Information providing method and information providing system

Abstract

To provide an information provision method capable of accurately and timely identifying the risk of infection by infectious diseases in each region and provide appropriate information to prevent the spread of infectious diseases.SOLUTION: Local infection information is acquired from one or more voice recognition devices. The local infection information includes an infection alert level that is obtained by analyzing voice signals by one or more voice recognition devices and the region associated with the infection alert level. The infection risk value that represents the magnitude of infection risk in each region is calculated based on the acquired local infection information. A piece of regional output information is generated according to the calculated infection risk value. The generated output information is transmitted to the devices corresponding to the region via a network.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present disclosure relates to a technique for providing information on infectious diseases using voice signals obtained by a voice recognition device.

Background Art

[0002] As an information providing system for providing information on conventional infectious diseases, Patent Document 1 is known. In Patent Document 1, the movement history of participants in an infection monitoring system is accumulated, and the approaching locations of the participants in the infection monitoring system are managed from the movement history of the participants in the infection monitoring system in which virus infection has been confirmed and estimated by hospitals and health centers. When another participant in the infection monitoring system approaches the approaching location, a technique is disclosed for notifying the other participant in the infection monitoring system of the approaching location and the date and time when the virus-infected person approached the approaching location.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional configuration, when identifying a virus-infected area, only the facilities where virus infection has been confirmed in medical institutions such as hospitals and the movement history of participants in the infection monitoring system where virus infection has been confirmed in medical institutions are considered. Therefore, there is a need for further improvement in accurately and timely identifying the infection risk for infectious diseases in each region.

[0005] An object of the present disclosure is to provide a technique for accurately and timely identifying the infection risk of infectious diseases in each region and providing appropriate information to prevent the spread of infectious diseases.

Means for Solving the Problems

[0006] An information providing method according to one aspect of the present disclosure is an information providing method in an information providing system that provides information related to infectious diseases. A computer of the information providing system acquires regional infection information from one or more voice recognition devices connected via a network. The regional infection information indicates one or more infection caution levels obtained by analyzing voice signals by the one or more voice recognition devices and one or more regions associated with the one or more infection caution levels. Based on the acquired regional infection information, an infection risk value representing the magnitude of the infection risk for each of the one or more regions is calculated. For each of the one or more regions, output information is generated according to the calculated infection risk value, and for each of the one or more regions, the generated output information is transmitted via the network to a device existing in the region corresponding to the output information.

[0007] A voice recognition device according to another aspect of the present disclosure is a voice recognition device that provides information related to infectious diseases, and includes a microphone that detects ambient sound and outputs a voice signal based on the detection result, a processor that performs voice recognition processing on the voice signal output by the microphone, a speaker, and a memory. The processor extracts first voice data including at least one of a word and a sound related to an infection risk from the result of the voice recognition processing of the voice signal, and an infection caution level specifying unit that specifies an infection caution level from the first voice data. From the result of the voice recognition processing, second voice data corresponding to the sound detected by the microphone in a certain period before and after the time when the sound corresponding to the first voice data was detected by the microphone is extracted, and a region associated with the first voice data is specified from the second voice data, or a region specifying unit that specifies a region associated with the first voice data using movement history data indicating the movement history of the speaker of the first voice data. A region infection information generation unit that generates region infection information associating the specified region and the specified infection caution level and stores it in the memory, and an output information generation unit that generates a voice message according to the infection caution level of the region from the stored region infection information are provided. The speaker outputs the voice message.

[0008] Another information providing method according to still another aspect of the present disclosure is an information providing method in an information providing system including a voice recognition device and a server, and providing information related to infectious diseases. The voice recognition device performs voice recognition on a voice signal based on a voice detected using a microphone, and identifies a person who may be infected with the infectious disease and the possibility of infection of the person with the infectious disease. The voice recognition device transmits first infection information indicating the possibility of infection to a mobile terminal of the person who may be infected. The mobile terminal to which the first infection information has been transmitted transmits association data in which the location information of the mobile terminal and the first infection information are associated to the server. The server uses a plurality of pieces of association data including the association data transmitted from a plurality of mobile terminals including the mobile terminal to generate mapping data in which a specific location on map data is associated with the number of persons who may be infected at the location, and transmits the mapping data to the mobile terminal of the person who may be infected or a mobile terminal of a person other than the person who may be infected. The mobile terminal of the person who may be infected or the mobile terminal of the other person generates a display screen using the mapping data and displays the display screen on a display.

Advantages of the Invention

[0009] According to the present disclosure, it is possible to accurately and timely identify the infection risk of infectious diseases for each region and provide appropriate information to prevent the spread of infectious diseases.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Embodiments for Carrying Out the Invention

[0011] (Background Leading to the Present Disclosure) When an infectious disease such as influenza spreads, patient data showing the number of infected persons for each region is published from medical institutions such as hospitals and health centers. Therefore, by referring to the patient data, users can recognize to some extent the degree of spread of the infectious disease for each region. However, since this patient data often shows the number of patients about one week past the time of publication, there is a problem of lack of timeliness. Therefore, even if measures against infectious diseases are taken after checking the patient data, it is often too late, and the patient data is insufficient for suppressing the spread of infectious diseases.

[0012] Therefore, when an infectious disease is spreading or a sign of spread appears, there is a demand to timely inform the degree of spread of the infectious disease for each region.

[0013] Incidentally, at home, when an infectious disease is spreading or signs of an infectious disease outbreak appear, conversations such as "I heard that influenza is spreading at AA Elementary School." or "It seems that influenza is spreading among the business partners of the company." are assumed to be exchanged. Therefore, by collecting such conversations and analyzing their content, it is possible to accurately and timely identify the infection risk for each region.

[0014] Therefore, in recent years, the present inventor has focused on smart speakers that are becoming increasingly popular. By using this smart speaker, it is possible to collect a large number of the above-mentioned conversations, and it becomes possible to accurately and timely identify the infection risk for each region. Furthermore, it also becomes possible to provide appropriate information to the user based on the identified infection risk.

[0015] In the above-mentioned Patent Document 1, since a smart speaker is not used, the above-mentioned conversations cannot be collected, and the infection risk for each region cannot be accurately and timely obtained.

[0016] Also, in Patent Document 1, only the proximity locations of the participants in the infection monitoring system where virus infection has been confirmed are considered, and the infection risk at the proximity locations is not considered at all. Therefore, in Patent Document 1, it is not possible to provide appropriate information to the user according to the infection risk, and problems such as causing the user to take excessive infectious disease countermeasures or the user's infectious disease countermeasures becoming insufficient occur.

[0017] On the other hand, due to the significant spread of mobile terminals such as smartphones and tablet terminals, it has become easier to identify the location information of users who possess mobile terminals. Therefore, by tracking the location information of a large number of potential infected persons who may be infected with an infectious disease from the conversation content, it is possible to accurately and timely identify where and to what extent potential infected persons exist.

[0018] If information mapping the number of potential infected persons at each location is presented to the user, it is possible to provide the user with decision-making materials such as whether to go to a specific location or pass through a specific location, and what infection prevention measures should be taken when going to or passing through a specific location.

[0019] In the above-mentioned Patent Document 1, since a smart speaker is not used, the above-mentioned utterances cannot be collected, and it is impossible to accurately and timely obtain the number of potential infected persons and their locations.

[0020] Also, in Patent Document 1, whether an infection monitoring system participant has been infected with an infectious disease is determined by the judgment result of a medical institution. Therefore, the location information of an infection monitoring system participant who has not received medical treatment but is aware of the infection is not tracked. As a result, Patent Document 1 cannot accurately and timely identify the degree of infection risk at each location. This leads to problems such as causing users to take excessive infection prevention measures or insufficient infection prevention measures for users.

[0021] The present disclosure has been made to solve the above problems, which is to accurately and timely identify the infection risk of infectious diseases in each region and provide appropriate information to prevent the spread of infectious diseases.

[0022] One aspect of the present disclosure is an information providing method in an information providing system that provides information regarding infectious diseases. In this method, a computer of the information providing system acquires regional infection information from one or more voice recognition devices connected via a network. The regional infection information indicates one or more infection alert levels obtained by analyzing voice signals by the one or more voice recognition devices, and one or more regions associated with the one or more infection alert levels. Based on the acquired regional infection information, an infection risk value representing the magnitude of the infection risk for each of the one or more regions is calculated. For each of the one or more regions, output information is generated according to the calculated infection risk value, and the generated output information for each of the one or more regions is transmitted via the network to a device existing in the region corresponding to the output information.

[0023] According to this configuration, regional infection information including one or more infection alert levels obtained by analyzing voice signals by the one or more voice recognition devices and regions associated with the one or more infection alert levels is acquired from one or more voice recognition devices connected via a network.

[0024] Then, an infection risk value representing the magnitude of the infection risk for each region is calculated based on the acquired regional infection information. Therefore, this configuration can collect a large number of regional infection information generated based on, for example, conversations held at home by users, and accurately and timely identify the infection risk value for each region.

[0025] Also, in this configuration, output information for each region is generated according to the infection risk value and transmitted to a device in the region corresponding to the output information. Therefore, appropriate information can be provided to the user according to the infection risk value, and a situation where the user is made to take excessive infectious disease countermeasures or the user's infectious disease countermeasures become insufficient can be avoided.

[0026] In the above aspect, the infection risk value may be calculated by calculating the number of reports for each of the one or more infection attention levels in each of the one or more regions, performing weighting according to the one or more infection attention levels on the calculated number of reports, and evaluating the weighted number of reports.

[0027] According to this configuration, the number of reported cases of infectious diseases for each infection attention level in each region is calculated from the regional infection information, the calculated number of reported cases is weighted according to the infection attention level, and the weighted number of reported cases is evaluated to calculate the infection risk value for each region. Therefore, this configuration can accurately calculate the infection attention level for each region.

[0028] In the above aspect, the one or more infection attention levels may be estimated using the voice recognition content obtained by the one or more voice recognition devices analyzing the voice signal.

[0029] For example, a statement such as "The next class has been closed due to influenza." can be estimated to have more infected people and thus a higher infection risk compared to a statement such as "AA is absent from school due to influenza.", and the infection risk can be classified into levels. According to this configuration, the infection attention level included in the regional infection information can be classified from such statement content.

[0030] In the above aspect, the number of users in each of the one or more regions and the assumed staying time of the users in each of the one or more regions are further obtained, and the infection risk value for each of the one or more regions is calculated using a first correction coefficient for the region corresponding to the infection risk value, where the first correction coefficient is a coefficient that increases the infection risk value for the corresponding region as at least one of the number of users in the corresponding region and the assumed staying time of the users in the corresponding region increases.

[0031] According to this configuration, it is possible to calculate a higher infection risk value for regions with a larger number of users and regions with a longer assumed staying time of users, and obtain a more accurate infection risk value.

[0032] In the above aspect, information including the regional infection word indicating the prevalence of the infectious disease in the one or more regions and the usage frequency of the regional infection word is further obtained from the social network service server, and each of the infection risk values of the one or more regions may be calculated using a second correction coefficient that increases the infection risk value of the corresponding region as the usage frequency of the regional infection word in the region corresponding to the infection risk value increases.

[0033] According to this configuration, when it becomes a topic on the social network that an infectious disease is occurring in a certain region, the topic can be reflected in the infection risk value.

[0034] In the above aspect, patient number data indicating the number of patients with the infectious disease in each of the one or more regions is further obtained, and each of the infection risk values of the one or more regions may be calculated using a third correction coefficient that increases the infection risk value of the corresponding region as the number of patients in the region corresponding to the infection risk value increases.

[0035] According to this configuration, the infection risk value can be calculated in consideration of the number of patients with the infectious disease in a certain region.

[0036] In the above aspect, measurement values are further obtained from virus sensors installed in each of the one or more regions, and each of the infection risk values of the one or more regions may be increased as the measurement value of the virus sensor installed in the region corresponding to the infection risk value increases.

[0037] According to this configuration, the infection risk value can be calculated in consideration of the magnitude of the measurement value of the virus sensor installed in a certain region.

[0038] In the above aspect, the device may be an audio output device, and the output information may be a first control command for causing the audio output device to output an audio message notifying an infection risk corresponding to the infection risk value.

[0039] According to this configuration, since an audio message corresponding to the infection risk value is output from the audio output device, it is possible to prompt the user to take necessary measures to prevent infection with an infectious disease, and the spread of the infectious disease can be suppressed.

[0040] In the above aspect, the device may be an air purifier, and the output information may be a second control command for operating the air purifier.

[0041] According to this configuration, for example, by transmitting a control command for removing a virus to an air purifier installed in an area with a high infection risk value, the spread of an infectious disease can be suppressed.

[0042] An audio recognition device according to one aspect of the present disclosure is an audio recognition device that provides information related to infectious diseases, and includes a microphone that detects ambient sound and outputs an audio signal based on the detection result, a processor that performs audio recognition processing on the audio signal output by the microphone, a speaker, and a memory. The processor extracts first audio data including at least one of a word and a sound related to an infection risk from the result of the audio recognition processing of the audio signal, an infection attention level specifying unit that specifies an infection attention level from the first audio data, and from the result of the audio recognition processing, second audio data corresponding to the sound detected by the microphone in a certain period before and after the time when the sound corresponding to the first audio data was detected by the microphone is extracted, and the area related to the first audio data is specified from the second audio data, or the area related to the first audio data is specified using movement history data indicating the movement history of the speaker of the first audio data. A region infection information generation unit that generates region infection information associating the specified region with the specified infection attention level and stores it in the memory, and an output information generation unit that generates an audio message according to the infection attention level of the region from the stored region infection information are provided, and the speaker outputs the audio message.

[0043] According to this configuration, first audio data including at least one of a word and a sound related to an infection risk is extracted from the audio signal detected by the microphone, and the infection attention level is specified. Also, second audio data corresponding to the sound detected by the microphone in a certain period before and after the time when the sound corresponding to the first audio data was detected by the microphone is extracted, and the area related to the first audio data, or the area related to the first audio data is specified using the movement history data of the speaker of the first audio data. Then, the specified infection attention level and the specified region are associated to generate region infection information, which is stored in the memory. An audio message corresponding to the infection attention level is generated from the stored region infection information and output from the speaker.

[0044] Therefore, this configuration can collect regional infection information generated based on the speech of the user, for example, the speech exchanged at home, and accurately and timely generate an audio message suitable for the infection attention level of each region and output it from the speaker.

[0045] Therefore, this configuration can provide appropriate information to the user according to the infection attention level, and avoid situations such as causing the user to take excessive infectious disease prevention measures or the user's infectious disease prevention measures being insufficient. The sounds included in the first audio data correspond to, for example, sounds such as sneezing and coughing by the user.

[0046] In the above aspect, the infection attention level specifying unit may estimate the infectious disease prevalent in the region or the infectious disease that a specific person is infected with from the speech content of the first audio data.

[0047] According to this configuration, in the first audio data, for example, when the speech content includes "Influenza is prevalent in area BB", it is presumed that influenza is prevalent in the corresponding area. Also, according to this configuration, for example, when the speech content includes "Person AA has contracted influenza", it is presumed that a specific person has been infected with influenza.

[0048] In the above aspect, the infection attention level specifying unit may estimate the period during which a specific person has been infected with an infectious disease from the speech content of the second audio data, and correct the infection attention level using the estimation result.

[0049] For example, when a person is infected with influenza, if one week has passed since the infection, it is expected that the person has recovered from influenza. In this configuration, the period during which the person has been infected with the infectious disease is estimated from the speech content of the second audio data, and the infection attention level is corrected based on the estimation result, so the infection attention level can be accurately specified.

[0050] In the above aspect, when there is insufficient information for generating the regional infection information, the regional infection information generation unit may output a question message from the speaker, acquire an answer voice signal of the question message using the microphone, and generate the regional infection information using the answer voice signal.

[0051] According to this configuration, when there is insufficient information for generating the regional infection information, a question message is output from the speaker, and the regional infection information is generated using the user's answer voice signal for the question message. Therefore, a situation where the regional infection information cannot be generated can be avoided as much as possible.

[0052] In the above aspect, the regional infection information is information associating one or more regions including the region with one or more infection caution levels including the infection caution level, and the processor classifies the regional infection information stored in the memory for each of the one or more regions and the one or more infection caution levels, thereby calculating the number of reported cases of the infectious disease for each of the one or more infection caution levels in each of the one or more regions, a reported case number calculation unit; and a risk of infection value calculation unit that calculates a risk of infection value for each of the one or more regions by performing weighting according to the one or more infection caution levels on the calculated number of reported cases and evaluating the weighted number of reported cases. The output information generation unit may further include a communication unit that generates output information for each of the one or more regions according to the calculated risk of infection value and transmits the generated output information for each of the one or more regions to a device existing in the region corresponding to the output information via a network.

[0053] According to this configuration, the number of reported cases of the infectious disease for each infection caution level in each region is calculated from the acquired regional infection information, the calculated number of reported cases is weighted according to the infection caution level, and the weighted number of reported cases is evaluated to calculate the risk of infection value for each region. Therefore, this configuration can accurately and timely identify the risk of infection value for each region.

[0054] In the above aspect, a social information acquisition unit is further provided that uses the communication unit to acquire information including the regional infection word indicating the prevalence of infectious diseases in each of the one or more regions and the usage frequency of the regional infection word from a social network service server, and the infection risk value calculation unit may calculate the infection risk value for each of the one or more regions using a correction coefficient that increases the infection risk value as the usage frequency of the regional infection word increases.

[0055] According to this configuration, when an infectious disease is a topic in a region on a social network, the topic can be reflected in the infection risk value.

[0056] In the above aspect, the memory may store regional infection information generated by other voice recognition devices.

[0057] According to this configuration, more accurate infection risk values can be calculated in cooperation with other voice recognition devices.

[0058] In the above aspect, the device is another voice recognition device connected to the voice recognition device via a network, and the output information generation unit may generate a first control command for causing the other voice recognition device to output a voice message corresponding to the infection risk value, and transmit it to the other voice recognition device.

[0059] According to this configuration, since a voice message corresponding to the infection risk value is output from another voice recognition device in a region where an infectious disease is prevalent, it is possible to prompt the user to take measures necessary to prevent infection with the infectious disease and suppress the spread of the infectious disease.

[0060] In the above aspect, the device is an air purifier, and the output information generation unit may generate a second control command for operating the air purifier and transmit it to the air purifier.

[0061] According to this configuration, for example, by transmitting a control command to remove the virus to an air purifier installed in an area with a high infection risk value, the spread of infectious diseases can be suppressed.

[0062] An information providing method according to an aspect of the present disclosure is an information providing method in an information providing system including a voice recognition device and a server, and providing information related to an infectious disease. The voice recognition device performs voice recognition on a voice signal based on a voice detected using a microphone, and identifies an infection possibility person who may be infected with the infectious disease and the infection possibility of the infection possibility person with respect to the infectious disease. The voice recognition device transmits first infection information indicating the infection possibility to a mobile terminal of the infection possibility person. The mobile terminal to which the first infection information has been transmitted transmits association data in which the location information of the mobile terminal and the first infection information are associated with each other to the server. The server uses a plurality of association data including the association data transmitted from a plurality of mobile terminals including the mobile terminal to generate mapping data in which a specific location on map data and the number of infection possibility persons at the location are associated with each other, and transmits the mapping data to the mobile terminal of the infection possibility person or a mobile terminal of a person different from the infection possibility person. The mobile terminal of the infection possibility person or the mobile terminal of the other person generates a display screen using the mapping data and displays the display screen on a display.

[0063] According to this configuration, the voice recognition device identifies the person at risk of infection and the risk of infection with an infectious disease for the person at risk of infection, and transmits first infection information including the risk of infection to the mobile terminal of the person at risk of infection. Further, the mobile terminal that has received the first infection information transmits association data in which its own location information is associated with the infection information to the server. Therefore, the server can acquire the location information of the person at risk of infection from the mobile terminal of the person at risk of infection, and can accurately and timely identify where and to what extent there are persons at risk of infection, that is, the infection risk for each region. Then, mapping data in which the location thus identified is associated with the number of persons at risk of infection is transmitted to the mobile terminal, and a display screen using the mapping data is displayed on the mobile terminal. Therefore, the user of the mobile terminal can recognize, for example, how many persons at risk of infection exist in the place where the user is about to go, and can take appropriate infectious disease countermeasures.

[0064] In the above aspect, the voice recognition device may estimate the infectious disease from which the person at risk of infection is infected from the speech content of the voice signal.

[0065] According to this configuration, for example, when the speech content includes "Influenza is prevalent", it is presumed that influenza is prevalent in the corresponding region.

[0066] In the above aspect, the server may calculate the infection risk at the location using the number of persons at risk of infection, and the mapping data may include the infection risk and advice information on infection prevention measures according to the infection risk.

[0067] According to this configuration, since the infection risk at a specific location and advice information on infection prevention measures according to the infection risk are displayed on the mobile terminal, the user can take thorough infectious disease countermeasures and go to the specific location.

[0068] In the above aspect, the mapping data may include measurement data of a sensor installed at the location and measuring environmental information of the location.

[0069] According to this configuration, information such as the presence or absence of a virus, humidity, and temperature at a specific location is displayed on the mobile terminal, so that it is possible to provide the user with materials for making decisions on infectious disease countermeasures and materials for determining whether or not to go to a specific location.

[0070] In the above aspect, the information providing system further includes an external server. The voice recognition device identifies a location related to the infectious disease and an infection caution level for the location from the voice signal, and transmits second infection information indicating the location and the infection caution level to the external server. The external server receives a plurality of pieces of second infection information including the second infection information, calculates the number of reports for each infection caution level at each location by classifying the plurality of pieces of second infection information for each location and infection caution level, performs weighting according to each infection caution level on the calculated number of reports, and calculates an infection risk value for each location by evaluating the weighted number of reports. The server acquires the infection risk value for each location from the external server, and the mapping data may include the infection risk value at each location.

[0071] According to this configuration, since the infection risk value at a specific location is displayed on the mobile terminal, it is possible to provide the user with materials for making decisions on infectious disease countermeasures and materials for determining whether or not to go to a specific location.

[0072] In the above aspect, the display screen may be a screen in which the number of possible infected persons at the location is superimposed on a map image.

[0073] According to this configuration, since the number of possible infected persons at a specific location is displayed on the map image, the user can easily recognize whether an infectious disease is prevalent at a specific location.

[0074] In the above aspect, the server may transmit the mapping data in response to a request from the mobile terminal.

[0075] According to this configuration, for example, when a user requests a server to search for a travel route in order to go out from a certain place now, it is possible to notify, together with the search results, the degree of presence of potentially infectious persons around the travel route, and present decision-making materials regarding infectious disease countermeasures to the user.

[0076] A mobile terminal according to still another aspect of the present disclosure is a mobile terminal in an information providing system that provides information regarding infectious diseases, including a communication unit that receives, from a server, mapping data associating a specific location on map data with the number of potentially infectious persons at each location, the infection risk at each location, and advice information on infection prevention measures according to the infection risk, and a control unit that generates a display screen for associating and displaying the number of potentially infectious persons, the infection risk, and the advice information at each location using the mapping data, and displays the display screen on a display unit.

[0077] A multi-device according to still another aspect of the present disclosure is a multi-device that provides information related to infectious diseases, including a processor that executes word recognition processing on an input signal input to the multi-device, a display unit, and a memory. The processor extracts first word data including a word related to an infection risk from the result of the word recognition processing of the input signal, an infection attention level specifying unit that specifies an infection attention level from the first word data, extracts second word data from the result of the word recognition processing of the input signal in a certain period before and after the time when the input signal corresponding to the first word data was obtained from the result of the word recognition processing of the input signal, and specifies a region related to the first word data from the second word data, or specifies a region related to the first word data using movement history data indicating the movement history of the multi-device, a region infection information generation unit that generates region infection information associating the specified region with the specified infection attention level, and stores the region infection information in the memory, and an output information generation unit that generates a message according to the infection attention level of the region from the stored region infection information. The display unit displays the message.

[0078] The present disclosure can also be realized as a computer program that causes a computer to execute each characteristic step included in such a method, or a server that operates according to this computer program. Needless to say, such a computer program can be distributed via a computer-readable non-transitory recording medium such as a CD-ROM or a communication network such as the Internet.

[0079] It should be noted that each of the embodiments described below shows a specific example of the present disclosure. The numerical values, shapes, components, steps, order of steps, etc. shown in the following embodiments are merely examples and are not intended to limit the present disclosure. In addition, among the components in the following embodiments, components not described in the independent claims indicating the most general concept are described as optional components. Also, in all embodiments, the respective contents can be combined.

[0080] (Embodiment 1) FIG. 1 is a diagram showing an example of the network configuration of an information providing system according to Embodiment 1 of the present disclosure. The information providing system calculates the risk of a user contracting an infectious disease for each region in a service application region including the region where the user to whom the service is applied resides and one or more regions within a certain range from that region, and provides various services for preventing the user from contracting an infectious disease based on the calculation result. Here, the region includes a district and a location. A district corresponds to one partition when the service application region is partitioned into a plurality of partitions based on a predetermined criterion such as a geographical factor, for example, a city, town, and village. A location indicates the location of a facility included in a region such as a commercial facility, a hospital, and a primary school. An infectious disease is a disease caused by a pathogen invading and multiplying in a living body, and examples include colds, influenza, dysentery, malaria, and norovirus.

[0081] The information providing system includes a server 1, a smart speaker 2 (an example of a voice recognition device and equipment), a mobile terminal 3, a virus sensor 4, a patient number DB (database) 5, an SNS word DB 6, a regional information DB 7, an infectious disease trend DB 8, a regional infection information DB 9, a registration information DB 10, a movement information DB 11, a search information DB 12, and an air purifier 13 (an example of equipment).

[0082] The server 1 to the air purifier 13 are communicably connected to each other via a network NT. The network NT includes, for example, an Internet communication network and a mobile phone communication network, etc.

[0083] The server 1 is, for example, a cloud server composed of one or more computers, and calculates the infection risk value of each region using the regional infection information obtained from the smart speaker 2.

[0084] The smart speaker 2 is installed, for example, in the user's home. The smart speaker 2, also called an AI speaker, is a device that collects voices exchanged in the home with a microphone, performs voice recognition on the collected voice signal, and provides various services to the user using the voice recognition result. The smart speaker 2 is an example of a voice recognition device and a voice output device. In the example of FIG. 1, two smart speakers 2_1 and 2_2 are shown, but this is just an example, and the number of smart speakers 2 may be one, or three or more.

[0085] The mobile terminal 3 is a device held by the user of the home where the smart speaker 2 is installed. The mobile terminal 3 is composed of, for example, a portable information processing device such as a smartphone, a tablet terminal, and a button-type mobile phone. In FIG. 1, three mobile terminals 3_1, 3_2, and 3_3 are shown, but this is just an example, and the number of mobile terminals 3 may be one, two, or four or more.

[0086] The virus sensor 4 is composed of, for example, a sensor that detects viruses such as influenza virus and norovirus.

[0087] The patient number DB5 stores patient number data indicating the distribution of the number of patients with infectious diseases for each region. Note that the patient number data is data generated by medical institutions such as hospitals and health centers. For example, when an infectious disease is prevalent, it is data generated to prompt regional residents to take measures against the infectious disease. However, since the number of patients included in the patient number data generally indicates the number of patients after a certain period (e.g., one week) after the prevalence of the infectious disease, the patient number data has the drawback of lacking timeliness. The patient number DB5 is a database constructed on a medical institution server managed by a medical institution and is connected to the network NT via the medical institution server.

[0088] The SNS (Social Network Service) word DB6 is a database that stores the words that have become topics on the SNS in association with the temporal transition of the usage frequency of those words. For example, if influenza is prevalent in the AA region and the usage frequency of "influenza" related to "AA region" on the SNS exceeds a certain value, the SNS word DB6 stores the temporal transition of the usage frequency regarding the regional infection word that associates the location and the infectious disease, such as "AA region - influenza". The SNS word DB6 is, for example, a database constructed on an SNS management server managed by the SNS administrator and is connected to the network NT via the SNS management server.

[0089] The regional information DB7 stores map data, route map data indicating the route maps of public transportation, and congestion status data indicating the congestion status of large facilities in the service applicable region. Large facilities are, for example, community centers, libraries, pools, and commercial facilities, etc. The regional information DB7 is, for example It is a database built on a management server managed by the administrator of this information providing service, and is connected to the network NT via the management server. Note that the map data included in the regional data is stored in the regional information DB7 by the management server importing the map data provided by, for example, the operating company of a search engine on the Internet. Also, the route map data of public transportation included in the regional data is stored in the regional information DB7 by the management server importing the route map data publicly available on the Internet by railway companies, bus companies, etc. Further, the congestion situation data included in the regional data is stored in the regional information DB7 by the management server importing the congestion situation data generated by, for example, the operating company of a search engine on the Internet.

[0090] The infectious disease transition DB8 stores infectious disease transition data showing how infectious diseases have transitioned in the past for each type and region of infectious disease. The infectious disease transition data stores, for example, the number of patients and the date of the epidemic for each type and region of infectious disease when the infectious disease was epidemic in the past. The infectious disease transition DB8 is, for example, a database built on a medical institution server and is connected to the network NT via the medical institution server.

[0091] The regional infection information DB9 is created based on the speech history of the user recognized by the smart speaker 2 and stores regional infection information indicating the infection caution level for each region. The registration information DB10 stores the personal information of the members of the household where the smart speaker 2 is installed. The regional infection information DB9 and the registration information DB10 are stored, for example, in the memory of the smart speaker 2. However, this is just an example, and the regional infection information DB9 and the registration information DB10 may be stored by an external server.

[0092] The movement information DB11 stores the movement information of the user who owns the mobile terminal 3. The movement information is, for example, data in which the position information calculated by the GPS sensor provided in the mobile terminal 3 is associated with the calculation time. The movement information DB11 is stored, for example, in the memory of the mobile terminal 3. However, this is just an example, and the movement information DB11 may be stored in an external server.

[0093] The search information DB12 stores search information indicating the user's search history for the search engine executed on the mobile terminal 3. The search information is, for example, data in which the search word input to the search engine and the search time are associated with each other.

[0094] The air purifier 13 is installed within the service applicable area and operates according to the second control command transmitted from the corresponding smart speaker 2. For example, when an infectious disease is prevalent in the installed area, the air purifier 13 operates according to the second control command from the smart speaker 2 installed in that area, and purifies the surrounding air to prevent the spread of the infectious disease.

[0095] FIG. 2 is a block diagram showing a configuration example of the information providing system shown in FIG. 1. The smart speaker 2 includes a data analysis unit 201, a memory 202, a speaker 203, a control unit 204, a communication unit 205, and a microphone 206. The data analysis unit 201 is composed of a processor that performs speech recognition processing on the speech signal collected by the microphone 206.

[0096] Here, the data analysis unit 201 extracts first voice data including at least one of a word related to the infection risk and the voice signal from the voice signal collected by the microphone 206, and identifies the infection caution level from the first voice data. Then, the data analysis unit 201 extracts second voice data from the voice signals collected by the microphone 206 in a certain period before and after the time when the first voice data was collected by the microphone 206, and identifies the area related to the first voice data from the second voice data. Alternatively, the data analysis unit 201 identifies the area related to the first voice data using the movement information of the speaker of the first voice data. Then, the data analysis unit 201 associates the identified area with the identified infection caution level to generate area infection information.

[0097] The infection caution level is data obtained by analyzing voice signals such as coughs and sneezes included in the first voice data or the speech content indicated by the first voice data, and quantifies the degree of spread of infectious diseases. As the certain period before and after the time when the first voice data was collected, the conversation time of a series of conversations related to infectious diseases exchanged between users is adopted. For example, values such as 10 seconds, 30 seconds, and 1 minute are adopted.

[0098] The memory 202 is composed of, for example, a semiconductor memory, and stores the registration information DB10 and the area infection information DB9. The details of the registration information DB10 and the area infection information DB9 will be described later.

[0099] The speaker 203 outputs a voice message under the control of the control unit 204.

[0100] The control unit 204 is composed of, for example, a CPU, and is in charge of the overall control of the smart speaker 2. The communication unit 205 is composed of a communication device for connecting the smart speaker 2 to the network NT. For example, the communication unit 205 transmits the area infection information generated by the data analysis unit 201 to the server 1. The microphone 206 collects ambient sound and converts it into a voice signal.

[0101] The mobile terminal 3 includes a GPS sensor 301, a memory 302, a control unit 303, a communication unit 304, a display unit 305, and an operation unit 306. The GPS sensor 301 periodically calculates the position of the smartphone.

[0102] The memory 302 is composed of, for example, a semiconductor memory, and stores the search information DB12 and the movement information DB11.

[0103] The control unit 303 is composed of, for example, a CPU, and controls the entire mobile terminal 3. For example, the control unit 303 associates the position calculated by the GPS sensor 301 with the calculation time to generate movement information, and stores it in the movement information DB11. Also, the control unit 303 associates the search word input to the search engine by operating the operation unit 306 with the search time to generate search information, and stores it in the search information DB12.

[0104] The communication unit 304 is composed of a communication device that connects the mobile terminal 3 to the network NT. The display unit 305 is composed of a display device such as a liquid crystal panel, and displays various images under the control of the control unit 303. For example, the display unit 305 displays an image of the search engine.

[0105] The operation unit 306 is composed of, for example, a touch panel, and accepts various operations input by the user. For example, the operation unit 306 accepts an operation of inputting a search word.

[0106] The virus sensor 4 includes a detection unit 401, a memory 402, a control unit 403, and a communication unit 404. The detection unit 401 includes, for example, a light source that irradiates light on a specimen to which at least one of sialic acid and gold nanoparticles is added, a light receiving element that detects the wavelength and reflectance (transmittance) of light that changes depending on the presence or absence of a virus, and a processor that determines the presence or absence of a virus using the detection result of the light receiving element.

[0107] The memory 402 is composed of, for example, a semiconductor memory, and stores the virus detection result of the detection unit 401.

[0108] The control unit 403 is composed of, for example, a CPU and is in charge of the overall control of the virus sensor 4. The communication unit 404 is composed of a communication device that connects the virus sensor 4 to the network NT.

[0109] The air purifier 13 includes a control unit 1301, an ion generation unit 1302, and a communication unit 1303. The control unit 1301 is composed of, for example, a CPU and is in charge of the overall control of the air purifier 13. The ion generation unit 1302 generates ions in the air to inactivate viruses. The communication unit 1303 is composed of a communication device that connects the air purifier 13 to the network NT.

[0110] The database group 14 collectively shows the patient number DB5, the SNS word DB6, the regional information DB7, and the infectious disease trend DB8 shown in FIG. 1, and is constructed on various servers described in FIG. 1.

[0111] FIG. 3 is a block diagram showing a configuration example of the server 1 shown in FIG. 2. The server 1 includes a processor 101, a communication unit 102, and a memory 103. The processor 101 is composed of, for example, a CPU and includes a reported case number calculation unit 111, an infection risk value calculation unit 112, an output information generation unit 113, and a social information acquisition unit 114. The reported case number calculation unit 111 to the social information acquisition unit 114 are realized by the processor 101 executing a control program that causes the computer stored in the memory 103 to function as the server 1.

[0112] The reported case number calculation unit 111 classifies the regional infection information received by the communication unit 102 from the smart speaker 2 for each region and infection attention level, and calculates the reported case number of infectious diseases for each infection attention level in each region.

[0113] The infection risk value calculation unit 112 weights the reported case number calculated by the reported case number calculation unit 111 according to the infection attention level, and calculates the infection risk value of each region by evaluating the weighted reported case number. Here, the infection risk value is an index indicating the magnitude of the infection risk of infectious diseases in each region.

[0114] The output information generation unit 113 generates output information from the infection risk values of each region calculated by the infection risk value calculation unit 112, and transmits it to the devices in the corresponding region using the communication unit 102. As the output information, for example, a first control command for causing the smart speaker 2 installed in a region determined to have a high infection risk value to output a voice message is adopted. The first control command includes the voice message to be output to the smart speaker 2.

[0115] The social information acquisition unit 114 acquires the regional infection words and the temporal transition of the usage frequency of the regional infection words from the SNS word DB6 using the communication unit 102. The memory 103 is composed of, for example, a semiconductor memory and stores the regional infection information aggregation DB50. The details of the regional infection information aggregation DB50 will be described later.

[0116] FIG. 4 is a diagram showing an example of the data configuration of the registration information DB10 stored in the memory 202 of the smart speaker 2. The registration information DB10 includes a basic information table T11 and a registration information table T12.

[0117] The basic information table T11 is a table that stores the installation location and setting contents of the smart speaker 2. Specifically, the basic information table T11 stores "smart speaker ID", "installation location", "notification setting", "notification area setting", and "device control setting". The "smart speaker ID" is an identifier uniquely assigned to the entered smart speaker 2. The "installation location" is the installation location of the smart speaker 2. Here, the address of the house where the smart speaker 2 is installed is adopted. The "notification setting" is setting information indicating whether to cause the smart speaker 2 to output a voice message when receiving the first control command from the server 1. For example, when the notification setting is ON When the smart speaker 2 receives the first control command from the server 1, the smart speaker 2 outputs the voice message included in the first control command. On the other hand, when the notification setting is OFF, even if the smart speaker 2 receives the first control command from the server 1, the smart speaker 2 does not output the voice message included in the first control command.

[0118] The "notification area setting" is information indicating whether to share the regional infection information stored in the regional infection information database 9 with the smart speakers 2 installed in the related areas. When the notification area setting is set to "including related areas", the smart speaker 2 causes the smart speakers 2 installed in the same area or the predetermined related areas to share the regional infection information.

[0119] The "device control setting" is setting information indicating whether to send a second control command for operating the corresponding air purifier 13 to the corresponding air purifier 13 when the smart speaker 2 receives the first control command from the server 1. For example, if the device control setting is "entrust", the smart speaker 2 sends the second control command to the corresponding air purifier 13. On the other hand, if the device control setting is not "entrust", the smart speaker 2 does not send the second control command to the corresponding air purifier 13. Here, the corresponding air purifier 13 refers to the air purifier 13 provided within the area where the smart speaker 2 is installed and pre-associated with the smart speaker 2. For example, if the smart speaker 2 is installed in a certain household, the air purifier 13 installed in that household corresponds to the corresponding air purifier 13.

[0120] The registration information table T12 is a table that stores the personal information of the members of the household where the smart speaker 2 is installed. The registration information table T12 is a table that stores one piece of registration information in one record. The registration information stores the associations of "No", "User", "First Nickname", "Second Nickname", "Third Nickname", "Voiceprint Registration No", "Age", "Gender", "Frequent Place 1", "Frequent Level 1", "Estimated Stay Time 1", "Frequent Place 2", "Frequent Level 2", "Estimated Stay Time 2", "Disease Information", "Related Nickname", and "Relationship".

[0121] "No (Number)" is an identifier for the members of the family. In the "User" column, the names of the members of the family are stored. Here, since the family consists of 4 members, the names of these 4 members are stored in the "User" column. "First Nickname", "Second Nickname", and "Third Nickname" are the nicknames within the family for each member. "First Nickname" to "Third Nickname" indicate the nickname from other members to oneself or the nickname of oneself by oneself within the family. Within the family, there are various variations of nicknames depending on the relationship between the speaker and the person being spoken to, etc. Therefore, here, three nicknames, "First Nickname" to "Third Nickname", are stored in the registration information table T12 to correspond to various variations.

[0122] "Voiceprint Registration No (Number)" indicates the index of the voiceprint data of each member. Since the voiceprint data of each member is pre-stored in the memory 202 in association with the voiceprint registration No, the corresponding member's voiceprint data is read from the memory 202 using the voiceprint registration No as a key. "Age" indicates the age of each member, and "Gender" indicates the gender of each member. "Most Frequently Visited Place 1" indicates the place where each member most frequently goes, such as the workplace or school. "Frequency Level of Most Frequently Visited Place 1" is data obtained by quantifying the frequency with which each member goes to Most Frequently Visited Place 1. Here, the number of visits per week is adopted as the "Frequency Level of Most Frequently Visited Place 1". Specifically, for "Frequency Level of Most Frequently Visited Place 1", if a place is visited 7 days a week, "5" is set; if a place is visited 4 to 6 days a week, "4" is set; if a place is visited 2 to 3 days a week, "3" is set; if a place is visited 1 day a week, "2" is set; and if a place is not visited every week but is visited more than twice a month, "1" is set. This also applies to "Frequency Level of Most Frequently Visited Place 2". The same applies to "Frequency Level of Most Frequently Visited Place 2".

[0123] "Estimated Stay Time 1" indicates the estimated stay time of each member at Most Frequently Visited Place 1. "Most Frequently Visited Place 2" indicates the place where each member frequently goes after Most Frequently Visited Place 1. "Frequency Level of Most Frequently Visited Place 2" and "Estimated Stay Time 2" respectively indicate the frequency level and estimated stay time for Most Frequently Visited Place 2.

[0124] "Disease Information" indicates the diseases that each member suffers from, such as metabolic syndrome (metabo) and atopic dermatitis (atopy). "Related Designation" indicates the designation of each member outside the family (e.g., at the company, school, etc.). "Relationship" indicates the relationship between the person who calls each member by the related designation (such as supervisor and friend) and each member.

[0125] In FIG. 4, "User", "First Designation" to "Third Designation", "Age", "Gender", "Disease Information", "Related Designation", and "Relationship" are, for example, data pre-input by the user using an input device or voice. "Voiceprint Registration No" is data assigned in the voiceprint registration phase. "Places Visited Frequently 1", "Levels of Places Visited Frequently 1", and "Estimated Stay Time 1" may be input by the user using an input device or voice, or may be identified using the movement information stored in the movement information DB11. The same applies to "Places Visited Frequently 2", "Levels of Places Visited Frequently 2", and "Estimated Stay Time 2". Each piece of information registered in the registration information table T12 may also be information automatically registered by the smart speaker 2 by machine learning the acquired voice.

[0126] FIG. 5 is a diagram showing an example of the data configuration of the regional infection information DB9 stored in the memory 202 of the smart speaker 2. The regional infection information DB9 is a database that is created based on the utterances of the members of the household where the smart speaker 2 is installed and stores regional infection information including the infection caution level for each region. The regional infection information DB9 stores one piece of regional infection information in one record. The regional infection information is information generated for each voice recognition result and includes "Time", "Detection", and "Analysis Result".

[0127] "Time" indicates the time recognized by voice, such as 2018 / 1 / 18 / 7:00 (7 o'clock on January 18, 2018). "Detection" indicates the voice recognition result and includes "Content" and "Source". "Content" indicates the content of the voice recognition result (voice recognition content). If the voice recognition content is speech, "Content" is composed of data obtained by texturizing the speech content, for example, "It seems that the person from the business partner I met at the company yesterday has influenza". Also, if the voice recognition content is sounds such as coughs and sneezes, "Content" is composed of data such as "cough sound" and "sneeze sound". "Source" indicates the source of the voice recognition content. Here, in the "Source" column, the identifier of the constituent member and the type of content are stored, such as "No.1 / Speech". The identifier of the constituent member is the identifier of the constituent member stored in the registration information table T12. For example, if it is Taro, it is No.1, and if it is Hanako, it is No.2.

[0128] The type of content indicates the type of voice recognition content. Here, there are "Speech" and "Search". "Speech" indicates that the voice recognition content is the speech of a constituent member or the cough sound or sneeze sound of a constituent member. "Search" indicates that the voice recognition content is a search request to the smart speaker 2 by a constituent member.

[0129] "Analysis result" indicates the analysis result for the voice recognition content and includes "Location", "Region", "Infection attention level", "Presumed infectious disease name", "Epidemic period correction value", "Subject No (number)", "Infection possibility", and "Attached data".

[0130] "Location" indicates the epidemic location of the infectious disease presumed from the voice recognition content. "Region" indicates the region to which the presumed epidemic location belongs. "Infection attention level" is data obtained by quantifying the degree of epidemic of the infectious disease presumed from the voice recognition content. Here, the higher the degree of epidemic of the infectious disease, the larger the numerical value is adopted from 1 to 5.

[0131] For example, if the voice recognition content indicates a large number (e.g., 2 or more) of infected persons, the infection alert level is set to "5". Also, if the voice recognition content can identify that there is at least one infected person although the number of people cannot be specified, the infection alert level is set to "4". Also, if the voice recognition content contains information related to infectious diseases although the disease name cannot be specified, the infection alert level is set to "3". Also, if the voice recognition content indicates the initial symptoms of an infectious disease (e.g., coughing sounds and sneezing sounds), the infection alert level is set to "2". Also, if the voice recognition content indicates an increasing interest in infectious diseases, the infection alert level is set to "1".

[0132] The regional infection information may be created using messages and search words input into multi-devices. The multi-device sets the infection alert level from the input words, identifies the region from the words or location information data input before and after the time when the word corresponding to the set infection alert level is input, and associates the infection alert level with the region.

[0133] The multi-device is, for example, a mobile terminal or a personal computer, and has a message sending function and / or a search function using a search engine.

[0134] "Presumed Infectious Disease Name" indicates the name of an infectious disease presumed from the voice recognition content, such as influenza and cold. "Epidemic Period Correction Value" is a correction coefficient for the infection attention level considering the epidemic period of the infectious disease. For example, if the infectious disease is influenza, it is generally recovered after one week. Therefore, the earlier the epidemic period of the infectious disease presumed from the voice recognition content goes back from the current time, the lower the epidemic period correction value is set within the range of 0 to 1. Here, when the epidemic period of the infectious disease presumed from the voice recognition content is within one week or unknown, the epidemic period correction value is set to "1". Also, if the epidemic period of the infectious disease presumed from the voice recognition content is within two weeks, the epidemic period correction value is set to "0.75". Also, if the epidemic period of the infectious disease presumed from the voice recognition content is within one month, the epidemic period correction value is set to "0.5". Also, if the epidemic period of the infectious disease presumed from the voice recognition content is within one and a half months, the epidemic period correction value is set to "0.25". Also, if the epidemic period of the infectious disease presumed from the voice recognition content is more than one and a half months in the past, the epidemic period correction value is set to "0".

[0135] The final value of the infection attention level is calculated by multiplying the correction value indicated by the epidemic period correction value.

[0136] "Subject No" is an identifier of a member presumed to be infected with an infectious disease from the voice recognition content, and here, the identifier of the member is adopted. "Infection Possibility" indicates the possibility that the member stored in the "Subject No" column, presumed from the voice recognition content, is infected with the infectious disease.

[0137] Here, the infection possibility is such that the higher the likelihood that a member has been infected with an infectious disease, the larger the value is adopted from the numbers 1 to 6. Specifically, when it can be determined that a member is an infected person, the infection possibility is set to "6". Also, when there is a possibility that a member has had close contact with an infected person, the infection possibility is set to "5". Further, if a member's stay time at the location where an infectious disease is prevalent is a long time (for example, 4 hours or more), the infection possibility is set to "4". Also, if a member's stay time at the location where an infectious disease is prevalent is a short time (for example, 3 hours or more and less than 4 hours), the infection possibility is set to "3". Also, although the stay time cannot be specified, when it can be presumed that a member has been to the location where an infectious disease is prevalent or when a member's stay time at the location where an infectious disease is prevalent is less than 3 hours, the infection possibility is set to "2". Also, when the likelihood that a member has been infected with an infectious disease is low, the infection possibility is set to "1".

[0138] In the column of "associated data", movement information indicating the movement route of the member registered in the column of "subject No." is stored. The movement information can be obtained from the movement information DB11 if the corresponding member has the mobile terminal 3. Therefore, here, associated data is registered for "Taro" who has the mobile terminal 3, and no associated data is registered for other members. Note that in the column of "associated data", "movement information / smartphone" indicates that the device from which the movement information was obtained is the mobile terminal 3. Also, the movement information registered in the "associated data" adopts the movement information for a certain period in the past based on the "time" of the voice recognition content. In this way, by storing the movement information, it is possible to identify the areas visited by members with a high infection possibility and reflect it in the calculation of the infection risk value in those areas.

[0139] FIG. 6 is a diagram for explaining the speech recognition process by the data analysis unit 201 of the smart speaker 2. First, the data analysis unit 201 performs speech recognition on the speech signal collected by the microphone 206. Here, as shown in the first row of the regional infection information DB 9, for example, speech recognition content such as "It seems that the person from the business partner I met at the company yesterday has influenza" is obtained. Also, by using the voiceprint data, the speaker of this utterance is identified. In the example of the first row, "Taro" of "No. 1" is identified as the speaker.

[0140] Next, the data analysis unit 201 extracts first audio data including a disease name word (a word related to the infection risk) from the speech recognition content.

[0141] In the example of the first row, "had influenza", which includes the disease name word, is extracted as the first audio data. Next, the data analysis unit 201 identifies the infection caution level from the utterance of the first audio data. In the example of the first row, since it can be estimated from the utterance content of "had influenza", which is the first audio data, that at least one person has been infected with influenza, "4" is set as the infection caution level.

[0142] Next, the data analysis unit 201 extracts second audio data from the audio signals collected by the microphone 206 within a certain period before and after the time when the first audio data was collected. In the example of the first row, "the person from the business partner I met at the company yesterday", which was spoken within a certain period before the first audio data "had influenza", is extracted as the second audio data.

[0143] Next, the data analysis unit 201 identifies the location related to the first audio data from the second audio data. In the example of the first row, in "the person from the business partner I met at the company yesterday", since the location word "company" is included, "company" is extracted.

[0144] Here, the speaker is "Taro", and in the registration information DB10, "AB Shoko", which is Taro's place of work, is stored as "One of the places Taro often goes to". Therefore, "AB Shoko" is specified as the place related to the first voice data from the second voice data. As a result, "AB Shoko" is stored in the "Place" column. Also, since the location of "AB Shoko" belongs to the "BB district", "BB district" is stored in the "District" column. Here, the data analysis unit 201 may specify the "district" to which the "place" belongs by referring to the map data included in the regional information DB7.

[0145] Next, the data analysis unit 201 specifies the date / time word and the person word from the second voice data respectively. In the example of the first line, in the second voice data "The person from the company I met yesterday", the date / time word "yesterday" and the person word "The person from the company I met" are included, so "yesterday" and "The person from the company I met" are specified.

[0146] In the example of the first line, since the recognized time of the voice is 7:00 on January 18, 2018 and the date / time word is "yesterday", "January 17, 2018" is specified as the date / time related to the first voice data. Here, since January 17, 2018 is within one week from the recognized time of the voice, that is, the current time, "×1" is set as the "epidemic period correction value".

[0147] Also, in the example of the first line, for the person word "The person from the company I met", the speaker "Taro" has met with "The person from the company", and there is a possibility of close contact. Therefore, "5" is set as the "infection possibility".

[0148] Also, in the example of the first line, since the speaker is "Taro", "1", which is the identifier of "Taro", is stored in the "Subject No".

[0149] Here, the data analysis unit 201 can read from the memory 202 word lists in which candidate words are pre-stored for each of the date and time word, location word, person word, and disease name word, and by referring to these word lists, identify each of the date and time word, location word, person word, and disease name word from the speech recognition content.

[0150] Referring to FIG. 5, in the example of the 6th line, since a sneezing sound was recognized from the voice signal collected by the microphone 206, the sneezing sound is stored as the speech recognition content. Also, since this sneezing sound is a statement by "Taro", in the "original" column, "No. 1", which is the identifier of Taro, and "statement" are stored. Also, since the sneezing sound was made at home where the smart speaker 2 is installed, "home" is stored in the "location" column, and since "home" belongs to the "CC area", "CC area" is stored in the "area" column. Also, since the sneezing sound is an initial symptom of an infectious disease, "2" is stored in the "infection caution level" column, and since the sneezing sound is made in the case of a cold, "cold" is stored in the "presumed infectious disease name" column. Also, since the sneezing sound is currently being made, "×1" is set for the "epidemic period correction value". Also, since the person who made the sneezing sound is "Taro", "1", which is the identifier of Taro, is stored in the "subject No." column. Also, since the one who made the sneezing sound is Taro himself and Taro is an infected person with a cold, "6" is stored in the "infection possibility" column. Also, since Taro has the mobile terminal 3 and movement information can be obtained, the movement information of Taro is stored in the "associated data" column.

[0151] Note that each time the smart speaker 2 adds new regional infection information to the regional infection information DB 9, it transmits the added regional infection information to the server 1. The transmitted regional infection information has the age and gender of the members indicated by the "subject number" further added to the generated regional infection information. Although the regional infection information includes the identifier of the member in the "subject number", since the server 1 does not have the registration information DB 10, it is impossible to specify personal information such as the name of the member from the "subject number". This prevents the leakage of personal information. Also, the reason for adding the age and gender to the regional infection information is to classify the regional infection information by age and gender in order to construct the third table T53 in FIG. 7.

[0152] FIG. 7 is a diagram showing an example of the data configuration of the regional infection information aggregation DB 50 stored in the memory 103 of the server 1. The regional infection information aggregation DB 50 is a database constructed by aggregating the regional infection information transmitted from the smart speakers 2_1, 2_2, etc., and includes a first table T51, a second table T52, a third table T53, and a fourth table T54.

[0153] Note that each time the analysis conditions shown in FIG. 9 are satisfied and the aggregation process is performed, one table is created for each of the first table T51 to the fourth table T54. FIG. 7 shows the table created by the aggregation process performed on January 18, 2018.

[0154] The first table T51 is a table constructed by classifying the regional infection information transmitted from the smart speaker 2 by location, and one record is assigned to each location.

[0155] The first table T51 stores the associations of "location", "number of reports by infection attention level", "correction factor based on the number of users" (an example of the first correction factor), "correction factor based on the assumed stay time" (an example of the first correction factor), "attention level based on SNS information" (an example of the second correction factor), "attention level based on patient number data" (an example of the third correction factor), "virus sensor", "infection attention risk value", and "related location".

[0156] The "location" column stores the name of the location included in the regional infection information. The "number of reports by infection attention level" indicates the value obtained by aggregating the number of reports of regional infection information for each infection attention level included in the regional infection information. For example, in the example of the first row, regarding "AB Corporation", 35 pieces of regional infection information with an infection attention level of 5 have been transmitted. Therefore, the number of reports "35" is stored in the column of the infection attention level "5" for "AB Corporation". Similarly, for the columns of the infection attention levels "4", "3", "2", and "1" of "AB Corporation", the number of reports "60", "101", "150", and "321" are stored respectively.

[0157] Also, for each level of the infection attention level, a weighting is set. The weighting is data learned by the infection risk value calculation unit 112 by comparing the infection attention level set in the smart speaker 2 with the actual epidemic results of infectious diseases. Here, for the actual epidemic results of infectious diseases, the infectious disease transition data stored in the infectious disease transition DB8 may be referred to.

[0158] For example, when the set "5" as the infection attention level is overestimated compared to the actual epidemic results of infectious diseases, a value lower than "5" is adopted for the weighting.

[0159] Specifically, a difference is calculated by subtracting the number of patients during the epidemic indicated by the infectious disease transition data from the number of reports of the currently calculated infection attention level "5". If the difference is larger than a predetermined value, it is considered overestimated, and the current weighting value of the infection attention level "5" is decreased by a predetermined adjustment range. On the other hand, if the difference is smaller than the predetermined value, it is considered not overestimated, and the current weighting value is maintained.

[0160] Also, if the difference is greater than or equal to a predetermined value in the negative direction, it is considered to be undervalued. After setting the maximum value to "5", the current weighted value of the infection caution level "5" is increased by a predetermined adjustment width. On the other hand, if the difference is less than the predetermined value in the negative direction, the current weighted value is maintained as it is considered not to be undervalued. In this way, the weighted value is updated each time the aggregation process is performed. Note that the weighted values of other infection caution levels are updated in the same manner.

[0161] In the example of FIG. 7, "3" is adopted as the weighting for the infection caution level "5". Under the same concept, for the infection caution levels "4", "3", "2", and "1", the weightings are set to "1", "0.7", "0.4", and "0.1", respectively. Note that the weightings are calculated and updated periodically.

[0162] The "correction coefficient based on the number of users" is set by the infection risk value calculation unit 112, and the larger the number of users in the corresponding location, the larger the value set. Here, the number of users in the corresponding location is specified by referring to the current congestion status of large facilities in the regional information DB7.

[0163] The "correction coefficient based on the assumed stay time" is set by the infection risk value calculation unit 112, and the longer the assumed stay time of the user in the corresponding location, the larger the value set. Here, the "correction coefficient based on the assumed stay time" adopts a value predetermined for each location.

[0164] The "caution level based on SNS information" is set by the infection risk value calculation unit 112, and the larger the current usage frequency of the regional infection word indicating the corresponding location on SNS, the larger the value set. Here, the usage frequency of the regional infection word is obtained from the SNS word DB6. The "caution level based on patient number data" is set to a larger value as the number of patients in the region including the location increases.

[0165] "Attention level based on patient number data" is set by the infection risk value calculation unit 112, and the larger the patient number data of the corresponding location, the larger the set value. Here, the patient number data of the corresponding location is obtained from the patient number DB5.

[0166] "Virus sensor" indicates the presence / absence and number of installed virus sensors 4 at the corresponding location, and the current measured value of the virus sensor 4. "Infection risk value" is calculated by the infection risk value calculation unit 112 and indicates the degree of prevalence of infectious diseases at the corresponding location.

[0167] Regarding the "infection risk value", assuming the weight of the infection attention level i (=1~5) is αi, the reported number of cases of the infection attention level i at location j is βij, the correction coefficient based on the number of users at location j is aj, the correction coefficient based on the assumed stay time at location j is bj, the attention level based on SNS information at location j is cj, and the attention level based on patient number data at location j is dj, the infection risk value calculation unit 112 calculates the infection risk value of location j according to the following formula (1).

[0168] Infection risk value at location j = aj × bj × cj × dj × Σiαi × βij (1) For example, in the case of AB Corporation, the infection risk value is calculated by aj × bj × cj × dj × (35×3 + 60×1 + 101×0.7 + 150×0.4 + 321×0.1).

[0169] Note that the weighting may be set for each of the "correction coefficient based on the number of users", "correction coefficient based on the assumed stay time", "attention level based on SNS information", and "attention level based on patient number data".

[0170] The weighting of the "correction coefficient based on the number of users" is set by the infection risk value calculation unit 112 and is data learned by comparing the actual prevalence results of infectious diseases with the number of users. The smaller the influence of the number of users on the actual prevalence results of infectious diseases, the smaller the set value of this weighting.

[0171] The weighting of the "correction coefficient based on the assumed stay time" is set by the infection risk value calculation unit 112, and the lower the impact of the assumed stay time on the actual epidemic results of the infectious disease, the smaller the value set. The weighting of the "attention level based on SNS information" is set by the infection risk value calculation unit 112, and the lower the impact of the SNS information on the actual epidemic results of the infectious disease, the smaller the value set. The weighting of the "attention level based on patient number data" is set by the infection risk value calculation unit 112, and the lower the impact of the number of patients on the actual epidemic results of the infectious disease, the smaller the value set.

[0172] Assuming that the weightings of the "correction coefficient based on the number of users", "correction coefficient based on the assumed stay time", "attention level based on SNS information", and "attention level based on patient number data" are p1, p2, p3, and p4 respectively, the infection risk value calculation unit 112 calculates the infection risk value using the following formula (2).

[0173] Infection risk value at location j = p1 × aj × p2 × bj × p3 × cj × p4 × dj × Σiαi × βij (2) Also, the number of installed units and measurement values of the virus sensor 4 may be considered for the infection risk value. In this case, the infection risk value calculation unit 112 may reduce the infection risk value obtained by formula (1) or formula (2) as the number of installed units of the virus sensor 4 increases, and increase the infection risk value obtained by formula (1) or formula (2) as the measurement value of the virus sensor 4 increases, so as to calculate the final infection risk value.

[0174] "Related location" indicates a location where users staying at the corresponding location are likely to go. For example, since many employees of "AB Corporation" go to "DD Gym", "DD Gym" is stored as a related location of "AB Corporation".

[0175] In this case, the infection risk value of the corresponding location may be set considering the infection risk values of the related locations. For example, the final infection risk value may be calculated by adding a value obtained by multiplying the infection risk value of the related location by a predetermined coefficient to the infection risk value of the corresponding location.

[0176] The second table T52 is a table constructed by classifying the regional infection information transmitted from the smart speaker 2 for each district. Since the second table T52 is the same as the first table T51 except that the regional infection information is classified for each district instead of each location, detailed description is omitted. However, the second table T52 has a "correction coefficient based on the number of stayers" instead of the "correction coefficient by the user". The "correction coefficient based on the number of stayers" indicates a correction coefficient corresponding to the people staying in the district. Also, the second table T52 has a "related district" instead of the "related location".

[0177] The third table T53 is a table constructed by classifying the regional infection information transmitted from the smart speaker 2 for each age group and gender, and one record is assigned to one age group and gender. Here, the age group and gender are adopted with age divided into 10-year intervals for each gender such as "male under 10 years old" and "female under 10 years old" as one category.

[0178] Similar to the first table T51, the third table T53 has "the number of reports by infection alert level", "alert level based on SNS information", and "alert level based on patient number data", and in addition, it has a "correction coefficient based on the overall ratio" and a "correction coefficient based on immunity" instead of the "correction coefficient based on the number of users" and the "correction coefficient based on the assumed stay time". The "correction coefficient based on the overall ratio" indicates the ratio of each age group to the total number of individuals aggregated from the regional infection information transmitted from the smart speaker 2. The "correction coefficient based on assumed immunity" is set to a smaller value for age groups with higher immunity.

[0179] The fourth table T54 is a table constructed by classifying the regional infection information transmitted from the smart speaker 2 for each location and infectious disease, and one record is assigned to one location. For example, in the case of AB Corporation in the first row, the number of reports by infectious disease according to the regional infection information is stored.

[0180] FIG. 8 is a flowchart showing an example of the processing of the information providing system according to Embodiment 1 of the present disclosure. In S101, the microphone 206 of the smart speaker 2 collects ambient sound and acquires an audio signal. In S102, the data analysis unit 201 of the smart speaker 2 analyzes the audio signal and generates regional infection information. Here, by performing speech recognition processing on the audio signal, speech recognition content such as "It seems that the person from the business partner I met at the company yesterday has influenza" is acquired. Also, here, by using voiceprint data, the speaker of this speech recognition content is identified. Further, from this speech recognition content, disease name words, location words, date and time words, and person words are extracted. Then, based on the extraction results of these words, data is stored in each column shown in the regional infection information DB9, and new regional infection information is added to the regional infection information DB9 (S103).

[0181] In S104, the communication unit 205 of the smart speaker 2 transmits the regional infection information with the data of "age" and "gender" added to the server 1.

[0182] In S111, the reported case number calculation unit 111 and the infection risk value calculation unit 112 of the server 1 update the regional infection information aggregation DB50 by using the regional infection information transmitted from the smart speaker 2 and using the database group 14 as necessary.

[0183] In S112, the output information generation unit 113 of the server 1 specifies the areas requiring attention and the age groups requiring attention with reference to the updated regional infection information aggregation DB50.

[0184] In S113, the output information generation unit 113 of the server 1 generates a first control command for causing the smart speaker 2 installed in the area requiring attention to output an audio message for notifying the infection risk, using the specified areas requiring attention and the age groups requiring attention, and transmits it to the corresponding smart speaker 2 using the communication unit 102.

[0185] In S105, the smart speaker 2 that has received the first control command outputs an audio message from the speaker 203 according to the first control command.

[0186] In S106, the smart speaker 2 that has received the first control command transmits a second control command to the corresponding air purifier 13.

[0187] In S121, the air purifier 13 that has received the second control command starts operating according to the second control command and purifies the surrounding air.

[0188] FIG. 9 is a flowchart showing details of the processing between the smart speaker 2 and the server 1 in FIG. 8. Since S201 to S204 are the same as S101 to 104 in FIG. 8, the description thereof is omitted.

[0189] In S301, the processor 101 of the server 1 determines whether or not an analysis start condition is satisfied. Here, the analysis start condition is a condition for starting the analysis of the regional infection information aggregation DB 50. For example, a condition that a certain period has elapsed since the previous analysis or a condition that a certain number of regional infection information has been received since the previous analysis is adopted.

[0190] When the analysis start condition is satisfied (YES in S301), the process proceeds to S302. When the analysis start condition is not satisfied (NO in S301), the process returns to S301.

[0191] In S302, the reported case number calculation unit 111 calculates the reported case number using the regional infection information newly received between the previous analysis and the current analysis.

[0192] Here, the reported case number calculation unit 111 classifies the newly received regional infection information by location and by infection caution level, calculates the reported case number for each infection caution level at each location, and generates the first table T51.

[0193] Referring to FIG. 7, for example, in the newly received regional infection information, there were 35 pieces of regional infection information with an infection alert level of "5" regarding "AB Corporation". Therefore, in the first table T51, the reported number of cases with an infection alert level of "5" for AB Corporation is "35" stored.

[0194] Similarly, the reported number calculation unit 111 classifies the newly received regional infection information by district and by infection alert level, calculates the reported number of cases for each district by infection alert level, and generates the second table T52.

[0195] Furthermore, the reported number calculation unit 111 classifies the newly received regional infection information by age group and gender and by infection alert level, calculates the reported number of cases for each age group and gender by infection alert level, and generates the third table T53.

[0196] Furthermore, the reported number calculation unit 111 classifies the newly received regional infection information by location and by "presumed infectious disease", calculates the reported number of cases of infectious diseases for each location, and generates the fourth table T54.

[0197] In S303, the infection risk value calculation unit 112 calculates the infection risk value for each of the generated first table T51, second table T52, and third table T53. Here, the infection risk value calculation unit 112 uses the above-described formula (1) or formula (2) to calculate the infection risk value for each location shown in the first table T51, the infection risk value for each district shown in the second table T52, and the infection risk value for each age group and gender shown in the third table T53.

[0198] In S304, the output information generation unit 113 determines whether there are regions where the infection risk value is higher than the threshold and age groups and genders. Referring to the first table T51 in FIG. 7, assuming that the threshold for the location is, for example, "300", the infection risk value of "AB Corporation" is "327.8", which is larger than the threshold, so AB Corporation is determined to be a location requiring attention.

[0199] Also, referring to the second table T52 in FIG. 7, if the threshold value for the region is, for example, "400", since the infection risk value of the "BB region" is "518.6", the "BB region" is determined to be a region requiring attention.

[0200] Also, referring to the third table T53 in FIG. 7, if the threshold values for age group and gender are "400" and the infection risk value of males in their teens is 500, then males in their teens are identified as an age group requiring attention.

[0201] In S304, if there is no region where the infection risk value is higher than the threshold value (NO in S304), the process returns to S301. If there is a region where the infection risk value is higher than the threshold value (YES in S304), the process proceeds to S305.

[0202] In S305, the output information generation unit 113 generates a first control command for the smart speaker 2 installed in the region and place requiring attention. Here, for example, the output information generation unit 113 may generate a first control command to output a voice message such as "Influenza is prevalent in the AA region" from the smart speaker 2. Alternatively, considering the age group requiring attention, the output information generation unit 113 may generate, for example, a first control command to output a voice message such as "Influenza is prevalent in the AA region. In particular, it is prevalent among males in their teens." from the smart speaker 2. Alternatively, the output information generation unit 113 may divide the level of the infection risk into, for example, about three levels of high, medium, and low according to the magnitude of the infection risk value, and generate a first control command to output a voice message corresponding to that level from the smart speaker 2. For example, if the level of the infection risk is high, a voice message such as "Avoid going out" is output, if the level of the infection risk is medium, a voice message such as "Wear a mask when going out. Also, gargle and wash your hands when you get home" is output, and if the level of the infection risk is low, a voice message such as "Wash your hands" is output from the smart speaker 2, and a first control command may be generated.

[0203] In S205, when the communication unit 205 of the smart speaker 2 receives the first control command (YES in S205), the process proceeds to S206. When the first control command is not received (NO in S205), the process returns to S201.

[0204] In S206, the control unit 204 of the smart speaker 2 causes the speaker 203 to output an audio message according to the received first control command. Here, as described above, an audio message notifying the user of the prevalence of infectious diseases, an audio message notifying the age group and gender of the prevalence, and an audio message notifying the level of infection risk are output.

[0205] In S207, the control unit 204 of the smart speaker 2 determines whether the device control setting is "automatic". If the device control setting is "automatic" (YES in S207), the control unit 204 of the smart speaker 2 transmits a second control command to the corresponding air cleaner 13 using the communication unit 205 (S208). On the other hand, if the device control setting is not "automatic" (NO in S207), the process returns to 201.

[0206] Figure 10 is a flowchart according to a modified example of Figure 8. In the flowchart of Figure 10, further processing of the mobile terminal 3 is added to the flowchart of Figure 8. In Figure 10, the same step numbers are assigned to the same processes as in Figure 8, and the description is omitted.

[0207] In S131, the control unit 303 of the mobile terminal 3 stores the usage information in the memory 302. Here, the usage information includes movement information and search information. The control unit 303 stores the movement information in the movement information DB11 at regular time intervals, and stores the input information and search information in the search information DB12 each time a message and / or search word is input by the user.

[0208] In S132, the communication unit 304 of the mobile terminal 3 transmits usage information to the smart speaker 2. Here, the control unit 303 of the mobile terminal 3 may include, in the usage information, the movement information of a certain period from the present to the past among the movement information stored in the movement information DB11, and may include, in the usage information, the search information of a certain period from the present to the past among the search information stored in the search information DB12.

[0209] Note that the mobile terminal 3 may periodically transmit the usage information to the smart speaker 2, or may transmit the usage information to the smart speaker 2 in response to a request from the smart speaker 2.

[0210] In S102A following S101, the data analysis unit 201 of the smart speaker 2 generates regional infection information by using the usage information as necessary in addition to the analysis of the voice signal. For example, assume that the time word can be specified from the voice recognition content, but the location word cannot be specified. In this case, if there is movement information of the speaker, the data analysis unit 201 may specify the location where the speaker was at the date and time indicated by the time word by using the movement information.

[0211] In this way, in the flow of FIG. 10, if there is information lacking in the voice recognition content in generating the regional infection information, the information lacking is supplemented by the usage information from the mobile terminal 3, and a situation where the regional infection information is not generated can be avoided as much as possible.

[0212] FIG. 11 is a diagram showing a use case of the information providing system of the present disclosure. In the home 603, Taro has uttered "I got the flu" (S601), and this utterance is voice-recognized by the smart speaker 2_3. The smart speaker 2_3, from the utterance of S601, determines that Taro has been infected with influenza, and specifies "AA Station" and "BB Park", where Taro has been, as attention locations from Taro's movement information (S602). Then, the specified attention locations are notified to the server 1.

[0213] In household 601, Hanako says, "It seems that influenza is spreading in the next class." (S603), and this utterance is recognized by smart speaker 2_1 through voice recognition. From the utterance in S603, smart speaker 2_1 identifies AA Elementary School, where Hanako goes to school, as the place of concern (S604). Then, it transmits regional infection information for notifying the identified place of concern to server 1.

[0214] By analyzing this regional infection information, server 1 determines that an infectious disease is spreading in CC District to which AA Elementary School belongs, and notifies smart speakers 2_1 and 2_2 in CC District of this fact (S605).

[0215] Upon receiving this notification, smart speaker 2_1 outputs a voice message such as "Do you want to set your commuting route to a route that does not pass through CC District?" Also, upon receiving this notification, smart speaker 2_2 outputs a voice message such as "How about making today's dinner a menu for improving immunity?" (S607), or outputs a voice message such as "The attention level for infectious disease prevention has increased in your area. Switch the air purifier to the infection prevention mode." (S608).

[0216] Thus, according to the information providing system of the present disclosure, regional infection information including the infection attention level obtained by the smart speaker 2 analyzing the voice signal and the region associated with the infection attention level is acquired from one or more smart speakers 2 connected via network NT.

[0217] Then, the number of reported cases of infectious diseases for each region's infection attention level is calculated from the acquired regional infection information, the calculated number of reported cases is weighted according to the infection attention level, and the weighted number of reported cases is evaluated to calculate the infection risk value for each region. Therefore, this information providing system can accurately and timely identify the infection risk value for each region by collecting a large number of regional infection information generated based on, for example, utterances exchanged at home by users.

[0218] In addition, in this information providing system, a first control command for causing the smart speaker 2 in each region to output an audio message according to the infection risk value is generated and transmitted to the smart speaker 2 in the corresponding region. Therefore, appropriate information can be provided to the user according to the infection risk value, and situations such as causing the user to take excessive infectious disease countermeasures or the user's infectious disease countermeasures becoming insufficient can be avoided.

[0219] Note that the following modification examples can be adopted in Embodiment 1.

[0220] (1-1) In the above Embodiment 1, the second control command is transmitted from the smart speaker 2 that has received the first control command to the air purifier 13, but the present disclosure is not limited to this. For example, the second control command may be directly transmitted from the server 1 to the air purifier 13. In this case, the server 1 may simply store the regions where each smart speaker 2 is installed in association with the communication addresses.

[0221] (1-2) In the above Embodiment 1, when generating the regional infection information, the data analysis unit 201 of the smart speaker 2 calculates the speech distance between the location word and the disease name word extracted from the speech recognition content. If the speech distance is separated by a certain value or more, a question message for asking the user whether the location specified from the location word is correct may be output from the speaker 203. Then, when the user says it is correct, the data analysis unit 201 may generate regional infection information associating the location specified from the location word with the infection caution level specified from the disease name word, and store it in the regional infection information DB9. Note that as the speech distance, the number of characters from the disease name word to the location word can be adopted in the text data indicating the speech recognition content. This is based on the idea that as the number of characters from the disease name word to the location word increases, the relevance between the two words decreases.

[0222] When generating the regional infection information in (1-3), the data analysis unit 201 of the smart speaker 2 may identify, from the movement information of the members (infected persons) whose infection attention level is equal to or higher than a certain level, which is specified from the voice recognition content, facilities such as stations, commercial facilities, and schools where a large number of people gather on the movement routes of the members, and notify the server 1 of the specified facilities using the communication unit 205. Then, the server 1 may increase the infection risk values of the locations and areas of the notified facilities by a predetermined value. Thereby, the infection risk values of the locations and areas where there are facilities on the movement routes of the infected persons can be calculated more accurately.

[0223] (1-4) In the above-described Embodiment 1, the first control command was transmitted to the smart speaker 2 in the region where the infection risk value is equal to or higher than the threshold value. However, the present disclosure is not limited to this, and the first control command may be transmitted to all the smart speakers 2. In this case, a first control command for causing the smart speaker 2 to output different voice messages according to the infection risk value may be transmitted to the smart speaker 2. For example, as described above, a first control command for causing the smart speaker 2 to output a voice message predetermined according to whether the infection risk value is high, medium, or low may be transmitted. Also, for the smart speaker 2 installed in the region where the infection risk value is equal to or lower than the threshold value, a first control command for causing the smart speaker 2 to output a voice message indicating that although an infectious disease is not prevalent in this region, it is prevalent in another region may be transmitted.

[0224] (1-5) In the above-described Embodiment 1, the weighting shown in FIG. 7 was described as being variable. However, the present disclosure is not limited to this, and a predetermined fixed value may be adopted for the weighting. In this case, for example, the values of the weightings for each of the levels "5" to "1" with respect to the number of reports by infection attention level may be "5" to "1".

[0225] (1-6) In the above-described Embodiment 1, the number of reported cases for each infection caution level is weighted according to the infection caution level, and the infection risk value is calculated by evaluating the weighted number of reported cases. However, the present disclosure is not limited to this. For example, the infection risk value may be calculated by evaluating the number of reported cases for each infection caution level without weighting.

[0226] (1-7) Specific examples of the multi-device described above are as follows. The multi-device includes a processor, a display unit, a memory, and an input unit. The processor executes word recognition processing on an input signal including a word input to the input unit. The words include messages and / or search words. The input unit is, for example, an operating device such as a touch panel, a keyboard, or a mouse, or a microphone. The input signal is a signal obtained by converting information including a word input by the input unit into an electrical signal.

[0227] The processor includes an infection caution level specifying unit, a region specifying unit, a regional infection information generating unit, and an output information generating unit. The infection caution level specifying unit executes word recognition processing on the input signal acquired by the input unit. The infection caution level specifying unit extracts first word data including words related to the infection risk from the result of the word recognition processing, and specifies the infection caution level from the first word data. The first word data is, for example, the disease name words shown in FIG. 6.

[0228] The region specifying unit executes word recognition processing on the input signals in a certain period before and after the time when the input unit acquired the input signal corresponding to the first word data from the result of the word recognition processing. The region specifying unit extracts second word data from the result of the word recognition processing, and specifies the region related to the first word data from the second word data. Alternatively, the region specifying unit specifies the region related to the first word data using movement history data indicating the movement history of the multi-device. The second word data is, for example, location words such as the company described in FIG. 6.

[0229] The regional infection information generation unit generates regional infection information associating the specified region with the specified infection caution level, and accumulates it in the regional infection information DB9 (equivalent to a memory).

[0230] The output information generation unit generates a message according to the infection caution level of the region from the regional infection information accumulated in the memory.

[0231] (Embodiment 2) FIG. 12 is a diagram showing an example of the network configuration of the information providing system according to Embodiment 2 of the present disclosure. Regarding the content overlapping with Embodiment 1 in Embodiment 2, the description is omitted. The information providing system in Embodiment 2 is one in which a plurality of smart speakers 2A cooperate instead of the server 1 to provide information related to infectious diseases to the user.

[0232] The information providing system in Embodiment 2 includes smart speakers 2A (an example of a voice recognition device and equipment), a mobile terminal 3, a regional infection information DB9, a registration information DB10, a movement information DB11, a search information DB12, and an air purifier 13 (an example of equipment).

[0233] These devices are communicably connected to each other via a network NT. The network NT includes, for example, an Internet communication network and a mobile phone communication network, etc.

[0234] FIG. 13 is a block diagram showing a configuration example of the smart speaker 2A shown in FIG. 12. The smart speaker 2A includes a processor 210, a microphone 220, a communication unit 230, a speaker 240, and a memory 250. The processor 210 performs voice recognition processing on the voice signal collected by the microphone 220.

[0235] The processor 210 includes an infection caution level specifying unit 211, a region specifying unit 212, a regional infection information generation unit 213, a reported case number calculation unit 214, an infection risk value calculation unit 215, an output information generation unit 216, and a social information acquisition unit 217.

[0236] The infection attention level specifying unit 211 extracts first voice data including at least one of words and sounds related to the infection risk from the voice signal collected by the microphone 220, and specifies the infection attention level from the first voice data. The infection attention level specifying unit 211 estimates the infectious diseases prevalent in the region or the infectious diseases that a specific person has contracted from the content of the utterance of the first voice data. The infection attention level specifying unit 211 estimates the period during which a specific person has contracted an infectious disease from the content of the utterance of the second voice data, and corrects the infection attention level using the estimation result.

[0237] The region specifying unit 212 extracts second voice data from the voice signals collected by the microphone within a certain period before and after the time when the first voice data was collected, and specifies the region related to the first voice data from the second voice data. Alternatively, the region specifying unit 212 specifies the region related to the first voice data using the movement information (an example of movement history data) of the speaker of the first voice data. As the certain period before and after the time when the first voice data was collected, the conversation time of a series of conversations related to infectious diseases exchanged between users is adopted, and values such as 10 seconds, 30 seconds, 1 minute, etc. are adopted.

[0238] The region infection information generating unit 213 generates region infection information by associating the region specified by the region specifying unit 212 with the infection attention level specified by the infection attention level specifying unit 211, and stores it in the region infection information DB9 of the memory 250. When the information for generating the region infection information is insufficient, the region infection information generating unit 213 outputs a question message from the speaker 240, acquires the answer voice signal of the question message using the microphone 220, and generates the region infection information using the answer voice signal.

[0239] The reported case number calculating unit 214 calculates the reported case numbers of infectious diseases for each infection attention level in each of one or more regions by classifying the region infection information stored in the region infection information DB9 by region and infection attention level.

[0240] The infection alert level is data obtained by analyzing voice signals such as coughs and sneezes included in the first voice data or the speech content indicated by the first voice data, which quantifies the degree of the spread of infectious diseases.

[0241] The infection risk value calculation unit 215 performs weighting according to the infection alert level on the number of reports calculated by the report count calculation unit 214, and calculates the infection risk value for each region by evaluating the weighted number of reports. Here, the infection risk value is an index indicating the magnitude of the infection risk of infectious diseases in each region.

[0242] The output information generation unit 216 generates a voice message corresponding to the infection risk value from the infection risk values of each region calculated by the infection risk value calculation unit 215. Here, for example, the output information generation unit 216 generates a first control command for outputting a voice message generated from another smart speaker 2A installed in a region where the infection risk value is determined to be high, and transmits it to the other smart speaker 2A using the communication unit 230. The output information generation unit 216 generates a second control command for operating the air purifier 13 installed in a region where the infection risk value is determined to be high, and transmits it to the air purifier 13.

[0243] The social information acquisition unit 217 acquires, using the communication unit 230, information including a regional infection word indicating the spread of infectious diseases in the region and the usage frequency of the regional infection word from a social network service server. In this case, the infection risk value calculation unit 215 calculates the infection risk value using a correction coefficient that increases the infection risk value of the corresponding region as the usage frequency of the regional infection word in the corresponding region increases.

[0244] The microphone 220 collects ambient sound and converts it into a voice signal. The communication unit 230 is composed of a communication device for connecting the smart speaker 2A to the network NT. The speaker 240 outputs a voice message under the control of the processor 210.

[0245] The memory 250 is composed of, for example, a semiconductor memory, and stores the registration information DB10, the regional infection information DB9, and the regional infection information aggregation DB50A. Details of the registration information DB10, the regional infection information DB9, and the regional infection information aggregation DB50A will be described later.

[0246] Since the data configuration of the registration information DB10 stored in the memory 250 of the smart speaker 2A is the same as that in FIG. 4, a detailed description thereof will be omitted.

[0247] However, in Embodiment 2, the "notification setting" shown in the basic information table T11 is setting information indicating whether or not to output an audio message to the smart speaker 2A when a first control command is received from another smart speaker 2A instead of the server 1. For example, when the notification setting is ON and a first control command is received from another smart speaker 2A, the smart speaker 2A outputs the audio message included in the first control command. On the other hand, when the notification setting is OFF, even if a first control command is received from another smart speaker 2A, the smart speaker 2A does not output the audio message included in the first control command.

[0248] Also, in Embodiment 2, the "device control setting" shown in the basic information table T11 is setting information indicating whether or not to transmit a second control command for operating the corresponding air cleaner 13 to the corresponding air cleaner 13 when a first control command is received from another smart speaker 2A instead of the server 1.

[0249] The "voiceprint registration No (number)" shown in the registration information table T12 indicates the index of the voiceprint data of each member, similar to Embodiment 1. However, in Embodiment 2, since the voiceprint data of each member is stored in the memory 250 in advance in association with the voiceprint registration No, the voiceprint data of the corresponding member is read from the memory 250 using the voiceprint registration No as a key.

[0250] Since the data configuration of the regional infection information DB9 stored in the memory 250 of the smart speaker 2A is the same as that in FIG. 5, detailed description thereof will be omitted.

[0251] The figure for explaining the voice recognition process by the processor 210 of the smart speaker 2A is the same as FIG. 6 described in the first embodiment, so detailed description thereof will be omitted. However, in the second embodiment, it is the infection attention level specifying unit 211 instead of the data analysis unit 201 that performs voice recognition on the voice signal collected by the microphone 220.

[0252] Also, in the second embodiment, it is the infection attention level specifying unit 211 instead of the data analysis unit 201 that extracts the first voice data including the disease name word (a word related to the infection risk) from the voice recognition content.

[0253] Also, in the second embodiment, it is the region specifying unit 212 instead of the data analysis unit 201 that extracts the second voice data from the voice signals collected by the microphone 220 during a certain period before and after the time when the first voice data was collected.

[0254] Also, in the second embodiment, it is the region specifying unit 212 instead of the data analysis unit 201 that specifies the location related to the first voice data from the second voice data.

[0255] Also, in the second embodiment, it is the region specifying unit 212 instead of the data analysis unit 201 that specifies the date / time word and the person word respectively from the second voice data.

[0256] Here, for each of the date / time word, location word, person word, and disease name word, the region specifying unit 212 may read out the word list in which candidate words are stored in advance from the memory 250, and refer to these word lists to specify each of the date / time word, location word, person word, and disease name word from the voice recognition content.

[0257] FIG. 14 is a diagram showing an example of the data configuration of the regional infection information aggregation DB50A stored in the memory 250 of the smart speaker 2A in Embodiment 2. The regional infection information aggregation DB50A is a database constructed by aggregating the regional infection information stored in the regional infection information DB9, and includes a first table T51A and a second table T52A.

[0258] Note that one table is created each time the analysis process of the regional infection information is executed when the analysis conditions of S4005 in FIG. 16 are satisfied. FIG. 14 shows the table created by the aggregation process performed on January 18, 2018. As the predetermined analysis conditions, for example, a condition that a certain period has elapsed since the previous analysis process was performed, or a condition that a certain number of regional infection information has been generated since the previous aggregation process can be adopted.

[0259] The first table T51A is a table constructed by classifying the regional infection information stored in the regional infection information DB9 for each location, and one record is assigned to each location.

[0260] The first table T51A stores the "location", "number of reports by infection caution level", "correction coefficient based on the number of users", "correction coefficient based on the assumed stay time", "caution level based on SNS information" (an example of a correction coefficient), "caution level based on patient number data", "caution level based on the linked smart speaker", "infection caution risk value", and "related location" in association with each other.

[0261] The "Location" column stores the names of locations included in the regional infection information. "Number of Reports by Infection Caution Level" indicates the value obtained by aggregating the number of reports of regional infection information for each infection caution level included in the regional infection information. For example, in the example of the first row, regarding "AB Corporation", since there were two pieces of regional infection information with an infection caution level of "5" among the newly generated regional infection information, the report count "2" is stored in the column for the infection caution level "5" of "AB Corporation". Similarly, for each of the columns for the infection caution levels "4", "3", "2", and "1" of "AB Corporation", the report counts "2", "4", "5", and "10" are stored.

[0262] Also, weights are set for each infection caution level. The weights are data learned by the infection risk value calculation unit 215 by comparing the infection caution level set in the smart speaker 2A with the actual epidemic results of infectious diseases. Here, for the actual epidemic results of infectious diseases, the infectious disease transition data stored in the infectious disease transition DB8 may be referred to. Since the details of the calculation of these weights are the same as those in Embodiment 1, detailed explanations are omitted.

[0263] The "Correction Coefficient Based on the Number of Users" is set by the infection risk value calculation unit 215, and the larger the number of users in the corresponding location, the larger the value set. Here, the number of users in the corresponding location is identified by referring to the current congestion status of large facilities in the regional information DB7.

[0264] The "Correction Coefficient Based on the Assumed Stay Time" is set by the infection risk value calculation unit 215, and the longer the assumed stay time of the user in the corresponding location, the larger the value set. Here, for the "Correction Coefficient Based on the Assumed Stay Time", a value predetermined for each location is adopted.

[0265] The "Attention Level Based on SNS Information" is set by the Infection Risk Value Calculation Unit 215, and on SNS, a larger value is set as the current usage frequency of the regional infection word indicating the corresponding location increases. Here, the usage frequency of the regional infection word is obtained from the SNS Word DB 6. The "Attention Level Based on Patient Number Data" is set such that a larger value is set as the number of patients in the region including the location increases.

[0266] The "Attention Level Based on Patient Number Data" is set by the Infection Risk Value Calculation Unit 215, and a larger value is set as the patient number data of the corresponding location is larger. Here, the patient number data of the corresponding location is obtained from the Patient Number DB 5.

[0267] The "Infection Risk Value by Linked Smart Speaker" indicates the infection risk value calculated for each region calculated by another linked smart speaker 2A.

[0268] Regarding the "Infection Risk Value", assuming that the weight of the infection attention level i (= 1 to 5) is αi, the number of reports of the infection attention level i at location j is βij, the correction coefficient based on the number of users at location j is aj, the correction coefficient based on the assumed stay time at location j is bj, the attention level based on SNS information at location j is cj, the attention level based on patient number data at location j is dj, and the infection risk value by the linked smart speaker at location j is ej, the Infection Risk Value Calculation Unit 215 calculates the infection risk value of location j by the following formula (3).

[0269] Infection risk value at location j = aj × bj × cj × dj × ej × Σiαi × βij (3) For example, in the case of AB Corporation, the infection risk value is calculated by aj × bj × cj × dj × ej × (2 × 3 + 2 × 1 + 4 × 0.7 + 5 × 0.4 + 10 × 0.1).

[0270] Note that the weighting may be set for each of the "correction coefficient based on the number of users", "correction coefficient based on the assumed stay time", "attention level based on SNS information", and "attention level based on patient number data".

[0271] The weighting of the "correction coefficient based on the number of users" is set by the infection risk value calculation unit 215 and is data learned by comparing the actual epidemic results of infectious diseases with the number of users. The smaller the influence of the number of users on the actual epidemic results of infectious diseases, the smaller the value set for this weighting.

[0272] The weighting of the "correction coefficient based on the assumed stay time" is set by the infection risk value calculation unit 215, and the smaller the influence of the assumed stay time on the actual epidemic results of infectious diseases, the smaller the value set. The weighting of the "attention level based on SNS information" is set by the infection risk value calculation unit 215, and the smaller the influence of the SNS information on the actual epidemic results of infectious diseases, the smaller the value set. The weighting of the "attention level based on patient number data" is set by the infection risk value calculation unit 215, and the smaller the influence of the number of patients on the actual epidemic results of infectious diseases, the smaller the value set. The weighting of the "infection risk value based on the linked smart speaker" is set by the infection risk value calculation unit 215, and the smaller the influence of the infection risk value based on the linked smart speaker on the actual epidemic results of infectious diseases, the smaller the value set.

[0273] Assuming that the respective weightings of the "correction coefficient based on the number of users", "correction coefficient based on the assumed stay time", "attention level based on SNS information", "attention level based on patient number data", and "infection risk value based on the linked smart speaker" are p1, p2, p3, p4, and p5, the infection risk value calculation unit 215 calculates the infection risk value using the following formula (4).

[0274] Infection risk value at location j = p1 × aj × p2 × bj × p3 × cj × p4 × dj × p5 × ej × Σiαi × βij (4) "Related location" indicates a location where users staying at the corresponding location are likely to go. For example, since many employees of "AB Corporation" go to "DD Gym", "DD Gym" is stored as a related location of "AB Corporation".

[0275] In this case, the infection risk value of the corresponding location may be set in consideration of the infection risk value of the related location. For example, the final infection risk value may be calculated by adding a value obtained by multiplying the infection risk value of the related location by a predetermined coefficient to the infection risk value of the corresponding location.

[0276] The second table T52A is a table constructed by classifying the regional infection information transmitted from the smart speaker 2A for each district. Since the second table T52A is the same as the first table T51A except that the regional infection information is classified for each district instead of for each location, detailed description thereof is omitted. However, the second table T52A has a "correction coefficient based on the number of stayers" instead of the "correction coefficient by the user". The "correction coefficient based on the number of stayers" indicates a correction coefficient corresponding to the persons staying in the district. Further, the second table T52A has a "related district" instead of the "related location".

[0277] FIG. 15 is a flowchart showing an example of the processing of the information providing system according to Embodiment 1 of the present disclosure. In S1001, the microphone 220 of the smart speaker 2A collects ambient sound and acquires an audio signal. In S1002, the infection caution level specifying unit 211 and the region specifying unit 212 of the smart speaker 2A analyze the audio signal, and the regional infection information generation unit 213 generates regional infection information from the analysis result of the audio signal. Here, by performing speech recognition processing on the audio signal, speech recognition content such as "It seems that the person from the business partner I met at the company yesterday has influenza" is acquired. Also, here, by using the voiceprint data, the speaker of this speech recognition content is specified. Further, from this speech recognition content, disease name words, location words, date and time words, and person words are extracted.

[0278] In S1003, the processor 210 of the smart speaker 2A_1 stores the newly generated regional infection information in the regional infection information DB9.

[0279] In S1004, the processor 210 of the smart speaker 2A_1 transmits the newly generated regional infection information to the smart speaker 2A_2 using the communication unit 230, and receives the regional infection information transmitted from the smart speaker 2A_2 using the communication unit 230 and stores it in the regional infection information DB9. As a result, the memory 250 of the smart speaker 2A accumulates the regional infection information generated by other smart speakers 2A.

[0280] In S1005, the report count calculation unit 214 and the infection risk value calculation unit 215 of the smart speaker 2A_1 update the regional infection information aggregation DB50A by aggregating the regional infection information stored in the regional infection information DB9. As a result, the first table T51A and the second table T52A shown in FIG. 14 are generated.

[0281] In S1006, the output information generation unit 216 of the smart speaker 2A_1 refers to the updated regional infection information aggregation DB50A to identify the area that requires attention. Here, it is assumed that the area where the smart speaker 2A_2 is installed is identified as the area that requires attention.

[0282] In S1007, the output information generation unit 216 of the smart speaker 2A_1 generates a first control command to output a voice message for notifying the infection risk from the smart speaker 2A_2 installed in the identified area that requires attention, and transmits it to the smart speaker 2A_2 using the communication unit 230.

[0283] In S1008, the output information generation unit 216 of the smart speaker 2A_1 generates a voice message for notifying the infection risk of the identified area that requires attention to the user of the smart speaker 2A_1, and outputs it from the speaker 240. The output of this voice message may be triggered, for example, by a voice that the user is going out or passing through the identified area that requires attention being spoken to the smart speaker 2A_1.

[0284] Note that since the processes of S2001 to S2005 performed by the smart speaker 2A_2 are the same as those of S1001 to S1005, the description is omitted.

[0285] In S2006, the smart speaker 2A_2 that has received the first control command causes the speaker 240 to output an audio message according to the first control command.

[0286] In S2007, the smart speaker 2A_2 that has received the first control command transmits a second control command to the corresponding air purifier 13.

[0287] In S3001, the air purifier 13 that has received the second control command starts operating according to the second control command and purifies the surrounding air.

[0288] FIG. 16 is a flowchart showing the details of the processing of the smart speaker 2A_1 in FIG. 15. Here, a use case will be described by taking as an example the case where the smart speaker 2A_1 receives a first control command from another smart speaker 2A_3 and transmits a second control command to the air purifier 13.

[0289] S4001 to S4004 are the same as S1001 to S1004 in FIG. 15, so the description thereof will be omitted. In S4005, the processor 210 of the smart speaker 2A_1 determines whether or not the analysis start condition is satisfied. Here, the analysis start condition is a condition for starting the analysis of the regional infection information aggregation DB 50A. For example, a condition that a certain period has elapsed since the previous analysis or a condition that a certain number of regional infection information has been received since the previous analysis is adopted.

[0290] If the analysis start condition is satisfied (YES in S4005), the process proceeds to S4006. If the analysis start condition is not satisfied (NO in S4005), the process returns to S4001.

[0291] In S4006, the reported case number calculation unit 214 calculates the reported case number using the regional infection information newly received from the previous analysis to the current analysis.

[0292] Here, the reported case number calculation unit 214 classifies the newly received regional infection information by location and by infection attention level, calculates the reported case numbers for each location by infection attention level, and generates the first table T51A.

[0293] Referring to FIG. 14, for example, in the newly received regional infection information, there are two pieces of regional infection information with an infection attention level of "5" regarding "AB Corporation". Therefore, in the first table T51A, the reported case number of AB Corporation with an infection attention level of "5" is "2" stored.

[0294] Similarly, the reported case number calculation unit 214 classifies the newly received regional infection information by district and by infection attention level, calculates the reported case numbers for each district by infection attention level, and generates the second table T52A.

[0295] In S4007, the infection risk value calculation unit 215 calculates the infection risk values for the generated first table T51A and second table T52A. Here, the infection risk value calculation unit 215 uses the above-described formula (3) or formula (4) to calculate the infection risk value for each location shown in the first table T51A and the infection risk value for each district shown in the second table T52A.

[0296] In S4008, the output information generation unit 216 determines whether there is a region where the infection risk value is higher than the threshold. Referring to the first table T51A in FIG. 14, assuming that the threshold for the location is, for example, "10", the infection risk value of "AB Corporation" is "13.8", which is larger than the threshold. Therefore, AB Corporation is determined to be a location requiring attention.

[0297] Also, referring to the second table T52A in FIG. 14, assuming that the threshold for the district is, for example, "400", since the infection risk value of "BB District" is "518.6", "BB District" is determined to be a district requiring attention.

[0298] In S4008, if there is no area where the infection risk value is higher than the threshold (NO in S4008), the process returns to S4001. If there is an area where the infection risk value is higher than the threshold (YES in S4008), the process proceeds to S4009.

[0299] In S4009, the output information generation unit 216 generates a first control command for the smart speaker 2A_2 installed in the area and place requiring attention. Here, for example, the output information generation unit 216 may generate a first control command to cause the smart speaker 2A_2 to output a voice message indicating that an infectious disease is prevalent in the area where the smart speaker 2A_2 is installed. Alternatively, the output information generation unit 216 may divide the level of the infection risk into, for example, three levels of strong, medium, and weak according to the magnitude of the infection risk value, and generate a first control command to cause the smart speaker 2A_2 to output a voice message corresponding to that level. For example, if the level of the infection risk is strong, a voice message such as "Avoid going out" may be output; if the level of the infection risk is medium, a voice message such as "Wear a mask when going out. Also, gargle and wash your hands when you return home" may be output; if the level of the infection risk is weak, a voice message such as "Wash your hands" may be output from the smart speaker 2A_2.

[0300] In S4010, when the communication unit 230 of the smart speaker 2A_1 receives a first control command from another smart speaker 2A_3 (YES in S4010), the process proceeds to S4011. When the first control command is not received (NO in S4010), the process returns to S4001.

[0301] In S4011, the output information generation unit 216 of the smart speaker 2A_1 causes the speaker 240 to output a voice message according to the received first control command. Here, voice messages notifying the user of the prevalence of an infectious disease and the level of the infection risk as described above are output.

[0302] In S4012, the output information generation unit 216 of the smart speaker 2A_1 determines whether the device control setting is "automatic". If the device control setting is "automatic" (YES in S4012), the output information generation unit 216 of the smart speaker 2A_1 transmits a second control command to the corresponding air purifier 13 using the communication unit 230 (S4013). On the other hand, if the device control setting is not "automatic" (NO in S4012), the process returns to 4001.

[0303] As described above, according to the present embodiment, since the regional infection information in which the infection caution level and the region are associated based on the utterances made by the user, for example, at home, is collected, it is possible to accurately and timely generate an audio message suitable for the infection caution level for each region and output it from the speaker.

[0304] Therefore, this configuration can provide appropriate information to the user according to the infection caution level, and can avoid a situation where the user is made to take excessive infection prevention measures or the user's infection prevention measures become insufficient.

[0305] (Embodiment 3) The information providing system according to Embodiment 2 is configured such that the smart speaker 2B and the server 1A cooperate to provide information regarding infectious diseases to the user. Regarding the contents overlapping with Embodiments 1 and 2 in Embodiment 3, the description will be omitted.

[0306] FIG. 17 is a diagram showing an example of the network configuration of the information providing system according to Embodiment 2 of the present disclosure.

[0307] In FIG. 17, in addition to the configuration of FIG. 13, a server 1A and a virus sensor 4 are further provided. The server 1A is, for example, a cloud server configured by one or more computers, and calculates the infection risk value for each region using the regional infection information acquired from the smart speaker 2B.

[0308] FIG. 18 is a block diagram showing a configuration example of the information providing system shown in FIG. 17. In FIG. 18, since the configurations other than the server 1A and the smart speaker 2B are the same as those in FIG. 2, the description thereof is omitted.

[0309] FIG. 19 is a block diagram showing a configuration example of the smart speaker 2B and the server 1A shown in FIG. 18. In FIG. 19, the differences from FIG. 13 are that the regional infection information aggregation DB 50A is provided in the memory 130 of the server 1A instead of the memory 250 of the smart speaker 2A, and the reported case number calculation unit 214, the infection risk value calculation unit 215, the output information generation unit 216, and the social information acquisition unit 217 are provided in the processor 110 of the server 1A instead of the processor 210 of the smart speaker 2A.

[0310] FIG. 20 is a flowchart showing an example of the processing of the information providing system according to Embodiment 3 of the present disclosure. In FIG. 20, the same steps as those in FIG. 15 are denoted by the same step numbers and the description thereof is omitted.

[0311] In S5001 following S1004, the reported case number calculation unit 214 and the infection risk value calculation unit 215 of the server 1A that have received the regional infection information from the smart speaker 2B update the regional infection information aggregation DB 50A by using the regional infection information transmitted from the smart speaker 2B and using the database group 14 as necessary.

[0312] In S5002, the output information generation unit 216 of the server 1A specifies the areas requiring attention by referring to the updated regional infection information aggregation DB 50A.

[0313] In S5003, the output information generation unit 216 of the server 1A generates a first control command for causing the smart speaker 2B installed in the area requiring attention to output a voice message for notifying the infection risk, and transmits the command to the corresponding smart speaker 2B using the communication unit 102.

[0314] In S2006A, the smart speaker 2B that has received the first control command causes the speaker 240 to output an audio message according to the first control command.

[0315] In S2007A, the smart speaker 2B that has received the first control command transmits a second control command to the corresponding air purifier 13.

[0316] In S3001, the air purifier 13 that has received the second control command starts operating according to the second control command and purifies the surrounding air.

[0317] FIG. 21 is a flowchart according to a modified example of FIG. 20. In the flow of FIG. 21, processing of the mobile terminal 3 is further added to the flow of FIG. 20. In FIG. 21, the same steps as those in FIG. 20 are assigned the same step numbers and the description thereof is omitted.

[0318] In S1301, the control unit 303 of the mobile terminal 3 stores usage information in the memory 302. Here, the usage information includes movement information and search information, and the control unit 303 may store the movement information in the movement information DB11 at regular time intervals and store the search information in the search information DB12 each time a search word is input by the user.

[0319] In S1302, the communication unit 304 of the mobile terminal 3 transmits the usage information to the smart speaker 2B. Here, the control unit 303 of the mobile terminal 3 may include the movement information of a certain period from the present to the past among the movement information stored in the movement information DB11 in the usage information and include the search information of a certain period from the present to the past among the search information stored in the search information DB12 in the usage information.

[0320] Note that the mobile terminal 3 may transmit the usage information to the smart speaker 2B periodically, or may transmit the usage information to the smart speaker 2B in response to a request from the smart speaker 2B.

[0321] In S1002A following S1001, the processor 210 of the smart speaker 2B generates regional infection information by using usage information as necessary in addition to analyzing the voice signal. For example, assume that the time word could be identified from the voice recognition content, but the location word could not be identified. In this case, if there is movement information of the speaker, the processor 210 may use the movement information to identify the location where the speaker was at the date and time indicated by the time word.

[0322] As described above, in the flow of FIG. 21, if there is information lacking in the voice recognition content in generating regional infection information, the lacking information is supplemented by the usage information from the mobile terminal 3, and a situation where the regional infection information cannot be generated can be avoided as much as possible.

[0323] Note that the following modification examples can be adopted in Embodiments 2 and 3.

[0324] (2-1) In the above Embodiments 2 and 3, as shown in FIG. 15, the second control command is transmitted from the smart speaker 2A_2 that has received the first control command to the air cleaner 13, but the present disclosure is not limited to this. For example, the second control command may be directly transmitted from the smart speaker 2A_1 that has transmitted the first control command to the air cleaner 13. In this case, the smart speaker 2A_1 may store by associating the region where each smart speaker 2A is installed with the communication address. This also applies to Embodiment 3. That is, in FIG. 20, the second control command may be directly transmitted from the server 1A that has transmitted the first control command to the air cleaner 13.

[0325] (2-2) In the above-described Embodiments 2 and 3, when generating regional infection information, the regional infection information generation unit 213 calculates the speech distance between the location word and the disease name word extracted from the speech recognition content. If the speech distance is separated by a certain value or more, a question message for asking the user whether the location specified from the location word is correct may be output from the speaker 240. Then, when a speech indicating that it is correct is received from the user, the regional infection information generation unit 213 may generate regional infection information associating the location specified from the location word with the infection caution level specified from the disease name word, and store it in the regional infection information DB 9. Note that as the speech distance, the number of characters from the disease name word to the location word can be adopted in the text data indicating the speech recognition content. This is based on the idea that as the number of characters from the disease name word to the location word increases, the relevance between the two words decreases.

[0326] (2-3) When generating regional infection information, the regional infection information generation unit 213 identifies facilities where a large number of people gather, such as stations, commercial facilities, and schools, located on the movement route of a member (infected person) whose infection caution level is equal to or higher than a certain level, specified from the speech recognition content. The identified facilities may be notified to another smart speaker 2A, 2B or the server 1A using the communication unit 230. Then, the other smart speaker 2A, 2B or the server 1A may increase the infection risk value of the location and area of the notified facility by a predetermined value. Thereby, the infection risk value in the location and area where there is a facility on the movement route of the infected person can be calculated more accurately.

[0327] (2-4) In the above-described Embodiments 2 and 3, the first control command was transmitted to the smart speakers 2A and 2B in the areas where the infection risk value is equal to or higher than the threshold value. However, the present disclosure is not limited to this, and the first control command may be transmitted to all the smart speakers 2A and 2B. In this case, a first control command for causing the smart speakers 2A and 2B to output different voice messages according to the infection risk value may be transmitted to the smart speakers 2A and 2B. For example, as described above, a first control command for causing the smart speakers 2A and 2B to output predetermined voice messages according to whether the infection risk value is high, medium, or low may be transmitted. Also, for the smart speakers 2A and 2B installed in the areas where the infection risk value is equal to or lower than the threshold value, a first control command for outputting a voice message indicating that although the infectious disease is not prevalent in this area, it is prevalent in another area may be transmitted.

[0328] (2-5) In Embodiments 2 and 3, the weighting shown in FIG. 14 was described as being variable. However, the present disclosure is not limited to this, and a predetermined fixed value may be adopted for the weighting. In this case, for example, the values of the weightings for levels "5" to "1" with respect to the number of reported cases by infection caution level may be "5" to "1".

[0329] (2-6) In the above-described embodiment, the voice message was generated based on the infection risk value described in the regional infection information aggregation DB 50A shown in FIG. 14. However, the present disclosure is not limited to this. For example, the voice message may be generated from the regional infection information DB 9 shown in FIG. 5. For example, assume that the smart speakers 2A and 2B receive a speech from the user asking to be informed of the places where the infectious disease is prevalent. In this case, the smart speakers 2A and 2B may calculate the total value of the infection caution levels in a certain period (for example, today) in the regional infection information, and generate a voice message indicating that the areas where the total value is equal to or higher than the threshold value are the places where the infectious disease is prevalent.

[0330] (Embodiment 4) FIG. 22 is a diagram showing an example of the network configuration of the information providing system according to Embodiment 4 of the present disclosure. The information providing system according to Embodiment 4 generates mapping data in which a specific location on map data is associated with the number of possible infected persons at that location in a service application area including the area where the user to whom the service is applied resides and one or more areas within a certain range from that area, and provides it to the user. In the present embodiment, descriptions of the same contents as those in Embodiments 1 to 3 are omitted.

[0331] The information providing system includes a server 1B, a smart speaker 2C, a mobile terminal 3A, a virus sensor 4, a patient number DB (database) 5, an SNS word DB 6, a region information DB 7, an infectious disease transition DB 8, a regional infection information DB 9, a registration information DB 10, a movement information DB 11, a search information DB 12, a countermeasure information DB 16, an infection risk value DB 14, and an external server 15.

[0332] The server 1B to the infection risk value DB 14 are connected to be communicable with each other via a network NT.

[0333] The server 1B is, for example, a cloud server composed of one or more computers, generates the above-described mapping data, and transmits it to the mobile terminal 3A.

[0334] The smart speaker 2C is installed, for example, in the user's home. The smart speaker 2C is an example of a voice recognition device. In the example of FIG. 22, two smart speakers 2C_1 and 2C_2 are shown, but this is just an example, and the number of smart speakers 2C may be one, or three or more.

[0335] The mobile terminal 3A is a device possessed by the user of the household where the smart speaker 2C is installed. The mobile terminal 3A is composed of a portable information processing device such as, for example, a smartphone, a tablet terminal, and a button-type mobile phone. In FIG. 22, three mobile terminals 3A_1, 3A_2, and 3A_3 are shown, but this is just an example, and the number of mobile terminals 3A may be one, two, or four or more.

[0336] In Embodiment 4, the regional information DB 7 is, for example, a database constructed on the external server 15 managed by the administrator of this information providing service, and is connected to the network NT via the external server 15. Note that the map data included in the regional data is stored in the regional information DB 7 by the external server 15 importing the map data provided by, for example, the operating company of a search engine on the Internet. Also, the route map data of public transportation included in the regional data is stored in the regional information DB 7 by the external server 15 importing the route map data publicly available on the Internet by railway companies, bus companies, etc. Further, the congestion status data included in the regional data is stored in the regional information DB 7 by the external server 15 importing the congestion status data generated by, for example, the operating company of a search engine on the Internet.

[0337] The regional infection information DB 9 is created based on the speech history of the user voice-recognized by the smart speaker 2C and stores regional infection information indicating the infection caution level of each region. The registration information DB 10 stores the personal information of the members of the household where the smart speaker 2C is installed. The regional infection information DB 9 and the registration information DB 10 are stored, for example, in the memory of the smart speaker 2C. However, this is just an example, and the regional infection information DB 9 and the registration information DB 10 may be stored by the external server 15.

[0338] The movement information DB11 stores the movement information of the user who owns the mobile terminal 3A. The movement information is, for example, data in which the position information calculated by the GPS sensor provided in the mobile terminal 3A is associated with the calculation time. The movement information DB11 is stored, for example, in the memory of the mobile terminal 3A. However, this is just an example, and the movement information DB11 may be stored in the external server 15.

[0339] The search information DB12 stores search information indicating the user's search history for the search engine executed on the mobile terminal 3A. The search information is, for example, data in which the search word input to the search engine and the search time are associated.

[0340] The countermeasure information DB13 stores measurement data including measurement data by the infection prevention sensor 20 (Fig. 23) that is installed in various facilities such as large commercial facilities, community centers, and libraries within the service application area and measures the surrounding environmental information.

[0341] The infection risk value DB14 is a database configured by the external server 15 and stores the infection risk value indicating the infection risk for each location. The details of the calculation of the infection risk value will be described later.

[0342] The external server 15 is a cloud server composed of one or more computers, and stores the regional information DB7, the countermeasure information DB13, and the infection risk value DB14. In addition, the external server 15 calculates the infection risk value for each location and stores it in the infection risk value DB14.

[0343] Fig. 23 is a block diagram showing a configuration example of the information providing system shown in Fig. 22. The smart speaker 2C includes a data analysis unit 201A, a memory 202, a speaker 203, a control unit 204A, a communication unit 205A, and a microphone 206. The data analysis unit 201A is composed of a processor that performs voice recognition processing on the voice signal collected by the microphone 206. In Fig. 23, the blocks overlapping with Fig. 2 are denoted by the same reference numerals as in Fig. 2, and the description thereof is omitted.

[0344] The data analysis unit 201A performs voice recognition on the voice signal collected by the microphone 206, identifies the potential infected persons who may be infected with an infectious disease and the infection possibility of the potential infected persons, and generates regional infection information (an example of the first infection information). The data analysis unit 201A estimates the infectious disease that the potential infected person is infected with from the speech content of the voice signal.

[0345] The communication unit 205A is composed of a communication device for connecting the smart speaker 2C to the network NT. For example, the communication unit 205A transmits the regional infection information generated by the data analysis unit 201A to the mobile terminal 3A of the potential infected person.

[0346] The mobile terminal 3A includes a GPS sensor 301, a memory 302, a control unit 303A, a communication unit 304, a display unit 305 (an example of a display), and an operation unit 306.

[0347] In addition to the functions of the control unit 303 shown in FIG. 2, when the communication unit 205A receives the regional infection information from the smart speaker 2C, the control unit 303A reads out the position information for a certain period in the past from the movement information DB11, generates association data associating the read position information with the received regional infection information, and transmits the association data to the server 1B using the communication unit 205A.

[0348] The server 1B includes a data analysis unit 1001, a memory 1002, a control unit 1003, and a communication unit 1004. The data analysis unit 1001 is composed of, for example, a CPU. When the communication unit 1004 receives the association data from the mobile terminal 3A, the data analysis unit 1001 uses the association data to generate mapping data associating a specific location on the map data with the number of potential infected persons at that location. Then, the data analysis unit 1001 stores the generated mapping data in the mapping DB1005. The map data refers to map data, and the specific location corresponds to the location extracted from the voice recognition content or the location on the predetermined map data.

[0349] The memory 1002 is composed of, for example, a semiconductor memory and stores the mapping DB 1005. Details of the mapping DB 1005 will be described later.

[0350] The control unit 1003 is composed of, for example, a CPU. When the communication unit 1004 receives a request from the mobile terminal 3A, the control unit 1003 transmits mapping data to the mobile terminal 3A that sent the request using the communication unit 1004. The communication unit 1004 is a communication device that connects the server 1B to the network NT. Here, the mobile terminal 3A that sends the request includes the mobile terminal 3A of a person who may be infected and the mobile terminal 3A of a person to whom other services are applicable.

[0351] The infection prevention sensor 20 is composed of, for example, an air purifier and includes a detection unit 2001, a memory 2002, a control unit 2003, and a communication unit 2004. The detection unit 2001 is composed of, for example, a temperature sensor and a humidity sensor and detects the ambient temperature and humidity. The detection unit 2001 acquires from the memory 2002 the set value of the infection prevention sensor 20 set by the control unit 2003. Here, as the set value of the infection prevention sensor 20, for example, set values of the purification ability of the infection prevention sensor 20 such as "strong", "medium", and "weak" are adopted.

[0352] The memory 2002 is composed of, for example, a semiconductor memory and stores the measurement data detected by the detection unit 2001 and the set value set by the control unit 2003.

[0353] The control unit 2003 is composed of, for example, a CPU and is in charge of overall control of the infection prevention sensor 20. The communication unit 2004 is composed of a communication device that connects the infection prevention sensor 20 to the network NT.

[0354] The database group 14A collectively shows the patient number DB 5, the SNS word DB 6, the regional information DB 7, the infectious disease trend DB 8, the countermeasure information DB 16, and the infection risk value DB 14 shown in FIG. 22 and is constructed on various servers described in FIG. 22.

[0355] Since the data configuration of the registration information DB10 stored in the memory 202 of the smart speaker 2C is the same as that in FIG. 4, detailed description thereof will be omitted.

[0356] However, in the fourth embodiment, the "notification setting" shown in the basic information table T11 is setting information indicating whether to output an audio message to the smart speaker 2C when a speech command is received from the server 1B or the external server 15. For example, when the notification setting is ON and a speech command is received from the server 1B or the external server 15, the smart speaker 2C outputs the audio message included in the speech command. On the other hand, when the notification setting is OFF, even if a speech command is received from the server 1B, the smart speaker 2C does not output the audio message included in the speech command.

[0357] Also, in the fourth embodiment, the "device control setting" shown in the basic information table T11 is setting information indicating whether to transmit a control command for operating the corresponding air purifier to the corresponding air purifier when a speech command is received from the server 1B or the external server 15. For example, if the device control setting is "automatic", the smart speaker 2C transmits a control command to the corresponding air purifier. On the other hand, if the device control setting is not "automatic", the smart speaker 2C does not transmit a control command to the corresponding air purifier. Here, the corresponding air purifier means the air purifier installed in the home where the smart speaker 2C is located if the smart speaker 2C is installed in a home.

[0358] Since the data configuration of the regional infection information DB9 stored in the memory 202 of the smart speaker 2C is the same as that in FIG. 5, detailed description thereof will be omitted.

[0359] However, in the fourth embodiment, "location" indicates the location extracted from the speech recognition content. "Region" indicates the region to which the extracted location belongs.

[0360] In addition, in Embodiment 4, in the column of "associated data", movement information indicating the movement route of the members registered in the column of "subject number" is stored. The movement information is obtained from the movement information DB11 of the mobile terminal 3A possessed by the members.

[0361] In the column of "associated data", "movement information / smartphone" indicates that the device from which the movement information was obtained is the mobile terminal 3A. Also, as the movement information registered in the "associated data", movement information for a certain period in the past is adopted based on the "time" of the voice recognition content. By storing the movement information in this way, it is possible to identify the places visited by members with a high risk of infection, and using the identified places, it is possible to identify the places where infectious diseases are prevalent.

[0362] The figure for explaining the voice recognition process by the data analysis unit 201A of the smart speaker 2C is the same as Fig. 6, so detailed description is omitted.

[0363] However, in the example of the first line, since the speaker "Taro" is a person who may have been infected with an infectious disease, that is, a person with a risk of infection, "1", which is the identifier of "Taro", is stored in the "subject number".

[0364] Fig. 24 is a diagram showing an example of the data configuration of the mapping DB1005 stored in the memory 1002 of the server 1B. In the mapping DB1005, one mapping data is assigned to one record, and it stores the number of persons at risk of infection and the temporal change of environmental information at one or more locations.

[0365] The "location" is the location included in the association data transmitted from the mobile terminal 3A, that is, the "location" included in the regional infection information DB9 shown in Fig. 5. Alternatively, the "location" may be a predetermined location where a large number of people gather, such as a large commercial facility, a community center, a school, a hospital, and a station, in the service application area. Hereinafter, these will be collectively described as specific locations.

[0366] In the example of FIG. 24, "AA Shopping Center" and "CC Supermarket" are specified as specific locations. Also, in the "AA Shopping Center", the number of potential infected persons at more detailed locations such as the Star Square and the Moon Square has been specified, so the number of potential infected persons is also remembered for these locations. Note that the detailed locations were specified in the AA Shopping Center because "Star Square of AA Shopping Center" and "Moon Square of AA Shopping Center" were remembered in the location column of the regional infection information shown in FIG. 5. Alternatively, for the AA Shopping Center, it was pre-determined to set the Star Square and the Moon Square as specific locations.

[0367] Here, the number of potential infected persons for each specific location is calculated in one-hour units such as 9:00 on January 18, 2018, 10:00 on January 18, 2018, etc. However, this one-hour is just an example, and the number of potential infected persons may be calculated for other time intervals such as one minute, ten minutes, two hours, etc.

[0368] Taking 10:00 on January 18, 2018 as an example, first, the data analysis unit 1001 extracts the movement information of potential infected persons from the association data transmitted from the mobile terminal 3A in the time period from the previous calculation time of the number of potential infected persons, "9:00 on January 18, 2018" to "10:00" on the same day. Specifically, the movement information stored in the "associated data" column of the regional infection information (FIG. 5) included in the association data is extracted.

[0369] Then, the data analysis unit 1001 determines whether a person with a potential for infection has stayed at a specific location for a predetermined time or more during this time period based on the extracted movement information. Here, as the predetermined time, for example, times such as 1 minute, 2 minutes, 5 minutes, and 10 minutes can be adopted. Also, the determination of whether a person with a potential for infection is at a specific location or not is, for example, in the case of the AA Shopping Center, the latitude range and longitude range of the AA Shopping Center are specified from the map data, and it is determined based on whether there are latitudes and longitudes indicated by the movement information of the person with a potential for infection within this latitude range and longitude range. Alternatively, it may be determined based on whether the latitude and longitude of the person with a potential for infection are located within a certain range from the center position of the AA Shopping Center.

[0370] Then, the data analysis unit 1001 calculates the number of persons with a potential for infection who have stayed at a specific location for a predetermined time or more for each specific location, calculates the number of persons with a potential for infection for each specific location, and stores it in the corresponding column of the mapping DB 1005.

[0371] In the example of FIG. 24, in the time period from 9:00 to 10:00, the movement information of 8 persons with a potential for infection showed that they had stayed at the Star Square of the AA Shopping Center for a predetermined time or more. Therefore, 8 persons were calculated as the number of persons with a potential for infection at the Star Square of the AA Shopping Center at 10:00 on January 18, 2018. Similarly, the number of persons with a potential for infection is calculated for other specific locations.

[0372] The environmental information indicates the environmental information and infection prevention information around a specific location, and is, for example, obtained from the infection prevention sensor 20 installed at the specific location. In the example of FIG. 24, as the environmental information, "temperature", "humidity", "setting value", "infection risk", and "infection risk value" are included. The setting value indicates the setting value of the purification ability of the infection prevention sensor 20 such as "strong", "medium", and "weak". When the infection prevention sensor 20 is not operating, OFF is stored as the setting value. The fact that the infection prevention sensor 20 is operating means that it is considered that infection prevention measures are being taken at a specific location. Therefore, when the "setting value" is "strong", "medium", or "weak", it is determined that environmental measures are being taken.

[0373] The infection risk indicates the infection risk at a specific location calculated by the data analysis unit 1001. The infection risk is calculated, for example, as follows. First, the data analysis unit 1001 calculates the density of infected persons at a specific location. For example, if the floor area of the AA Shopping Center obtained from the regional information DB7 is S, the current number of epidemic-infected persons in the AA Shopping Center is n, and the density of infected persons is nr, the data analysis unit 1001 calculates the density of infected persons by nr = n / S. Next, the data analysis unit 1001 multiplies the density of infected persons by the temperature coefficient kt determined from the current temperature of the AA Shopping Center, the humidity coefficient km determined from the humidity, and the setting value coefficient kl determined from the setting value, to calculate the infection risk evaluation value α (= nr · kt · km · kl) of the AA Shopping Center. For example, since the influenza virus is more likely to grow as the humidity is lower and the temperature is lower, the humidity coefficient km and the temperature coefficient kt are set larger as the humidity and temperature decrease. Also, since the virus decreases as the setting value increases, the setting value coefficient kl is set smaller as the setting value is larger.

[0374] Then, the data analysis unit 1001 calculates the infection risk according to which numerical range among the numerically defined ranges for each of "high", "medium", and "low" the infection risk evaluation value α belongs to. That is, the infection risk is represented in three levels: "high", "medium", and "low". However, this is just an example, and the infection risk may be represented in two levels or four or more levels.

[0375] The infection risk value is an index that quantifies the infection risk at a specific location obtained by the external server 15 analyzing a large number of regional infection information transmitted from the smart speaker 2C. The infection risk value is stored in the infection risk value DB14, and the server 1B acquires the infection risk value of a specific location from the infection risk value DB14.

[0376] The infection risk value is calculated by the external server 15 as follows. First, the external server 15 receives regional infection information (an example of the second infection information) from the smart speaker 2C at any time. Then, the external server 15 classifies the regional infection information for each specific location and infection alert level to calculate the number of reported cases for each infection alert level at a specific location. Referring to Figure 5, assume that the external server 15 has received 10, 8, 7, 15, and 20 pieces of regional infection information with infection alert levels "5" to "1" respectively from AB Corporation. In this case, the external server 15 calculates the number of reported cases for each of the infection alert levels "5" to "1" for AB Corporation as 10, 8, 7, 15, and 20 respectively.

[0377] Next, the external server 15 calculates the infection risk value by weighted addition of the number of reported cases using predetermined weightings for each of the infection alert levels "5" to "1". For example, if the weightings for the infection alert levels "5" to "1" are "k5", "k4", "k3", "k2", "k1" respectively, the infection risk value for AB Corporation is calculated as follows.

[0378] Infection risk value for AB Corporation = k5·10 + k4·8 + k3·7 + k2·15 + k1·20 The external server 15 executes such processing for each specific location to calculate the infection risk value for each specific location. Here, the external server 15 calculates the infection risk value every predetermined time (e.g., every day) and stores it in the infection risk value DB 14 in time series. Therefore, when receiving a request to obtain the infection risk value from the server 1B, the external server 15 may simply send the latest infection risk value to the server 1B.

[0379] Figure 25 is a flowchart showing an example of the processing of the information providing system shown in Figure 22. In S1101, the control unit 303A of the mobile terminal 3A stores usage information in the memory 302. Here, the usage information includes movement information and search information. The control unit 303A may store the movement information in the movement information DB11 at regular time intervals, and store the search information in the search information DB12 each time a search word is input by the user.

[0380] In S1102, the communication unit 304 of the mobile terminal 3A transmits the usage information to the smart speaker 2C. Here, the control unit 303A of the mobile terminal 3A may include, in the usage information, the movement information of a certain period (for example, 1 hour) from the present to the past among the movement information stored in the movement information DB11, and the search information of a certain period (for example, 1 hour) from the present to the past among the search information stored in the search information DB12. Note that the mobile terminal 3A may transmit the usage information to a predetermined smart speaker 2C installed, for example, in the user's home.

[0381] Note that the mobile terminal 3A may transmit the usage information to the smart speaker 2C regularly (for example, every 1 hour), or may transmit the usage information to the smart speaker 2C in response to a request from the smart speaker 2C.

[0382] In S2101, the microphone 206 of the smart speaker 2C collects ambient sound and acquires an audio signal. In S2102, the data analysis unit 201A of the smart speaker 2C analyzes the audio signal. Here, by performing speech recognition processing on the audio signal, speech recognition content such as "It seems that the business contact person I met at the company yesterday has influenza" is acquired. Also, here, by using voiceprint data, the speaker of this speech recognition content is identified. Further, from this speech recognition content, a disease name word, a location word, a date and time word, and a person word are extracted.

[0383] In S2103, the data analysis unit 201A of the smart speaker 2C generates regional infection information using the usage information transmitted from the mobile terminal 3A and the voice recognition content obtained in S2102, and stores it in the regional infection information DB9. As a result, data is stored in each column shown in the regional infection information DB9, and new regional infection information is added to the regional infection information DB9. For example, the identifier of the speaker is stored in the column of "corresponding person No.", the name of the infectious disease estimated from the disease name word is stored in the column of "estimated infectious disease name", the location and area estimated from the location word are stored in the columns of "location" and "area", the "epidemic period correction value" is determined from the time estimated from the date and time word, the estimated infectivity from the person word is stored in the column of "infectivity", and the usage information is stored in the column of "accompanying data".

[0384] In S2104, the data analysis unit 201A of the smart speaker 2C transmits the generated regional infection information to the mobile terminal 3A of the person with potential infection using the communication unit 205A. Here, the person with potential infection is a member of the family where the smart speaker 2C is installed, and the smart speaker 2C has previously stored the communication addresses of the mobile terminals 3A of each member in the memory 302. Therefore, the smart speaker 2C can transmit the regional infection information to the mobile terminal 3A of the person with potential infection. Also, each time the smart speaker 2C generates regional infection information, it may transmit the regional infection information to the corresponding mobile terminal 3A.

[0385] In S1104, the control unit 303A of the mobile terminal 3A associates the regional infection information transmitted in S2104 with the location information to generate association data. Here, the control unit 303A may read the movement information and search information for a certain period in the past (for example, 1 hour) after receiving the regional infection information from the movement information DB11 and the search information DB12 and include them in the association data.

[0386] In S1105, the communication unit 304 of the mobile terminal 3A transmits the association data generated in S1104 to the server 1B. Thereafter, the communication unit 304 of the mobile terminal 3A transmits it regularly (for example, The association data is sent to server 1B every hour (1 time per hour), and each time it is sent, the processing after S3102 is performed, and the mapping data will be updated regularly.

[0387] In S3101, the control unit 204A of server 1B accumulates the association data transmitted in S1105 in the memory 1002.

[0388] In S3102, the data analysis unit 1001 of server 1B generates mapping data from the association data accumulated in the memory 1002 and stores it in the mapping DB 1005. Here, the data analysis unit 1001 generates mapping data at predetermined time intervals, and may generate mapping data using the association data stored in the memory 1002 during the time from when the previous mapping data was generated to when the current mapping data is generated.

[0389] In S3103, the control unit 1003 of server 1B transmits a control command for operating the infection prevention sensor 20 to the infection prevention sensor 20 using the communication unit 1004. Here, the control unit 1003 may generate a control command according to the number of persons at risk of infection at the current time with reference to the "location" shown in FIG. 24. In the example of FIG. 24, at 10:00 on January 18, 2018, the number of persons at risk of infection in the star plaza of the AA shopping center is "8 persons". Also, assume that "8 persons" is equal to or greater than a predetermined threshold value. In this case, the control unit 1003 transmits a control command for operating the infection prevention sensor 20 installed in the star plaza to the infection prevention sensor 20. In this case, the control unit 1003 may transmit a control command for operating the infection prevention sensor 20 with a set value of purification ability corresponding to "8" persons. For example, if it is 1 to 5 persons, it is "weak", if it is 5 to 10 persons, it is "medium", and if it is more than 10 persons, it is "strong". If the set value is determined according to such a rule, the control unit 1003 may transmit a control command for operating with the "medium" set value to the infection prevention sensor 20. Here, the set value included in the control command is determined according to the number of persons at risk of infection, but this is just an example, and it may be determined according to the infection density at a specific location.

[0390] In S4101, the control unit 2003 of the infection prevention sensor 20 operates the infection prevention sensor 20 with set values according to the transmitted control commands.

[0391] In S4102, the control unit 2003 of the infection prevention sensor 20 transmits, using the communication unit 2004, the measurement data detected by each of the humidity sensor and the temperature sensor constituting the detection unit 2001 and the current set value stored in the memory 2002 to the server 1B.

[0392] In S3104, the data analysis unit 1001 of the server 1B reflects the measurement data in the mapping data. For example, assume that measurement data of temperature "24.5 degrees" and humidity "54%" and a set value "medium" are transmitted from the infection prevention sensor 20 installed in the star plaza of the AA shopping center at 10:00 on January 18, 2018. In this case, the data analysis unit 1001 may store "temperature: 24.5 degrees, humidity: 54%, set value: medium" in the "environmental information" column of "star plaza" at 10:00 on January 18, 2018 shown in FIG. 24.

[0393] In S1106, when a transmission instruction request is input from the user using the operation unit 306, the control unit 303A of the mobile terminal 3A transmits the request to the server 1B using the communication unit 304. For example, a provided application for providing the service of this information presentation system is installed in the mobile terminal 3A, and when the user inputs an operation to start this provided application, a request may be transmitted. Alternatively, when the user inputs a request to view map information using this provided application, a request may be transmitted. Alternatively, when the provided application detects that an existing route search application in the mobile terminal 3A has obtained a movement route to a certain destination from the server according to the user's instruction In this case, a request may be sent. In this case, a request may be sent to obtain mapping data for specific locations located around the movement route acquired by the route search application. Alternatively, if the provision application detects that the user has launched a map application on the mobile terminal 3A, a request may be sent to obtain mapping data for specific locations within a certain area from the central location of the map screen being viewed by the user.

[0394] In S3105, the communication unit 1004 of the server 1B transmits mapping data including the latest number of potential infected persons and environmental information from the mapping DB 1005 to the mobile terminal 3A. Note that various modes can be adopted regarding which mapping data of specific locations is to be transmitted. For example, if a request indicating a movement route is sent from the mobile terminal 3A, mapping data of specific locations located around the movement route may be transmitted. Also, mapping data of specific locations within a certain area around the current position of the mobile terminal 3A may be transmitted. Alternatively, when the user is viewing a map on the map application of the mobile terminal 3A, mapping data of specific locations within a certain area from the central location of the map screen may be transmitted. Or, mapping data of all specific locations stored in the mapping DB 1005 may be transmitted.

[0395] Here, in addition to temperature, humidity, set values, infection risk, and infection risk values, the server 1B may include the virus detection result by the virus sensor 4 as environmental information to be included in the mapping data to be transmitted. For example, if the virus sensor 4 is installed at the AA Shopping Center and the virus detection result can be obtained from this virus sensor 4, the server 1B may include the virus detection result at the AA Shopping Center in the mapping data.

[0396] FIG. 26 is a diagram showing display screens G1 and G2 displayed on the mobile terminal 3A that has received mapping data. The display screens G1 and G2 are generated by the control unit 303A of the mobile terminal 3A using the mapping data transmitted from the server 1B.

[0397] On the display screen G1, display columns 801 and 802 for displaying information regarding infectious diseases at each specific location are shown on the map image. Here, as the specific locations, AA Shopping Center and CC Supermarket are specified, so the display column 801 corresponding to the AA Shopping Center and the display column 802 corresponding to the CC Supermarket are shown. Note that the display screen G1 is displayed when the user launches the provided application or launches the map application.

[0398] In the display column 801, the number of persons with infection possibility, infection control measures, and infection risk at the AA Shopping Center are displayed. The number of persons with infection possibility indicates the latest number of persons with infection possibility at the AA Shopping Center stored in the mapping DB1005.

[0399] The infection control measures indicate the presence or absence of infection control measures at the AA Shopping Center. Here, since infection control measures have been taken, a double-circle mark and a button labeled "Details" are displayed. When an operation of selection by the user is input to the "Details" button, the control unit 303A switches the display screen from the display screen G1 to the display screen G2.

[0400] The infection risk is the infection risk calculated for the AA Shopping Center. Here, the infection risk is displayed as "Low", and advice information on infection control measures corresponding to "Low" is displayed. Here, advice information such as "Wash your hands and gargle when you get home" is displayed. Note that the advice information adopts a message predetermined according to the infection risks of "High", "Medium", and "Low".

[0401] In the display column 802, the same content as in the display column 801 is displayed. Note that in CC Supermarket, since infection prevention measures are not taken, "?" is displayed as an infection prevention measure, and the "Details" button is not displayed. Also, since the infection risk of CC Supermarket was calculated as medium, the infection risk is displayed as "Medium", and as advice information on infection prevention measures corresponding to "Medium", "Wear a mask when going out and wash your hands and gargle after returning home" is displayed.

[0402] The display screen G2 is a screen that displays detailed information on infection prevention measures at a specific location. Here, the detailed information of AA Shopping Center is displayed. The display screen G2 has four display columns R1 to R4. The display column R1 shows the infection prevention measures for the entire AA Shopping Center. Here, since infection prevention measures are being taken, the infection prevention measure is displayed as a double circle. Whether infection prevention measures are being taken or not is determined by, for example, the presence or absence of the operation of the infection prevention sensor 20. If the infection prevention sensor 20 is operating, a double circle is displayed, and if it is not operating, an "X" is displayed. Also, the infection risk value "340" for the AA Shopping Center is displayed in the display column R1.

[0403] The display column R2 shows the detailed information on infection prevention measures in the Star Square of the AA Shopping Center. Here, "Temperature: 24.5°C, Humidity: 54%, Air Cleaner Setting: Strong, Virus Sensor: No Reaction, Infection Risk: Low" is displayed. These information are the information included in the mapping data transmitted from the server 1B in S3103 of FIG. 25. The air cleaner setting indicates the set value of the infection prevention sensor 20.

[0404] The display column R3 shows the detailed information on infection prevention measures in the Moon Square of the AA Shopping Center. Here, the same information as in the Star Square is displayed.

[0405] The display column R4 shows the calculated infection possibility for the corresponding user by the smart speaker 2C installed in the home of the user of the corresponding mobile terminal 3A. Refer to FIG. 5. For example, assume that this mobile terminal 3A is "Taro" with the identifier "No. 1". In this case, the infection possibility of Taro stored in the regional infection information DB9 is displayed in the display column R4. If there are multiple infection possibilities regarding "Taro" stored in the regional infection information DB9, the average value of the infection possibilities included in the regional infection information for a certain period from the current time (for example, one day) may be displayed in the display column R4. Since the infection possibility can be calculated only for the user in whose home the smart speaker 2C is installed, the display in the display column R4 is omitted for the mobile terminal 3A of the user in whose home the smart speaker 2C is not installed.

[0406] The infection possibility may be calculated, for example, by the mobile terminal 3A obtaining the infection possibility of the corresponding user from the smart speaker 2C in the home when the provided application is launched.

[0407] Mapping data may be added with environmental information used for calculating the infection risk according to a specific location. FIG. 27 is a diagram showing another example of a display screen displayed on the mobile terminal 3A that has received the mapping data. In the example of FIG. 27, the specific location is a hospital (AB General Hospital). The display screen G3 corresponds to the display screen G1 in FIG. 26 and includes display columns 801 and 802 that display information related to infectious diseases. The display screen G4 corresponds to the display screen G2 in FIG. 26 and displays detailed information on infection prevention measures at a specific location. In the example of FIG. 27, an item of "number of infected patients today" is added to the display column R1. The item of "number of infected patients today" indicates the number of patients who were found to have an infectious disease among the patients who visited the AB General Hospital on the same day. Also, in the example of FIG. 27, infection prevention measure columns are provided in the display columns R2 and R3. When this column is selected, a display screen G5 indicating "infection prevention measures" is displayed. The display screen G5 displays items for infection prevention measures, such as "thorough wearing of masks", "classification of medical examinations for those at risk of infection", "ventilation implementation", and "installation of disinfectants", and evaluations corresponding to each item. The evaluation indicates the degree of implementation of the infection prevention measures. Here, symbols such as double circles (◎) and circles (〇, with a lower degree of implementation than ◎) are used for the evaluation.

[0408] As described above, according to this embodiment, the smart speaker 2C identifies the persons at risk of infection and the risk of infection with an infectious disease for the persons at risk of infection, and transmits regional infection information including the risk of infection to the mobile terminal 3A of the persons at risk of infection. Further, the mobile terminal 3A that has received the regional infection information transmits association data in which its own location information is associated with the regional infection information to the server 1B. Therefore, the server 1B can acquire the location information of the person at risk of infection from the mobile terminal 3A of the person at risk of infection, and can accurately and timely identify where and to what extent the persons at risk of infection are present. Then, mapping data in which the location thus identified is associated with the number of persons at risk of infection is transmitted to the mobile terminal 3A, and display screens G1 and G2 using the mapping data are displayed on the mobile terminal 3A. Therefore, the user of the mobile terminal 3A can recognize, for example, to what extent the persons at risk of infection are present at the place where the user is about to go, and can take appropriate infection prevention measures.

[0409] Note that the following modifications can be adopted in the fourth embodiment.

[0410] (4-1) In S1106 of the flow in FIG. 25, a request is transmitted from the mobile terminal 3A that has transmitted the association data to the server 1B, that is, the mobile terminal 3A of the person at risk of infection, but the present disclosure is not limited to this. For example, a request may be transmitted from a mobile terminal 3A of a person other than the person at risk of infection. In this case, in S3105, the server 1B may transmit the mapping data to the mobile terminal 3A of the corresponding person.

[0411] (4-2) In S4102 of the flow in FIG. 25, the server 1B receives the measurement data from the infection prevention sensor 20, but the present disclosure is not limited to this. For example, the server 1B may receive the measurement data of a specific location from the countermeasure information DB13. In this case, when the virus sensor 4 also accumulates the measurement data in the countermeasure information DB13, the server 1B may acquire, from the countermeasure information DB13, the measurement data of the virus sensor 4 in addition to the measurement data of the infection prevention sensor 20.

Industrial Applicability

[0412] According to the present disclosure, a technique useful for preventing the spread of infectious diseases can be provided.

Description of Signs

[0413] 1, 1A, 1B: Server 2, 2A, 2B, 2C: Smart Speaker 3, 3A: Mobile Terminal 4: Virus Sensor 13: Air Cleaner 15: External Server 20: Infection Countermeasure Sensor 101, 110: Processor 103, 130: Memory 111: Report Count Calculation Unit 112: Infection Risk Value Calculation Unit 113: Output Information Generation Unit 114: Social Information Acquisition Unit 201, 201A: Data Analysis Unit 202: Memory 203: Speaker 204, 204A: Control Unit 205, 205A: Communication Unit 206: Microphone 210: Processor 211: Infection Caution Level Identification Unit 212: Region Identification Unit 213: Region Infection Information Generation Unit 214: Report Count Calculation Unit 215: Infection Risk Value Calculation Unit 216: Output Information Generation Unit 217: Social Information Acquisition Unit 220: Microphone 230: Communication Unit 240: Speaker 250: Memory 301: GPS Sensor 302: Memory 303, 303A: Control Unit 304: Communication Unit 305: Display section 306: Operation section 1001: Data analysis section 1002: Memory 1003: Control section 1004: Communication section 10: Registration information DB 1005: Mapping DB 11: Movement information DB 12: Search information DB 14: Infection risk value DB 16: Countermeasure information DB 5: Patient number DB 50, DB50A: Regional infection information aggregation 7: Regional information DB 8: Infectious disease trend DB 9: Regional infection information DB

Claims

1. An information providing method in an information providing system including a voice recognition device and a server, for providing information related to infectious diseases, wherein the voice recognition device performs voice recognition on a voice signal based on a sound detected using a microphone, identifies a person with a possibility of being infected with the infectious disease and the possibility of infection of the person with the infectious disease, and transmits first infection information indicating the possibility of infection to a mobile terminal of the person with the possibility of infection, the mobile terminal to which the first infection information has been transmitted transmits association data in which the location information of the mobile terminal and the first infection information are associated to the server, the server uses a plurality of pieces of association data including the association data transmitted from a plurality of mobile terminals including the mobile terminal to generate mapping data associating a specific location on map data with the number of persons with a possibility of infection at the location, and transmits the mapping data to the mobile terminal of the person with the possibility of infection or a mobile terminal of a person different from the person with the possibility of infection, the mobile terminal of the person with the possibility of infection or the mobile terminal of the other person generates a display screen using the mapping data and displays the display screen on a display, Information providing method.

2. The voice recognition device estimates the infectious disease with which the person with the possibility of infection is infected from the speech content of the voice signal, The information providing method according to claim 1.

3. The server calculates an infection risk at the location using the number of persons with a possibility of infection, the mapping data includes the infection risk and advice information on infection prevention measures according to the infection risk, The information providing method according to claim 1 or 2.

4. The mapping data includes measurement data of a sensor installed at the location and measuring environmental information of the location, The information providing method according to any one of claims 1 to 3.

5. The information providing system further includes an external server, The voice recognition device identifies a location related to the infectious disease and an infection attention level for the location from the voice signal, and transmits second infection information indicating the location and the infection attention level to the external server, The external server receives a plurality of pieces of second infection information including the second infection information, calculates the number of reports for each infection attention level at each location by classifying the plurality of pieces of second infection information for each location and infection attention level, performs weighting according to each infection attention level on the calculated number of reports, and calculates an infection risk value for each location by evaluating the weighted number of reports, The server acquires the infection risk value for each location from the external server, The mapping data includes the infection risk value at each location, The information providing method according to any one of claims 1 to 4.

6. The display screen is a screen in which the number of possible infected persons at the location is superimposed on a map image, The information providing method according to any one of claims 1 to 5.

7. The server transmits the mapping data in response to a request from the mobile terminal, The information providing method according to any one of claims 1 to 6.

8. An information providing system for providing information on infectious diseases, The information providing system includes a voice recognition device, a plurality of mobile terminals, and a server, The voice recognition device performs voice recognition on a voice signal based on a voice detected using a microphone, identifies a possible infected person who may be infected with the infectious disease and the possibility of infection of the possible infected person with the infectious disease, and transmits first infection information including the possibility of infection to the mobile terminal of the possible infected person among the plurality of mobile terminals, The mobile terminal to which the first infection information is transmitted transmits association data associating the location information of the mobile terminal and the first infection information to the server, The server generates mapping data that associates a specific location on map data with the number of infection - possible persons at the location, using a plurality of association data including the association data transmitted from the plurality of mobile terminals, and transmits the mapping data to the mobile terminal of the infection - possible person or another mobile terminal among the plurality of mobile terminals, The mobile terminal or the other mobile terminal generates a display screen using the mapping data and displays it on a display. Information providing system.

Images