits the acquired image data of still images and moving images, audio data, etc. to the server device 10-1. The acquisition unit 31 also transmits the acquired measurement data such as humidity, noise, intrusion detection signals, human detection signals, and gas detection signals to the server device 10-1.

[0102] (2-4-2. Communication Unit 32) The communication unit 32 controls data communication with other devices. For example, the communication unit 32 performs data communication with each communication device via a router, etc. The communication unit 32 can also perform data communication with a terminal (not shown).

[0103] 3. Flow of each process in the patrol monitoring system 100-1 The processing flow of the patrol monitoring system 100-1 according to the embodiment will be described with reference to Fig. 7. Note that the processing of the following steps S101 to S104 may be executed in a different order. Also, some of the processing of the following steps S101 to S104 may be omitted.

[0104] (3-1. Monitoring data collection process) First, the server device 10-1 executes a monitoring data collection process (step S101). For example, the server device 10-1 collects image data, such as still images, captured every second from the camera 30A installed at each monitored location. The server device 10-1 also collects measurement data, such as temperature, measured every second from the sensor 30B installed at each monitored location.

[0105] (3-2. Event detection processing) Second, the server device 10-1 executes an event detection process (step S102). For example, the server device 10-1 analyzes image data and detects, as events, a person who appears at a monitored location, the person's behavior, and the like. The server device 10-1 also analyzes measurement data and detects, as events, abnormal conditions such as room temperature and noise that occur at a monitored location. At this time, the server device 10-1 can also detect each event that occurs at each monitored location using an analysis model AM that outputs an event when monitoring data is input.

[0106] (3-3. Monitoring report generation process) Third, the server device 10-1 executes a monitoring report generation process (step S103). For example, the server device 10-1 uses a generation model GM, which is a language generation model, to generate a monitoring report including text data indicating the details of an event that occurred in the monitored area. At this time, the server device 10-1 can also generate a monitoring report including text data according to the importance associated with the event. Furthermore, the server device 10-1 can also generate a monitoring report including audio data and video data in addition to the text data.

[0107] (3-4. Monitoring report notification processing) Fourth, the server device 10-1 executes a monitoring report notification process (step S104). For example, the server device 10-1 transmits the generated monitoring report to the operator terminal 20 and causes the monitor of the operator terminal 20 to display text indicating the details, summary, and statistical values ​​of the event. The server device 10-1 also causes the operator terminal 20 to display text indicating the details, summary, and statistical values ​​of the event, and can also read the text aloud or display synchronized video. Furthermore, the server device 10-1 can also display an alarm on the monitor of the operator terminal 20.

[0108] 4. Effects of the First Embodiment Finally, the effects of the first embodiment will be described below. Effects 1 to 9 corresponding to the processing according to the first embodiment will be described below.

[0109] (4-1. Effect 1) First, in the process according to the embodiment described above, the server device 10-1 collects monitoring data acquired by the monitoring devices 30 installed at each of the multiple monitored locations included in the monitored area, detects events that have occurred at each of the multiple monitored locations based on the collected monitoring data, and generates a monitoring report including the output text data using a generative model GM that, upon input of the detection results, outputs text data indicating the contents of the events that have occurred in the monitored area. Therefore, this process makes it possible to effectively grasp events that have occurred in the monitored area.

[0110] (4-2. Effect 2) Second, in the process according to the embodiment described above, the server device 10-1 collects, as monitoring data, image data acquired by the cameras 30A installed at multiple monitored locations, detects events at the monitored locations based on the collected image data, and generates a monitoring report including the output text data using a generative model GM that outputs text data indicating the details of the event when the detection results are input. Therefore, in this process, by detecting events that have occurred at monitored locations through image analysis, it is possible to effectively grasp events that have occurred in the monitored area.

[0111] (4-3. Effect 3) Third, in the process according to the embodiment described above, the server device 10-1 collects, as monitoring data, measurement data acquired by sensors 30B installed at multiple monitored locations, detects events at the monitored locations based on the collected measurement data, and generates a monitoring report including the output text data using a generation model GM that outputs text data indicating the contents of the event when the detection results are input. Therefore, in this process, by detecting events that have occurred at monitored locations through sensor analysis, it is possible to effectively grasp events that have occurred in the monitored area.

[0112] (4-4. Effect 4) Fourth, in the process according to the embodiment described above, the server device 10-1 identifies the importance associated with an event and generates a monitoring report including text data indicating the content of the event according to the conditions assigned to the identified importance. Therefore, in this process, by generating text data according to the importance of the event, it is possible to effectively grasp events that have occurred in the monitored area.

[0113] (4-5. Effect 5) Fifth, in the process according to the embodiment described above, if the importance level associated with an event is equal to or greater than a first threshold, the server device 10-1 generates a monitoring report containing text data describing the event with no upper limit on the number of characters. Therefore, in this process, by generating text data that clearly describes the content of events with high importance, it is possible to effectively grasp events that have occurred in the monitored area.

[0114] (4-6. Effect 6) Sixth, in the process according to the embodiment described above, when the importance associated with an event is less than the first threshold and equal to or greater than the second threshold, the server device 10-1 generates a monitoring report containing, as text data, at least one of an event description and event statistical value within the upper limit of the number of characters. Therefore, in this process, by generating text data that describes the content of an event of medium importance using a specified number of characters or less, it is possible to effectively grasp events that have occurred in the monitored area.

[0115] (4-7. Effect 7) Seventh, in the process according to the embodiment described above, if the importance level associated with an event is less than the second threshold, the server device 10-1 generates a monitoring report including statistical values ​​of the event as text data. Therefore, in this process, by generating text data that briefly describes the contents of events with low importance levels, it is possible to effectively grasp events that have occurred in the monitored area.

[0116] (4-8. Effect 8) Eighth, in the process according to the embodiment described above, the server device 10-1 generates a monitoring report that includes text data indicating the content of the event as well as audio data indicating the content of the event. Therefore, in this process, by reading out the content of the event aloud, it is possible to effectively grasp the events that have occurred in the monitored area.

[0117] (4-9. Effect 9) Ninth, in the process according to the embodiment described above, the server device 10-1 generates a monitoring report that includes text data indicating the content of the event, audio data indicating the content of the event, and video data synchronized with the audio data. Therefore, in this process, the content of the event is read out aloud and a video of the event is displayed, thereby enabling an event that has occurred in the monitored area to be effectively identified.

[0118] [Embodiment 2] Below, we will explain the configuration and processing of the patrol monitoring system 100-2 according to embodiment 2, the configuration and processing of each device in the patrol monitoring system 100-2, and the processing flow of the patrol monitoring system 100-2, and finally explain the effects of embodiment 2. Note that we will omit explanations of configurations and processing that are common to embodiment 1.

[0119] 1. Configuration and Processing of Patrol Monitoring System 100-2 The configuration and processing of the patrol monitoring system 100-2 according to embodiment 2 will be described in detail using Fig. 8. Fig. 8 is a diagram showing an example of the configuration and processing of the patrol monitoring system 100-2 according to embodiment 2. Below, an example of the overall configuration of the patrol monitoring system 100-2, an example of the processing of the patrol monitoring system 100-2, and the effects of the patrol monitoring system 100-2 will be described.

[0120] (1-1. Example of the overall configuration of the patrol monitoring system 100-2) The patrol monitoring system 100-2 includes a server device 10-2, an operator terminal 20, and monitoring equipment 30. The server device 10-2, the operator terminal 20, and the monitoring equipment 30 are connected to each other via a predetermined communication network (not shown) so as to be able to communicate with each other by wire or wirelessly. The predetermined communication network may be any of various communication networks such as the Internet or a dedicated line.

[0121] (1-1-1. Server device 10-2) The server device 10-2 is an information providing device that analyzes monitoring data (image data, measurement data) collected from the monitoring devices 30 and generates a monitoring report. For example, the server device 10-2 may be realized in a cloud environment, an on-premise environment, an edge environment, or the like. Note that the patrol monitoring system 100-2 shown in FIG. 8 may include multiple server devices 10-2.

[0122] (1-1-2. Operator terminal 20) The operator terminal 20 is a manager terminal used by an operator O who is the manager of the area to be monitored. Note that the patrol monitoring system 100-1 shown in FIG.

[0123] (1-1-3. Monitoring equipment 30) The monitoring devices 30 are installed at each monitored location within the monitored area, and are realized by cameras 30A, sensors 30B, etc. Here, the cameras 30A are, for example, photographing devices such as security cameras and monitoring cameras installed at each monitored location. The sensors 30B are, for example, measuring devices such as thermometers, hygrometers, sound level meters, intrusion detection sensors, human presence sensors, gas detectors, etc. installed at each monitored location.

[0124] (1-2. Example of overall processing of patrol monitoring system 100-2) The overall processing of the above-described patrol surveillance system 100-2 will be described. Note that the processing of the following steps S11 to S17 may be executed in a different order. Also, some of the processing of the following steps S11 to S17 may be omitted.

[0125] (1-2-1. Candidate information display process) First, the operator terminal 20 displays candidate information (step S11). For example, the operator terminal 20 displays on the monitor a setting screen that presents, as candidate information, a list of identification information of AI logics for each analysis category, a list of output values ​​for each AI logic, etc.

[0126] Here, the analysis category is a classification of the analysis target, such as "person behavior" indicating the behavior of a person analyzed from image data, "person identification" indicating the attributes of a person analyzed from image data (e.g., name, affiliation, authority, gender, age, etc.), "object identification" indicating an object involved in the behavior of a person analyzed from image data, etc. Furthermore, the analysis category is, for example, "anomaly type" indicating the type of anomaly analyzed from measurement data, "anomaly cause" indicating the cause of an anomaly analyzed from measurement data, etc.

[0127] "Personal behavior" is the subject of analysis in image analysis, and is an analysis category that corresponds to "what happened," which is the behavior of a person, such as "entering a room," "leaving a room," "taking out," "leaving behind," "using violence," "falling down," "vomiting," and "crying."

[0128] Furthermore, the above-mentioned "human actions" are examples of actions that are detected when the subject of behavior analysis is a person, but as other examples, in the case of a robot or construction machinery, actions performed by the robot or construction machinery, such as "grabbing," "lifting," "placing," and "excavating," may be targeted. Furthermore, when the subject of behavior analysis is an animal, the animal's actions may also be detected.

[0129] "Person identification" is the analysis target in image analysis, and is an analysis category that corresponds to "who," which is a person's attribute, such as "pre-registered person authority A," "pre-registered person authority B," or "non-registered person."

[0130] Furthermore, the above "person identification" is an example in which the subject of behavior analysis is a person, but as another example, if the subject of photography is a place where a person and a robot are working together, the robot may be included, or a work vehicle such as construction machinery may also be the subject.Animals may also be the subject.

[0131] "Object identification" is an analysis category that corresponds to "what" - the object being analyzed in image analysis, such as a "desk," "chair," "cardboard box," "locker," "file," "safe," "seal," "potted plant," "shredder," or other objects that are involved in a person's behavior.

[0132] "Type of abnormality" is the analysis target in sensor analysis, and is an analysis category corresponding to "what" which is a classification of abnormal conditions such as "temperature abnormality," "humidity abnormality," "noise abnormality," "intrusion detection abnormality," "person detection abnormality," and "gas detection abnormality."

[0133] "Cause of abnormality" is an analysis target in sensor analysis, and is an analysis category corresponding to "why" that is the cause of an abnormal state, such as "failure," "human factor," or "external factor."

[0134] Furthermore, AI logic is an analysis method implemented by an analysis model AM, which is a trained machine learning model that outputs an analysis target. Furthermore, the output value list is a list of analysis items, which are analysis targets output by each AI logic. Here, the output value list may be a list of common analysis items.

[0135] (1-2-2. Setting information input process) Second, the operator O inputs setting information into the operator terminal 20 (step S12). For example, the operator O inputs the selection of the AI ​​logic to be used for analysis as setting information by selecting the identification information of an arbitrary AI logic from a list of identification information of AI logic for each analysis category.

[0136] At this time, operator O selects the AI ​​logic by, for example, selecting "AI Logic 1" for {Analysis Category 1: Person Behavior}, selecting "AI Logic A" for {Analysis Category 2: Person Identification}, and selecting "AI Logic W" for {Analysis Category 3: Object Identification}.

[0137] Furthermore, the operator O selects analysis items output by the selected AI logic for each analysis category, and assigns importance to events that are combinations of the selected analysis items, thereby inputting the importance corresponding to the events as setting information. At this time, the operator O may also input, as setting information, a reaction to be executed by the server device 10-2 corresponding to the importance.

[0138] At this time, the operator O assigns an importance level of "8" indicating urgency to an event that is a combination of analysis items, for example, {"Who": "Unregistered user", "When": "Weekday business hours", "What": "File", "How": "Taking out"}. Similarly, the operator O assigns an importance level to each of the other combinations of analysis items as events that he or she wants to detect.

[0139] (1-2-3. Setting information transmission process) Third, the operator terminal 20 transmits the setting information to the server device 10-2 (step S13). For example, the operator terminal 20 transmits the selection of AI logic for each analysis category, the importance corresponding to the event, the reaction corresponding to the importance, etc., input to the operator terminal 20 by the operator O, to the server device 10-2 as setting information. At this time, the server device 10-2 saves the received setting information.

[0140] (1-2-4. Monitoring data collection process) Fourth, server device 10-2 collects monitoring data from monitoring devices 30 (step S14). For example, server device 10-2 collects image data of still images taken every second from cameras 30A (30A-1, 30A-2, ...) installed at each monitored location. Server device 10-2 also collects temperature measurement data measured every second from sensors 30B (30B-1, 30B-2, ...) installed at each monitored location.

[0141] At this time, the server device 10-2 stores the collected monitoring data together with the shooting time and measurement time. The image data may be image data of a moving image or data including audio data. The measurement data may be data on humidity, noise, an intrusion detection signal, a motion detection signal, a gas detection signal, etc.

[0142] (1-2-5. Event detection processing) Fifth, the server device 10-2 detects an event (step S15). For example, the server device 10-2 detects an event by analyzing the monitoring data using the AI ​​logic selected for each analysis category by the operator O, with reference to the setting information. At this time, the server device 10-2 inputs the monitoring data into the analysis model AM corresponding to each AI logic, acquires the analysis items that are the output analysis targets for each analysis category, and identifies the combination of the acquired analysis items as an event.

[0143] That is, in the above example, the server device 10-2 inputs image data into the analysis model AM-A corresponding to "AI logic A" as {analysis category 2: person identification}, and acquires an analysis item corresponding to "who." The server device 10-2 also identifies the time the image data was captured and acquires an analysis item corresponding to "when." The server device 10-2 also inputs image data into the analysis model AM-W corresponding to "AI logic W" as {analysis category 3: object identification}, and acquires an analysis item corresponding to "what." The server device 10-2 also inputs image data into the analysis model AM-1 corresponding to "AI logic 1" as {analysis category 1: person behavior}, and acquires an analysis item corresponding to "what happened." The server device 10-2 then identifies a combination of the analysis items "who," "when," "what," and "how" as an event.

[0144] (1-2-6. Monitoring report generation process) Sixth, the server device 10-2 generates a monitoring report (step S16). For example, the server device 10-2 generates a monitoring report including text data indicating the details of events that have occurred in the monitored area. At this time, the server device 10-2 generates a monitoring report indicating the details of each event that has occurred at each monitored location using a generation model GM that outputs text data indicating the details of an event when an event detection result is input. Note that the details of the monitoring report generation process are the same as those in embodiment 1, so a description thereof will be omitted.

[0145] (1-2-7. Monitoring report notification processing) Seventh, the server device 10-2 notifies the operator O of the monitoring report (step S17). For example, the server device 10-2 transmits the generated monitoring report to the operator terminal 20 and causes a text indicating the details, summary, and statistical values ​​of the event to be displayed on the monitor of the operator terminal 20. The server device 10-2 can also cause the operator terminal 20 to not only display the text indicating the details, summary, and statistical values ​​of the event, but also read out the text or display synchronized video.

[0146] (1-3. Effects of the Patrol Monitoring System 100-2) The effects of the patrol monitoring system 100-2 will be described below. Note that the outline and problems of the reference technology are the same as those of the first embodiment, so a description thereof will be omitted.

[0147] (1-3-1. Overview of the Patrol Monitoring System 100-2) The patrol monitoring system 100-2 executes the following processes. First, the operator terminal 20 displays a setting screen on the monitor, presenting candidate information such as a list of AI logic identification information for each analysis category and a list of output values ​​for each AI logic. Second, the operator O inputs, into the operator terminal 20, the selection of an AI logic to be used for analysis and the importance corresponding to the combination of analysis items output by the selected AI logic as setting information. Third, the operator terminal 20 transmits, as setting information, the selection of an AI logic for each analysis category and the importance corresponding to the combination of analysis items to the server device 10-2. Fourth, the server device 10-2 collects monitoring data such as image data and measurement data from the monitoring devices 30 installed at the monitored locations. Fifth, the server device 10-2 analyzes the collected monitoring data and detects events that have occurred at the monitored locations. Sixth, the server device 10-2 generates a monitoring report including text, audio, and video of event details, summaries, and statistical values. Seventh, the server device 10-2 notifies the operator O of the monitoring report.

[0148] (1-3-2. Effects of the Patrol Monitoring System 100-2) In addition to the patrol monitoring system 100-1 according to embodiment 1, the patrol monitoring system 100-2 can detect events using AI logic selected for each analysis category, thereby enabling more accurate event detection and generating more accurate monitoring reports.

[0149] As described above, the patrol monitoring system 100-2 can more effectively grasp events that occur in the monitored area.

[0150] 2. Configuration and Processing of Each Device in the Patrol Monitoring System 100-2 The configuration and processing of each device included in the patrol monitoring system 100-2 shown in Fig. 8 will be described using Fig. 9. Fig. 9 is a block diagram showing an example configuration of each device of the patrol monitoring system 100-2 according to the second embodiment. Below, an example configuration of the entire patrol monitoring system 100-2 according to the second embodiment will be described, followed by detailed descriptions of an example configuration and processing of the server device 10-2 and an example configuration and processing of the operator terminal 20. Note that the example configuration and processing of the monitoring device 30 are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0151] (2-1. Example of the overall configuration of the patrol monitoring system 100-2) An example of the overall configuration of the patrol monitoring system 100-2 shown in Fig. 8 will be described using Fig. 9. As shown in Fig. 9, the patrol monitoring system 100-2 has a server device 10-2, an operator terminal 20, and monitoring equipment 30. The server device 10-2, the operator terminal 20, and the monitoring equipment 30 are communicatively connected via a communication network N realized by the Internet, a dedicated line, or the like.

[0152] The server device 10-2 is installed in a cloud environment, an on-premise environment, an edge environment, etc. The operator terminal 20 is installed in a monitoring room or the like of a facility or equipment managed by an operator O. The monitoring device 30 is installed at a monitoring target base, which is the monitoring site of the facility or equipment.

[0153] (2-2. Configuration Example and Processing Example of Server Device 10-2) An example of the configuration and processing of server device 10-2 will be described with reference to Fig. 9. Server device 10-2 is an information providing device, and includes input unit 11, output unit 12, communication unit 13, storage unit 14-2, and control unit 15-2.

[0154] (2-2-1. Input section 11) The input unit 11 controls input of various information to the server device 10-2. Note that the configuration example and processing example of the input unit 11 are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0155] (2-2-2. Output section 12) The output unit 12 controls the output of various information from the server device 10-2. Note that the configuration and processing examples of the output unit 12 are the same as those in the first embodiment, and therefore will not be described here.

[0156] (2-2-3. Communications Department 13) The communication unit 13 controls data communication with other devices. Note that the configuration and processing example of the communication unit 13 are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0157] (2-2-4. Storage section 14-2) The storage unit 14-2 stores various information referenced by the control unit 15-2 when it operates and various information acquired when the control unit 15-2 operates. The storage unit 14-2 includes a monitoring data storage unit 14a, a monitoring report storage unit 14b, an analytical model storage unit 14c-2, a generative model storage unit 14d, a candidate information storage unit 14e, and a setting information storage unit 14f. The storage unit 14-2 may be implemented, for example, by a semiconductor memory device such as RAM or flash memory, or a storage device such as a hard disk or optical disk. While the storage unit 14-2 is installed inside the server device 10-2 in the example of FIG. 9, it may be installed outside the server device 10-2, or multiple storage units may be installed.

[0158] (2-2-4-1. Monitoring data storage unit 14a) The monitoring data storage unit 14a stores the monitoring data. Note that the configuration example and processing example of the monitoring data storage unit 14a are the same as those in the first embodiment, and therefore a description thereof will be omitted.

[0159] (2-2-4-2. Monitoring report storage unit 14b) The monitoring report storage unit 14b stores the monitoring report. Note that the configuration example and processing example of the monitoring report storage unit 14b are the same as those in the first embodiment, and therefore a description thereof will be omitted.

[0160] (2-2-4-3. Analysis model storage unit 14c-2) The analytical model storage unit 14c-2 stores analytical models AM. For example, the analytical model storage unit 14c-2 stores a plurality of analytical models AM, which are machine learning models used by the analysis unit 15b of the control unit 15-2 (described later) and which output an analysis target of a monitored site when monitoring data is input. In this case, the analytical model storage unit 14c-2 stores a plurality of analytical models AM for each analytical category of the analysis target to be output. Here, an example of data stored in the analytical model storage unit 14c-2 will be described with reference to FIG. 10. FIG. 10 is a diagram illustrating an example of the analytical model storage unit 14c-2 of the server device 10-2 according to the second embodiment. In the example of FIG. 10, the analytical model storage unit 14c-2 has items such as "analysis category," "AI logic," and "analysis model."

[0161] "Analysis category" indicates identification information for identifying the category of the analysis target, such as an identification number or identification symbol for a category such as a person's behavior, a person's attributes, an object involved in the person's behavior, a type of abnormality, or a cause of the abnormality. "AI logic" indicates identification information for identifying an AI logic that can be analyzed by the server device 10-2, such as an identification number or identification symbol for the AI ​​logic. "Analysis model" is model data of a machine learning model corresponding to the "AI logic," such as data including execution data for executing the algorithm of the analysis model AM of each AI logic, model parameters that are setting values, hyperparameters, etc.

[0162] That is, in Figure 10, for the analysis category identified by "Analysis Category #1", the following are true: {AI Logic: "AI Logic 1", Analysis Model: "Analysis Model 1", ···}, {AI Logic: "AI Logic 2", Analysis Model: "Analysis Model 2", ···}, {AI Logic: "AI Logic 3", Analysis Model: "Analysis Model 3", ···}, {AI Logic: "AI Logic 4", Analysis Model: "Analysis Model 4", ···}, and for the analysis category identified by "Analysis Category #2", the following are true: {AI Logic: "AI Logic A", Analysis Model: "Analysis Model A", ···}, {AI Logic: "AI Logic B", Analysis Model: "Analysis Model C", ···} , analysis model: "Analysis Model B", ···}, {AI logic: "AI Logic C", analysis model: "Analysis Model C", ···}, and for the analysis category identified by "Analysis Category #3", data such as {AI logic: "AI Logic X", analysis model: "Analysis Model X", ···}, {AI logic: "AI Logic Y", analysis model: "Analysis Model Y", ···}, {AI logic: "AI Logic Z", analysis model: "Analysis Model Z", ···}, {AI logic: "AI Logic W", analysis model: "Analysis Model W", ···} is stored in the analysis model memory unit 14c-2.

[0163] (2-2-4-4. Candidate information storage unit 14e) The candidate information storage unit 14e stores candidate information. For example, the candidate information storage unit 14e stores candidate information including identification information of AI logic for each analysis category that can be analyzed by the analysis unit 15b of the control unit 15-2 (described later), an output value list, and the like. Furthermore, the analysis category of the analysis target in image analysis includes, for example, at least one of a person's attributes, a person's behavior, and an object involved in the person's behavior. Furthermore, the analysis category of the analysis target in sensor analysis includes, for example, at least one of an anomaly type and an anomaly cause. Here, an example of data stored in the candidate information storage unit 14e will be described with reference to FIG. 11. FIG. 11 is a diagram illustrating an example of the candidate information storage unit 14e of the server device 10-2 according to the second embodiment. In the example of FIG. 11, the candidate information storage unit 14e has items such as "analysis category," "AI logic," and "output value list."

[0164] "Analysis category" indicates identification information for identifying the category of the analysis target, such as an identification number or identification symbol for a category such as a person's behavior, a person's attributes, an object involved in a person's behavior, a type of abnormality, or a cause of the abnormality. "AI logic" indicates identification information for identifying an AI logic that can be analyzed by the server device 10-2, such as an identification number or identification symbol for the AI ​​logic. "Output value list" is a list of analysis items that are the analysis target output by each AI logic, such as a list of a person's behavior, a list of a person's attributes, a list of objects involved in a person's behavior, a list of types of abnormalities, or a list of causes of abnormalities.

[0165] That is, in Figure 11, for the analysis category identified by "Analysis Category #1", the following are true: {AI Logic: "AI Logic 1", Output Value List: "Output Value List 1", ···}, {AI Logic: "AI Logic 2", Output Value List: "Output Value List 2", ···}, {AI Logic: "AI Logic 3", Output Value List: "Output Value List 3", ···}, {AI Logic: "AI Logic 4", Output Value List: "Output Value List 4", ···}, and for the analysis category identified by "Analysis Category #2", the following are true: {AI Logic: "AI Logic A", Output Value List: "Output Value List A", ···}, {AI Logic: "AI Logic B", Output Value List: "Output Value List B", ···} , output value list: "Output Value List B", ···}, {AI logic: "AI Logic C", output value list: "Output Value List C", ···}, and for the analysis category identified by "Analysis Category #3", data such as {AI logic: "AI Logic X", output value list: "Output Value List X", ···}, {AI logic: "AI Logic Y", output value list: "Output Value List Y", ···}, {AI logic: "AI Logic Z", output value list: "Output Value List Z", ···}, {AI logic: "AI Logic W", output value list: "Output Value List W", ···} is stored in the candidate information storage unit 14e.

[0166] The candidate information storage unit 14e may include, as the candidate information, features of AI logics, etc. For example, the candidate information storage unit 14e may store, as features of AI logics, data such as {AI logic: "AI logic 1", feature: "face recognition",...}, {AI logic: "AI logic 2", feature: "personal identification based on gait",...}, {AI logic: "AI logic 3", feature: "gender and age estimation",...}, {AI logic: "AI logic 4", feature: "clothing and accessory detection",...}, etc.

[0167] (2-2-4-2. Setting information storage unit 14f) The setting information storage unit 14f stores setting information. For example, the setting information storage unit 14f stores setting information including the selection of AI logic for each analysis category, the importance corresponding to an event, etc., which is input by the operator O via a setting screen and accepted by the accepting unit 15e of the control unit 15-2 (described later). Here, an example of data stored in the setting information storage unit 14f will be described with reference to FIG. 12. FIG. 12 is a diagram illustrating an example of the setting information storage unit 14f of the server device 10-2 according to the second embodiment. In the example of FIG. 12, the setting information storage unit 14f has items such as "monitoring device," "monitoring target location," "analysis category," "AI logic," "output value list," and "importance information."

[0168] The term "monitoring equipment" refers to identification information for identifying photographing equipment or measuring equipment, such as the identification number or symbol of camera 30A or sensor 30B. The term "monitored location" refers to identification information for identifying facilities, equipment, or sections in the monitored area where photographing equipment or measuring equipment is installed, such as the identification number or symbol of the facility, equipment, or section. The term "analysis category" refers to identification information for identifying the classification of the analysis target, such as the classification of a person's behavior, person's attributes, or objects involved in a person's behavior, which are the analysis targets in image analysis, or the classification of the type of anomaly, cause of anomaly, etc., which are the analysis targets in sensor analysis. The term "AI logic" refers to identification information for identifying the AI ​​logic accepted by the accepting unit 15e, such as the identification number or symbol of the AI ​​logic. The term "output value list" refers to a list of analysis items that are the analysis targets output by each AI logic, such as a list of a person's behavior, a list of a person's attributes, a list of objects involved in a person's behavior, a list of types of anomalies, a list of causes of anomalies, etc. "Importance information" is a list of importance assigned to events, which are combinations of analysis items that are the subject of analysis output by each AI logic, such as a list of combinations of each analysis item, such as "who," "when," "what," "how," "what," and "why," and the importance corresponding to each combination.

[0169] That is, Figure 12 shows an example in which, for the monitoring device 30 identified by "monitoring device #1" and the monitored location identified by "monitored location #1", data such as {Analysis category: "Analysis category #1", AI logic: "AI logic 1", output value list: "Output value list 1"}, {Analysis category: "Analysis category #2", AI logic: "AI logic A", output value list: "Output value list A"}, {Analysis category: "Analysis category #3", AI logic: "AI logic W", output value list: "Output value list W"}, and whose importance information is "Importance information #1" are stored in the setting information storage unit 14f.

[0170] The setting information storage unit 14f may include, as setting information, a reaction corresponding to the importance level. For example, the setting information storage unit 14f may store, as a reaction corresponding to the importance level, data such as {importance level: "0", reaction: "event record"}, {importance level: "1 to 6", reaction: "monitoring data record"}, {importance level: "7 to 10", reaction: "monitoring data record" or "alarm notification"}.

[0171] (2-2-5. Control unit 15-2) The control unit 15-2 controls the entire server device 10-2. The control unit 15-2 includes a collection unit 15a, an analysis unit 15b, a generation unit 15c, a notification unit 15d, and a reception unit 15e. The control unit 15-2 may be realized by, for example, an electronic circuit such as a CPU or an MPU, or an integrated circuit such as an ASIC or an FPGA.

[0172] (2-2-5-1. Collection unit 15a) The collection unit 15a collects various types of information. Note that the configuration and processing examples of the collection unit 15a are the same as those in the first embodiment, and therefore will not be described here.

[0173] (2-2-5-2. Analysis section 15b) The analysis unit 15b analyzes various pieces of information. The analysis unit 15b may acquire the various pieces of information from the storage unit 14-2. The analysis unit 15b may store the analysis results in the storage unit 14-2. The event detection process will be described below.

[0174] (Event detection processing) The analysis unit 15b executes an event detection process. For example, the analysis unit 15b inputs the collected monitoring data into the analysis model AM whose selection has been accepted, and detects events that have occurred at each of the multiple monitored locations according to the output targets.

[0175] To explain a specific example, the analysis unit 15b inputs {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", monitoring data: "monitoring data #1-1"} as monitoring data into "analysis model 1" used in "AI logic 1", and obtains analysis item "analysis item 1-3" as the output result. Also, the analysis unit 15b inputs {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", monitoring data: "monitoring data #1-1"} as monitoring data into "analysis model A" used in "AI logic A", and obtains analysis item "analysis item A-3" as the output result. Furthermore, the analysis unit 15b inputs {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", monitoring data: "monitoring data #1-1"} as monitoring data into the "analysis model W" used in the "AI logic W" and obtains the output result, analysis item "analysis item W-5". Furthermore, the analysis unit 15b obtains the analysis item "analysis item T-1" indicating the occurrence time of an event identified from {monitoring device: "monitoring device #1", monitored location: "monitored location #1", time: "time #1", monitoring data: "monitoring data #1-1"} as monitoring data. Then, the analysis unit 15b detects {AI logic 1: "analysis item 1-3", AI logic A: "analysis item A-3", AI logic W: "analysis item W-5", occurrence time: "analysis item T-1"} as an event that occurred at the monitored location 1.

[0176] (2-2-5-3. Generation unit 15c) The generating unit 15c generates various types of information. Note that the configuration example and processing example of the generating unit 15c are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0177] (2-2-5-4. Notification section 15d) The notification unit 15d notifies various types of information. Note that the configuration and processing examples of the notification unit 15d are the same as those in the first embodiment, and therefore description thereof will be omitted.

[0178] (2-2-5-5. Reception desk 15e) The reception unit 15e receives various types of information. The reception unit 15e may store the received various types of information in the storage unit 14-2. The setting screen display control process, the AI ​​logic selection reception process, and the importance information reception process will be described below.

[0179] (Settings screen display control processing) The reception unit 15e executes a setting screen display control process. For example, the reception unit 15e presents a list of multiple analysis models AM for each analysis category of the analysis target, and displays an AI logic selection screen as a setting screen for receiving input of a selection of an analysis model AM for each analysis category on the user terminal of the user.

[0180] To explain a specific example of the AI ​​logic selection screen, the reception unit 15e transmits candidate information to the operator terminal 20 used by the operator O, and displays on the input / output unit 21 of the operator terminal 20 {"AI Logic 1", "AI Logic 2", "AI Logic 3", "AI Logic 4"} for "Analysis Category #1", {"AI Logic A", "AI Logic B", "AI Logic C"} for "Analysis Category #2", and {"AI Logic X", "AI Logic Y", "AI Logic Z", "AI Logic W"} for "Analysis Category #3".

[0181] Furthermore, the reception unit 15e displays, on the user terminal of the user, an output value list viewing screen as a setting screen presenting a list of analysis targets output by each of the plurality of analysis models AM.

[0182] To explain a specific example of the output value list viewing screen, the reception unit 15e transmits candidate information to the operator terminal 20 used by the operator O, and displays {"Analysis Item 1-1", "Analysis Item 1-2", "Analysis Item 1-3", "Analysis Item 1-4", "Analysis Item 1-5", "Analysis Item 1-6", "Analysis Item 1-7", "Analysis Item 1-8"} for the "Output Value List 1" that the operator O wishes to view on the input / output unit 21 of the operator terminal 20.

[0183] In addition, the reception unit 15e presents a list of analysis targets output by the analysis model AM for which selection has been accepted for each analysis category of the analysis target, and displays an importance setting screen on the user's user terminal as a setting screen for accepting input of combinations of analysis targets for each analysis category and input of the importance of each combination.

[0184] To explain a specific example of the importance setting screen, the reception unit 15e transmits candidate information to the operator terminal 20 used by the operator O, and selects {"analysis item 1-1", "analysis item 1-2", "analysis item 1-3", "analysis item 1-4", "analysis item 1-5", "analysis item 1-6", "analysis item 1-7", "analysis item 1-8"} for "AI logic 1" selected by the operator O, and {"analysis item A-1", "analysis item B-2", "analysis item C-3", "analysis item D-4", "analysis item E-5", "analysis item F-6", "analysis item F-7", "analysis item E-8"} for "AI logic A" selected by the operator O, and selects {"analysis item A-1", "analysis item B-2", "analysis item E-9", "analysis item E-10", "analysis item E-11", "analysis item E-12", "analysis item E-13", "analysis item E-14", "analysis item E-15", "analysis item E-16", "analysis item E-17", "analysis item E-18"} for "AI logic A" selected by the operator O, and selects {"analysis item A-1", "analysis item B-2", "analysis item B-3", "analysis item B-4", "analysis item B-5", "analysis item B-6", "analysis item B-7", "analysis item B-8"} for "AI logic B" selected by the operator O, and selects {"analysis item A-1", "analysis item B-1", "analysis item B-2", "analysis item B-3", "analysis item B-4", "analysis item B-5", "analysis item B-6", "analysis item B-7", "analysis item B-8"} for "AI logic B" selected by the operator O, and selects {"analysis item A-1", "analysis The reception unit 15e then causes the input / output unit 21 of the operator terminal 20 to display the combination of analysis items {"analysis item W-1", "analysis item W-2", "analysis item W-3", "analysis item W-4", "analysis item W-5", "analysis item W-6", "analysis item W-7", "analysis item W-8", "analysis item W-9"} for the "AI logic W" selected by the operator O, and {"analysis item T-1", "analysis item T-2", "analysis item T-3"} for the occurrence time of the event. Then, the reception unit 15e causes the input / output unit 21 of the operator terminal 20 to display an input screen for "importance" associated with the combination of analysis items {"analysis item 1-3", "analysis item A-3", "analysis item W-5", "analysis item T-1"} selected by the operator O.

[0185] (AI logic selection acceptance processing) The reception unit 15e executes an AI logic selection reception process. For example, the reception unit 15e receives a selection of an AI logic, thereby receiving a selection of an analysis model AM from a plurality of analysis models AM to be used for the AI ​​logic. At this time, the reception unit 15e receives a selection of an AI logic for each analysis category, thereby receiving a selection of an analysis model AM from a plurality of analysis models AM to be used for the AI ​​logic for each analysis category.

[0186] To explain a specific example of the AI ​​logic selection reception process, the reception unit 15e receives the following AI logics input by the operator O by operating the AI ​​logic selection screen displayed on the monitor of the operator terminal 20: {Analysis category: "Analysis category #1", AI logic: "AI logic 1"}, {Analysis category: "Analysis category #2", AI logic: "AI logic A"}, {Analysis category: "Analysis category #3", AI logic: "AI logic W"}, and stores them in the setting information storage unit 14f.

[0187] (Importance information reception processing) The receiving unit 15e executes an importance information receiving process. For example, the receiving unit 15e receives importance associated with a combination of analysis targets. At this time, the receiving unit 15e receives importance associated with a combination of analysis targets for each analysis category. The receiving unit 15e may also receive a reaction according to the importance.

[0188] To explain a specific example of the importance information reception process, the reception unit 15e receives importance information input by the operator O by operating the importance setting screen displayed on the monitor of the operator terminal 20, such as "importance information #1" in which an importance level of "8" is assigned to a combination of analysis item "analysis item 1-3" output by "AI logic 1" selected in "analysis category #1," analysis item "analysis item A-3" output by "AI logic A" selected in "analysis category #2," analysis item "analysis item W-5" output by "AI logic W" selected in "analysis category #3," and analysis item "analysis item T-1" indicating the time of occurrence of an event, and stores the information in the setting information storage unit 14f.

[0189] (2-3. Configuration Example and Processing Example of Operator Terminal 20) 9 again, a description will be given of an example of the configuration and processing of the operator terminal 20. The operator terminal 20 is a posting device and a viewing device, and includes an input / output unit 21, a transmitting / receiving unit 22, and a communication unit .

[0190] (2-3-1. Input / output section 21) The input / output unit 21 controls the input of various information to the operator terminal 20. For example, the input / output unit 21 is realized by a mouse, a keyboard, a touch panel, or the like, and accepts input of various information to the operator terminal 20. The input / output unit 21 also controls the display of various information from the operator terminal 20. For example, the input / output unit 21 is realized by a display, or the like, and displays various information stored in the operator terminal 20.

[0191] Furthermore, the input / output unit 21 displays candidate information transmitted from the server device 10-2, which is an information providing device. For example, the input / output unit 21 displays an AI logic selection screen, an output value list viewing screen, an importance setting screen, etc. as setting screens based on the candidate information. Details of the AI ​​logic selection screen will be described later in (2-3-4. Specific example 1 of display screen of operator terminal 20). Details of the importance setting screen will be described later in (2-3-5. Specific example 2 of display screen of operator terminal 20).

[0192] The input / output unit 21 also displays text data included in the monitoring report transmitted from the server device 10-2, and plays back audio data and video data included in the monitoring report transmitted from the server device 10-2.

[0193] (2-3-2. Transmitter / receiver 22) The transmitting / receiving unit 22 transmits various types of information. For example, the transmitting / receiving unit 22 transmits setting information input by the operator O via a setting screen to the server device 10-2.

[0194] The transmitting / receiving unit 22 receives various types of information. For example, the transmitting / receiving unit 22 receives candidate information transmitted from the server device 10-2. The transmitting / receiving unit 22 also receives monitoring reports transmitted from the server device 10-2. The transmitting / receiving unit 22 also receives alarms transmitted from the server device 10-2.

[0195] (2-3-3. Communications Department 23) The communication unit 23 controls data communication with other devices. Note that the configuration and processing examples of the communication unit 23 are the same as those in the first embodiment, and therefore will not be described here.

[0196] (2-3-4. Specific Example 1 of Display Screen of Operator Terminal 20) Here, specific example 1 of a display screen output by the input / output unit 21 of the operator terminal 20 will be described with reference to Fig. 13. Fig. 13 is a diagram showing specific example 1 of a display screen of the operator terminal 20 according to embodiment 2. Below, the "AI logic selection screen," "person action," "person identification," "object identification," "AI logic feature viewing screen," and "output value list viewing screen" will be described.

[0197] (2-3-4-1. AI logic selection screen) As shown in the example of FIG. 13, the operator terminal 20 displays an "AI logic selection screen," which is a setting screen that accepts input of a selection of an AI logic (i.e., an analysis model AM) for each analysis category. Here, the operator O can input a selection of an AI logic for each analysis category by clicking on the AI ​​logic displayed in each of the items "Analysis category example 1: human motion," "Analysis category example 2: human identification," and "Analysis category example 3: object identification." Note that in the example of FIG. 13, the operator terminal 20 displays selectable AI logics for each of the three analysis categories, "Analysis category example 1: human motion," "Analysis category example 2: human identification," and "Analysis category example 3: object identification," but the analysis categories displayed by the operator terminal 20 are not limited to the above example.

[0198] (2-3-4-2.Human movements) As shown in the example of FIG. 13, the operator terminal 20 displays "person movement," which indicates the behavior of a person, as one of the analysis categories. In the example of FIG. 13, "AI Logic 1," "AI Logic 2," "AI Logic 3," and "AI Logic 4" are displayed as AI logics that output "person movement." Here, the AI ​​logic that outputs "person movement" is, for example, an analysis method that realizes movement estimation, skeletal structure estimation, violent act detection, fall detection, person tracking, etc. by inputting image data, but the analysis method that outputs "person movement" is not limited to the above example.

[0199] (2-3-4-3.Person identification) As shown in the example of FIG. 13, the operator terminal 20 displays "person identification," which indicates the attributes of a person, as one of the analysis categories. In the example of FIG. 13, "AI Logic A," "AI Logic B," and "AI Logic C" are displayed as AI logics that output "person identification." Here, the AI ​​logic that outputs "person identification" is, for example, an analysis method that inputs image data to realize facial recognition, individual identification based on gait, gender and age estimation, clothing and equipment detection, and detection of persons requiring assistance, but the analysis method that outputs "person identification" is not limited to the above example. Furthermore, the analysis targets of behavior may include, in addition to people, work vehicles such as robots and construction machinery, animals, etc., and therefore the actions performed by each analysis target may be the analysis target.

[0200] Furthermore, "person identification" is an example of AI logic for identifying a subject, and it is also possible to adopt AI logic that outputs "animal identification" for identifying animals, "work machine identification" for identifying work vehicles such as robots and construction machinery, and "natural object identification" for identifying natural objects such as flowing water in a river or falling rocks.

[0201] (2-3-4-4. Object Identification) As shown in the example of FIG. 13, the operator terminal 20 displays "object identification," which indicates objects involved in a person's behavior, as one of the analysis categories. In the example of FIG. 13, "AI Logic Z," "AI Logic Y," "AI Logic X," and "AI Logic W" are displayed as AI logics that output "object identification." Here, the AI ​​logic that outputs "object identification" is, for example, an analysis method that realizes object type recognition, vehicle detection, animal recognition, plant recognition, dangerous object detection, etc. by inputting image data, but the analysis method that outputs "object identification" is not limited to the above example.

[0202] Furthermore, "object identification" is an example of AI logic that identifies an object, and it is also possible to adopt AI logic that outputs the above-mentioned "person identification."

[0203] (2-3-4-5. AI logic feature viewing screen) The operator terminal 20 can also display an "AI logic feature viewing screen," which is a setting screen that presents the features of the AI ​​logic, to support the operator O in inputting the selection of the AI ​​logic. For example, when the operator O clicks on the "AI logic" button for "AI logic 1" in "Analysis category example 1: human behavior," the operator terminal 20 displays information such as "face recognition," which is a feature of "AI logic 1."

[0204] (2-3-4-6. Output value list viewing screen) The operator terminal 20 can also display an "output value list viewing screen," which is a setting screen that presents a list of analysis items output by the AI ​​logic, to support the operator O in inputting the selection of the AI ​​logic. For example, when the operator O clicks the "output value list" button for "AI logic 1" in "analysis category example 1: human behavior," the operator terminal 20 displays information such as "enter the room," "leave the room," "take out," "leave behind," "be violent," "fall down," "vomit," and "cry" as a list of analysis items output by "AI logic 1."

[0205] (2-3-5. Specific Example 2 of Display Screen of Operator Terminal 20) Here, a specific example 2 of a display screen output by the input / output unit 21 of the operator terminal 20 will be described with reference to Fig. 14. Fig. 14 is a diagram showing a specific example 2 of a display screen of the operator terminal 20 according to the second embodiment. In the following, "Importance setting screen," "Person identification," "Occurrence time," "Object identification," "Person action," "Importance," and "Reaction" will be described.

[0206] (2-3-5-1. Importance setting screen) As shown in the example of FIG. 14, the operator terminal 20 displays an "importance setting screen," which is a setting screen for accepting the importance associated with a combination of analysis items (i.e., an event that occurs) for each analysis category. Here, the operator O can input a combination of analysis items for each analysis category by clicking the check boxes of the analysis items displayed in each of the fields "who," "when," "what," and "how." The operator O can also input an "importance" indicating the urgency, etc., corresponding to the combination of analysis items for each analysis category. The operator O can also input a "reaction," such as an alarm notification, corresponding to the importance.

[0207] (2-3-5-2.Person identification) As shown in the example of FIG. 14, the operator terminal 20 displays "Who" corresponding to the above-mentioned "Analysis Category Example 2: Person Identification" as one of the analysis categories. In the example of FIG. 14, "Pre-registered Person Authority A," "Pre-registered Person Authority B," and "Non-registered Person" are displayed as analysis items output by the AI ​​logic of "Person Identification" selected by the operator O on the above-mentioned "AI Logic Selection Screen." Furthermore, "Non-registered Person" is selected by an operation of the operator O. Note that the analysis items output by the AI ​​logic of "Person Identification" are not limited to the above example.

[0208] In this case, the analysis item output by the "person identification" AI logic may be an analysis item directly output by the analysis model AM, or may be an analysis item converted from the output analysis item. For example, the analysis model AM may directly output one of the analysis items "Pre-registered Person Authority A," "Pre-registered Person Authority B," or "Non-registered Person" in response to the input of image data, or may convert the input of image data into one of the analysis items "Pre-registered Person Authority A," "Pre-registered Person Authority B," or "Non-registered Person" associated with the personal name output by facial recognition and output the result.

[0209] (2-3-5-3. Time of occurrence) As shown in the example of Fig. 14, the operator terminal 20 displays "when" corresponding to the time when the event occurred as one of the analysis categories. In the example of Fig. 14, "weekday business hours," "weekday outside business hours," "weekday late night hours," "holiday daytime hours," and "holiday nighttime hours" are displayed as analysis items that can be identified from the shooting time of the image data. Furthermore, "weekday business hours" is selected by an operation of the operator O. Note that the analysis items that can be identified from the shooting time of the image data are not limited to the above example.

[0210] In this case, the analysis item that can be identified as the time when an event occurred from the time when the image data was taken may be classified by the server device 10-2 based on the company work schedule, school attendance schedule, etc. that have been registered in advance, or may be output based on the day of the week, time, etc. set by the operator O. Furthermore, the analysis item for the time when an event occurred may be output based on the analysis model AM that directly outputs analysis items in response to the input of image data.

[0211] (2-3-5-4. Object Identification) As shown in the example of FIG. 14, the operator terminal 20 displays "What" corresponding to the above-mentioned "Analysis Category Example 3: Object Identification" as one of the analysis categories. In the example of FIG. 14, "Desk," "Chair," "Cardboard Box," "Locker," "File," "Safe," "Seal," "Houseplant," and "Shredder" are displayed as analysis items output by the AI ​​logic of "Object Identification" selected by the operator O on the above-mentioned "AI Logic Selection Screen." Also, "File" is selected by the operation of the operator O. Note that the analysis items output by the AI ​​logic of "Object Identification" are not limited to the above example.

[0212] In this case, the analysis item output by the AI ​​logic of "object identification" may be the analysis item directly output by the analysis model AM, or may be the analysis item output after converting the output analysis item. Also, the operator O can skip the selection of "object identification" if there is no object corresponding to the "human action."

[0213] (2-3-5-5.Human movements) As shown in the example of FIG. 14, the operator terminal 20 displays "What happened" corresponding to the above-mentioned "Analysis Category Example 1: Person's Action" as one of the analysis categories. In the example of FIG. 14, "Enter the room," "Leave the room," "Take out," "Leave behind," "Be violent," "Fall," "Vomit," and "Cry" are displayed as analysis items output by the AI ​​logic of "Person's Action" selected by the operator O on the above-mentioned "AI Logic Selection Screen." Furthermore, "Take out" is selected by the operation of the operator O. Note that the analysis items output by the AI ​​logic of "Person's Action" are not limited to the above example.

[0214] In this case, the analysis items output by the AI ​​logic for "human behavior" may be analysis items directly output by the analysis model AM, or may be analysis items that are converted from the output analysis items.

[0215] (2-3-5-6.Importance) As shown in the example of Fig. 14, the operator terminal 20 allows input of an "importance" indicating the urgency, etc., corresponding to a combination of analysis items for each analysis category. In the example of Fig. 14, an "importance of 8" (minimum value 0, maximum value 10) is input for the combination of analysis items {who: "unregistered user", when: "weekday business hours", what: "file", how: "take out"} selected by the operator O. Note that the input format of the "importance" is not limited to the above example, and may be expressed as a score of 0 to 100%, or as a rank of A, B, C, high, medium, low, etc.

[0216] (2-3-5-7. Reaction) The operator terminal 20 can input a "reaction" such as an alarm notification corresponding to the "importance." For example, the following can be input as reactions to be executed by the server device 10-2: {importance: "0", reaction: "event record"}, {importance: "1 to 6", reaction: "image data record"}, {importance: "7 to 10", reaction: "image data record" "alarm notification"}, etc.

[0217] 3. Flow of Each Process in the Patrol Monitoring System 100-2 The processing flow of the patrol monitoring system 100-2 according to the second embodiment will be described with reference to Fig. 15. Note that the processing of the following steps S201 to S207 may be executed in a different order. Also, some of the processing of the following steps S201 to S207 may be omitted.

[0218] (3-1. Candidate information display process) First, the operator terminal 20 executes a candidate information display process (step S201). For example, the operator terminal 20 displays on the monitor a setting screen that presents, as candidate information, a list of identification information of AI logics for each analysis category, a list of output values ​​for each AI logic, etc.

[0219] (3-2. Setting information input process) Second, the operator O executes a setting information input process (step S202). For example, the operator O selects an AI logic to be used for analysis from a list of identification information of the AI ​​logic for each analysis category, thereby inputting the selection of the AI ​​logic to be used for analysis as setting information, selects analysis items to be output by the selected AI logic for each analysis category, and assigns importance to events that are combinations of the selected analysis items, thereby inputting the importance corresponding to the events as setting information.

[0220] (3-3. Setting information transmission process) Third, the operator terminal 20 executes a setting information transmission process (step S203). For example, the operator terminal 20 transmits the selection of AI logic for each analysis category, the importance corresponding to the event, and the like, which have been input to the operator terminal 20 by the operator O, to the server device 10-2 as setting information.

[0221] (3-4. Monitoring data collection process) Fourth, the server device 10-2 executes a monitoring data collection process (step S204). For example, the server device 10-2 collects image data, such as still images, captured every second from the camera 30A installed at each monitored location. The server device 10-2 also collects measurement data, such as temperature, measured every second from the sensor 30B installed at each monitored location.

[0222] (3-5. Event detection processing) Fifth, the server device 10-2 executes an event detection process (step S205). For example, the server device 10-2 analyzes image data using the analysis model AM corresponding to the selected AI logic, and detects events that are combinations of attributes of people, etc., who appear at the monitored location, their actions, and objects related to the actions. The server device 10-2 also analyzes measurement data using the analysis model AM corresponding to the selected AI logic, and detects events that are combinations of abnormal values, such as room temperature, at the monitored location, and causative devices.

[0223] (3-6. Monitoring report generation process) Sixth, the server device 10-2 executes a monitoring report generation process (step S206). For example, the server device 10-2 uses the generation model GM, which is a language generation model, to generate a monitoring report including text data indicating the details of an event that occurred in the monitored area. At this time, the server device 10-2 can also generate a monitoring report including text data according to the importance associated with the event. Furthermore, the server device 10-2 can also generate a monitoring report including audio data and video data in addition to the text data.

[0224] (3-7. Monitoring report notification processing) Seventh, the server device 10-2 executes a monitoring report notification process (step S207). For example, the server device 10-2 transmits the generated monitoring report to the operator terminal 20 and causes the monitor of the operator terminal 20 to display a text showing the details and summary of the event. The server device 10-2 also causes the operator terminal 20 to display a text showing the details, summary, and statistical values ​​of the event, and can also read the text aloud or display a synchronized video. Furthermore, the server device 10-2 can also display an alarm on the monitor of the operator terminal 20.

[0225] 4. Effects of the Second Embodiment In the process according to the second embodiment described above, the server device 10-2 stores a plurality of analytical models AM that output the target of a monitored location when monitoring data is input, accepts a selection of an analytical model AM from the plurality of analytical models AM, collects monitoring data acquired by monitoring devices 30 installed at each of the plurality of monitored locations included in the monitored area, inputs the collected monitoring data into the analytical model AM whose selection was accepted, detects events that have occurred at each of the plurality of monitored locations according to the output analysis target, and generates a monitoring report including the output text data using a generation model GM that outputs text data indicating the contents of the events that have occurred in the monitored area when the detection results are input. Therefore, this process enables highly accurate detection of events that have occurred at each monitored location and effective understanding of events that have occurred in the monitored area.

[0226] 〔system〕 The information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0227] Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown. In other words, all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0228] Furthermore, all or any part of the processing functions performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0229] [Hardware] Next, an example of the hardware configuration of the server device 10 (10-1, 10-2) which is an information providing device will be described. Note that other devices may also have a similar hardware configuration. FIG. 16 is a diagram showing an example of the hardware configuration according to the first and second embodiments. As shown in FIG. 16, the server device 10 has a communication device 10a, an HDD (Hard Disk Drive) 10b, a memory 10c, and a processor 10d. Furthermore, the components shown in FIG. 16 are connected to each other via a bus or the like.

[0230] The communication device 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores programs and databases that operate the functions shown in FIGS.

[0231] The processor 10d reads out from the HDD 10b or the like a program that executes the same processes as the respective processing units shown in FIGS. 2 and 9 and loads the program into the memory 10c, thereby operating a process that executes the respective functions described in FIGS. 2 and 9, etc. For example, this process executes the same functions as the respective processing units of the server device 10. Specifically, the processor 10d reads out from the HDD 10b or the like a program that has the same functions as the collection unit 15a, the analysis unit 15b, the generation unit 15c, the notification unit 15d, the reception unit 15e, etc. Then, the processor 10d executes a process that executes the same processes as the collection unit 15a, the analysis unit 15b, the generation unit 15c, the notification unit 15d, the reception unit 15e, etc.

[0232] In this way, the server device 10 operates as a device that executes various processing methods by reading and executing a program. The server device 10 can also realize functions similar to those of the above-described embodiment by reading the program from a recording medium using a media reader and executing the read program. Note that the program in these other embodiments is not limited to being executed by the server device 10. For example, the present invention can also be applied in the same way to cases where another computer or server executes the program, or where these execute the program in cooperation with each other.

[0233] This program can be distributed via a network such as the Internet. In addition, this program can be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disk (DVD), and can be executed by being read from the recording medium by a computer.

[0234] 〔others〕 Some examples of combinations of the disclosed technical features are set out below.

[0235] (1) An information providing device comprising: a collection unit that collects monitoring data acquired by monitoring equipment installed at each of a plurality of monitored locations included in a monitored area; an analysis unit that detects events that have occurred at each of the plurality of monitored locations based on the collected monitoring data; and a generation unit that generates a monitoring report including the text data using a machine learning model that, when the detection results are input, outputs text data indicating the content of the events that have occurred in the monitored area.

[0236] (2) The information providing device described in (1), wherein the collection unit collects image data acquired by photographing equipment installed at the multiple monitored locations as monitoring data, the analysis unit detects the event based on the collected image data, and the generation unit generates the monitoring report using a machine learning model that outputs the text data when the detection result is input.

[0237] (3) The information providing device described in (1) or (2), wherein the collection unit collects, as monitoring data, measurement data acquired by measuring equipment installed at the multiple monitored locations, the analysis unit detects the event based on the collected measurement data, and the generation unit generates the monitoring report using a machine learning model that outputs the text data when the detection result is input.

[0238] (4) An information providing device described in any one of (1) to (3), wherein the generation unit identifies the importance associated with the event and generates the monitoring report including the text data according to the conditions assigned to the importance.

[0239] (5) The information providing device described in (4), wherein the generation unit generates the monitoring report including a description of the event with no character limit as the text data when the importance associated with the event is equal to or greater than a first threshold.

[0240] (6) The generation unit An information providing device according to (4) or (5), wherein, when the importance associated with the event is less than a first threshold and greater than or equal to a second threshold, the monitoring report is generated, the text data including a description of the event within an upper limit of the number of characters, and at least one of statistical values ​​of the event.

[0241] (7) An information providing device described in any one of (4) to (6), wherein the generation unit generates the monitoring report including statistical values ​​of the event as the text data when the importance associated with the event is less than a second threshold.

[0242] (8) An information providing device described in any one of (1) to (7), wherein the generation unit generates the monitoring report including audio data indicating the content of the event together with the text data indicating the content of the event.

[0243] (9) An information providing device described in any one of (1) to (8), wherein the generation unit generates the monitoring report including the text data indicating the content of the event, audio data indicating the content of the event, and video data synchronized with the audio data.

[0244] (10) An information providing device described in any one of (1) to (9), further comprising a memory unit that stores a plurality of machine learning models that output an analysis target of a monitored location when the monitoring data is input, and a reception unit that receives a selection of a machine learning model from the plurality of machine learning models, wherein the analysis unit inputs the collected monitoring data to the machine learning model whose selection was received, and detects an event that occurred at each of the plurality of monitored locations according to the output analysis target.

[0245] (11) An information provision method in which a computer collects monitoring data acquired by monitoring equipment installed at each of multiple monitored locations included in a monitored area, detects events that have occurred at each of the multiple monitored locations based on the collected monitoring data, and generates a monitoring report including the text data using a machine learning model that, when the detection results are input, outputs text data indicating the content of the events that have occurred in the monitored area.

[0246] (12) An information provision program that causes a computer to execute a process of collecting monitoring data acquired by monitoring equipment installed at each of a plurality of monitored locations included in a monitored area, detecting events that have occurred at each of the plurality of monitored locations based on the collected monitoring data, and generating a monitoring report including the text data using a machine learning model that, when the detection results are input, outputs text data indicating the content of the events that have occurred in the monitored area. [Explanation of symbols]

[0247] 10, 10-1, 10-2 Server device 11 Input section 12 Output section 13 Communications Department 14-1, 14-2 Storage section 14a Monitoring data storage unit 14b Monitoring report storage section 14c-1, 14c-2 Analysis model storage section 14d Generative model memory 14e Candidate information storage unit 14f Setting information storage section 15-1, 15-2 Control section 15a Collection Section 15b Analysis section 15c Generator 15d Notification Department 15e Reception 20 Operator terminal 21 Input / output section 22 Transmitter / Receiver 23 Communications Department 30 Monitoring equipment 31 Acquisition Department 32 Communications Department 100-1, 100-2 Patrol Monitoring System

Claims

1. A collection unit that collects monitoring data acquired by monitoring equipment installed at each of the multiple monitoring locations included in the monitoring area, An analysis unit that detects events occurring at each of the multiple monitored locations based on the collected monitoring data, A generation unit that generates a monitoring report including text data showing the content of the event that occurred in the monitored area, An information-providing device equipped with the following features.

2. The generating unit is When the detection results from the analysis unit are input, a machine learning model that outputs text data indicating the content of the event that occurred in the monitored area is used to generate the monitoring report including the text data. The information providing device according to feature 1.

3. The aforementioned collection unit is As monitoring data, image data acquired by imaging devices installed at the multiple monitoring locations is collected. The aforementioned analysis unit, Based on the collected image data, the event is detected, The generating unit is The monitoring report is generated using a machine learning model that outputs the text data when the detection result is input. The information providing device according to claim 1.

4. The aforementioned collection unit is As monitoring data, measurement data acquired by measuring devices installed at the multiple monitoring locations is collected. The aforementioned analysis unit, Based on the collected measurement data, the event is detected, The generating unit is The monitoring report is generated using a machine learning model that outputs the text data when the detection result is input. The information providing device according to claim 1.

5. The generating unit is Identify the importance level associated with the aforementioned event, and generate the monitoring report including the text data according to the conditions assigned to the importance level. The information providing device according to claim 1.

6. The generating unit is If the importance level associated with the event is equal to or greater than the first threshold, the monitoring report is generated, which includes a description of the event with no upper limit on the number of characters, as text data. The information providing device according to claim 5.

7. The generating unit is If the importance associated with the event is less than the first threshold but greater than or equal to the second threshold, the monitoring report is generated, which includes, as text data, a description of the event and at least one of the event's statistics, within the upper limit of the number of characters. The information providing device according to claim 5.

8. The generating unit is If the importance associated with the event is less than the second threshold, the monitoring report is generated as text data, including the statistical values ​​of the event. The information providing device according to claim 5.

9. The generating unit is The monitoring report is generated, which includes, along with the text data describing the content of the event, audio data describing the content of the event. The information providing device according to claim 1.

10. The generating unit is The monitoring report is generated, which includes the text data describing the content of the event, audio data describing the content of the event, and video data synchronized with the audio data. The information providing device according to claim 1.

11. A storage unit that stores multiple machine learning models that output the analysis targets of the monitored locations when the aforementioned monitoring data is input, A receiving unit that accepts the selection of a machine learning model from the aforementioned multiple machine learning models, Furthermore, The aforementioned analysis unit, The collected monitoring data is input to the machine learning model that has been selected, and according to the output analysis target, events that occurred at each of the multiple monitoring target locations are detected. An information providing device according to any one of claims 1 to 10.

12. Computers The monitoring data acquired by monitoring equipment installed at each of the multiple monitoring locations included in the monitoring area is collected. Based on the collected monitoring data, events occurring at each of the multiple monitored locations are detected. A monitoring report is generated that includes text data indicating the content of the event that occurred in the monitored area. A method for providing information to execute a process.

13. On the computer, The monitoring data acquired by monitoring equipment installed at each of the multiple monitoring locations included in the monitoring area is collected. Based on the collected monitoring data, events occurring at each of the multiple monitored locations are detected. A monitoring report is generated that includes text data indicating the content of the event that occurred in the monitored area. A program that provides information to initiate a process.

Images