Information processing device, information processing method, and program

Abstract

Creating a hazard map using social media information. [Solution] The information processing device 10 includes an acquisition unit 11 that, when a disaster occurs, acquires posted information related to the disaster, including location information and keywords; a processing unit 12 that sets an impact level of the disaster indicated by the posted information for each of the acquired posted information based on the keywords, and classifies each of the acquired posted information into one of a plurality of predetermined areas based on the location information; a determination unit 13 that determines an impact level for the entire area for each area based on the impact level set for the posted information classified into that area; a judgment unit 14 that determines whether or not the area is dangerous for each area based on the impact level for the entire area; and a generation unit 15 that generates a hazard map for areas that the judgment unit 14 judges to be dangerous by superimposing the impact level for the entire area on map information.

Description

[Technical field]

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

[0002] Hazard maps exist that display the predicted damage situation on a map in the event of a disaster such as an earthquake, a tsunami caused by an earthquake, heavy rain, a volcanic eruption, etc. Hazard maps are used to provide residents with various information about disasters in an easy-to-understand format so that they can reduce damage caused by disasters, to help them recognize the disaster risk in their area, and to minimize damage when a disaster actually occurs.

[0003] Hazard maps are generally created based on damage information from past disasters. Therefore, when a disaster actually occurs, the damage situation may not be the same as the disaster risk displayed on the hazard map, and hazard maps are not necessarily used to their full potential. Therefore, related technology for creating hazard maps that display real-time damage situations when a disaster occurs is being considered (for example, Patent Document 1).

[0004] Patent Document 1 discloses a real-time dynamic flood simulation system that, in the event of a flood or other water damage, uses current river information to perform real-time flood analysis and river channel water level predictions, and dynamically displays the calculated information.

[0005] Incidentally, in recent years, SNS (Social Networking Services) such as Twitter (registered trademark) and Facebook (registered trademark) have become widespread around the world. SNS is a service that enables users to easily post about events occurring in their surroundings, and a huge amount of information can be collected by collecting SNS information. Therefore, it is expected that various services will be provided using SNS information. For example, as shown in Patent Document 2, it is being considered to use SNS information to deliver disaster-related information in real time when a disaster occurs.

[0006] Patent document 2 discloses a method for collecting SNS information, analyzing the collected SNS information, and outputting real-time information on items such as the age group and gender of the sender of the SNS information, the evacuation status of people in the vicinity, the damage status, and the type of disaster. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2004-197554 A [Patent Document 2] JP 2014-164381 A Summary of the Invention [Problem to be solved by the invention]

[0008] As described above, SNS is a service that allows users to easily post about events that occur nearby, and it is possible to provide various services using SNS information. Therefore, the inventor considered creating a hazard map that can be used by many users by using SNS information.

[0009] Here, Patent Document 1 does not disclose the creation of a hazard map using SNS information. Patent Document 2 discloses a technology for acquiring and analyzing SNS information when a disaster occurs, and distributing disaster-related information. However, in order to apply this to a hazard map, it is necessary to analyze the acquired SNS information and output quantified disaster information. Patent Document 2 does not disclose the use of SNS information to output quantified disaster information. Therefore, even if the technology disclosed in Patent Document 2 is used, it is not possible to create a hazard map using SNS information.

[0010] The object of the present disclosure has been made to solve such problems, and is to provide an information processing device, a hazard map generating method, and a program capable of creating a hazard map using SNS information. [Means for solving the problem]

[0011] The information processing device of the first aspect includes an acquisition unit that, when a disaster occurs, acquires posting information related to the disaster posted by a plurality of users, the posting information including location information and any of a plurality of pre-registered keywords including information indicating danger and information indicating safety; a processing unit that sets an impact level of the disaster indicated by the posting information for each of the acquired posting information based on the keywords included in the acquired posting information, and classifies each of the acquired posting information into one of a plurality of predetermined areas based on the location information included in the acquired posting information; a determination unit that determines an impact level of the entire area for each area based on the impact level set for the posting information classified into that area; a determination unit that determines whether the area is dangerous for each area based on the impact level of the entire area; and a generation unit that generates a hazard map for areas determined by the determination unit to be dangerous by superimposing the impact level of the entire area on map information.

[0012] A hazard map generation method according to a second aspect is a hazard map generation method in an information processing device, which, when a disaster occurs, acquires posted information related to the disaster posted by a plurality of users, the posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety, sets an impact level of the disaster indicated by the posted information for each of the acquired posted information based on the keywords included in the acquired posted information, and classifies each of the acquired posted information into one of a plurality of predetermined areas based on the location information included in the acquired posted information, determines an impact level of the entire area for each area based on the impact level set for the posted information classified into that area, determines whether the area is dangerous for each area based on the impact level of the entire area, and, for areas determined to be dangerous, superimposes the impact level of the entire area on map information to generate a hazard map.

[0013] The program of the third aspect is a program that causes a computer to execute the following steps when a disaster occurs: acquiring posted information related to the disaster posted by a plurality of users, the posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety; setting an impact level of the disaster indicated by the posted information for each of the acquired posted information based on the keywords included in the acquired posted information, and classifying each of the acquired posted information into one of a plurality of predetermined areas based on the location information included in the acquired posted information; determining an impact level of the entire area for each area based on the impact level set for the posted information classified into that area; determining whether the area is dangerous for each area based on the impact level of the entire area; and generating a hazard map for areas determined to be dangerous by superimposing the impact level of the entire area on map information. Effect of the Invention

[0014] According to the above-described aspect, it is possible to create a hazard map using SNS information. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram showing an example of a configuration of an information processing device according to an embodiment. [Diagram 2] FIG. 1 is a schematic configuration diagram illustrating a configuration example of an information processing system according to a first embodiment. [Diagram 3] FIG. 11 is a diagram illustrating an example of a disaster information table. [Figure 4] FIG. 11 is a diagram illustrating an example of a location information table. [Diagram 5] FIG. 13 is a diagram illustrating an example of a keyword table. [Figure 6] FIG. 2 is a diagram illustrating a concept of a determination process performed by a determination unit in the first embodiment. [Figure 7] FIG. 2 is a diagram illustrating a concept of a determination process performed by a determination unit in the first embodiment. [Figure 8] FIG. 2 is a diagram illustrating a concept of a determination process performed by a determination unit in the first embodiment. [Figure 9] FIG. 13 is a diagram showing an example of a generated hazard map. [Figure 10] 4 is a flowchart illustrating an example of the operation of the information processing device according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating a concept of a process performed by a processing unit according to the second embodiment. [Figure 12] FIG. 11 is a diagram for explaining a hazard map generated by a generating unit according to the second embodiment. [Figure 13A] 11 is a flowchart illustrating an example of the operation of the information processing device according to the second embodiment. [Figure 13B] 11 is a flowchart illustrating an example of the operation of the information processing device according to the second embodiment. [Figure 14] FIG. 11 is a schematic configuration diagram illustrating a configuration example of an information processing system according to a third embodiment. [Figure 15]FIG. 11 illustrates an example of a time information table. [Figure 16] 13 is a flowchart illustrating an example of the operation of the information processing device according to the third embodiment. [Figure 17] FIG. 13 is a schematic configuration diagram illustrating a configuration example of an information processing device according to another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, an embodiment will be described with reference to the drawings. In the embodiments, the same elements are denoted by the same reference numerals, and duplicated explanations will be omitted. (Outline of the embodiment) First, prior to describing the embodiment, an overview of the embodiment will be described. An information processing device 10 according to the overview of the embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the configuration of an information processing device according to the overview of the embodiment.

[0017] The information processing device 10 may be, for example, an information processing device such as an SNS server, a server that provides a hazard map, or an SNS server that provides a hazard map. Alternatively, the information processing device 10 may be a mobile phone terminal, a smartphone terminal, a tablet terminal, a personal computer device, or the like. The information processing device 10 includes an acquisition unit 11, a processing unit 12, a determination unit 13, a determination unit 14, and a generation unit 15.

[0018] When a disaster occurs, the acquisition unit 11 acquires posted information related to the disaster posted by a plurality of users, the posted information including location information and any one of a plurality of preregistered keywords including information indicating danger and information indicating safety. The posted information may be posted information (SNS information) posted by users on SNS such as Twitter and Facebook.

[0019] The location information may be a specific place name, a building name, or information indicating the name of a city, town, or village. The multiple keywords are information including information indicating danger and information indicating safety. The keywords are pre-registered information and are information regarding whether the posted content is danger information or safety information. The keywords can also be said to be information that serves as a criterion for determining whether the posted content is danger information or safety information. The keywords can also be said to be information that makes it possible to infer whether the place or location indicated by the location information included in the posted information is dangerous or safe due to a disaster. The keywords may be, for example, information such as "danger," "risky," "bad," "stay away," "evacuate," "safe," "okay," "no problem," "nothing happening," and "safe."

[0020] The acquisition unit 11 may acquire disaster-related posted information including location information and keywords directly from multiple users, or may acquire the posted information from an SNS server that collects posted information from multiple users.

[0021] The processing unit 12 sets, for each piece of acquired posted information, a disaster impact level indicated by the posted information based on a keyword included in the acquired posted information. The processing unit 12 also classifies each piece of acquired posted information into one of a plurality of predetermined areas based on location information included in the acquired posted information.

[0022] The processor 12 sets a disaster impact level for each piece of acquired posted information based on the correspondence between preregistered keywords and impact levels. The impact level may be, for example, three levels, high, medium, and low, or ten levels.

[0023] The processing unit 12 classifies each of the acquired posted information into one of a plurality of predetermined areas based on the correspondence between the preregistered location information and area information.

[0024] The predetermined area may be, for example, an area in terms of a city, such as Yokohama City or Kawasaki City, or an area in terms of a ward, town, or village. Alternatively, the predetermined area may be an area divided at predetermined distances based on the disaster location. Alternatively, the predetermined area may be an area divided at predetermined distances based on the location where the most posted information was posted among the posted information acquired by the acquisition unit 11.

[0025] The determination unit 13 determines the influence level of the entire area of ​​the target area based on the influence level set for the posted information classified for each area. The influence level of the entire area may be the average or median of the influence levels set for the classified posted information. Alternatively, the influence level of the entire area may be determined by further classifying the classified posted information into two categories based on a predetermined criterion and using the influence levels of the classified posted information.

[0026] The determination unit 14 determines whether or not each area is dangerous based on the impact level of the entire area for that area. The determination unit 14 may determine that the target area is dangerous when the impact level of the entire area is equal to or greater than a predetermined threshold.

[0027] The generating unit 15 generates a hazard map by superimposing the impact level of the entire area on the map information for the area determined to be dangerous by the determining unit 14. The generating unit 15 may generate a hazard map by setting the impact level of the entire area for the area determined to be dangerous by the determining unit 14 in pre-stored map information. Alternatively, the generating unit 15 may obtain a hazard map from a server that provides the hazard map, and generate a hazard map by superimposing the impact level of the entire area on the obtained hazard map.

[0028] As described above, the information processing device 10 according to the outline of the embodiment acquires posted information related to a disaster, and sets an impact level of the disaster for each piece of acquired posted information. The information processing device 10 determines an impact level for the entire area based on the impact level set for each piece of posted information. This makes it possible to create data for reflecting the acquired posted information in a hazard map.

[0029] Furthermore, the information processing device 10 determines whether an area is dangerous based on the impact level of the entire area, and creates a hazard map in which the impact level of the entire dangerous area is superimposed on map information. Since the hazard map sets the predicted damage situation in the event of a disaster only for dangerous areas, by doing as described above, it becomes possible to provide disaster information only for dangerous areas, similar to general current hazard maps. Therefore, according to the outline of the embodiment, it becomes possible to create a hazard map using SNS information.

[0030] (Embodiment 1) Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Embodiment 1 is an embodiment in which the outline of the embodiments is detailed.

[0031] The information processing system 100 according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a schematic configuration diagram showing a configuration example of the information processing system according to the first embodiment. The information processing system 100 includes a disaster information providing server 20, an SNS server 21, a hazard map providing server 22, an information processing device 40, and a communication terminal 50.

[0032] The disaster information providing server 20 is a server installed in, for example, a government agency such as the Meteorological Agency or a municipality, and provides disaster information when a disaster occurs. The disaster information providing server 20 is connected to an information processing device 40 via the Internet 30. The disaster information providing server 20 may also be connected to an SNS server 21 and a hazard map providing server 22 via the Internet 30.

[0033] When a disaster occurs, the disaster information providing server 20 distributes disaster information including the type of disaster, the location of the disaster, the date and time of the disaster, the scale of the disaster, etc. The disaster information providing server 20 may distribute other information in addition to the above information, or may distribute only a part of the above information.

[0034] The SNS server 21 is a server that collects SNS information such as Twitter and Facebook, and collects posted information from multiple users who subscribe to the SNS. The SNS server 21 is connected to the information processing device 40 via the Internet 30. The posted information may be text data, image data, video data, or audio data, or may be a combination of the above information, such as text data and image data, or text data and video data.

[0035] The SNS server 21 provides the collected posted information to other users who subscribe to the SNS. In other words, users who subscribe to the SNS can view posted information posted by other users. In the following explanation, the SNS server 21 will be explained as a server that provides SNS information via Twitter. Note that on Twitter, posted information is sometimes referred to as "mutterings" or "tweets," so in the following explanation, posted information may be referred to as "mutterings" or "tweets."

[0036] The hazard map providing server 22 is, for example, a server installed in a city, ward, town, or village, and provides a general current hazard map created based on past disaster information. The hazard map providing server 22 is connected to an information processing device 40 via the Internet 30.

[0037] The communication terminal 50 is a communication device capable of receiving a hazard map generated by the information processing device 40 and displaying the received hazard map. The communication terminal 50 may be, for example, a communication device such as a mobile phone terminal, a smartphone terminal, a tablet terminal, a personal computer device, etc. Although only one communication terminal 50 is illustrated in FIG. 2, a configuration including multiple communication terminals may be used.

[0038] The information processing device 40 corresponds to the information processing device 10 in the outline of the embodiment. The information processing device 40 includes an acquisition unit 41, a storage unit 42, a processing unit 43, a determination unit 44, a determination unit 45, a generation unit 46, a distribution unit 47, and a display unit 48.

[0039] The acquisition unit 41 corresponds to the acquisition unit 11 in the outline of the embodiment. The acquisition unit 41 connects to the disaster information providing server 20, the SNS server 21, and the hazard map providing server 22 via the Internet 30. The acquisition unit 41 can also be called a communication unit because it connects to and communicates with other devices. When a disaster occurs, the acquisition unit 41 acquires disaster information from the disaster information providing server 20. Furthermore, the acquisition unit 41 acquires a general current hazard map from the hazard map providing server 22.

[0040] Furthermore, when a disaster occurs, the acquisition unit 41 acquires, from among the posted information posted to the SNS server 21, posted information related to the disaster that has occurred and including location information and keywords. In other words, the acquisition unit 41 collects, via the Internet, only tweets related to the currently occurring disaster from among tweets posted by users who have joined the SNS. The acquisition unit 41 performs natural language processing, such as morphological analysis, on the text data included in the posted information to determine and acquire the posted information that should be acquired.

[0041] The acquisition unit 41 refers to a disaster information table T1 in which information related to the disaster is set, a location information table T2 in which location information is set, and a keyword table T3 in which keywords are set, to determine and acquire posted information that should be acquired.

[0042] An example of the disaster information table T1 will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the disaster information table. The disaster information table T1 is a table for registering an occurred disaster and related disaster information indicating a disaster that may occur simultaneously after the occurred disaster in association with each other. In the disaster information table T1, disaster types and related disaster information are set.

[0043] The disaster type is set to a type of disaster. In the example shown in Fig. 3, "earthquake", "volcanic eruption", "heavy rain", and "fire" are set as the disaster types. The related disaster information is set with information on related disasters that may occur simultaneously after the occurrence of a disaster indicated by the disaster type set in the same row. In the example shown in Fig. 3, for example, when the disaster type is "earthquake", "tsunami", "fire" and "fire" may occur simultaneously after the earthquake, so "tsunami", "fire" and "fire" are set in addition to "earthquake". It should be noted that the disaster types and related disaster information shown in Fig. 3 are merely examples, and other disaster types and related disaster information may be set.

[0044] Next, an example of the location information table T2 will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the location information table. In the location information table T2, location information capable of identifying a position and area information indicating to which area the location information belongs are registered in association with each other.

[0045] The location information is registered with information capable of identifying a location, such as an address, landmark information, and place name. In the example shown in Fig. 4, "Station A", "Station B", "Station C", and "Tower D" are set as the location information. Of course, other information may be registered as the location information.

[0046] The area information is set to indicate which area the location information set in the same row belongs to. In the example shown in FIG. 4, the area information is written as area information for each town, and indicates that "A Station" belongs to the "A Town" area. Of course, the area information may be set to an area that is wider than a town unit, such as a city unit, rather than an area for each town, or an area that is narrower than a town unit. Alternatively, the area information may be set to an area arbitrarily determined by the administrator of the information processing device 40, rather than an area for each town or city.

[0047] Next, an example of the keyword table T3 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the keyword table. The keyword table T3 is a table for registering keywords relating to whether the posted content is danger information or safety information and an impact level estimated by an occurring disaster in association with each other. In the keyword table T3, keywords and impact levels are set.

[0048] The keywords are set with a plurality of pieces of information, which are pre-registered information and include information indicating danger and information indicating safety. The keywords are set with information regarding whether the posted content is danger information or safety information. It can also be said that the keywords are set with information that is a criterion for determining whether the posted content is danger information or safety information. It can also be said that the keywords are set with information that can infer whether the place or position indicated by the location information included in the posted information is dangerous or safe due to a disaster. In the example shown in FIG. 5, the keywords are set with information such as "safe", "no worries", "no worries", "safe", "no worries", "damage", "shaking", "stay away", "danger", "dangerous", "evacuation", "bad", and "emergency".

[0049] The impact level is set as an impact level associated with a keyword, and indicates an estimated degree of danger due to a disaster. In this embodiment, the impact level is expressed in 10 levels, with the higher the number, the higher the impact level due to the disaster. In the example shown in FIG. 5, an impact level of "1" is set for "safe", and an impact level of "2" is set for "no worries". Of course, the keywords and impact levels shown in FIG. 5 are merely examples, and other keywords may be registered, and the impact levels associated with the keywords may be different.

[0050] Here, an example of the posted information acquired by the acquisition unit 41 will be described with reference to Figs. 3 to 5. For example, it is assumed that the posted information includes posted information such as "The building at A station collapsed due to the recent earthquake and is dangerous" and "I am currently in D Tower, but it is safe even though the earthquake occurred 10 minutes ago". The acquisition unit 41 determines that the posted information includes disaster-related posted information because the information "earthquake" is included in the related disaster information of the disaster information table T1. The acquisition unit 41 also determines that the posted information includes location information because the information "A station" and "D Tower" are included in the location information of the location information table T2. Furthermore, the acquisition unit 41 determines that the posted information includes keywords because the information "danger" and "safe" are included in keywords of the keyword table T3. Therefore, the acquisition unit 41 determines that the posted information "The building at A station collapsed due to the recent earthquake and is dangerous" and "I am currently in D Tower, but it is safe even though the earthquake occurred 10 minutes ago" is posted information to be acquired and acquires it.

[0051] If the posted information includes the poster's current location information, called a GEO tag, the acquisition unit 41 may determine that the posted information includes location information, and may treat the location information indicated by the GEO tag as location information. In addition, it is assumed that the same user posts multiple pieces of posted information. In this case, the acquisition unit 41 may acquire one of the multiple pieces of posted information by the same user. This is because if all of the multiple pieces of posted information from the same user are used, it is assumed that the contents indicated by the posted information may be biased. In addition, after a disaster occurs, the acquisition unit 41 may periodically acquire posted information including location information and keywords from among the disaster-related posted information posted by multiple users.

[0052] Next, returning to Fig. 2, the storage unit 42 will be described. The storage unit 42 stores a disaster information table T1, a location information table T2, and a keyword table T3. The storage unit 42 also stores the hazard map acquired by the acquisition unit 41 from the hazard map providing server 22. The storage unit 42 then classifies the posted information acquired by the processing unit 43 from various perspectives, and stores the listed data (posted information).

[0053] Next, the processing unit 43 will be described. The processing unit 43 corresponds to the processing unit 12 in the outline of the embodiment. The processing unit 43 sets, for each piece of acquired posted information, an impact level due to a disaster indicated by the posted information, based on a keyword included in the posted information acquired by the acquisition unit 41. Specifically, the processing unit 43 searches the keyword table T3 for a keyword that matches a keyword included in each piece of acquired posted information, and sets the impact level associated with the searched keyword as the impact level due to a disaster for each piece of acquired posted information.

[0054] For example, if the posted information is "The building at station A collapsed due to the recent earthquake and it is dangerous", referring to the keyword table T3, the impact level corresponding to "danger" is "7", so the impact level 7 is set for the posted information. Also, if the posted information is "I'm in tower D now, but it's safe even though there was an earthquake 10 minutes ago", referring to the keyword table T3, the impact level corresponding to "safe" is "1", so the impact level 1 is set for the posted information. It is assumed that the posted information contains multiple keywords. In this case, the processing unit 43 may set the highest impact level or the lowest impact level among the impact levels corresponding to each of the multiple keywords. Alternatively, the processing unit 43 may set the median or average value of the impact levels corresponding to each of the multiple keywords.

[0055] Furthermore, the processing unit 43 classifies each piece of acquired posted information into one of a plurality of predetermined areas based on the location information included in the acquired posted information. Specifically, the processing unit 43 searches the location information table T2 for location information that matches the location information included in each piece of acquired posted information, and identifies area information associated with the searched location information. The processing unit 43 classifies each piece of acquired posted information into the identified area. In the following description, it is assumed that the predetermined area is an area in units of "town".

[0056] For example, if the posted information is "The building at A Station collapsed due to the recent earthquake and is dangerous," the area information corresponding to "A Station" in the location information table T2 is the "A Town" area, so the processing unit 43 classifies the posted information into the "A Town" area. Note that it is also assumed that the location information included in the acquired posted information is location information indicating an area larger than the area to be classified (in units of "town"), such as "K City." In this case, the processing unit 43 may replace the location information "K City" included in the posted information with "K Station," which is a representative station in "K City." Alternatively, the processing unit 43 may replace the location information "K City" included in the posted information with "K City Hall" where the city hall of "K City" is located, or the address where the K City Hall is located.

[0057] The processing unit 43 classifies and lists the posted information acquired by the acquisition unit 41 according to the type of posted information, such as posted information including images, posted information including videos, and posted information including text. The processing unit 43 also classifies and lists the posted information, such as posted information by date, posted information by time, posted information by area, and posted information by impact level. The processing unit 43 stores the posted information classified as described above in the storage unit 42. In this way, by classifying the posted information in advance from various viewpoints, the processing time required for processing the posted information can be shortened.

[0058] Next, the determination unit 44 will be described. The determination unit 44 corresponds to the determination unit 13 according to the outline of the embodiment. The determination unit 44 determines an influence level for the entire area based on an influence level set for posted information classified into each area.

[0059] Specifically, the determination unit 44 classifies, for each area, posted information into posted information having impact levels of 1 to 5 and posted information having impact levels of 6 to 10, among the impact levels set for the posted information classified into the area. That is, the determination unit 44 classifies posted information into posted information having impact levels of 1 to 5 and posted information having impact levels of 6 to 10, with a classification threshold of 5. Posted information having impact levels of 1 to 5 can be said to be posted information indicating a low degree of impact from a disaster and safety. Posted information having impact levels of 6 to 10 can be said to be posted information indicating a high degree of impact from a disaster and danger. Therefore, the determination unit 44 classifies posted information into posted information indicating safety and posted information indicating danger. In the following description, posted information having impact levels of 1 to 5 may be referred to as "safe tweets", and posted information having impact levels of 6 to 10 may be referred to as "danger tweets". In the following description, the classification threshold is set to 5, but may be a value that can be appropriately changed by the administrator of the information processing device 40.

[0060] Next, the determination unit 44 calculates the average impact level of safety tweets and the average impact level of danger tweets for each area. The determination unit 44 determines the difference between the average impact level of safety tweets and the average impact level of danger tweets as the impact level of the disaster for the entire area. In the following description, the difference between the average impact level of safety tweets and the average impact level of danger tweets may be referred to as the "difference impact level."

[0061] Here, the concept of the determination process performed by the determination unit 44 to determine the influence level of the entire area will be described with reference to Figures 6 to 8. Figures 6 to 8 are diagrams for explaining the concept of the determination process performed by the determination unit in the first embodiment.

[0062] FIG. 6 is a diagram showing the state before the determination unit 44 performs the determination process, and the state after the processing unit 43 sets an impact level for each piece of posted information and classifies it into a plurality of areas. FIG. 6 also shows posted information for a certain area among the plurality of classified areas. Assume that there are 50 pieces of posted information (tweets) classified into a certain area. The circles shown in FIG. 6 are each tweet, and represent a portion of the 50 tweets. The "shadow X (X: an integer of 1 or more)" written inside each circle represents the impact level due to a disaster set for each tweet, and the higher the impact level number, the higher the degree of danger indicated by the posted information.

[0063] Fig. 7 shows a state after the determination unit 44 classifies the tweets into safe tweets and dangerous tweets in the state of Fig. 6. As shown in Fig. 7, of the 50 tweets classified into a certain area, 10 tweets are safe tweets and 40 tweets are dangerous tweets.

[0064] Fig. 8 shows the state where the determination unit 44 has calculated the average value of the impact level of the safety tweets, the average value of the impact level of the danger tweets, and their differential impact level. As shown in Fig. 8, if the average value of the impact level of the safety tweets is 2.8 and the average value of the impact level of the danger tweets is 6.8, the differential impact level is 4. The determination unit 44 determines the differential impact level "4" as the impact level for the entire area.

[0065] In addition, since users who subscribe to SNS can post information based on their subjective opinions, it is possible that they may post information about past events, and furthermore, that they may post information that is different from objective facts. Therefore, the determination unit 44 may determine the influence level of the entire area when the number of posted information items acquired per unit time for each classified area is, for example, 50 or more. In this way, the determination unit 44 can determine the influence level of the entire area based on more objective information.

[0066] Furthermore, the determination unit 44 may determine that an emergency disaster has occurred when the number of pieces of posted information in a certain area is equal to or greater than a predetermined value (e.g., 50 pieces) per unit time (e.g., one minute). In this case, the determination unit 44 may set an impact level for the entire area for this area, and instruct the generation unit 46 to immediately generate a hazard map. In this case, the generation unit 46 may also be instructed to generate a hazard map every five minutes, for example.

[0067] On the other hand, the determination unit 44 may determine that an area does not require urgency when the posted information in the area is less than a predetermined value (e.g., 50 items) per unit time (e.g., 1 minute). In this case, the determination unit 44 may set the impact level of the entire area at the time when the number of tweets collected is equal to or greater than the predetermined value.

[0068] Next, the determination unit 45 will be described. The determination unit 45 corresponds to the determination unit 14 in the outline of the embodiment. For each area, the determination unit 45 determines whether or not the area is dangerous based on the impact level of the entire area. Specifically, the determination unit 45 determines whether or not the area is dangerous when the impact level of the entire area is equal to or greater than the determination threshold. For example, as shown in FIG. 8, it is assumed that the determination unit 44 determines the impact level of the entire area to be 4. Then, when the determination threshold is set to 4, the determination unit 45 determines that the area is dangerous.

[0069] Next, the generating unit 46 will be described. The generating unit 46 corresponds to the generating unit 15 according to the outline of the embodiment. The generating unit 46 generates a hazard map by superimposing the impact level of the entire area for the area determined to be dangerous by the determining unit 45 on map information. Specifically, the generating unit 46 generates a hazard map by superimposing the impact level of the entire area for the area determined to be dangerous by the determining unit 45 on the hazard map acquired by the acquiring unit 41 from the hazard map providing server 22.

[0070] Here, an example of a hazard map generated by the generating unit 46 will be described with reference to FIG. 9. FIG. 9 is a diagram showing an example of a generated hazard map. As shown in FIG. 9, the predetermined areas are the a-town area including the A station, the b-town area including the B station, and the c-town area including the C station and the D tower. Also, the determining unit 44 sets the impact level of the entire a-town area to 5, the impact level of the entire b-town area to 6, and the impact level of the entire c-town area to 4, and the determining unit 45 determines that all areas are dangerous. In this case, as shown in FIG. 9, the generating unit 46 generates a hazard map drawn so that the same image expression is visually obtained for the same impact level so that a user who uses the hazard map can easily grasp visually. The generating unit 46 may generate a hazard map by displaying the differential impact degree as a number in the map information, or may predetermine a color corresponding to the magnitude of the differential impact level and display the differential impact level as a color. Alternatively, the generation unit 46 may generate a hazard map by setting the map information on an XY plane and making the magnitude of the differential influence level correspond to a value in the Z axis direction.

[0071] For example, when the acquisition unit 41 no longer acquires disaster information from the disaster information providing server 20 or when the acquisition unit 41 no longer acquires disaster-related posted information, it may be determined that the disaster in this area has subsided and no urgency is required. In this case, the generation unit 46 may delete information on the impact level of the entire area that is set by superimposing it on the map information. In other words, the generation unit 46 may generate a general current hazard map that is generated by adding information from fixed cameras and local governments.

[0072] 2, the distribution unit 47 will be described. The distribution unit 47 distributes the hazard map generated by the generation unit 46 to the communication terminal 50. The distribution unit 47 communicates with the communication terminal 50, and therefore may also be called a communication unit. The display unit 48 is a display capable of displaying the hazard map generated by the generation unit 46.

[0073] Next, an example of an operation performed by the information processing device 40 will be described with reference to Fig. 10. Fig. 10 is a flowchart illustrating an example of an operation performed by the information processing device according to the first embodiment. The process shown in Fig. 10 is performed when a disaster occurs and periodically after a disaster occurs.

[0074] First, post information related to a disaster, including location information and keywords, is acquired (step S1). Specifically, the acquisition unit 41 extracts, from among a plurality of pieces of posted information, posted information that includes information registered in the related disaster information of the disaster information table T1. Furthermore, the acquisition unit 41 acquires posted information that includes location information registered in the location information of the location information table T2 and keywords registered in the keywords of the keyword table T3.

[0075] Next, an impact level indicating the degree of impact of the disaster that occurred is set for each of the acquired posted information (step S2). Specifically, the processing unit 43 refers to the keyword table T3, acquires an impact level corresponding to a keyword included in each of the acquired posted information from the keyword table T3, and sets an impact level for each of the acquired posted information.

[0076] Next, each of the acquired posted information is classified into one of a plurality of predetermined areas (step S3). Specifically, the processing unit 43 refers to the location information table T2, acquires area information corresponding to the location information included in each of the acquired posted information, and classifies each of the acquired posted information into the area set in the area information.

[0077] Next, the posted information is classified by data type and stored by classified data type (step S4). Specifically, the processing unit 43 classifies and lists the posted information acquired by the acquisition unit 41 according to the type of posted information, such as posted information including images, posted information including videos, and posted information including text. The processing unit 43 also classifies and lists the posted information, such as posted information by date, posted information by time, posted information by area, and posted information by impact level. The processing unit 43 stores the posted information classified as described above in the storage unit 42.

[0078] Next, steps S5 to S7 are executed for each area classified in step S3. In step S5, an impact level due to the disaster for the entire area is set based on the impact level set for the classified posted information (step S5). Specifically, the determination unit 44 compares the impact level set for the classified posted information with the classification threshold, and classifies the posted information into those below the classification threshold and those equal to or above the classification threshold. The determination unit 44 calculates a differential impact level between the average impact level of the posted information below the classification threshold and the average impact level of the posted information equal to or above the classification threshold, and determines it as the impact level for the entire area.

[0079] Next, based on a comparison between the impact level of the entire area and a judgment threshold, it is judged whether the area is a dangerous area or not (step S6). Specifically, when the impact level of the entire area is equal to or greater than the judgment threshold, the judgment unit 45 judges that the area is a dangerous area, and when the impact level is less than the judgment threshold, it judges that the area is not a dangerous area.

[0080] In step S6, if the area is determined to be dangerous (YES in step S6), the impact level of the entire area is set (step S7) on a general current hazard map provided by the hazard map providing server 22. Specifically, if the impact level of the entire area is equal to or greater than the determination threshold (YES in step S6), the generation unit 46 superimposes the impact level of the entire area on the general current hazard map acquired from the hazard map providing server 22 (step S7).

[0081] On the other hand, in step S6, if the impact level of the entire area is less than the determination threshold, that is, if it is determined that the area is not dangerous (NO in step S6), steps S5 to S7 are executed for the next area.

[0082] After executing the above steps S5 to S7 for all areas, the generation unit 46 generates a hazard map (step S8).

[0083] The generated hazard map is distributed and displayed (step S9). The distribution unit 47 distributes the generated hazard map to the communication terminal 50. The display unit 48 displays the generated hazard map.

[0084] As described above, the information processing device 40 according to the first embodiment acquires posted information related to a disaster, and sets an impact level due to the disaster for each acquired posted information. The information processing device 40 determines an impact level for the entire area based on the impact level set for each posted information. The information processing device 40 determines whether the area is dangerous or not based on the impact level for the entire area, and creates a hazard map in which the impact level for the entire dangerous area is superimposed on map information. Therefore, according to the first embodiment, it is possible to create a hazard map using SNS information.

[0085] Furthermore, in this embodiment, it is possible to obtain a general current hazard map from the hazard map providing server 22 and generate a new hazard map by superimposing the impact level of the entire area determined from the SNS information on the general current hazard map. Therefore, it is possible to add more information to the general current hazard map. Therefore, it is possible to provide a hazard map that is more useful than ever before by using the hazard map generated by the information processing device 40 according to this embodiment.

[0086] (Embodiment 2) Next, a description will be given of embodiment 2. Embodiment 2 is an improved example of embodiment 1. In this embodiment, an object is to specify, as a landmark, a position with the most amount of posted information within the area in embodiment 1.

[0087] The information processing system according to the second embodiment is similar to that according to the first embodiment, and therefore a description thereof will be omitted. In addition, a configuration example of the information processing device 40 according to the second embodiment is also basically the same as that of the first embodiment, and therefore only the differences from the first embodiment will be described with reference to FIG. 2. The information processing device 40 according to the second embodiment will be described. The information processing device 40 according to the second embodiment has different configurations of a processing unit 43, a deciding unit 44, and a judging unit 45.

[0088] In addition to the configuration of the processing unit 43 according to the first embodiment, the processing unit 43 identifies a location indicated by place information with the largest number of pieces of posted information within an area from the posted information for each classified area. The location with the largest number of pieces of posted information is generally considered to be a large city within an area. Therefore, in this embodiment, the processing unit 43 identifies the location with the largest number of pieces of posted information, and identifies the location indicated by the identified location as a landmark within the area classified in the first embodiment. For convenience of explanation, the area classified by the processing unit 43 according to the first embodiment will be described as a first area.

[0089] Specifically, the processing unit 43 classifies each piece of posted information acquired by the acquisition unit 41 into a plurality of first areas, and then counts the number of pieces of place information included in the posted information for each first area to identify the location indicated by the location information with the largest number of pieces of posted information. The processing unit 43 also calculates the distance between the location indicated by the location information included in the acquired posted information and the location indicated by the location information with the largest number of pieces of posted information for each first area. Then, the processing unit 43 classifies each piece of acquired posted information into a plurality of second areas divided by a predetermined distance based on the location indicated by the location information with the largest number of pieces of posted information based on the calculated distance. In this embodiment, the predetermined distance is described as 2 km. Of course, the predetermined distance may be, for example, 50 m, or may be another value.

[0090] Here, the concept of the process performed by the processing unit 43 will be described with reference to Fig. 11. Fig. 11 is a diagram showing the concept of the process performed by the processing unit according to the present embodiment. The processing unit 43 classifies the acquired posted information into an A town area and a B town area (first area) in Fig. 11 using location information of the posted information.

[0091] Next, the processing unit 43 identifies the location indicated by the place information with the largest number of pieces of posted information from the posted information classified into the a town area and the b town area. In FIG. 11, it is assumed that, among the posted information in the a town area, the largest number of pieces of posted information has A station as place information, and, among the posted information in the b town area, the largest number of pieces of posted information has B station as place information. Then, the processing unit 43 identifies A station and B station. Then, the processing unit 43 calculates the distance between the location indicated by the place information included in each piece of acquired posted information and A station and B station.

[0092] Next, the processing unit 43 classifies each of the acquired posted information into one of a plurality of areas (second areas) divided at predetermined distances based on the calculated distance. The dotted lines shown in Fig. 11 are lines representing area boundaries at 2 km intervals with Station A as the base. The dashed and dotted lines are lines representing area boundaries at 2 km intervals with Station B as the base. For example, if the position indicated by the location information included in the posted information T is the position shown in Fig. 11 and the distance from Station A is 3 km, the processing unit 43 classifies the posted information T into an area from 2 km to 4 km.

[0093] Returning to FIG. 2, the determination unit 44 will be described. In the first embodiment, the determination unit 44 calculated the impact level of the entire area of ​​the first area for each first area. In the present embodiment, the determination unit 44 determines the impact level of the entire area of ​​the second area for each second area. As the determination unit 44 determines the impact level of the entire area for each second area in the same manner as in the first embodiment, a description thereof will be omitted.

[0094] Next, the determination unit 45 will be described. In the first embodiment, the determination unit 45 determined for each first area whether or not it is a dangerous area based on the impact level of the entire first area. In the present embodiment, the determination unit 45 determines for each second area whether or not it is a dangerous area based on the impact level of the entire second area. The determination unit 45 determines whether or not it is a dangerous area in the same way as in the first embodiment, so a description thereof will be omitted.

[0095] Next, an example of a hazard map generated by the generation unit 46 will be shown with reference to Fig. 12. Fig. 12 is a diagram for explaining the hazard map generated by the generation unit according to the present embodiment. The configuration of the generation unit 46 according to the present embodiment is similar to that of the generation unit 46 according to the first embodiment. However, since the hazard maps generated are different, the hazard map generated by the generation unit 46 will be explained.

[0096] As shown in Fig. 12, the generation unit 46 generates a hazard map by setting an impact level for the entire area for areas determined to be dangerous among multiple areas (second areas) every 2 km based on "A Station," which has the most posted information in the a town area (first area). Similarly, the generation unit 46 generates a hazard map by setting an impact level for the entire area for areas determined to be dangerous among multiple areas (second areas) every 2 km based on "B Station," which has the most posted information in the b town area (first area). Then, the generation unit 46 generates a hazard map by combining both hazard maps as the final hazard map.

[0097] 12, areas hatched with horizontal lines indicate an impact level of 7, and areas hatched with vertical lines indicate an impact level of 6. Areas hatched with dots indicate an impact level of 5. Areas shown with dotted diagonal lines indicate an impact level of 4. Areas that are not hatched indicate areas that the determination unit 45 has determined not to be dangerous areas.

[0098] With Station A as the base, the area from 0 km to 2 km has an impact level of 7. With Station A as the base, the area from 2 km to 4 km has an impact level of 6. With Station A as the base, the area from 4 km to 6 km has an impact level of 5. With Station A as the base, the determination unit 45 has determined that there is no danger from 6 km onwards. Then, as shown in FIG. 12, for each 2 km area that the determination unit 45 has determined to be dangerous, the impact level of the entire area determined by the determination unit 44 is set.

[0099] Similarly, with Station B as the base, the area from 0 km to 2 km has an impact level of 4. With Station b as the base, the area from 2 km to 4 km has an impact level of 5. With Station b as the base, the determination unit 45 has determined that there is no danger from 4 km onwards. Then, as shown in Fig. 12, for each 2 km area that the determination unit 45 has determined to be dangerous, the impact level of the entire area determined by the determination unit 44 is set.

[0100] 12, the impact level of the area from 0 km to 2 km from Station A is higher than the impact level of the area from 0 km to 2 km from Station B. Therefore, users can determine that it is safer to evacuate to Station B than to Station A.

[0101] 12, among the area of ​​2 km to 4 km based on Station A, there is an area that overlaps with the area of ​​2 km to 4 km based on Station B, and the overlapping area is generated so that the hatching overlaps. However, for that area, the average of the influence level of the area of ​​2 km to 4 km based on Station A and the influence level of the area of ​​2 km to 4 km based on Station B may be set as the influence level of the overlapping area.

[0102] Next, an operation example of the information processing device 40 according to the present embodiment will be described with reference to Fig. 13A and Fig. 13B. Fig. 13A and Fig. 13B are flowcharts for explaining an operation example of the information processing device according to the second embodiment. Fig. 13A and Fig. 13B basically correspond to Fig. 10. Therefore, the same reference numbers are used for the processes that perform the same operations as those in the first embodiment, and the explanation will be omitted as appropriate. Fig. 13A and Fig. 13B are performed when a disaster occurs and periodically after a disaster occurs.

[0103] First, steps S1 to S4 shown in Fig. 13A are the same as those in embodiment 1. Since the area in embodiment 1 is the first area, the classified area is described as the first area in step S3. The operation following step S4 is shown in Fig. 13B.

[0104] 13B, steps S11 to S16 are performed for each first area. Note that, as will be described in detail later, steps S14 to S16 are further performed for each second area.

[0105] In step S11, for each first area, the place information with the largest number of pieces of posted information is identified, and the position indicated by the place information is identified (step S11). Specifically, the processing unit 43 classifies the acquired posted information by first area, counts the place information of the posted information for each first area, and identifies the place information with the largest number of pieces of posted information. The processing unit 43 identifies the position indicated by the place information. By performing this process, it becomes possible to determine a landmark within the first area.

[0106] Next, using the location information included in each piece of posted information acquired in step S1 and the location identified in step S11, the distance from the location identified in step S11 is calculated (step S12). Specifically, the processing unit 43 identifies a location from the location information included in each piece of posted information acquired in step S1, and calculates the distance from the location identified in step S11.

[0107] Next, each of the acquired posted information is classified into one of a plurality of second areas every 2 km based on the calculated distance (step S13). Specifically, the processing unit 43 classifies each of the acquired posted information into a corresponding area out of a plurality of areas every 2 km based on the position specified in step S11, using the distance calculated in step S12.

[0108] Next, steps S14 to S16 are performed for each second area. Steps S14 to S16 are processes performed for each second area, but as they are similar to the processes of steps S5 to S7 in the first embodiment, detailed explanations will be omitted. The generation unit 46 generates hazard maps for all second areas (step S8). The distribution unit 47 distributes the generated hazard maps to the communication terminal 50, and the display unit 48 displays the generated hazard maps (step S9).

[0109] As described above, in the present embodiment, the acquired posted information is classified into predetermined areas, and a hazard map in which an impact level is set for each area is generated, basically similar to the first embodiment. Therefore, the information processing device 40 according to the present embodiment can provide the same effects as the first embodiment.

[0110] In the present embodiment, the processing unit 43 specifies, as a landmark, a position indicated by the place information with the most posted information among the areas (first area) in the first embodiment. Then, the processing unit 43 calculates a distance from the specified position from the place information set in each of the acquired posted information, and classifies the area (second area) according to the distance. Here, it is estimated that a large number of people exist in the position indicated by the place information with the most posted information among the first area. A user can check the hazard map generated in the present embodiment and easily determine which landmark among a plurality of landmarks to evacuate to. Therefore, the user can easily determine a safer landmark, and can evacuate with peace of mind. Therefore, according to the present embodiment, it is possible to generate a hazard map that is easier for users to use than the first embodiment.

[0111] (Embodiment 3) Next, a third embodiment will be described. The third embodiment is an improved version of the first and second embodiments. Therefore, the first embodiment will be used to explain the present embodiment, with a focus on differences from the first embodiment. In the first embodiment, the acquisition unit 41 acquires posted information including location information and keywords, but in the present embodiment, the acquisition unit 41 acquires posted information further including time information.

[0112] First, a configuration example of the information processing system 100 and the information processing device 40 according to the third embodiment will be described with reference to Fig. 14. Fig. 14 is a schematic configuration diagram showing a configuration example of the information processing system according to the third embodiment. The information processing system 100 according to the third embodiment differs from the information processing system 100 according to the first embodiment only in the configuration of the information processing device 40. Therefore, a description of the configuration example of the information processing system 100 according to the third embodiment will be omitted.

[0113] Next, a configuration example of the information processing device 40 according to the present embodiment will be described. The configuration example of the information processing device 40 according to the present embodiment is basically the same as that of the first embodiment, so only the difference from the first embodiment will be described. In the information processing device 40 according to the third embodiment, the storage unit 42 in the first embodiment is replaced with a storage unit 49. Also, the information processing device 40 according to the third embodiment has different configurations of the acquisition unit 41, the processing unit 43, and the generation unit 46.

[0114] The acquisition unit 41 acquires posted information including location information, keywords, and time information from among posted information related to a disaster. That is, compared to the first embodiment, the acquisition unit 41 acquires posted information further including time information. Specifically, the acquisition unit 41 refers to the time information table T4 and acquires posted information further including time information registered in the time information table T4.

[0115] Here, the time information table T4 will be described with reference to Fig. 15. The time information table T4 is a table in which time information and estimated time / time information are registered in association with each other.

[0116] As shown in FIG. 15, time information is information that can be used to estimate the date and time indicated by the posted information from the date and time the posted information was posted, such as “now,” “just now,” “just now,” “a little while ago,” “today,” “yesterday,” or “x o’clock.”

[0117] The estimated time / time information is information associated with the time information, and is information for estimating when the posted information indicates information from the time information. In the example shown in FIG. 15, if the time information is "now, now", it can be estimated that the posted information indicates information from 10 minutes ago, so the estimated time / time information is set to "10 minutes before the posted date and time". If the time information is "just now, a little while ago", it can be estimated that the posted information indicates information from one hour ago, so the estimated time / time information is set to "one hour before the posted date and time". If the time information is "today", "12 o'clock (0:00 PM) on the posted date" is registered as the estimated time / time information. If the time information is "yesterday", "12 o'clock (0:00 PM) on the day before the posted date" is set as the estimated time / time information. If the time information is "hh o'clock", the estimated time / time information is set to "hh o'clock on the posted date". It should be noted that the time information and the estimated time / time information shown in FIG. 15 are, of course, examples and are not limited to these. For example, the estimated time / time information may be set in seconds, such as "hh hours, mm minutes, ss seconds on the posting date."

[0118] Returning to Fig. 14, the processing unit 43 will be described. The processing unit 43 estimates the date and time indicated by the acquired posted information by using time information included in the acquired posted information and the posted date and time of the acquired posted information. Furthermore, the processing unit 43 extracts, from the acquired posted information, posted information whose estimated date and time are included within a predetermined time from the present.

[0119] Specifically, the processing unit 43 searches the time information table T4 for time information that matches the time information included in the acquired posted information, and identifies the estimated time / time information associated with the searched time information. The processing unit 43 estimates the date and time indicated by the posted information using the identified estimated time / time information and the posted date and time. Then, the processing unit 43 extracts posted information whose estimated date and time are within a predetermined time, for example, within 3 hours, from the present. Note that the predetermined time is of course not limited to 3 hours, and can be changed as appropriate.

[0120] Next, the generating unit 46 will be described. The generating unit 46 generates a hazard map for each time period (e.g., every three hours) that the processing unit 43 uses to extract specific posted information. That is, the generating unit 46 always generates a hazard map using the latest information.

[0121] Next, a description will be given of the storage unit 49. The storage unit 49 stores a time information table T4 in addition to the configuration of the storage unit 42 in the first embodiment.

[0122] Next, an operation example of the information processing device 40 according to the present embodiment will be described with reference to Fig. 16. Fig. 16 is a flowchart for explaining an operation example of the information processing device according to the third embodiment. Fig. 16 basically corresponds to Fig. 10. Therefore, the same reference numbers are used for the processes that perform the same operations as those in the first embodiment, and the explanation will be omitted as appropriate. Fig. 16 is performed when a disaster occurs and periodically after a disaster occurs.

[0123] First, post information about a disaster including location information, keywords, and time information is acquired (step S21). Specifically, the acquisition unit 41 acquires post information about a disaster including location information, keywords, and time information by referring to the disaster information table T1, the location information table T2, the keyword table T3, and the time information table T4.

[0124] Next, the processing unit 43 estimates the date and time indicated by the posted information, and extracts posted information within a predetermined time from the present (step S22). Specifically, the processing unit 43 refers to the time information table T4, and estimates the date and time indicated by the posted information, using the time information included in the posted information and the posted date and time of the posted information. Then, the processing unit 43 extracts posted information within a predetermined time from the present (for example, within 3 hours).

[0125] Next, steps S2 to S7 are executed. Steps S2 to S7 are the same as the operation example explained in FIG. 10, so the explanation will be omitted.

[0126] After executing steps up to step S7, the generation unit 46 generates a hazard map at predetermined time intervals (e.g., every three hours) (step S23). The distribution unit 47 distributes the generated hazard map to the communication terminal 50, and the display unit 48 displays the generated hazard map (step S9).

[0127] As described above, the present embodiment is basically the same as the first embodiment, and therefore the same effects as the first embodiment can be obtained. In the present embodiment, the acquisition unit 41 acquires posted information further including time information, and the processing unit 43 estimates the date and time indicated by the posted information and extracts posted information within a predetermined time. The generation unit 46 generates a hazard map every predetermined time. Therefore, according to the present embodiment, it is possible to generate a hazard map having real-time characteristics in which the latest information is updated every predetermined time. Therefore, according to the present embodiment, a user can evacuate appropriately using a hazard map reflecting newer information, and therefore it is possible to minimize damage caused by a disaster.

[0128] Although the above description has been given using the first embodiment, it is also possible to apply the present embodiment to the second embodiment. Therefore, according to the present embodiment, it is possible to obtain the same effects as those of the second embodiment.

[0129] (Modification) In the third embodiment, the processing unit 43 estimates the date and time indicated by the acquired posted information, and extracts posted information in which the estimated date and time is within a predetermined time from the present, from among the acquired posted information. However, the present invention is not limited to this, and the processing unit 43 may further classify the acquired posted information into posted information for each predetermined time based on the estimated date and time, for example. In this case, the determination unit 44 determines the impact level of the entire area for each predetermined time, the determination unit 45 determines whether each of the classified areas is a dangerous area for each predetermined time, and the generation unit 46 generates a hazard map for each predetermined time. In this way, the user can view the hazard map for each predetermined time. In other words, the user can check the situation of the area to which the user is going to evacuate in chronological order.

[0130] (Other embodiments) Fig. 17 is a block diagram showing a configuration example of the information processing devices 10 and 40 (hereinafter referred to as information processing devices 10, etc.) described in the above-mentioned embodiments. Referring to Fig. 17, the information processing device 10, etc. includes a network interface 1201, a processor 1202, and a memory 1203. The network interface 1201 is used to communicate with other network node devices constituting the communication system. The network interface 1201 may include, for example, a network interface card (NIC) conforming to the IEEE 802.3 series.

[0131] The processor 1202 reads out and executes software (computer programs) from the memory 1203 to perform the processing of the information processing device 10 and the like described using the flowcharts in the above-mentioned embodiment. The processor 1202 may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). The processor 1202 may include multiple processors.

[0132] The memory 1203 is configured by a combination of volatile memory and non-volatile memory. The memory 1203 may include storage located remotely from the processor 1202. In this case, the processor 1202 may access the memory 1203 via an I / O interface (not shown).

[0133] 17, the memory 1203 is used to store a group of software modules. The processor 1202 reads out and executes the group of software modules from the memory 1203, thereby performing the processing of the information processing device 10 and the like described in the above-mentioned embodiment.

[0134] As described with reference to FIG. 17, each of the processors included in the information processing device 10 or the like executes one or more programs including a group of instructions for causing a computer to execute the algorithm described with reference to the drawings.

[0135] In the above example, the program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives) and magneto-optical recording media (e.g., magneto-optical disks). Further, examples of the non-transitory computer readable media include CD-ROM (Read Only Memory), CD-R, and CD-R / W. Further, examples of the non-transitory computer readable media include semiconductor memory. The semiconductor memory includes, for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (Random Access Memory). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0136] The present disclosure is not limited to the above-described embodiment, and may be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure may be implemented by appropriately combining the respective embodiments.

[0137] Furthermore, some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. (Appendix 1) an acquisition unit that acquires, when a disaster occurs, posted information related to the disaster posted by a plurality of users, the posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety; a processing unit that sets an impact level of the disaster indicated by each of the acquired posted information based on a keyword included in the acquired posted information, and classifies each of the acquired posted information into one of a plurality of predetermined areas based on location information included in the acquired posted information; a determination unit that determines an impact level of an entire area based on the impact level set for each area in the posted information classified into the area; a determination unit that determines, for each area, whether or not the area is dangerous based on an impact level of the entire area; a generating unit that generates a hazard map for an area that the determining unit has determined to be dangerous by superimposing an impact level of the entire area on map information. (Appendix 2) The information processing device described in Appendix 1, wherein the determination unit classifies, for each area, each piece of posted information classified into the area into first posted information whose impact level is less than a first threshold and second posted information whose impact level is equal to or greater than the first threshold, and determines the impact level of the entire area based on the impact level of the first posted information and the impact level of the second posted information. (Appendix 3) The information processing device according to claim 2, wherein the determination unit determines a differential influence level between an average value of the influence level of the first posted information and an average value of the influence level of the second posted information as the influence level of the entire area. (Appendix 4) 4. The information processing device according to any one of claims 1 to 3, wherein the determination unit determines that the area is dangerous when an impact level of the entire area is equal to or higher than a second threshold. (Appendix 5) the area is a first area, the processing unit identifies, for each first area, location information with the largest number of pieces of posted information, calculates a distance between a first location indicated by the identified location information and a second location indicated by location information included in the acquired posted information, and classifies, based on the calculated distance, each piece of acquired posted information into one of a plurality of second areas divided at predetermined distances based on the first location; The determination unit determines an impact level of the entire area for each second area; 5. The information processing device according to claim 1, wherein the determination unit determines, for each of the second areas, whether or not the second area is dangerous. (Appendix 6) The acquisition unit acquires posted information further including time information, the processing unit estimates a date and time indicated by the posted information using time information included in the acquired posted information and a posting date and time of the acquired posted information, and extracts, from the acquired posted information, posted information in which the estimated date and time is included within a predetermined time from the present; The information processing device according to any one of claims 1 to 5, wherein the generation unit generates the hazard map at each predetermined time. (Appendix 7) The information processing device according to any one of claims 1 to 6, further comprising a distribution unit that distributes the generated hazard map information to a communication terminal. (Appendix 8) a management table for managing the keywords and the impact levels in association with each other, The information processing device according to any one of claims 1 to 7, wherein the processing unit uses the management table to set the impact level for each of the acquired posted information. (Appendix 9) 9. The information processing device according to any one of claims 1 to 8, further comprising a display unit that displays the generated hazard map. (Appendix 10) When a disaster occurs, from among posted information related to the disaster posted by a plurality of users, posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety is acquired; setting an impact level of the disaster indicated by each piece of the acquired posted information based on a keyword included in the acquired posted information, and classifying each piece of the acquired posted information into one of a plurality of predetermined areas based on location information included in the acquired posted information; determining an impact level for the entire area based on the impact level set for each area in the posted information classified into the area; For each area, determine whether the area is at risk based on an impact level of the entire area; A hazard map generating method in an information processing device, which generates a hazard map for an area determined to be dangerous by superimposing an impact level of the entire area on map information. (Appendix 11) When a disaster occurs, acquiring posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety from posted information related to the disaster posted by a plurality of users; setting an impact level of the disaster indicated by each of the acquired posted information based on a keyword included in the acquired posted information, and classifying each of the acquired posted information into one of a plurality of predetermined areas based on location information included in the acquired posted information; determining, for each area, an impact level of the entire area based on the impact level set for the posted information classified into the area; determining, for each area, whether the area is at risk based on an overall impact level of the area; and generating a hazard map for an area determined to be dangerous by superimposing the impact level of the entire area on map information. (Appendix 12) The program described in Appendix 11, wherein the step of determining the impact level of the entire area includes classifying, for each area, each piece of posted information classified into the area into first posted information whose impact level is less than a first threshold and second posted information whose impact level is equal to or greater than the first threshold, and determining the impact level of the entire area based on the impact level of the first posted information and the impact level of the second posted information. (Appendix 13) A social networking service (SNS) server that collects information posted by multiple users; An information processing device, The information processing device includes: an acquisition unit that acquires, when a disaster occurs, posted information related to the disaster from the SNS server, the posted information including location information and any one of a plurality of pre-registered keywords including information indicating danger and information indicating safety; a processing unit that sets an impact level of the disaster indicated by each of the acquired posted information based on a keyword included in the acquired posted information, and classifies each of the acquired posted information into one of a plurality of predetermined areas based on location information included in the acquired posted information; a determination unit that determines an impact level of an entire area based on the impact level set for each area in the posted information classified into the area; a determination unit that determines, for each area, whether or not the area is dangerous based on an impact level of the entire area; A generating unit generates a hazard map for an area determined to be dangerous by the determining unit by superimposing an impact level of the entire area on map information. (Appendix 14) The information processing system described in Appendix 13, wherein the determination unit classifies, for each area, each piece of posted information classified into the area into first posted information whose impact level is less than a first threshold and second posted information whose impact level is equal to or greater than the first threshold, and determines the impact level of the entire area based on the impact level of the first posted information and the impact level of the second posted information. [Explanation of symbols]

[0138] 10, 40 Information processing device 11, 41 Acquisition Department 12, 43 Processing section 13, 44 Decision Section 14, 45 Judgment section 15, 46 Generation part 100 Information Processing Systems 20 Disaster information server 21 Social Networking Server 22 Hazard map providing server 30 Internet 42, 49 Storage section 47 Distribution Department 48 Display section 50 Communication terminal

Claims

1. an acquisition unit that acquires posted information related to a disaster posted by a plurality of users, the posted information including location information and pre-registered keywords indicating at least a degree of danger and a degree of safety; and a generation unit that generates a hazard map by superimposing an impact level indicating the degree of risk of the disaster in an area corresponding to location information included in the posted information, the impact level being determined based on the keyword included in the posted information, onto map information.

2. The information processing device according to claim 1 , wherein the generation unit superimposes the effect of the disaster on the map information using an image representation that differs for each of the levels.

3. A computer acquires posted information about a disaster posted by a plurality of users, the posted information including location information and pre-registered keywords indicating at least a degree of danger and a degree of safety; An information processing method executed by a computer, in which the computer generates a hazard map by superimposing an impact level indicating the degree of risk of the disaster in the area corresponding to the location information included in the posted information, which impact level is determined based on the keywords included in the posted information, onto map information.

4. The information processing method according to claim 3 , wherein the computer superimposes the effect of the disaster on the map information using a different image representation for each of the levels.

5. A process of acquiring posted information related to a disaster posted by a plurality of users, the posted information including location information and pre-registered keywords indicating at least a degree of danger and a degree of safety; and generating a hazard map by superimposing an impact level indicating the degree of risk of the disaster in the area corresponding to the location information included in the posted information, the impact level being determined based on the keyword included in the posted information, onto map information.

6. The program according to claim 5 , wherein in the generating process, the effect of the disaster is superimposed on the map information using a different image representation for each of the levels.

Images