System, server device, and method and program for controlling server device

Abstract

Provided is a system that contributes to achieving safe and secure child-rearing. The system includes a first terminal, a second terminal, and a server device. The first terminal is worn by a first user and records audio data of the first user. The second terminal is used by a second user. The server device communicates with at least the second terminal. The server device: analyses the audio data of the first user; generates an analysis report about the first user on the basis of the analysis results; and sends the generated analysis report to the second terminal.

Description

[Technical field]

[0001] The present invention relates to a system, a server device, a control method for a server device, and a storage medium. [Background technology]

[0002] There are systems that provide various information by utilizing voice information, position information, and the like of users.

[0003] For example, Patent Document 1 describes that a technology is provided that can detect harmful behaviors such as power harassment, sexual harassment, and bullying in a workplace environment and support dealing with them. The harmful behavior detection system of Patent Document 1 includes an information terminal and a server as a computer that observes and detects harmful behaviors including power harassment, sexual harassment, and bullying among people in a workplace environment. The computer acquires voice data inputted from the voices around the subject, acquires voice information including words and emotion information from the voice data, and acquires data such as vital data, date and time, and location of the subject. The computer calculates an index value for harmful behaviors using five elements, namely the words and emotions of others, the words and emotions of the subject, and the vital data, estimates the state of the harmful behavior based on the index value, and outputs dealing data for dealing with the harmful behavior according to the estimated state.

[0004] Patent Document 2 describes that the use of multiple smart speakers enables appropriate information provision. The information processing device of Patent Document 2 has an acquisition unit and a determination unit. The acquisition unit acquires sensor information detected by either one of a first terminal device arranged in a user's house and a second terminal device arranged in the user's mobile body. The determination unit determines information to be provided by one of the terminal devices based on emotion information indicating the emotion of a target user located around the one terminal device estimated by the sensor information.

[0005] Patent Document 3 describes a method for forming a group by a simple method, and for notifying a user when the user leaves the group without incurring any costs. The mobile communication device in Patent Document 3 includes a registration processing unit, a transmission processing unit, and a reception processing unit. The registration processing unit stores an input common group code in a memory unit to form a group. The transmission processing unit periodically transmits a call signal by the common group code stored in the memory unit from the short-range communication unit according to a transmission cycle. The reception processing unit receives a call signal including the common group code transmitted by another mobile communication device by the short-range communication unit, and issues a warning when the call signal including the common group code cannot be received for a time period equal to or longer than the separation warning time. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2020-123204 A [Patent Document 2] JP 2020-030535 A [Patent Document 3] JP 2007-074574 A Summary of the Invention [Problem to be solved by the invention]

[0007] Many parents have concerns about raising children. In particular, in households where both spouses work, parents may not have enough time to talk to their children. Also, since "accidental accidents" are one of the leading causes of death in children, parents who go out with their children are required to keep a close eye on them. However, these problems regarding raising children cannot be solved by applying the technologies disclosed in Patent Documents 1 to 3. For example, the technology disclosed in Patent Document 1 is intended to detect power harassment, sexual harassment, and the like, and cannot prevent accidental accidents involving children.

[0008] The main object of the present invention is to provide a system, a server device, a control method for a server device, and a storage medium that contribute to realizing safe and secure child-rearing. [Means for solving the problem]

[0009] According to a first aspect of the present invention, there is provided a system including a first terminal worn by a first user and recording voice data of the first user, a second terminal used by a second user, and a server device that communicates with at least the second terminal, wherein the server device analyzes the voice data of the first user, generates an analysis report on the first user based on the analysis results, and transmits the generated analysis report to the second terminal.

[0010] According to a second aspect of the present invention, there is provided a server device comprising: an analysis report generation unit that analyzes voice data of a first user recorded on a first terminal worn by the first user and generates an analysis report regarding the first user based on the analysis results; and a transmission unit that transmits the generated analysis report to a second terminal used by a second user.

[0011] According to a third aspect of the present invention, there is provided a method for controlling a server device, in which a server device analyzes voice data of a first user recorded on a first terminal worn by the first user, generates an analysis report on the first user based on the analysis results, and transmits the generated analysis report to a second terminal used by a second user.

[0012] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a program for causing a computer mounted on a server device to execute the following processes: analyzing voice data of a first user recorded on a first terminal worn by the first user, and generating an analysis report regarding the first user based on the analysis results; and transmitting the generated analysis report to a second terminal used by a second user. Effect of the Invention

[0013] According to each aspect of the present invention, a system, a server device, a control method for a server device, and a storage medium are provided that contribute to realizing safe and secure child-rearing. Note that the effects of the present invention are not limited to the above. The present invention may achieve other effects instead of or in addition to the effects. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram for explaining an overview of an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a schematic configuration of the information processing system according to the first embodiment. [Diagram 3] FIG. 3 is a diagram for explaining the operation of the information processing system according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a processing configuration of the child terminal according to the first embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a processing configuration of a parent terminal according to the first embodiment. [Figure 6] FIG. 6 is a diagram for explaining the operation of the child terminal management unit according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a processing configuration of the server device according to the first embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of the operation of the analysis report generating unit according to the first embodiment. [Figure 9] FIG. 9 is a diagram for explaining the operation of the analysis report generating unit according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of table information used by the analysis report generating unit according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 16] FIG. 16 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 17] FIG. 17 is a diagram illustrating an example of an analysis report according to the first embodiment. [Figure 18] FIG. 18 is a sequence diagram illustrating an example of the operation of the information processing system according to the first embodiment. [Figure 19] FIG. 19 is a diagram illustrating an example of a processing configuration of a parent terminal according to the second embodiment. [Figure 20] FIG. 20 is a diagram illustrating an example of table information used by the warning unit according to the second embodiment. [Figure 21] FIG. 21 is a diagram illustrating an example of a processing configuration of a child terminal according to the second embodiment. [Figure 22] FIG. 22 is a diagram illustrating an example of a processing configuration of a server device according to a modification of the second embodiment. [Diagram 23] FIG. 23 is a diagram illustrating an example of a processing configuration of a server device according to the third embodiment. [Figure 24] FIG. 24 is a diagram illustrating an example of a hardware configuration of a server device according to the present disclosure. [Diagram 25] FIG. 25 is a diagram illustrating an example of a processing configuration of a server device according to a modification of the present disclosure. [Figure 26] FIG. 26 is a diagram illustrating an example of a processing configuration of a server device according to a modification of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] First, an outline of one embodiment will be described. The reference numerals in the drawings are added to each element for convenience as an example to aid in understanding, and the description of the outline is not intended to be limiting. Furthermore, unless otherwise specified, the blocks shown in each drawing represent functional units rather than hardware units. The connection lines between the blocks in each drawing include both bidirectional and unidirectional. The unidirectional arrows are used to diagrammatically indicate the flow of the main signal (data) and do not exclude bidirectionality. In this specification and the drawings, elements that can be similarly described may be given the same reference numerals to avoid redundant description.

[0016] The system according to one embodiment includes a first terminal 101, a second terminal 102, and a server device 103 (see FIG. 1). The first terminal 101 is worn by a first user and records voice data of the first user. The second terminal 102 is a terminal used by the second user. The server device 103 communicates with at least the second terminal 102. The server device 103 analyzes the voice data of the first user, generates an analysis report on the first user based on the analysis result, and transmits the generated analysis report to the second terminal 102.

[0017] In the above system, the voice of a first user (e.g., a child) who is active away from a second user (e.g., a parent) is collected. The server device 103 generates an analysis report including information useful to the parent by analyzing the collected voice of the child. For example, the analysis report includes what the child is thinking, what the child is interested in, what the child is saying, etc. In a dual-income household, both parents are busy and often have limited time to spend with their child. Even if the parents do not have time to spend with their child and are unable to fully listen to what the child has to say, the parents can accurately grasp what the child is thinking, what the child is interested in, etc. in a short time by checking the analysis report. By accurately grasping the actual situation regarding the child's daily life, the parents can easily grasp the problems that the child is experiencing. In other words, a safe and secure child-rearing environment is realized.

[0018] Specific embodiments will be described in more detail below with reference to the drawings.

[0019] [First embodiment] The first embodiment will be described in more detail with reference to the drawings.

[0020] [System configuration] Fig. 2 is a diagram showing an example of a schematic configuration of an information processing system according to the first embodiment. As shown in Fig. 2, the information processing system includes a server device 10, a child terminal 20, and a parent terminal 30.

[0021] The server device 10 is a device that provides various services to users. For example, the server device 10 provides useful information to guardians (second users; parents, grandparents, etc.) of children (first users; infants, children, etc.). The server device 10 may be installed in a building of a system operating company, etc., or may be installed on a network (cloud).

[0022] The child terminal 20 is attached to an infant, a child, or the like, whose behavior needs to be carefully monitored. The child terminal 20 is a device carried by a person to be monitored, such as an infant. The child terminal 20 has a key ring shape so that it can be attached to clothing, a school bag, or the like. The child terminal 20 includes a microphone, a storage medium such as a USB (Universal Serial Bus) memory, and a communication circuit such as Bluetooth (registered trademark). The child terminal 20 is attached to a child and is a device that records the voice data of the child.

[0023] The parent terminal 30 is a terminal used by a parent or guardian, etc. The parent or guardian uses the parent terminal 30 to manage the child terminal 20 and to receive information from the server device 10.

[0024] The server device 10 and the parent terminal 30 are configured to be able to communicate with each other by wireless communication means such as 4G (4th Generation) or 5G (5th Generation). The child terminal 20 and the parent terminal 30 are configured to be able to communicate with each other by short-range wireless means such as Bluetooth (registered trademark). The server device 10 is configured to be able to communicate with at least the parent terminal 30.

[0025] [Operation overview] Next, an outline of the operation of the information processing system according to the first embodiment will be described.

[0026] Here, the operation modes of the child terminal 20 include a "data collection mode" and a "walk mode."

[0027] The data collection mode is a mode in which the child terminal 20 collects the child's speech (voice data). The information processing system uses the collected data to generate data that can grasp the child's situation, condition, environment, etc., and provides it to the guardian (parent, grandparent, etc.).

[0028] The walk mode is a mode for ensuring the safety of a child (a person to be watched over) when the child and the guardian act together (for example, when going for a walk together). Details of the walk mode will be described in the second embodiment.

[0029] A child (an infant, a young child, etc.) moves around at school etc. while carrying the child terminal 20. The child terminal 20 collects the child's voice using a microphone and records it on a storage medium.

[0030] When the child returns home, the child terminal 20 and the parent terminal 30 communicate with each other via Bluetooth (registered trademark) etc. The parent terminal 30 acquires the voice data (child's voice data) recorded in the child terminal 20 (see FIG. 3).

[0031] The parent terminal 30 transmits the acquired voice data to the server device 10.

[0032] The server device 10 analyzes the voice data of the child and generates an analysis report on the child (the person being watched over) based on the analysis result. The server device 10 transmits the generated analysis report to the parent terminal 30.

[0033] For example, the server device 10 analyzes the voice data and calculates the child's emotions (happy, sad, fun, bored, depressed, emotionally unstable, etc.). The server device 10 generates an "analysis report" based on the calculated emotions and transmits it to the parent terminal 30.

[0034] Alternatively, the server device 10 may analyze the voice data and calculate the child's interests (such as subjects of interest). The server device 10 may generate an "analysis report" based on the calculated interests.

[0035] The guardian who receives the analysis report via the guardian terminal 30 can take appropriate action based on the notified child's feelings and interests, realizing safe child rearing. Specifically, guardians (parents, grandparents, etc.) can understand the child's daily interests through the analysis report. For example, if a child attends a nursery school during the daytime on weekdays (8:00 to 18:00), voice data from the nursery school is transmitted to the server device 10 via the guardian terminal 30, and an analysis report is generated. For example, if a child who is usually active becomes depressed throughout the day, the parent can take action such as interacting with the child attentively.

[0036] Next, each device included in the information processing system according to the first embodiment will be described in detail.

[0037] [Children's device] Fig. 4 is a diagram showing an example of a processing configuration (processing module) of the child terminal 20 according to the first embodiment. Referring to Fig. 4, the child terminal 20 includes a communication control unit 201, a mode management unit 202, a voice data acquisition unit 203, a voice data management unit 204, and a storage unit 205.

[0038] The communication control unit 201 is a means for controlling communication with other devices. For example, the communication control unit 201 receives data (packets) from the parent terminal 30. The communication control unit 201 also transmits data to the parent terminal 30. The communication control unit 201 passes data received from other devices to other processing modules. The communication control unit 201 transmits data acquired from other processing modules to other devices. In this way, the other processing modules transmit and receive data to and from other devices via the communication control unit 201. The communication control unit 201 has a function as a receiving unit that receives data from other devices and a function as a transmitting unit that transmits data to other devices.

[0039] The communication control unit 201 communicates with another device (parent terminal 30) using a short-range wireless communication means such as Bluetooth (registered trademark). When the communication control unit 201 detects the parent terminal 30 as a communication partner, it notifies other modules, particularly the audio data management unit 204, to that effect. For example, when Bluetooth (registered trademark) is used, when pairing with the parent terminal 30 is successful, the other modules are notified to that effect.

[0040] The mode management unit 202 is a means for managing the operation mode of the child terminal 20. The mode management unit 202 acquires the operation mode of the child terminal 20 from the user (mainly, the guardian) using any means.

[0041] For example, the mode management unit 202 may acquire the operation mode of the child terminal 20 by communicating with the parent terminal 30. Alternatively, the mode management unit 202 may acquire the operation mode by a hardware key (for example, a mode switching button) provided in the child terminal 20.

[0042] In the first embodiment, a case where the "data collection mode" is set as the operation mode of the child terminal 20 will be described.

[0043] The audio data acquisition unit 203 is a means for acquiring the child's audio data. The audio data acquisition unit 203 acquires the child's audio and records the acquired audio in a storage medium. For example, the audio data acquisition unit 203 acquires an audio file related to the audio collected by a microphone, and records an encoded audio file (audio data) such as a WAV file (Waveform Audio File) or an MP3 (MPEG-1 Audio Layer-3) file in the storage medium.

[0044] The voice data acquisition unit 203 constantly acquires voice data and records it in a storage medium while the child terminal 20 is powered on. The voice data acquisition unit 203 also stores the recording date and time of the voice data in the storage medium.

[0045] The voice data management unit 204 is a means for managing voice data (voice files) recorded in a storage medium. For example, the voice data management unit 204 deletes voice data recorded in a storage medium according to an instruction from a user (e.g., a guardian).

[0046] Furthermore, when the child terminal 20 detects the parent terminal 30, the voice data management unit 204 transmits the voice data recorded in the storage medium to the parent terminal 30. When the voice data management unit 204 has completed transmitting the voice data, it may delete the voice data from the storage medium.

[0047] The storage unit 205 is a means for storing information necessary for the operation of the child terminal 20. The storage unit 205 stores voice data.

[0048] [Parent device] Examples of the parent terminal 30 include a mobile terminal device such as a smartphone, a mobile phone, a game machine, a tablet, etc., a computer (personal computer, notebook computer), etc. The parent terminal 30 can be any equipment or device that can accept operations by the parent and communicate with the server device 10, etc.

[0049] Fig. 5 is a diagram showing an example of a processing configuration (processing module) of the parent terminal 30 according to the first embodiment. Referring to Fig. 5, the parent terminal 30 includes a communication control unit 301, a child terminal management unit 302, an analysis report request unit 303, an analysis report output unit 304, and a storage unit 305.

[0050] The communication control unit 301 is a means for controlling communication with other devices. For example, the communication control unit 301 receives data (packets) from the server device 10 and the child terminal 20. The communication control unit 301 also transmits data to the server device 10 and the child terminal 20. The communication control unit 301 passes the data received from the other devices to the other processing modules. The communication control unit 301 transmits the data acquired from the other processing modules to the other devices. In this way, the other processing modules transmit and receive data to and from the other devices via the communication control unit 301. The communication control unit 301 has a function as a receiver that receives data from the other devices and a function as a transmitter that transmits data to the other devices.

[0051] The communication control unit 301 communicates with another device (child terminal 20) using a short-range wireless communication means such as Bluetooth (registered trademark). The communication control unit 301 communicates with the server device 10 using a mobile line or an Internet line.

[0052] The child terminal management unit 302 is a means for managing the child terminal 20. For example, the child terminal management unit 302 manages and sets the operation mode of the child terminal 20. For example, the child terminal management unit 302 displays a GUI (Graphical User Interface) as shown in FIG. 6 in response to a predetermined operation by a user (guardian). The child terminal management unit 302 uses the GUI to obtain the operation mode to be set in the child terminal 20. The child terminal management unit 302 notifies the child terminal 20 of the obtained operation mode.

[0053] When the child terminal 20 and the parent terminal 30 are in close proximity to each other, notification (setting) of the operation mode is performed. This is because communication between these devices is performed by a communication means such as Bluetooth (registered trademark). Also, as described above, when the operation mode of the child terminal 20 is set by a hardware key or the like of the device, notification and setting of the operation mode from the parent terminal 30 is not required.

[0054] The analysis report request unit 303 is a means for requesting the server device 10 to provide an analysis report. The analysis report request unit 303 acquires voice data from the child terminal 20. The analysis report request unit 303 transmits an “analysis report request” including the acquired voice data to the server device 10.

[0055] The analysis report output unit 304 is a means for outputting the analysis report provided by the server device 10. For example, the analysis report output unit 304 outputs the analysis report to a display device such as a liquid crystal panel. Alternatively, the analysis report output unit 304 may output the contents of the analysis report from an audio device such as a speaker.

[0056] The storage unit 305 is a means for storing information necessary for the operation of the parent terminal 30 .

[0057] [Server device] 7 is a diagram showing an example of a processing configuration (processing module) of the server device 10 according to the first embodiment. Referring to FIG. 7, the server device 10 includes a communication control unit 401, an analysis report generating unit 402, and a storage unit 403.

[0058] The communication control unit 401 is a means (communication unit) for controlling communication with other devices. For example, the communication control unit 401 receives data (packets) from the parent terminal 30. The communication control unit 401 also transmits data to the parent terminal 30. The communication control unit 401 passes the data received from the other devices to the other processing modules. The communication control unit 401 transmits data acquired from the other processing modules to the other devices. In this way, the other processing modules transmit and receive data to and from the other devices via the communication control unit 401. The communication control unit 401 has a function as a receiving unit that receives data from the other devices and a function as a transmitting unit that transmits data to the other devices.

[0059] The analysis report generating unit 402 is a means for generating an analysis report. The analysis report generating unit 402 analyzes the voice data of a child (infant, child) acquired via the parent terminal 30, and generates an analysis report.

[0060] The operation of the analysis report generating unit 402 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the operation of the analysis report generating unit 402.

[0061] The analysis report generating unit 402 extracts valid voice data from the acquired voice data (extraction of voice data; step S101). More specifically, the analysis report generating unit 402 extracts voice data containing substantial information. For example, when voice data as shown in FIG. 9 is to be analyzed, the analysis report generating unit 402 extracts voice data contained in each period between times t1 and t2 and between times t3 and t4 as "voice data". Since existing technology can be used to extract the voice data, detailed description will be omitted. For example, the analysis report generating unit 402 extracts a section in which signal energy equal to or greater than a predetermined threshold continues as voice data.

[0062] The analysis report generating unit 402 calculates, for each of the extracted voice data, the child's emotion when the voice corresponding to the voice data is uttered (step S102).

[0063] For example, the analysis report generating unit 402 obtains the child's emotions by inputting the extracted audio data into a learning model prepared in advance. The learning model is obtained by preparing a large amount of voice data to which labels (emotions) are assigned, and learning the large amount of voice data as teacher data. For example, a label such as "happy" is assigned to voice data with a bright tone (tone of voice), and a label such as "sad" is assigned to voice data with a dark tone.

[0064] The analysis report generating unit 402 extracts keywords contained in each of the extracted voice data (step S103).

[0065] The analysis report generating unit 402 converts the contents recorded in the audio data into text using a voice recognition technique. The analysis report generating unit 402 can convert the voice into text using existing voice recognition processing, so a detailed description will be omitted, but the analysis report generating unit 402 performs the following process in summary.

[0066] The analysis report generating unit 402 performs a filter process to remove noise and the like from the sound data. Next, the analysis report generating unit 402 identifies phonemes from the sound waves of the sound data. A phoneme is the smallest building block of a word. The analysis report generating unit 402 identifies a sequence of phonemes and converts them into words. The analysis report generating unit 402 creates a sentence from the sequence of words and generates a text file.

[0067] The analysis report generating unit 402 extracts keywords from the text file. For example, the analysis report generating unit 402 refers to an extracted keyword list in which keywords to be extracted are described in advance, and extracts the keywords described in the list from the text file. Alternatively, the analysis report generating unit 402 may extract nouns contained in the text file as keywords. Note that the analysis report generating unit 402 may use an existing part-of-speech analysis tool (application) or the like when extracting nouns.

[0068] The analysis report generating unit 402 stores the extracted voice data, the calculated emotion of the child, the extracted keywords, etc. (see FIG. 10). As shown in FIG. 10, the ID (IDentifier) ​​of the voice data, the time when the voice data (voice data) was recorded, the emotion, the keyword, etc. are stored in association with each other. In FIG. 10, the start time of the voice data is used as the time when the voice data was recorded.

[0069] When the pre-processing of the voice data (extraction of voiced data, calculation of emotions, extraction of keywords) is completed, the analysis report generating unit 402 generates an analysis report (step S104). The analysis report generating unit 402 can generate analysis reports from various viewpoints.

[0070] <Emotion analysis report> The analysis report generating unit 402 quantifies the child's emotion when the keyword was uttered as an "emotion score." For example, the analysis report generating unit 402 calculates the emotion score by assigning a positive value to positive emotions such as "fun" and "happy." On the other hand, the analysis report generating unit 402 calculates the emotion score by assigning a negative value to negative emotions such as "boredom" and "sad."

[0071] The analysis report generating unit 402 can calculate the emotion score by referring to table information that stores emotions in association with emotion scores to be assigned to the emotions. Alternatively, the analysis report generating unit 402 may acquire the emotion score using a learning model that outputs an emotion score when a child's voice data (voice data) is input.

[0072] The analysis report generating unit 402 generates an analysis report that visualizes the time change of the quantified emotion (emotion score) (change of the child's emotion during the audio data collection period). For example, in the example of Fig. 10, the emotion in the section with the audio data ID "aID01" is "fun", so the analysis report generating unit 402 assigns a positive value as the emotion score of the section. In contrast, the emotion in the section with the audio data ID "aID02" is "bored", so the analysis report generating unit 402 assigns a negative value as the emotion score of the section.

[0073] The analysis report generating unit 402 generates a graph as shown in Fig. 11 as an "analysis report" based on the emotion scores calculated above. The graph as shown in Fig. 11 is referred to as an "emotion graph." In this way, the analysis report generating unit 402 may use the emotion scores to generate an emotion graph showing the change over time in the child's emotions.

[0074] <Analysis report on comments> The analysis report generating unit 402 may generate an analysis report on the child's utterances. As described above, the analysis report generating unit 402 extracts predetermined keywords from the words uttered by the child. The analysis report generating unit 402 counts the number of times each extracted keyword is uttered.

[0075] For example, the analysis report generating unit 402 arranges the keywords uttered by the child in descending order and generates an analysis report. The analysis report generating unit 402 generates table information such as that shown in Fig. 12 as an "analysis report". That is, the analysis report generating unit 402 compiles keywords that are repeatedly uttered by the child as a "comment list" and generates an analysis report. In this way, the analysis report generating unit 402 may generate a comment list that includes the number of times each extracted keyword was uttered.

[0076] <Analysis report on topics of interest> The analysis report generating unit 402 may generate an analysis report on the child's interests from the keywords uttered by the child. The analysis report generating unit 402 classifies each keyword uttered by the child (keywords extracted as shown in FIG. 10) into predetermined interests.

[0077] For example, in the example of FIG. 12, "Character A1" and "Character A2" are sorted into "Animation A." Note that Character A1 and Character A2 are keywords that have a certain relationship. For example, the characters that appear in Animation A are "Character A" and "Character B." These character names are classified into the interest "Animation A (Anime A)."

[0078] Or, "Animal B" and "Animal C" might be grouped under "Animals." For example, keywords like "cats" and "dogs" might be grouped under the "Animals" interest.

[0079] The analysis report generating unit 402 calculates the number of each interest converted from a keyword (the total number of keywords corresponding to each interest) as an "interest score." For example, in the example of Fig. 12, "Character A1" and "Character A2" correspond to the interest "Animation A," so the interest score of animation A is "18." Similarly, the interest score of animals is "9."

[0080] For example, the analysis report generating unit 402 arranges each of the concerns in descending order of the concern score to generate a "concern list." For example, the analysis report generating unit 402 generates a concern list as shown in FIG.

[0081] The system designer, administrator, etc. may decide how to convert the keywords into topics of interest. For example, the analysis report generating unit 402 may treat the keywords as topics of interest as they are. In the above example, "character A", "character B", "cats", and "dogs" may be treated as topics of interest.

[0082] A system administrator or the like registers table information for converting keywords into matters of interest in the server device 10. The analysis report generating unit 402 may calculate matters of interest from keywords by referring to the table information. Alternatively, the analysis report generating unit 402 may calculate matters of interest by inputting keywords into a learning model prepared in advance.

[0083] In this way, the analysis report generating unit 402 may generate an interest list based on keywords uttered by the child. More specifically, the analysis report generating unit 402 may generate an interest list in which the interests of the child are arranged in order based on the number of times the keywords extracted from the child's voice data are uttered.

[0084] If a person's name (for example, the name of a friend who attends the same nursery school as the child) is extracted as a keyword, the analysis report generating unit 402 can generate a "child of interest (list) ranking" for the child.

[0085] <Analysis report on topics of interest that take into account emotions> The analysis report generating unit 402 may generate a list of interests while considering the child's emotions. For example, the analysis report generating unit 402 calculates the score of each interest (interest score) by adding up the emotion scores when a keyword corresponding to each interest (for example, character A1 and character A2 corresponding to animation A) is uttered.

[0086] For example, in the above example, the analysis report generation unit 402 calculates the interest score for animation A by adding the emotion score when character A1 corresponding to animation A is spoken and the emotion score when character A2 is spoken.

[0087] 12, for example, consider a case where the number of times that character A1 has spoken is "10," the number of times that character A2 has spoken is "8," and the emotion score for the emotion "fun" when the keyword is spoken is set to "10." In this case, the interest score for animation A is calculated to be 180 (10×10+8×10=180).

[0088] 12, consider a case where the number of comments made by animal B is "5" and the number of comments made by animal C is "4", and the emotion score for the emotion "boredom" when the keyword is said is set to "-10". In this case, the interest scores of the animals are calculated as -90 (5 x (-10) + 4 x (-10) = -90).

[0089] In this way, the analysis report generating unit 402 may generate a list of the child's interests based on the number of times each extracted keyword is said and the emotion score corresponding to each keyword. Note that even if the same keyword is used, the emotion at the time of the statement may differ. For example, even if a child makes a statement about the character A1, the emotion at the time may be "fun" or "bored." Even in such a case, the analysis report generating unit 402 calculates the interest score using the emotion score assigned to each emotion, so that the child's interests can be accurately calculated.

[0090] When calculating a list of interests taking emotion into consideration, for example, a list of interests such as that shown in Fig. 14 is obtained. Referring to Figs. 13 and 14, it can be seen that the ranking of each interest changes significantly by taking into consideration the emotion when the keyword was uttered.

[0091] The analysis report generating unit 402 may generate an analysis report by identifying what the child is most interested in and what he or she is least interested in from the interest list as shown in Fig. 13 or 14. For example, by extracting the most interesting and least interesting things from the interest list shown in Fig. 14, an analysis report as shown in Fig. 15 is generated.

[0092] In this way, the analysis report generating unit 402 can calculate the child's interests from the child's comments. In this case, the analysis report generating unit 402 may calculate the strength of the interest from the number of times a keyword is said. In other words, the analysis report generating unit 402 treats a keyword that is said many times as one that the child is highly interested in. Alternatively, the analysis report generating unit 402 can generate an analysis report that can grasp the child's interests more accurately by calculating the interest taking into account the child's feelings when the keyword is said.

[0093] <Sentiment graph and interest score> The analysis report generating unit 402 may generate the analysis report by combining the child's emotions and interests. More specifically, the analysis report generating unit 402 may generate the analysis report by reflecting all or a part of the interests included in the interest list in the emotion graph.

[0094] For example, the analysis report generating unit 402 generates an analysis report by displaying a subject of interest at the time when a keyword corresponding to the subject of interest was uttered in the emotion graph. For example, when a comment on the subject of interest "animation A" is reflected in the emotion graph, an analysis report such as that shown in FIG. 16 is obtained.

[0095] The analysis report generating unit 402 can reflect all or some of the interests listed in the interest list in the emotion graph. Specifically, as shown in Fig. 16, the interest in which the child is most interested may be reflected in the emotion graph, or as shown in Fig. 17, the interest in which the child is least interested may also be reflected in the emotion graph.

[0096] The analysis report generating unit 402 transmits the generated analysis report to the parent terminal 30 (step S105 in FIG. 8).

[0097] The storage unit 403 is a means for storing information necessary for the operation of the child terminal 20 .

[0098] [System Operation] Next, a description will be given of the operation of the information processing system according to the first embodiment. Fig. 18 is a sequence diagram showing an example of the operation of the information processing system according to the first embodiment.

[0099] The child terminal 20 records the child's voice data (step S01).

[0100] When the child terminal 20 detects the parent terminal 30 (when pairing is successful), the child terminal 20 transmits the recorded voice data to the parent terminal 30 (step S02).

[0101] The parent terminal 30 transmits an analysis report request including the voice data to the server device 10 (step S03).

[0102] The server device 10 analyzes the voice data and generates an analysis report (step S04).

[0103] The server device 10 transmits the generated analysis report to the parent terminal 30 (step S05).

[0104] The parent terminal 30 outputs an analysis report (step S06). For example, the parent terminal 30 outputs an analysis report including contents and information as shown in Figs.

[0105] For example, a user (parent) who sees an analysis report such as that shown in Fig. 11 can know that the emotion score is negative between times t3 and t4. The parent can then ask the child about events that occurred during that time period.

[0106] For example, a user (guardian) who sees an analysis report like that shown in Fig. 12 can know that the child often makes comments about characters A1 and A2. The guardian can plan an event (such as a trip) related to the child's interests.

[0107] For example, a user (guardian) who sees an analysis report such as those shown in Fig. 13 to Fig. 15 can learn about the things that interest their child. In particular, by seeing an interest list generated in consideration of emotions such as those shown in Fig. 14, the guardian can learn more accurately about the interests of the child. The guardian can use the interests to help with future education, etc.

[0108] For example, a user (guardian) who sees an analysis report such as that shown in FIG. 16 can know that the child is happy and enjoying the events related to animation A.

[0109] Alternatively, a user (guardian) who sees an analysis report such as that shown in FIG. 17 can learn that the child is happy when an event related to animation A occurs, but is bored when an event related to animals occurs.

[0110] As shown in step S03 of FIG. 18, the parent terminal 30 can transfer the voice data received from the child terminal 20 to the server device 10, but the parent terminal 30 may prohibit the parent from checking the contents of the voice data (child's voice). Alternatively, the parent terminal 30 may permit the parent to check the voice data together with the analysis report after receiving the analysis report from the server device 10. More specifically, the parent terminal 30 may not permit the parent to check the voice data at step S03 shown in FIG. 18, but may permit the parent to check the voice data after step S06. By taking such measures, a system that takes into consideration the privacy of the people (children, their friends, etc.) from whom the voice data is collected is constructed.

[0111] As described above, the information processing system according to the first embodiment collects the voice of a child who is active away from his / her parents. The server device 10 can provide useful information to parents by analyzing the collected voice of the child. Parents can know what their children are thinking, what interests them, what they say, etc. through the analysis report. In particular, in households where both parents work, both parents are often busy and have limited time to spend with their children. Even if parents do not have time to spend with their children and cannot fully listen to what their children say, they can accurately grasp what the children are thinking, what they are interested in, etc. in a short time. In addition, if a parent confirms signs of bullying in the comments, the parent can have an opportunity to discuss the signs of bullying with the child. In this way, by accurately grasping the actual situation regarding the child's daily life, the problem can be dealt with before it becomes serious. In other words, safe and secure child-rearing is realized.

[0112] [Second embodiment] Next, the second embodiment will be described in detail with reference to the drawings.

[0113] In the first embodiment, a guardian refers to the analysis report to understand the daily life of the child and take measures as necessary. In the second embodiment, a guardian and a child are monitored when they act together.

[0114] For example, in the second embodiment, it is assumed that when a child requests to go out with his / her grandparents, the parent requests the grandparents to take a walk with the child. However, the purpose is not to limit the people who take a walk with the child to the grandparents, and the parent or a relative may take a walk with the child. In this case, the grandparent operates the guardian terminal 30 that he / she owns to set the operation mode of the child terminal 20 to "walk mode."

[0115] The configuration of the information processing system according to the second embodiment can be the same as that of the first embodiment, so a description corresponding to FIG. 2 will be omitted.

[0116] The following description will focus on the differences between the first and second embodiments.

[0117] Fig. 19 is a diagram showing an example of a processing configuration (processing module) of the parent terminal 30 according to the second embodiment. Referring to Fig. 19, a warning unit 306 is added to the configuration of the parent terminal 30 according to the first embodiment.

[0118] The warning unit 306 is a means for issuing a first warning regarding the safety of a child (first user).

[0119] The operation mode of the child terminal 20 according to the second embodiment is set to a "walking mode". In the walking mode, the child terminal 20 and the parent terminal 30 maintain a communication state using a short-range wireless communication means such as Bluetooth (registered trademark).

[0120] The communication control unit 201 of the child terminal 20 and the communication control unit 301 of the parent terminal 30 transmit and receive predetermined data (any data) to and from each other. The communication control unit 301 of the parent terminal 30 notifies the warning unit 306 of an indicator indicating the communication state. For example, the communication control unit 301 passes radio wave strength (RSSI; Received Signal Strength Indication) to the warning unit 306.

[0121] The warning unit 306 estimates the distance between the child terminal 20 and the parent terminal 30 based on the radio wave intensity.

[0122] The warning unit 306 issues the first warning according to the estimated distance (the distance between the device itself and the child terminal 20). Specifically, the warning unit 306 issues a warning when the distance between the device and the child terminal 20 becomes longer than a predetermined threshold. For example, a voice message such as "Your child is far away! Watch out!" is output. For example, when a child finds an animal (e.g., a frog) on ​​the side of the road while taking a walk, the child runs over to catch the frog. Then, the parent terminal 30 carried by the parent issues the warning.

[0123] The warning unit 306 may determine a threshold value for whether or not to issue the warning (hereinafter, referred to as a warning threshold value) depending on the location (place of stay) of the child terminal 20 or the parent terminal 30.

[0124] Specifically, the warning unit 306 calculates the current position of its own device (parent terminal 30). The warning unit 306 receives a GPS signal from a GPS (Global Positioning System) satellite to perform positioning, and generates position information including the latitude, longitude, and altitude of its own device. Alternatively, the warning unit 306 may communicate with a base station or a wireless access point, and treat the position of the base station or the like as the position of its own device. Alternatively, the warning unit 306 may generate position information based on the strength of radio waves received from the base station or the like.

[0125] The warning unit 306 may acquire the warning threshold value by referring to table information that stores the relationship between the current position and the warning threshold value (see FIG. 20). The warning threshold value shown in FIG. 20 is determined according to the characteristics and properties of the place where the child and guardian are (where they are walking). For example, when a child is playing in a park, the warning threshold value is set to be long so that a warning is not issued even if the child and guardian are somewhat apart. On the other hand, when walking along a main road, the warning threshold value is set to be short so that a warning is issued immediately if the child and guardian are even slightly apart. Alternatively, the warning threshold value may be determined (changed) according to the type of road (road with sidewalk, road without sidewalk).

[0126] In this way, the warning threshold for issuing a warning (alert) may be determined according to the relationship between the current locations of the guardian and child and the surrounding environment. Note that, in order to change the warning threshold, map information in which the warning threshold is written may be used instead of the table information.

[0127] The warning unit 306 may determine the warning threshold based on the current position of the child (the person being watched over). In this case, the child terminal 20 includes a processing module as shown in Fig. 21. Referring to Fig. 21, the child terminal 20 according to the second embodiment includes a position calculation unit 206.

[0128] The position calculation unit 206 calculates the current position of its own device (child terminal 20) periodically or at a predetermined timing. The position calculation unit 206 transmits the calculated current position to the parent terminal 30.

[0129] In this way, the current location of the person being watched over (child) may be grasped by the child terminal 20 carried by the child, or may be grasped by the parent terminal 30. However, taking into consideration the power source (battery) of the child terminal 20, the child terminal 20 may not be provided with a location information generation function, and the device functions may be limited to a communication function and a voice recording function, thereby reducing power consumption.

[0130] Alternatively, activation or deactivation of some functions of the child terminal 20 may be controlled according to the operation mode. For example, the child terminal 20 may execute calculation of position information, etc. only when the operation mode of the child terminal 20 is set to the "walk mode."

[0131] Next, a modified example of the second embodiment will be described.

[0132] <Modification of the second embodiment> The warning unit 306 may determine a threshold value (warning threshold value) for whether or not to issue the warning based on the child's emotion. In this case, the voice data acquisition unit 203 of the child terminal 20 transmits the voice data to the parent terminal 30 in real time. The warning unit 306 of the parent terminal 30 transmits the acquired voice data to the server device 10.

[0133] Server device 10 according to the modified example of the second embodiment includes emotion data generation unit 404 as shown in Fig. 22. Emotion data generation unit 404 generates an emotion of the child based on voice data acquired from parent terminal 30. Emotion data generation unit 404 transmits emotion data including the generated emotion to parent terminal 30. Note that the process related to generation of the child's emotion by emotion data generation unit 404 can be the same as the process related to generation of emotion by analysis report generation unit 402, and therefore a description thereof will be omitted.

[0134] The warning unit 306 acquires the child's emotions (emotion data) from the server device 10 in real time. The warning unit 306 may determine the warning threshold based on the child's emotions. For example, if the child's emotions are calm, the warning unit 306 sets the warning threshold to a high value. On the other hand, if the child's emotions are unstable, the warning unit 306 sets the warning threshold to a low value. In this way, when the person being watched over (child) is calm, the warning unit 306 can determine that the risk is low (relatively safe), and so sets the threshold for determining that a warning is necessary (warning threshold; threshold for determining that the child is in a dangerous state) to a high value. On the other hand, if the state of the person being watched over is unstable, the warning unit 306 determines that there is a possibility of high risk (not being safe), and sets the warning threshold to a low value.

[0135] As described above, the information processing system according to the second embodiment urges the guardian to ensure the safety of the child according to the distance between the child and the guardian. The behavior of the child may exceed the imagination of the adult, resulting in a situation that the adult cannot foresee. Even in such a case, the guardian terminal 30 can issue an appropriate warning, so that the safety of the child can be ensured. Therefore, even when the parent leaves the child with elderly grandparents, the parent can leave the child in their care with peace of mind. That is, in the second embodiment, the safety and security of the child, which is the most important matter, is realized.

[0136] [Third embodiment] Next, a third embodiment will be described in detail with reference to the drawings.

[0137] In the second embodiment, a case where the parent terminal 30 issues a warning to strengthen monitoring of the child is described. In the third embodiment, a case where a warning is issued to ensure the safety of the parent and the child is described.

[0138] The configuration of the information processing system according to the third embodiment can be the same as that of the first embodiment, so a description corresponding to FIG. 2 will be omitted.

[0139] The following description will focus on the differences between the first to third embodiments.

[0140] The server device 10 generates "alert information" based on information acquired from an external device (for example, a social networking service (SNS) server or a local government server). The server device 10 transmits the generated alert information to the parent / guardian terminal 30. The parent / guardian terminal 30 (alert unit 306) issues a second alert regarding the safety of the child and parent / guardian in response to the alert information.

[0141] Fig. 23 is a diagram showing an example of a processing configuration (processing module) of the server device 10 according to the third embodiment. Referring to Fig. 23, an alert information transmission unit 405 is added to the configuration of the server device 10 according to the first embodiment.

[0142] For example, the warning information transmitting unit 405 generates information on a suspicious person as warning information based on a message posted on an SNS. For example, when the warning information transmitting unit 405 acquires a message on an SNS such as “There is a suspicious person near Station A”, the warning information transmitting unit 405 transmits the message to the guardian terminal 30.

[0143] Alternatively, when the warning information transmission unit 405 obtains information regarding fires, accidents, animals (bears, wild boars), etc. from a local government server, etc., it transmits warning information including the location (e.g., the location where the fire occurred) and content related to the information to the parent terminal 30.

[0144] Alternatively, the alert information transmitting unit 405 may transmit weather information related to sudden heavy rain (so-called guerilla downpour) to the parent terminal 30 as alert information.

[0145] In this way, the warning information transmitting unit 405 transmits to the guardian terminal 30 warning information including a place where caution is required for actions (for example, a place name, a region, a station name, etc.).

[0146] The parent terminal 30 issues the second warning based on the location information of the parent terminal 30 itself and the warning information. For example, the warning unit 306 of the parent terminal 30 issues a warning when the current location of the parent terminal 30 itself corresponds to a location included in the warning information. On the other hand, the warning unit 306 does not issue a warning when the current location of the parent terminal 30 itself does not correspond to a location included in the warning information.

[0147] In the above example of suspicious person information, if the current location of the device (parent and child) is near station A, the warning unit 306 warns that there may be a suspicious person lurking nearby. For example, the warning unit 306 outputs a message such as "There is information about a suspicious person at station A. Please act with caution." On the other hand, if the current location of the device is far away from station A, the warning unit 306 does not take any special action. In this way, the parent terminal 30 determines whether to issue a second warning based on the current location of the device and the location that requires caution for behavior included in the warning information.

[0148] Next, a modified example of the third embodiment will be described.

[0149] <Modification of the third embodiment> When the warning unit 306 of the parent terminal 30 receives attention-requiring information, the warning unit 306 may change the warning threshold based on the attention-requiring information. For example, when the warning unit 306 receives attention-requiring information indicating that a suspicious person is lurking nearby, the warning unit 306 may set the warning threshold to be extremely short (small). In this way, when the parent terminal 30 receives a notification regarding a suspicious person, the parent terminal 30 may be configured to issue a warning if the person being watched over (child) moves away even a little in order to ensure the safety of the person being watched over.

[0150] As described above, the information processing system according to the third embodiment urges the user to ensure the safety of the child and the guardian based on information acquired from the outside. That is, in the third embodiment, the safety and security of the child, which is the most important issue, is realized by immediately informing the guardian of any imminent danger around the child or guardian.

[0151] Next, the hardware of each device constituting the information processing system will be described.

[0152] The server device 10 can be configured by an information processing device (so-called a computer), and has the configuration exemplified in Fig. 24. For example, the server device 10 has a processor 311, a memory 312, an input / output interface 313, and a communication interface 314. The components such as the processor 311 are connected by an internal bus or the like, and are configured to be able to communicate with each other.

[0153] However, the configuration shown in Fig. 24 is not intended to limit the hardware configuration of the server device 10. The server device 10 may include hardware not shown, and may not include the input / output interface 313 as necessary. In addition, the number of processors 311 and the like included in the server device 10 is not intended to be limited to the example shown in Fig. 24, and for example, the server device 10 may include multiple processors 311.

[0154] The processor 311 is, for example, a programmable device such as a central processing unit (CPU), a micro processing unit (MPU), or a digital signal processor (DSP). Alternatively, the processor 311 may be a device such as a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). The processor 311 executes various programs including an operating system (OS).

[0155] The memory 312 is a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), a solid state drive (SSD), etc. The memory 312 stores an OS program, application programs, and various data.

[0156] The input / output interface 313 is an interface for a display device and an input device (not shown). The display device is, for example, a liquid crystal display, etc. The input device is, for example, a keyboard, a mouse, etc. that accepts user operations.

[0157] The communication interface 314 is a circuit, a module, etc. that communicates with other devices. For example, the communication interface 314 includes a network interface card (NIC).

[0158] The functions of the server device 10 are realized by various processing modules. The processing modules are realized, for example, by the processor 311 executing a program stored in the memory 312. The program can be recorded in a computer-readable storage medium. The storage medium can be a non-transitory medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. That is, the present invention can also be embodied as a computer program product. The program can be downloaded via a network or updated using a storage medium storing the program. The processing modules may also be realized by a semiconductor chip.

[0159] The parent terminal 30 and the like can also be configured from an information processing device, similar to the server device 10, and the basic hardware configuration is the same as that of the server device 10, so a description thereof will be omitted.

[0160] The server device 10, which is an information processing device, is equipped with a computer, and can realize the functions of the server device 10 by causing the computer to execute a program. The server device 10 also executes a control method for the server device 10 by the program.

[0161] [Variations] The configuration, operation, etc. of the information processing system described in the above embodiment are merely examples, and are not intended to limit the system configuration, etc.

[0162] In the above embodiment, the description has been given assuming that the person being watched over (first user) is a child (an infant, a small child, etc.), but the person being watched over may also be an adult.

[0163] The server device 10 (analysis report generating unit 402) may generate an emotion graph for each type of emotion. For example, the server device 10 may express the time changes of emotions that can be classified as the same positive emotion (e.g., emotions such as "fun" and "happy") in different emotion graphs.

[0164] The server device 10 may calculate the degree of emotion (for example, a little fun, fun, very fun) by analyzing the voice data even for the same type of emotion. The server device 10 may generate an interest list using these calculated emotions.

[0165] The contents of the analysis report described above are merely examples, and the server device 10 may generate an analysis report including other information. For example, the server device 10 may calculate lessons of interest, needs and behaviors at the nursery school, relationships between children (for example, close friends) and the like from words (keywords) uttered by the children, and provide the analysis report including this information to the guardian.

[0166] In the above embodiment, it has been described that the server device 10 transmits the analysis report to the parent / guardian terminal 30. The server device 10 may transmit "recommended information" instead of or in addition to the analysis report. The server device 10 may generate the recommended information based on the child's emotions and / or interests obtained by analyzing the voice data. In this case, the server device 10 includes a recommended information generating unit 406 as shown in FIG. 25.

[0167] The recommendation information generating unit 406 may transmit recommendation information including information on recommended experiences based on the child's emotions to the guardian (guardian terminal 30). For example, if the child is very interested in animals, the recommendation information generating unit 406 may recommend a trip to the zoo. Alternatively, if the child is interested in art pieces, the recommendation information generating unit 406 may notify the guardian of information on art museums.

[0168] The recommendation information generating unit 406 may generate information about a present to be given to a child as recommendation information. For example, when the recommendation information generating unit 406 determines from a child's statement that the child is interested in a particular toy, the recommendation information generating unit 406 may provide information about the toy to the guardian. Alternatively, the recommendation information generating unit 406 may generate recommendation information taking into account the results of emotion analysis. For example, the recommendation information generating unit 406 may recommend as a present a toy whose name is uttered by the child in an excited situation, and may not recommend a toy whose name is uttered by the child in a depressed situation.

[0169] Furthermore, the recommendation information generating unit 406 may include, in the recommendation information about a present, information about an electronic commerce (EC) site that handles the present (for example, a uniform resource locator (URL) of the EC site). In this way, by including information about the EC site, etc. in the recommendation information transmitted to the guardian terminal 30, guardians (especially elderly grandparents, etc.) can purchase the right present.

[0170] In the above embodiment, it has been described that either the data collection mode or the walk mode can be selected, but these modes may be operated simultaneously. More specifically, the data collection mode may be enabled during the walk mode. In this manner, a parent can check the voice of a child who has gone for a walk with his / her grandparents.

[0171] The server device 10 may provide information according to the child's situation and condition during the walk mode. For example, when the server device 10 determines that the child is tired by analyzing the voice data, it may notify the parent terminal 30 of that fact. Alternatively, the server device 10 may transmit a message (analysis report) to the parent terminal 30 urging the child to return home because the child is tired. Alternatively, the server device 10 may transmit recommended information to the parent terminal 30 including a means of transportation and a route for returning home, taking into account the child's degree of fatigue.

[0172] In the above embodiment, it is assumed that only the voice of the person being watched over (the child wearing the child terminal 20) is recorded in the voice data acquired from the child terminal 20. However, it is assumed that the voice of other people (such as the child's friends) is actually included. Therefore, it is desirable that the analysis report generating unit 402 of the server device 10 has a speaker recognition function. The guardian provides the voice data of the person being watched over to the server device 10, and the server device 10 generates a learning model using the provided voice data as teacher data. The server device 10 (analysis report generating unit 402) may input voice data of the person being watched over to the learning model and acquire the voice data of the person being watched over. The analysis report generating unit 402 may analyze the voice data of the person being watched over (voice data) and exclude voice data of other people from the analysis target. The server device 10 removes voice data of people other than the person being watched over from the voice data received from the child terminal 20 via the guardian terminal 30 and provides the voice data to the guardian, thereby appropriately protecting personal information and privacy of people other than the person being watched over (such as the child's friends). In this way, the server device 10 may provide the guardian with voice data obtained by processing the original voice data, rather than providing the guardian with the original voice data recorded by the child terminal 20.

[0173] The parent terminal 30 may have a function of playing back the voice data acquired from the child terminal 20. If the recorded data is long, the parent terminal 30 may extract the audio data. By playing back the audio data, the parent terminal 30 can check only what the child is saying.

[0174] In the above embodiment, the server device 10 detects the voice data. However, the voice data may be detected by the child terminal 20 or the parent terminal 30. By having the child terminal 20 detect the voice data, the amount of communication between the child terminal 20 and the parent terminal 30 can be reduced.

[0175] In the above embodiment, the case where the server device 10 generates the analysis report has been described, but the analysis report may be generated by the child terminal 20 or the parent terminal 30. When the child terminal 20 generates the analysis report, when the child terminal 20 detects the parent terminal 30 (when pairing is successful), the analysis report may be automatically transmitted to the parent terminal 30.

[0176] In the above embodiment, it has been described that voice data is transmitted to the parent / guardian terminal 30 when the child returns home, and an analysis report is generated. However, the child's voice data may be transmitted to the server device 10 in real time, and the server device 10 may calculate the child's emotion in real time. The server device 10 may notify the parent / guardian terminal 30 of a necessary warning or the like based on the emotion calculated in real time. For example, when it is determined that the child is in an emotionally unstable situation based on the calculated emotion, the server device 10 may notify the parent / guardian terminal 30 of that effect. When the child's emotion is calculated in real time, the child's terminal 20 communicates with the server device 10 using a mobile line or the like.

[0177] When the child terminal 20 and the server device 10 directly communicate with each other and the child terminal 20 has a speaker, the server device 10 may talk to the child through the speaker (may output voice data). In this case, the server device 10 has a dialogue unit 407 as shown in FIG. 26. When the dialogue unit 407 determines that a danger is imminent based on the position of the person to be watched over (infant, child; child), it may notify the child of the danger through the child terminal 20. For example, when the child is playing by the side of the road, the dialogue unit 407 may transmit warning information such as "Stay away from the road!" to the child terminal 20. Alternatively, when the child is overly excited, the dialogue unit 407 may output a message (voice data) to calm the excited child.

[0178] Alternatively, the dialogue unit 407 may change the voice or character used when speaking to the child depending on the child's age or gender. In this case, the server device 10 acquires attribute information (age, gender, etc.) of the child from the guardian or the like.

[0179] Assuming that the parent terminal 30 takes a walk with multiple children (persons to be watched over), the parent terminal 30 may have a function capable of communicating with multiple child terminals 20. For example, when the parent terminal 30 and the child terminal 20 communicate with each other using Bluetooth (registered trademark), the parent terminal 30 may have a multipoint function. In this case, the parent terminal 30 may issue a warning to the parent when the positions (distance) of the children become significantly separated from each other.

[0180] The server device 10 and the parent terminal 30 may be provided with an interface for receiving an analysis report desired by the parent. For example, the parent terminal 30 may acquire information such as "I would like to submit an emotion graph" or "I would like to submit a message list" through a GUI or the like. The parent terminal 30 may notify the server device 10 of the acquired parent's request (selection), and the server device 10 may generate and output an analysis report according to the notified request.

[0181] In the third embodiment, the parent terminal 30 (alert unit 306) estimates the distance between the child terminal 20 and the parent terminal 30 based on the strength of the received radio wave. However, the parent terminal 30 may estimate the distance by other methods. For example, the parent terminal 30 may estimate (calculate) the distance from the position information of its own device and the position information of the child terminal 20.

[0182] Although the format of data transmission and reception between each device (server device 10, child terminal 20, parent terminal 30) is not particularly limited, data transmitted and received between these devices may be encrypted. Voice data, analysis reports, etc. are transmitted and received between these devices, and in order to appropriately protect this information, it is desirable to transmit and receive encrypted data.

[0183] In the flow charts (flow charts, sequence diagrams) used in the above description, multiple steps (processes) are described in order, but the order of execution of the steps executed in the embodiments is not limited to the order described. In the embodiments, the order of the steps shown in the figures can be changed to a degree that does not interfere with the content, such as executing each process in parallel.

[0184] The above-mentioned embodiments have been described in detail to facilitate understanding of the present disclosure, and it is not intended that all of the configurations described above are necessary. In addition, when a plurality of embodiments are described, each embodiment may be used alone or in combination. For example, it is possible to replace a part of the configuration of an embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of an embodiment. Furthermore, it is possible to add, delete, or replace a part of the configuration of an embodiment with another configuration.

[0185] From the above explanation, it is clear that the present invention has industrial applicability, and the present invention can be suitably applied to an information processing system that authenticates users who have registered as members.

[0186] A part or all of the above-described embodiments may be described as, but is not limited to, the following supplementary notes. [Appendix 1] a first terminal worn by a first user and configured to record voice data of the first user; a second terminal used by a second user; A server device that communicates with at least the second terminal; Including, The server device analyzes the voice data of the first user, generates an analysis report on the first user based on the analysis results, and transmits the generated analysis report to the second terminal. [Appendix 2] The first terminal transmits voice data of the first user to the second terminal; The system described in Appendix 1, wherein the second terminal transmits the voice data of the first user to the server device. [Appendix 3] The system described in Appendix 1 or 2, wherein the server device calculates an emotion score that quantifies the emotion of the first user from the voice data of the first user, and extracts keywords from the voice data of the first user. [Appendix 4] The system of claim 3, wherein the server device uses the emotion score to generate an emotion graph showing changes in the emotion of the first user over time. [Appendix 5] The system according to claim 4, wherein the server device generates a comment list including the number of comments for each of the extracted keywords. [Appendix 6] The system according to claim 4 or 5, wherein the server device generates a list of interests of the first user based on the number of times each of the extracted keywords has been stated. [Appendix 7] The system according to any one of appendix 4 to 5, wherein the server device generates a list of interests of the first user based on the number of times each of the extracted keywords has been stated and the emotion score. [Appendix 8] The system of claim 7, wherein the server device reflects the interests included in the interest list in the emotion graph. [Appendix 9] 9. The system according to any one of claims 1 to 8, wherein the second terminal issues a first warning regarding the safety of the first user depending on the distance between the second terminal and the first terminal. [Appendix 10] The system of claim 9, wherein the second terminal estimates a distance between the second terminal and the first terminal, and issues the first warning if the estimated distance is longer than a warning threshold. [Appendix 11] The system of claim 10, wherein the second terminal determines the warning threshold value depending on a location of the second terminal or the first terminal. [Appendix 12] The server device generates alert information based on information acquired from an external device, and transmits the generated alert information to a second terminal; 12. The system according to any one of claims 9 to 11, wherein the second terminal issues a second warning regarding the safety of the first and second users in response to the warning information. [Appendix 13] The server device transmits the warning information including a location where caution is required for an action to the second terminal, The system of claim 12, wherein the second terminal determines whether to issue the second warning based on a current location of the device and a location where the behavior requires attention. [Appendix 14] an analysis report generating unit that analyzes voice data of a first user recorded on a first terminal worn by the first user, and generates an analysis report on the first user based on the analysis result; a transmission unit that transmits the generated analysis report to a second terminal used by a second user; A server device comprising: [Appendix 15] In the server device, Analyzing voice data of a first user recorded on a first terminal worn by the first user, and generating an analysis report on the first user based on the analysis result; A method for controlling a server device, the method comprising: transmitting the generated analysis report to a second terminal used by a second user. [Appendix 16] A computer installed in the server device A process of analyzing voice data of a first user recorded on a first terminal worn by the first user, and generating an analysis report on the first user based on the analysis result; A process of transmitting the generated analysis report to a second terminal used by a second user; A computer-readable storage medium that stores a program for executing the above.

[0187] The disclosures of the above cited prior art documents are incorporated herein by reference. Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. It will be understood by those skilled in the art that these embodiments are merely illustrative and that various modifications are possible without departing from the scope and spirit of the present invention. In other words, the present invention naturally includes various modifications and amendments that a person skilled in the art can make in accordance with the entire disclosure, including the scope of the claims, and the technical ideas. [Explanation of symbols]

[0188] 10. Server equipment 20 Children's Devices 30 Parental Terminal 101 First Terminal 102 Second Terminal 103 Server device 201 Communication control section 202 Mode Management Section 203 Voice data acquisition unit 204 Voice Data Management Unit 205 Storage section 206 Position calculation unit 301 Communication Control Unit 302 Child Device Management Department 303 Analysis report request section 304 Analysis report output section 305 Storage section 306 Warning section 311 Processor 312 Memory 313 Input / Output Interface 314 Communication Interface 401 Communication control section 402 Analysis report generation unit 403 Storage section 404 Emotion Data Generation Unit 405 Warning Information Transmission Unit 406 Recommendation information generation unit 407 Dialogue Section

Claims

1. a first terminal attached to a first user and configured to record voice data of the first user; a second terminal used by a second user; A server device that communicates with at least the second terminal; Including, the server device analyzes the voice data of the first user, generates an analysis report on the first user based on an analysis result, and transmits the generated analysis report to the second terminal; The first terminal transmits voice data of the first user to the second terminal; The second terminal transmits the voice data of the first user to the server device.

2. The system according to claim 1 , wherein the server device calculates an emotion score that quantifies the emotion of the first user from the voice data of the first user, and extracts keywords from the voice data of the first user.

3. The system according to claim 2 , wherein the server device uses the emotion score to generate an emotion graph showing a change over time in the emotion of the first user.

4. The system according to claim 3 , wherein the server device generates a message list including the number of messages for each of the extracted keywords.

5. 5. The system according to claim 3, wherein the server device generates an interest list of the first user based on the number of times each of the extracted keywords has been commented.

6. The system according to claim 3 , wherein the server device generates an interest list of the first user based on the number of times each of the extracted keywords has been said and the emotion score.

7. an analysis report generating unit that analyzes voice data of a first user recorded on a first terminal worn by the first user, and generates an analysis report on the first user based on the analysis result; a transmission unit that transmits the generated analysis report to a second terminal used by a second user; Equipped with The analysis report generation unit Calculating an emotion score by quantifying an emotion of the first user from the voice data of the first user and extracting keywords from the voice data of the first user; generating an emotion graph showing a time-varying emotion of the first user using the emotion score; A server device that generates an interest list of the first user based on the number of times each of the extracted keywords is said and the emotion score.

8. In the server device, Analyzing voice data of a first user recorded on a first terminal worn by the first user, and generating an analysis report on the first user based on the analysis result; A method for controlling a server device, the method comprising: transmitting the generated analysis report to a second terminal used by a second user, the method comprising: Calculating an emotion score by quantifying an emotion of the first user from the voice data of the first user and extracting keywords from the voice data of the first user; generating an emotion graph showing a time-varying emotion of the first user using the emotion score; A method for controlling a server device, the method comprising: generating a list of interests of the first user based on the number of times each of the extracted keywords has been stated and the emotion score.

9. A computer installed in the server device A process of analyzing voice data of a first user recorded on a first terminal worn by the first user, and generating an analysis report on the first user based on the analysis result; A process of transmitting the generated analysis report to a second terminal used by a second user; A program for executing The computer includes: A process of calculating an emotion score by quantifying an emotion of the first user from the voice data of the first user and extracting keywords from the voice data of the first user; A process of generating an emotion graph showing a time change of the emotion of the first user using the emotion score; generating a list of interests of the first user based on the number of times each of the extracted keywords is said and the emotion score; A program that executes the following.

Images