Disaster prevention support system

Abstract

To provide a disaster prevention support system that can appropriately send disaster prevention measures according to the circumstances of every business office.SOLUTION: The present invention pertains to a disaster prevention support system that supports disaster prevention by predicting disaster prevention measures to be necessary in a business office according to a predicted situation, and comprises: a determination data acquisition unit 600 that acquires determination data including prediction data and business operation data related to business operations carried out in the business office; a learned model storage unit 62 that stores a learning model 12 that has machine-learned the correlation between input data including the prediction data and the business operation data related to the business operations carried out in the business office and output data including data on whether disaster prevention measures are required or not; and an inference unit 601 that inputs the determination data acquired by the determination data acquisition unit to the learning model to infer the data on whether disaster prevention measures are required or not.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to a disaster prevention support system that accurately disseminates disaster prevention measures. [Background technology]

[0002] Information on the occurrence or prediction of disasters such as earthquakes and wind and flood damage includes emergency earthquake alerts and various weather forecasts (typhoon occurrence, advisories and warnings, rain cloud radar, sudden heavy rain, and many more), and currently push notification methods include email alert services and alert services via smartphone apps (for example, Yahoo! (registered trademark) Disaster Prevention and Weather News apps). However, the above-mentioned email and smartphone app alert services do not provide information on what measures are necessary when a disaster occurs. Therefore, a disaster prevention support system has been proposed that outputs appropriate disaster prevention actions for meteorological disasters in response to ever-changing conditions. For example, Patent Document 1 (JP 2020-201704 A) discloses a disaster prevention support system that includes an action suggestion unit that suggests disaster prevention actions for a target disaster based on forecast information, and an output processing unit that outputs instruction information corresponding to the disaster prevention actions suggested by the action suggestion unit from an output unit. This disaster prevention support system enables even people with little specialized knowledge of disasters or little work experience to carry out necessary disaster prevention activities in a timely manner. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-201704 Summary of the Invention [Problem to be solved by the invention]

[0004] The prior art described in Patent Document 1 employs a configuration in which a behavior memory unit stores in advance the correspondence between "type of disaster," "application conditions," and "disaster prevention actions," and when the application conditions are met, the disaster prevention action is acquired from the behavior memory unit. Although disaster prevention actions at construction sites are essentially special actions tailored to the circumstances of each construction site, the disaster prevention support system proposed in the prior art does not take such circumstances into consideration, which has been a problem.

[0005] Furthermore, when multiple disasters are imminent, the number of disaster prevention activities that need to be carried out increases, making it difficult to understand the content presented, and making it difficult to make quick decisions and take action. [Means for solving the problem]

[0006] The present invention is intended to solve the above-mentioned problems, and the disaster prevention support system of the present invention is a disaster prevention support system that provides disaster prevention support by predicting disaster prevention measures that will be required at a business establishment depending on the expected situation, and is characterized by comprising: a judgment data acquisition unit that acquires judgment data including prediction data and business data related to work performed at the business establishment; a learned model memory unit that stores a learning model that has been machine-learned to determine the correlation between input data including the prediction data and business data related to work performed at the business establishment and output data including data on the necessity of disaster prevention measures; and an inference unit that inputs the judgment data acquired by the judgment data acquisition unit into the learning model and infers data on the necessity of disaster prevention measures.

[0007] The disaster prevention support system according to the present invention is characterized by further comprising an output unit that outputs necessary disaster prevention measures based on the data on necessity of disaster prevention measures in the inference unit.

[0008] Furthermore, the disaster prevention support system according to the present invention is characterized in that the prediction data includes prediction data relating to changes in natural conditions.

[0009] In addition, the disaster prevention support system according to the present invention is characterized in that the business data includes data on the progress of business.

[0010] In addition, the disaster prevention support system according to the present invention is characterized in that the business data includes data on the types of products and services handled by the business establishment.

[0011] In addition, the disaster prevention support system of the present invention is characterized by having an input unit that inputs data related to the inference results inferred by the inference unit into a text generation service providing server, a receiving unit that receives output data from the text generation service providing server, and a notification unit that notifies the output data received by the receiving unit. [Effects of the Invention]

[0012] The disaster prevention support system of the present invention is configured to infer necessary disaster prevention measures by inputting judgment data, including prediction data and business data related to the work carried out at the business, into a learning model.Therefore, with this disaster prevention support system of the present invention, it is possible to appropriately disseminate disaster prevention measures that are appropriate to the circumstances and business content of each business, and the products and services handled at the business.

[0013] Furthermore, according to an embodiment of the disaster prevention support system using a text generation service providing server, it is possible to clearly present the items of disaster prevention activities that need to be carried out, which can contribute to the rapid implementation of disaster prevention activities. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is an overall configuration diagram showing an example in which a disaster prevention support system according to an embodiment of the present invention is applied to a construction site. [Figure 2] 1 is an example of the data structure of disaster prevention countermeasure data 15 in the disaster prevention support system according to the embodiment of the present invention. [Figure 3] 1A is a diagram showing an example of data constituting forecast data, (B) construction data, and (C) on-site data. FIG. [Figure 4]This is a table showing the correspondence between the progress of construction work and the necessary disaster prevention measures. (A) is for the case where the building under construction has a reinforced concrete (RC) frame, and (B) is for the case where the building under construction has a steel frame. [Figure 5] FIG. 2 is a diagram showing an example of the configuration of learning data 13. [Figure 6] FIG. 2 is a diagram showing the relationship between a learning model 12 and learning data 13. [Figure 7] 2 is a block diagram showing an example of functions of an information processing device 6 according to an embodiment of the present invention. FIG. [Figure 8] 10 is a flowchart showing an example of an information processing method by the information processing device 6. [Figure 9] 10 is a flowchart showing an example of a process using a text generation service providing server. [Figure 10] 8A and 8B are diagrams illustrating examples of displays on a display unit of a smartphone 800. [Figure 11] 8A and 8B are diagrams illustrating examples of displays on a display unit of a smartphone 800. [Figure 12] FIG. 9 is a hardware configuration diagram showing an example of a computer 900 that can constitute a disaster prevention support system. [Figure 13] FIG. 8 is a hardware configuration diagram of a smartphone 800 that can constitute a disaster prevention support system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The disaster prevention support system according to the present invention predicts disaster prevention measures required at each business establishment in response to predicted changes in natural conditions (such as changes in weather, the occurrence of earthquakes or tsunamis, and the occurrence of eruptions at active volcanoes). In this specification, the business establishment is assumed to be, for example, a business establishment related to a product manufacturing line or a business establishment related to services such as transportation, but there is no particular limitation on the type of business that the disaster prevention support system according to the present invention is applied to. The disaster prevention measures predicted by the disaster prevention support system according to the present invention are notified to the user to contribute to disaster prevention support.

[0016] In the following embodiments, a construction site will be used as an example of a business establishment. FIG. 1 is an overall configuration diagram showing an example of a disaster prevention support system according to an embodiment of the present invention when applied to a construction site. The disaster prevention support system according to this embodiment predicts disaster prevention measures required at a construction site in response to future changes in natural conditions such as predicted weather, and provides disaster prevention support by notifying users of the predicted disaster prevention measures. Users of the disaster prevention support system according to the present invention are expected to be, for example, disaster prevention personnel working at a construction site.

[0017] The disaster prevention support system according to the present invention has, as a main system, an information processing device 6 operated, for example, in a disaster prevention control center, etc. The information processing device 6 is configured, for example, as a general-purpose or dedicated computer (see below), and is connected to a wired or wireless network 7 so as to be able to send and receive various types of data.

[0018] An example of a user is disaster prevention personnel at different construction sites. In the example of FIG. 1, three construction sites are shown: construction site A, construction site B, and construction site C. It is assumed that users at each construction site carry a smartphone 800 (see below) connected to the network 7 as an example of an information processing device. The smartphone 800 is capable of referring to information notified from the information processing device 6, or transmitting a response to the notified information to the information processing device 6.

[0019] The expected weather conditions vary depending on the location of each of the construction sites A, B, and C. Therefore, the disaster prevention measures required at each construction site will differ. The information processing device 6 predicts the disaster prevention measures required at each construction site, and notifies the smartphones 800 of users at the construction sites where disaster prevention measures are required of information related to the disaster prevention measures (items of disaster prevention measures required, advice on disaster prevention measures).

[0020] The information processing device 6 has at least a learning model 12, learning data 13, construction data 14, and disaster prevention countermeasure data 15 stored in its storage device. Of these data, data to be notified to the user's smartphone 800 is stored in the disaster prevention countermeasure data 15. FIG. 2 shows an example of the data structure of the disaster prevention countermeasure data 15 in a disaster prevention support system according to an embodiment of the present invention. As shown in FIG. 2, under the heading "Type of Disaster," there are broad headings called "Major Headings," and under these headings there are further headings called "Response Details," which are disaster prevention countermeasures required at each construction site. The information notified to the smartphone 800 from the information processing device 6 as disaster prevention countermeasures includes information related to the "Response Details" heading.

[0021] The data structure shown in Figure 2 is just an example, and the data structure of the disaster prevention measures data 15 can be a simple data structure in which corresponding items are listed without any major items, or a data structure with a more complex hierarchical structure in which medium items, minor items, etc. are listed under major items.

[0022] Furthermore, if the business establishment is not a construction site, the "construction data" can be generally referred to as "business data."

[0023] The information processing device 6 also functions as a main device in the inference phase of machine learning. The learning model 12 stored in the information processing device 6 is data that has already been machine-learned using learning data 13. The information processing device 6 uses the learning model 12 generated by machine learning to predict disaster prevention measures that will be required depending on the situation at each construction site.

[0024] Furthermore, the learning data 13 stored in the information processing device 6 is a data set for performing machine learning on the learning model 12. The information processing device 6 inputs multiple sets of learning data 13 into the learning model 12 and causes the learning model 12 to learn correlations between the prediction data, construction data, and site data included in the learning data 13 and data on the necessity of disaster prevention measures, thereby generating a trained learning model 12. When the information processing device 6 performs machine learning, any method such as online learning, batch learning, or mini-batch learning can be adopted.

[0025] The construction data 14 stored in the information processing device 6 is a collection of data related to construction work carried out at each construction site. The construction data 14 is used as one of the input data when the information processing device 6 performs inference using the learning model 12. The construction data 14 is also one of the input data in the learning data 13.

[0026] 1, the forecast data providing server 20 is a server that is connected to the network 7 and transmits various forecast data 25 to the information processing device 6. The forecast data 25 is not particularly limited as long as it predicts future changes in natural conditions, but examples include data that predict weather and data that predict earthquakes.

[0027] 1, the site data 26 is data acquired at each construction site. It is assumed that such site data 26 is acquired, for example, by sensors (not shown) and transmitted to the information processing device 6 via the network 7. The site data 26 may be any data relating to the current situation at each construction site, and may include, for example, data acquired by a rain gauge.

[0028] The text generation service server 30 uses a large-scale language model to understand input text data and generate new text data in natural language related to the input text data. For example, if the input text data includes a description of a request, the text generation service server 30 generates text data that responds to the request. In the disaster prevention support system according to the present invention, text data related to construction data 14, forecast data 25, site data 26, and data on the necessity of disaster prevention measures predicted by the learning model 12 are input to the text generation service server 30, and advice on disaster prevention measures related to these data is output. The text data generated by the text generation service server 30 is expected to be non-standard and easy to understand.

[0029] Next, we will explain specific examples of the forecast data 25, construction data 14, and site data 26. Figure 3 is a diagram showing examples of data constituting (A) forecast data, (B) construction data, and (C) site data.

[0030] The forecast data 25 is data that predicts future conditions, and can include weather forecast data, earthquake forecast data, evacuation data provided by the government or local government, etc., as shown in FIG. 3(A).

[0031] The construction data 14 is data related to the construction work being carried out at each construction site, and may include, for example, data on the skeleton of the building being constructed at the construction site, data on the progress of the construction work, and organizational data on the organization and structure of the workers engaged in the construction. In particular, the skeleton data and construction progress data in the construction data 14 are highly important in determining whether or not disaster prevention measures are necessary. The reason for this will be explained with reference to Figure 4.

[0032] In this embodiment, since the business establishment is a construction site, "data relating to the progress of construction" is included as one of the "construction data," but in general cases where the business establishment is not a construction site, "construction data" can be replaced with "business data," and "data relating to the progress of construction" can be replaced with "data relating to the progress of business."

[0033] Figure 4 is a table showing the correspondence between the progress of construction work and the necessary disaster prevention measures. (A) shows the case where the building under construction has a reinforced concrete (RC) structure, and (B) shows the case where the building under construction has a steel structure.

[0034] The table in Figure 4 divides the construction progress from start to completion into four stages, with a circle marking the disaster prevention measures required for each stage. The four stages, in order from start to finish, are the earthwork stage, the framework stage, the exterior finishing stage, and the interior and equipment construction stage. For example, "water protection measures for excavated areas" are required for the earthwork stage, but not for other stages. In this way, the disaster prevention measures required depend on the progress of the construction work, and by taking the progress of the construction work into consideration, it becomes possible to more appropriately determine whether or not disaster prevention measures are required.

[0035] Figures 4(A) and 4(B) show the differences in disaster prevention measures required depending on the skeleton of the building under construction. For example, the disaster prevention measure "Stopping steel frame erection work in the event of strong winds" is not required in any process if the skeleton is reinforced concrete, but is required in the skeleton construction process if the skeleton is steel. Similarly, the disaster prevention measure "Rain protection for poured concrete" is not required in any process if the skeleton is steel, but is required in the skeleton construction process if the skeleton is reinforced concrete. In this way, the disaster prevention measures required depend on the skeleton of the building under construction, and by taking the type of skeleton into consideration, it is possible to more appropriately determine whether or not disaster prevention measures are required.

[0036] In this embodiment, since the business establishment is a construction site, data regarding the type of building structure is handled as described above, but in general cases where the business establishment is not a construction site, "data regarding the type of structure" can be replaced with "data regarding the type of products and services handled at the business establishment."

[0037] The construction data 14 may include data on the equipment to be installed in the building under construction, data on the client of the building under construction, and data on the disaster prevention manual set up for the building under construction. 3(C), the site data 26 may include data acquired by a rain gauge installed at the construction site, data acquired by an anemometer installed at the construction site, data acquired by a seismometer installed at the construction site, or data from a surveillance camera installed at the construction site and capturing images of the construction site, etc. Furthermore, the site data 26 may also include data related to news around the construction site, data from social media that includes content about the construction site, etc.

[0038] Next, an example of the configuration of the training data 13 in the disaster prevention support system according to the present invention will be described. The training data dataset is teacher data used for machine learning of the learning model 12. FIG. 5 is a diagram showing an example of the configuration of the training data, and multiple training data datasets are prepared for machine learning of the learning model 12. The applicant provides a service called "Pinpoint Timeline" (registered trademark), and training data datasets accumulated through such a service can be used. Furthermore, the training data dataset can be increased by data augmentation to improve the accuracy of machine learning.

[0039] The input data for the learning data 13 can be any one of prediction data, construction data, and on-site data, or a combination of these. The output data can be data related to the necessity of disaster prevention measures. For example, for one of the disaster prevention measures, "Necessity of demolition / removal," a value indicating that demolition / removal is necessary as a disaster prevention measure and a value indicating that demolition / removal is not necessary as a disaster prevention measure are calculated. If demolition / removal is absolutely necessary as a disaster prevention measure, the output data is set so that the former value is 1 and the latter value is 0. The sum of the value indicating that demolition / removal is necessary and the value indicating that demolition / removal is not necessary is set to 1. The output data for the learning data 13 is data used as a correct answer label in supervised learning.

[0040] FIG. 6 is a diagram showing an example of the learning model 12 and the learning data 13. The learning data 13 used for machine learning of the learning model 12 can be composed of, for example, data sets of prediction data, construction data, and site data, and data on the necessity of disaster prevention measures. Note that the following description will be based on three sets of prediction data, construction data, and site data as input data for the learning data 13, but the invention can also be established with just one of the prediction data, construction data, and site data as input data. However, if the input data for the learning data 13 is the three data sets of prediction data, construction data, and site data, it is expected that the accuracy of machine learning will be improved.

[0041] The data constituting the learning data 13 includes at least one of prediction data, construction data, and on-site data. The necessity data for each disaster prevention measure constituting the learning data 13 is expressed, for example, as a graded value or a continuous value, and in the case of a continuous value, the value can be normalized to a predetermined range (for example, 0 to 1).

[0042] Each of the forecast data, construction data, and site data may be point-in-time data indicating the state at a predetermined point in time, or may be time-series data consisting of multiple point-in-time data at predetermined time intervals (every hour, every day, every week, every month, etc.), or may be representative data indicating a representative value (average, maximum, minimum, etc.) of multiple point-in-time data included in a predetermined period. The definitions of the forecast data, construction data, and site data may be changed as appropriate, in which case the data configuration of the input data in the learning model 12 and learning data 13 may be changed as appropriate.

[0043] The learning model 12 employs, for example, a neural network structure and includes an input layer 120, an intermediate layer 121, and an output layer 122. Synapses (not shown) that connect each neuron are laid between each layer, and each synapse is associated with a weight. A group of weight parameters consisting of the weights of each synapse is adjusted by machine learning.

[0044] The input layer 120 has neurons corresponding in number to the input data of prediction data, construction data, and site data, and values ​​of the prediction data, construction data, and site data are input to each neuron. The output layer 122 has neurons corresponding in number to the number of disaster prevention measures items for necessity data as output data, and prediction results (inference results) of the necessity data of disaster prevention measures for the prediction data, construction data, and site data are output as output data. When the learning model 12 is configured as a regression model, the necessity data of disaster prevention measures is output as a numerical value normalized to a predetermined range (e.g., 0 to 1). When the learning model 12 is configured as a classification model, the necessity data of disaster prevention measures is output as a score (accuracy) for each class as a numerical value normalized to a predetermined range (e.g., 0 to 1).

[0045] Machine learning is performed by inputting multiple sets of learning data 13 into the learning model 12 and having the learning model 12 learn the correlation between the prediction data, construction data, and on-site data contained in the learning data 13 and the data on the need for disaster prevention measures, thereby generating a trained learning model 12.

[0046] 7 is a block diagram showing an example of functions of an information processing device 6 according to an embodiment of the present invention. The information processing device 6 includes a control unit 60. The control unit 60 functions as a judgment data acquisition unit 600, a trained model storage unit 62, an inference unit 601, and an output processing unit 602.

[0047] The determination data acquisition unit 600 is connected to an external device via the network 7 and acquires prediction data, construction data, and site data used to predict the necessity data for disaster prevention measures. As described above, the inference unit 601 generates the necessity data for disaster prevention measures based on the prediction data, construction data, and site data output by inputting the prediction data, construction data, and site data acquired by the determination data acquisition unit 600 into the learning model 12 as input data.

[0048] In addition, the inference unit 601 may perform predetermined pre-processing on the input data (prediction data, construction data, site data) input to the learning model 12, or may perform predetermined post-processing on the output data (data on the need for disaster prevention measures) output from the learning model 12.

[0049] The trained model storage unit 62 in the inference unit 601 stores trained learning models 12. Note that the number of stored learning models 12 is not limited to the above example, and for example, multiple trained models with different conditions may be stored and selectively used depending on the machine learning method, type of data, etc. Also, the storage unit for the learning models 12 may be substituted by a storage unit of an external computer (e.g., a server-type computer or a cloud-type computer), in which case the inference unit 601 simply needs to access the external computer.

[0050] The output processing unit 602 performs an output process of the necessity data of disaster prevention measures generated by the inference unit 601. The output processing unit 602 outputs items of disaster prevention measures generated by the inference unit 601 for which the value indicating that disaster prevention measures are necessary based on the necessity data is equal to or greater than a predetermined value. One form of output by the output processing unit 602 is a notification of disaster prevention measures to the smartphone 800. Note that other output forms from the output processing unit 602 can be various methods such as SNS, email, in-house broadcasting, and distribution to digital signage.

[0051] An example of an information processing method by the information processing device 6 will be described with reference to Fig. 8. In the flowchart of Fig. 8, when processing starts in step S100, prediction data, construction data, and site data are acquired as determination data in step S101. The prediction data and site data are acquired by the information processing device 6 via the network 7.

[0052] In the next step S102, the judgment data consisting of the prediction data, construction data, and on-site data is input into the learning model 12 to generate data on the necessity of disaster prevention measures. Then, in step S103, disaster prevention measures items whose "necessary" value in the generated disaster prevention measure necessity data is equal to or greater than a predetermined value are output. The output in step S103 can be output to a smartphone 800 carried by the user via the network 7.

[0053] An example of a display on the smartphone 800 that has received the output in step S103 is shown in Fig. 10. In this example display, the disaster prevention measures listed are "dismantling and removal (where possible)," "binding and removing nets and sheets," and "moving documents and equipment to higher places."

[0054] Next, a description will be given of an embodiment that utilizes the prediction data providing server 20. FIG.

[0055] When processing starts in step S200, in the next step S201, disaster prevention measures items whose "necessary" value is equal to or greater than a predetermined value are input as text data to the writing generation service providing server 30. At this time, in addition to the disaster prevention measures items, text data that is likely to prompt appropriate document generation from prediction data, construction data, and on-site data may also be input to the writing generation service providing server 30. The writing generation service providing server 30 outputs text data in response to such input.

[0056] In step S202, when the information processing device 6 receives output data from the text generation service providing server 30, the received output data from the text generation service providing server 30 is subsequently notified to the smartphone 800 via the network 7 in step S203. FIG. 11 shows an example of a display on the smartphone 800 that has received such a notification. In the disaster prevention support system according to the present invention, by utilizing the text generation service providing server 30, the display example in FIG. Disaster prevention advice [Construction site name: A]

[0057] Typhoon X is approaching. Please install waterproof panels to protect against heavy rain. Please tidy up the outdoors and lock windows and doors to protect against strong winds. Please instruct employees not to come to work. Please announce temporary closures. Provide users with non-formatted, human-readable documentation, as shown in

[0058] As described above, the disaster prevention support system of the present invention is configured to infer the necessary disaster prevention measures by inputting judgment data including weather forecast data and construction data related to work being carried out at the construction site into the learning model 12.Therefore, with this disaster prevention support system of the present invention, it is possible to appropriately disseminate disaster prevention measures that are tailored to the circumstances of each construction site.

[0059] Furthermore, according to an embodiment of the disaster prevention support system using the text generation service providing server 30, it is possible to clearly present the items of disaster prevention activities that need to be carried out, which can contribute to the rapid implementation of disaster prevention activities. (Configuration of computer 900) FIG. 12 is a hardware configuration diagram showing an example of a computer 900 that can constitute the information processing device 6 of the disaster prevention support system.

[0060] The information processing device 6 of the disaster prevention support system is configured by a general-purpose or dedicated computer 900. The computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0061] The processor 912 is composed of one or more arithmetic processing devices (such as a central processing unit (CPU), a micro-processing unit (MPU), a digital signal processor (DSP), or a graphics processing unit (GPU)), and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (such as a DRAM or SRAM) that functions as a main memory, and a non-volatile memory (such as a ROM or flash memory).

[0062] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrated into one device, such as a touch panel display. The storage device 920 is composed of, for example, a hard disk drive (HDD), a solid state drive (SSD), etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and the program 930.

[0063] The storage device 920 can store an operating system, an application program for the disaster prevention support system of the present invention that runs on this operating system, and a learning model 2, learning data 13, construction data 14, disaster prevention measures data 15, etc. that are used by the disaster prevention support system application program.

[0064] The communication I / F unit 922 is connected to a network 940 such as the Internet or an intranet (which may be the same as network 7 in FIG. 1) via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication protocol. The external device I / F unit 924 is connected to an external device 950 such as a camera, printer, scanner, or reader / writer via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication protocol. The I / O device I / F unit 926 is connected to I / O devices 960 such as various sensors and actuators and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I / O devices 960. The media input / output unit 928 is formed by a drive device such as a DVD (Digital Versatile Disc) drive or a CD (Compact Disc) drive and reads and writes data from and to media (non-transitory storage media) 970 such as DVDs and CDs.

[0065] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the medium 970 in an installable file format or an executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the communication I / F unit 922 over the network 940. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA (field-programmable gate array) or an ASIC (application specific integrated circuit).

[0066] The computer 900 is an electronic device of any type, such as a desktop computer or a portable computer. Depending on the intended use of the computer 900, the computer 900 may be a client computer or an edge computer, or may be a server computer or a cloud computer. (Configuration of Smartphone 800) The configuration of a smartphone 800, which is an example of an information processing device that can be used in the disaster prevention support system according to the present invention, will be described. Fig. 13 is a hardware configuration diagram of the smartphone 800 that can be used to configure the disaster prevention support system according to the embodiment of the present invention. Note that, although the present embodiment will be described based on an example in which a smartphone is used as a computer, other devices such as a tablet terminal device can also be used as a computer in the disaster prevention support system according to the present invention.

[0067] The control unit 811 is a configuration equivalent to a central processing unit (processor) and various programs executed on the central processing unit. A basic operating system 816 that runs on the central processing unit also includes programs that realize basic timekeeping functions such as a calendar and a clock.

[0068] The memory unit 815 is a storage such as a volatile memory (DRAM, SRAM, etc.) or a non-volatile memory (ROM, flash memory, etc.) that stores data. The memory unit 815 is configured to hold data written by the control unit 811, to allow the control unit 811 to refer to the written data, and to erase data that is no longer needed by the control unit 811.

[0069] The storage unit 815 stores a basic operating system 816, a disaster prevention support system application program 817 of the present invention that runs on the basic operating system 816, and the disaster prevention support system application program 817. Each program stored in the storage unit 815 is executed by the control unit 811.

[0070] The disaster prevention support system of the present invention is designed to realize various functions by the control unit 811 executing various processes based on the disaster prevention support system application program 817, which is application software installed in the memory unit 815.

[0071] In the figure, the control unit 811 is capable of issuing various control commands to block configurations (such as the touch panel unit 830) connected to it, transferring various data, and receiving data acquired by the block configurations.

[0072] The communication unit 820 realizes data communication and voice calls with external devices via wireless communication. Based on instructions from the control unit 11, the communication unit 820 can, for example, transmit data written in the storage unit 815 to the external device, or transfer data received from the external device to the control unit 811.

[0073] The GPS receiver 823 is configured to receive GPS (Global Positioning System) signals from multiple satellites to determine its own latitude and longitude. The latitude and longitude determined by the GPS receiver 823 are transmitted to the control unit 811. The control unit 811 works in conjunction with a map data application (not shown) stored in the storage unit 815 to determine the location of the smartphone 800 itself on the map, and ultimately the location of the user who is expected to be carrying the smartphone 800.

[0074] The imaging unit 825 is configured to acquire still image imaging data and moving image imaging data. The still image imaging data and moving image imaging data acquired by the imaging unit 825 are subjected to image processing by the control unit 811, and are displayed on the touch panel unit 830, and are stored in the storage unit 815 as necessary. The still image imaging data stored in the storage unit 815 can be configured to be available for use in the disaster prevention support system 5.

[0075] The touch panel unit 830 provided in the smartphone 800 is used as a user interface. The touch panel unit 830 is an integrated unit consisting of an input unit 831 that detects contact with the user's finger to allow the user to input information, and a display unit 832 that displays information to the user. In the touch panel unit 830, the display unit 832 and the input unit 831 are provided so as to overlap each other, and the input unit 831 is transparent, so that the user can make input based on the display by touching the display of the display unit 832 with their finger. For input operations by the user based on such touch panel unit 830, conventionally known techniques are applicable to the present invention.

[0076] For example, a capacitance type may be used for the input unit 831 of the touch panel unit 830. For the display unit 32 of the touch panel unit 830, a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) may be used.

[0077] The input operations commonly known on the touch panel section 830 of the smartphone 800, such as "tap," "double tap," "long tap," "drag," "move," "flick," "swipe," "pinch," and "pinch out," can also be adopted in the disaster prevention support system 5 of the present invention.

[0078] The audio processing unit 835 modulates and demodulates audio signals. The audio processing unit 835 modulates a signal provided from the microphone 836 and provides the modulated signal to the control unit 811. The audio processing unit 835 also provides the audio signal to the speaker 837. The audio processing unit 835 is realized by, for example, a processor for audio processing. The microphone 836 functions as an audio input unit that receives an input of an audio signal and outputs it to the control unit 811. The speaker 837 functions as an audio output unit that outputs the audio signal to the outside of the smartphone 800.

[0079] The acceleration sensor 841 is an inertial sensor that measures the acceleration applied to the smartphone 800, and may be, for example, a MEMS acceleration sensor that applies MEMS (Micro Electro Mechanical System) technology as a method for detecting acceleration.

[0080] The geomagnetic sensor 842 is a sensor that measures the magnitude and direction of a magnetic field (magnetic field). As the geomagnetic sensor 842, a Hall element sensor that uses the Hall effect of a Hall element, an MR sensor that uses a magnetoresistive element, or the like can be used.

[0081] The gyro sensor 843 is an angular velocity sensor that measures the rotational angular velocity of the smartphone 800. As such a gyro sensor 843, a vibration type gyro sensor using MEMS technology can be suitably used.

[0082] Although the present invention has been described above based on the embodiments, the present invention is not limited to the above embodiments. Various modifications can be made to the above embodiments and the embodiments can be combined within the scope of the same or equivalent to the present invention. [Explanation of symbols]

[0083] 6. Information processing device, 7. Network, 12. Learning model, 13. Learning data 14 Construction data, 15 Disaster prevention data, 20 Prediction data providing server, 25 Prediction data, 26 Site data, 30 Text generation service providing server 62: trained model memory unit, 120: input layer, 121: intermediate layer, 122: output layer 600: judgment data acquisition unit, 601: inference unit, 602: output processing unit, 800: Smartphone (an example of an information processing device), 811: Control unit, 815: Memory unit, 816: Basic operating system, 817: Disaster prevention support system application program, 820: Communication unit, 823: GPS receiving unit, 825: Imaging unit, 830: Touch panel unit, 831: Input unit, 832: Display unit, 835: Audio processing unit, 836: Microphone, 837: Speaker, 841: Acceleration sensor, 842: Geomagnetic sensor, 843: Gyro sensor 900...computer, 910...bus, 912...processor, 914...memory, 916...input device, 917...output device, 918...display device, 920...storage device, 922...communication I / F (interface) section, 924...external device I / F section, 926...I / O (input / output) device

Claims

1. A disaster prevention support system that provides disaster prevention support by predicting disaster prevention measures required at a business establishment according to the expected situation, a determination data acquisition unit that acquires determination data including prediction data and business data related to business performed at the business establishment; a learned model storage unit that stores a learned model that has been machine-learned to determine the correlation between input data including prediction data and business data related to business operations performed at the business establishment, and output data including data on the necessity of disaster prevention measures; A disaster prevention support system characterized by comprising an inference unit that inputs the judgment data acquired by the judgment data acquisition unit into the learning model and infers data on the necessity of disaster prevention measures.

2. 2. The disaster prevention support system according to claim 1, further comprising an output unit that outputs necessary disaster prevention measures based on the data on necessity of disaster prevention measures in the inference unit.

3. 2. The disaster prevention support system according to claim 1, wherein the prediction data includes prediction data relating to changes in natural conditions.

4. 2. The disaster prevention support system according to claim 1, wherein the business data includes data relating to the progress of business.

5. 2. The disaster prevention support system according to claim 1, wherein the business data includes data relating to the types of products and services handled by the business establishment.

6. an input unit that inputs data related to the inference result inferred by the inference unit into a text generation service providing server; a receiving unit that receives output data from the text generation service providing server; 2. The disaster prevention support system according to claim 1, further comprising: a notification unit that notifies the user of the output data received by the receiving unit.

Images