JP2018106224A - Server, information processing method, network system, and terminal - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique for realizing a more suitable dialogue with a user.SOLUTION: A server 100 comprises a communication interface 160 for communicating with a terminal 300 having a speaker 370 and a microphone 380, a memory 120 for storing a plurality of types of message information, and a processor 110 for causing the terminal 300 to exchange messages with the user via the communication interface 160 and for initiating the output of another type of message to the terminal 300 when it is determined that message exchange terminates.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technology for a server, an information processing method, a network system, and a terminal for outputting voice such as a message.

  Conventionally, a technique for outputting a message suitable for a user is known. For example, Japanese Patent Laying-Open No. 2016-24636 (Patent Document 1) discloses a control device, a control method, and a control program. According to Patent Literature 1, the control device is searched by a search unit that searches for advertisement information that is information related to an advertisement that is output as a response message, based on the characteristics of sound in a conversation between the dialog agent system and the user, and the search unit. And an output control unit that controls to output an advertisement related to the advertisement information as a response message. For this reason, the control apparatus can output a message suitable for the user.

JP 2016-24636 A

  The objective of this invention is providing the technique for implement | achieving the interaction with a more suitable user.

  According to an aspect of the present invention, a communication interface for communicating with a terminal having a speaker and a microphone, a memory for storing a plurality of types of message information, and a message exchange with a user via the communication interface. A server is provided that includes a processor for causing the terminal to start outputting another type of message when it is determined that the message exchange is completed.

  According to another aspect of the present invention, a communication interface for communicating with a terminal having a speaker and a microphone, a memory for storing a plurality of types of message information, and a message exchange with a user via the communication interface And a processor for causing a terminal to start outputting another type of message when message exchange stops for a predetermined time or longer.

  Preferably, the processor causes the terminal to output advertisement information via the communication interface when a predetermined condition regarding message exchange with the user is satisfied.

  Preferably, the processor outputs advertisement information based on a first time zone for each user.

  Preferably, the processor changes a condition for causing the terminal to start outputting another type of message in the first time zone and the other time zone for each user.

  Preferably, the processor changes another type of message to be output based on a message exchange with a past user.

  When another situation of this invention is followed, the information processing method in the server containing a communication interface, memory, and a processor is provided. An information processing method includes a step in which a processor causes a terminal to exchange messages with a user via a communication interface, and when the processor determines that the exchange of messages is finished or the exchange of messages is stopped for a predetermined time or more. And a step of causing the terminal to start outputting another type of message.

  According to another aspect of the present invention, a terminal having a speaker for outputting a message and a microphone for obtaining a message from the user, and causing the terminal to perform message exchange with the user are determined to complete message exchange. And a server that causes a terminal to start outputting another type of message when message exchange is stopped for a predetermined time or longer.

  According to another aspect of the present invention, a speaker, a microphone, a message is output to the speaker, and when it is determined that the message exchange is completed based on the sound acquired through the microphone, or the message exchange is a predetermined time or more. A terminal is provided that includes a processor for causing a speaker to start outputting another type of message when stopped.

  As described above, according to the present invention, a more suitable dialogue with the user is possible.

1 is a diagram illustrating an overall configuration of a network system 1 according to a first embodiment. It is a figure which shows the 1st operation | movement outline | summary of the network system 1 concerning 1st Embodiment. It is a figure which shows the 2nd operation | movement outline | summary of the network system 1 concerning 1st Embodiment. It is a figure which shows the 3rd operation | movement outline | summary of the network system 1 concerning 1st Embodiment. It is a block diagram which shows the structure of the voice service server 100 concerning 1st Embodiment. It is an image figure which shows the theme table 121 concerning 1st Embodiment. It is an image figure which shows the dialogue scenario database 122 concerning 1st Embodiment. It is a block diagram which shows the function structure of the voice service server 100 in 1st Embodiment. It is a flowchart which shows the information processing in the voice service server 100 concerning 1st Embodiment. It is a block diagram which shows the structure of the electric equipment 300 concerning 1st Embodiment. It is a flowchart which shows the 1st information processing in the voice service server 100 concerning 2nd Embodiment. It is a flowchart which shows the 2nd information processing in the voice service server 100 concerning 2nd Embodiment. It is a figure which shows the golden time of 3rd Embodiment. It is a flowchart which shows the 1st information processing in the voice service server 100 concerning 3rd Embodiment. It is a flowchart which shows the 2nd information processing in the voice service server 100 concerning 3rd Embodiment. It is a flowchart which shows the 3rd information processing in the voice service server 100 concerning 3rd Embodiment. It is an image figure which shows the reaction table 123 concerning 4th Embodiment. It is a flowchart which shows the information processing in the voice service server 100 concerning 4th Embodiment. It is a flowchart which shows the information processing in the voice service server 100 concerning 5th Embodiment. It is an image figure which shows the dialogue scenario database 122B concerning 6th Embodiment. It is a flowchart which shows the information processing in the voice service server 100 concerning 6th Embodiment. It is a figure which shows the operation | movement outline | summary of the electric equipment 300 concerning 7th Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.
<First Embodiment>
<Overall configuration of network system 1>

  First, the overall configuration of the network system 1 according to the present embodiment will be described with reference to FIG. The network system 1 according to the present embodiment mainly includes a voice service server 100, other information providing servers 100B and 100C, and electric devices (communication terminals) such as a robot 300A, a refrigerator, and an air conditioner. The electrical device according to the present embodiment outputs a message by voice based on data from the voice service server 100 in response to a message from a user.

Note that the electric device (communication terminal) is not limited to the robot 300A, but includes a refrigerator, a microwave oven, an air conditioner, a washing machine, a vacuum cleaner, an air purifier, a humidifier, a dehumidifier, a rice cooker, a lighting appliance, a mobile phone, AV (audio / visual) equipment such as smartphones, televisions, hard disk recorders, projectors, music players, game consoles, personal computers, built-in lighting, solar power generators, intercoms, water heaters, and hot water washing toilet seat controllers, etc. It may be. Hereinafter, these electric devices (communication terminals) are also collectively referred to as an electric device 300.
<Operation overview of network system 1>

  Next, an outline of the operation of the network system 1 according to the present embodiment will be described with reference to FIGS. Regarding the network system 1 according to the present embodiment, a dialogue is performed, that is, a voice message is exchanged when the user talks to the electric device 300 such as the robot 300A or the electric device 300 talks to the user. More specifically, in the present embodiment, the voice service server 100 causes the electric device 300 to output a voice message or obtains a voice message from the user via the electric device 300.

  Then, as shown in FIG. 2, the voice service server 100 determines whether or not the user has heard the voice message that has been output in advance according to the user's reaction, or relates to the voice message or message that has been output earlier. It is determined whether the user is interested in a topic.

  In particular, in the present embodiment, as shown in FIG. 3, the voice service server 100 is interacting with the user regarding a certain theme based on data of messages of a plurality of types of themes and scenarios prepared in advance. On the other hand, when it is determined that it is difficult to continue the conversation, the conversation of another topic is started based on the scenario data of another topic.

  In addition, as shown in FIG. 4, the voice service server 100, based on a plurality of types of themes and scenario message data prepared in advance, has passed a predetermined time while the conversation with the user regarding a certain theme has ended. When this happens, another topic conversation is started based on the scenario data of another topic.

As described above, the voice service server 100 according to the present embodiment can smooth the dialog with the user by the electric device 300. That is, it is possible to provide a space between the user and the electric device 300, and it is easy to make the user comfortable or keep it in a good state. Hereinafter, a specific configuration of the network system 1 for realizing such a function will be described in detail.
<Hardware Configuration of Voice Service Server 100>

  First, an aspect of the hardware configuration of the voice service server 100 configuring the network system 1 according to the present embodiment will be described. Since the other information providing servers 100B and 100C have the same configuration as the voice service server 100, description thereof will not be repeated here.

  Referring to FIG. 5, voice service server 100 includes a CPU (Central Processing Unit) 110, a memory 120, an operation unit 140, and a communication interface 160 as main components.

  The CPU 110 controls each unit of the voice service server 100 by executing a program stored in the memory 120. For example, the CPU 110 executes programs stored in the memory 120 and executes various processes described later by referring to various data.

  The memory 120 is realized by various RAMs (Random Access Memory), various ROMs (Read-Only Memory), and the like. The memory 120 is a program executed by the CPU 110, data generated by the execution of the program by the CPU 110, input data, the theme table 121, the interactive scenario database 122, and the user being interested in the message. A database used for a voice service such as a plurality of types of keywords indicating the first level indicating that the user has simply heard a message, and the like are stored. Of course, these data may not be stored in the voice service server 100 itself, but may be stored in another device accessible by the voice service server 100.

  Here, with reference to FIG. 6, the theme table 121 stores the correspondence between theme IDs and theme names for each theme. Referring to FIG. 7, dialogue scenario database 122 stores a correspondence relationship between a dialogue scenario ID, a theme ID, and text data or voice data for each scenario or message. Hereinafter, a series of messages for interacting with the user is also referred to as a scenario.

  With this configuration, in the present embodiment, the CPU 110 executes the program in the memory 120, and as shown in FIG. 8, the dialogue scenario selection unit 110A, the dialogue scenario execution processing unit 110B, The associative scenario search unit 110C and the like are realized.

  More specifically, the dialogue scenario selection unit 110A selects a theme and a scenario from the dialogue scenario database 122 before starting a message exchange with the user. The dialogue scenario execution processing unit 110B transmits a message included in the scenario to the electric device 300 via the communication interface 160, thereby causing the electric device 300 to execute a dialogue with the user.

  Then, when the dialogue of the scenario ends, when the dialogue ends and silence continues for a predetermined time, or when a message following the current scenario is not prepared, the associative scenario search unit 110C selects the theme selected previously. A scenario related to a scenario or message is searched, and a new message is extracted from the dialogue scenario database 122. Accordingly, the dialogue scenario execution processing unit 110B again transmits a message included in the scenario to the electric device 300 via the communication interface 160 in response to a message from the user, thereby allowing the electric device 300 to interact with the user. Is executed.

  Returning to FIG. 5, the operation unit 140 receives a command from a service manager or the like and inputs the command to the CPU 110.

  The communication interface 160 transmits data from the CPU 110 to another device such as the electric device 300 via the Internet, a carrier network, a router, or the like. Conversely, the communication interface 160 receives data from another device via the Internet, a carrier network, a router, etc., and passes it to the CPU 110.

The configuration of the other information providing servers 100B and 100C differs in the data of the memory 120 and the processing of the CPU 110, but the hardware configuration is generally the same as that of the voice service server 100, and therefore the description thereof will not be repeated here.
<Information Processing in Voice Service Server 100>

  Next, information processing in the voice service server 100 according to the present embodiment will be described with reference to FIG.

  The CPU 110 of the voice service server 100 executes the following processing for each electrical device 300 periodically for each user or each electrical device 300. First, the CPU 110 determines whether or not a conversation is currently in progress (step S102). During the dialogue (YES in step S102), CPU 110 extracts the user's message from the audio data from electric device 300, and analyzes the message (step S104).

  CPU 110 refers to the data in memory 120 to determine whether the user is interested in the message output by electric device 300, the theme thereof, or the like (step S112). For example, when the extracted message includes a first level keyword such as “I love you!” Or “I like you” or a question from the user, the user is interested in a series of messages. If the message does not contain the first level keyword, it is determined that the user did not show interest in the series of messages. Alternatively, the CPU 110 issues a quiz to the user via the electrical device 300, and when there is a response from the user, the CPU 110 determines that the user is interested in a series of messages, and there is no response to the quiz. In addition, it may be determined that the user did not show interest in the series of messages. Or, when the user answers “Yes” or “Yes” after asking the user “Is interested?”, It is determined that the user is interested in a series of messages. If there is an answer “No” or “No” to the question, or if there is no answer, it is determined that the user did not show interest in the message.

  If it is determined that the user is interested in the message (YES in step S112), CPU 110 identifies the user specific information, the specific information of the message output by electric device 300, the specific information of the theme, and the time zone. , Data indicating that the user is interested is stored in the memory 120 (step S114). CPU110 performs the process from step S132.

  If it is determined that the user has not shown interest in the message (NO in step S112), CPU 110 refers to the data in memory 120 to determine whether the user has heard the message from electrical device 300 or not. (Step S122). For example, the CPU 110 determines that the user has heard the message when the extracted user message includes a second level keyword such as “Yes” or “Hey.”, And the second message is included in the message. If the keyword of the level is not included, it is determined that the user did not listen to the message. Alternatively, when the user answers “Yes,” or “Yes.” After asking the question “Hey, are you listening?”, The user is judged to have heard the message, and the question is answered. On the other hand, if there is an answer such as “No” or “No” or no answer, it is determined that the user did not listen to the message.

  If it is determined that the user has heard the message (YES in step S122), CPU 110 determines the specific information of the user, the specific information of the message output by electric device 300, the specific information of the theme, and the time zone. The data indicating that the user has heard the message is stored in the memory 120 in association with (step S124). CPU110 performs the process from step S132.

  If it is determined that the user has not heard the message (NO in step S122), CPU 110 executes the processing from step S132.

  Preferably, the CPU 110 "per user, per user group such as age / address / gender or the entire user", "per message, per theme, or per time zone", The rate of listening or the rate of interest in the message is calculated and stored in the memory 120, or the information is provided to another server via the communication interface 160.

  In step S132, CPU 110 refers to dialog scenario database 122 and determines whether a message subsequent to the message output by electrical device 300 is prepared. If a subsequent message is prepared (YES in step S132), CPU 110 causes electric device 300 to continue the dialog with the user as it is. That is, the CPU 110 transmits the next message to the electric device 300 or waits for the next message from the electric device 300 via the communication interface 160. Alternatively, step S102 is repeated for each electrical device 300 every first predetermined time, for example, every second.

  If a subsequent message is not prepared (NO in step S132), CPU 110 refers to theme table 121 and identifies the next theme (step S144). Note that the CPU 110 may determine the next theme in the order of the theme IDs in the theme table 121, may determine the next theme based on popular news, or user settings or user's settings as described later. The next theme may be determined based on the past history or the like.

  CPU 110 refers to dialog scenario database 122, reads a message corresponding to the identified theme, and transmits message data to electrical device 300 via communication interface 160 (step S146). As a result, the CPU 310 of the electrical device 300 can start a dialogue on a new theme based on the data from the voice service server 100. The CPU 110 of the voice service server 100 waits for the next message from the electric device 300 via the communication interface 160. Alternatively, Step S102 is repeated for each electrical device 300 after the first predetermined time has elapsed.

  On the other hand, when the conversation is not in progress (YES in step S102), CPU 110 determines whether or not a second predetermined time, for example, 20 seconds has elapsed since the conversation stopped (step S142). CPU110 performs the process from step S144, when 2nd predetermined time passes (when it is YES in step S142).

If the second predetermined time has not elapsed (NO in step S142), CPU 110 waits for the next message from electric device 300 via communication interface 160. Alternatively, Step S102 is repeated for each electrical device 300 after the first predetermined time has elapsed.
<Hardware Configuration of Electric Device 300>

  Next, with reference to FIG. 10, one aspect of the configuration of the electric device 300 configuring the network system 1 will be described. The electric device 300 includes a CPU 310, a memory 320, a display 330, an operation unit 340, a camera 350, a communication interface 360, a speaker 370, a microphone 380, and a device driving unit 390 as main components.

  The CPU 310 controls each unit of the electric device 300 by executing a program stored in the memory 320 or an external storage medium.

  The memory 320 is realized by various RAMs, various ROMs, and the like. The memory 320 is connected to the device driving program, conversation program, and other programs executed by the CPU 310, data generated by execution of the program by the CPU 310, data received from the voice service server 100 and other servers, and the operation unit 340. The input data is stored.

  The display 330 outputs characters and images based on signals from the CPU 310. The display 330 may simply be lights 330A and 330B as shown in FIG.

  The operation unit 340 is realized by a button, a touch panel, and the like, receives a command from the user, and inputs the command to the CPU 310. The display 330 and the operation unit 340 may constitute a touch panel.

  The operation unit 340 may be a proximity sensor, a temperature sensor, or the like. In this case, the CPU 310 detects that the user has held his / her hand over the electric device 300 via a proximity sensor or a temperature sensor as the operation unit 340 and starts various operations. For example, the electric device 300 may be a robot, and the electric device 300 may detect that the user strokes or strikes the electric device 300 by arranging the proximity sensor in the vicinity of the forehead.

  The camera 350 takes an image and transfers the image data to the CPU 310. The CPU 310 may specify the user's movement from the image data, or may provide the image data to the server 100 and the server 100 may specify the user's movement.

  The communication interface 360 is realized by a communication module such as wireless LAN communication or wired LAN. The communication interface 360 exchanges data with other devices such as the voice service server 100 by wired communication or wireless communication.

  The speaker 370 outputs sound based on the signal from the CPU 310. More specifically, in the present embodiment, CPU 310 causes speaker 370 to output a voice message based on voice data received from server 100 via communication interface 360. Alternatively, CPU 310 creates an audio signal based on text data received from server 100 via communication interface 360 and causes speaker 370 to output an audio message. Alternatively, CPU 310 reads out voice data of the message from memory 320 based on the message ID received from server 100 via communication interface 360 and causes speaker 370 to output the voice message.

  The microphone 380 creates an audio signal based on external audio and inputs it to the CPU 310.

  The device driving unit 390 controls each unit (such as a motor and a heater) of the electric device 300 based on a signal from the CPU 310.

As described above, in the voice service according to the present embodiment, another topic is started when message data for subsequent conversation is not prepared, or when a predetermined time elapses after the conversation is stopped. Therefore, it becomes difficult for the user of the electric device 300 to be bored and to feel comfortable. Furthermore, in the voice service according to the present embodiment, for example, the voice service is provided with a provider of conversation information and advertisement information, “for each user, for each user layer such as age, address, and sex, or for the entire user. ”,“ Per message, per topic, per theme, or per time period ”,“ percentage of listening to a message or interest in a message ”, etc. Such information can be used for calculation of fees collected from advertisement providers, calculation of fees paid to other information providers, various marketing, and the like.
<Second Embodiment>

  The voice service server 100 further outputs an advertisement of a company, a product, or a service from the electric device 300 when the user shows an interest, speaks a positive message, or a conversation is excited (see FIG. 2 and the like). ), When the user does not show interest, speaks a negative message, or does not excite the dialogue, it may have a function of preventing the electronic device 300 from outputting advertisements of companies, products, and services.

  More specifically, referring to FIG. 11, when CPU 110 determines that the user has shown interest in the message (YES in step S112), CPU 110 performs an electrical connection via communication interface 160 in addition to step S114. Data for advertisement is transmitted to the device 300 (step S118). Thereby, as shown in FIG. 2, the electric device 300 outputs an advertisement based on the data from the voice service server 100.

  On the other hand, if it is determined that the user has not shown interest in the message (NO in step S112), CPU 110 determines whether the user has heard the message from electrical device 300 (step S122). In this case, the advertisement is not output to the electric device 300.

  Alternatively, referring to FIG. 12, if CPU 110 determines that the user has shown an interest in the message (YES in step S112), CPU 110 adds the electric power to the first predetermined number of times or more in addition to step S114. It is determined whether or not the device 300 is responding to a message output, for example, whether or not the user has input a message to the electric device 300 for a first predetermined number of times (step S116). When the user has input a message to electrical device 300 for the first predetermined number of times or more (YES in step S116), CPU 110 transmits advertising data to electrical device 300 via communication interface 160. (Step S118). As a result, as shown in FIG. 2, the electric device 300 outputs an advertisement based on the data from the voice service server 100.

  On the other hand, if the user has not yet input a message to electrical device 300 for the first predetermined number of times (NO in step S116), or if it is determined that the user has not shown interest in the message (in step S112) CPU 110 does not cause electric device 300 to output an advertisement.

  Note that a positive first message is set in advance, and the CPU 110 of the voice service server 100 determines that the user is positive when the user's message includes the first message, and the user's message May not determine that the user is negative if it does not include the first message.

  Alternatively, a negative second message is set in advance, and the CPU 110 of the voice service server 100 determines that the user is negative when the user message includes the second message, and the user message May determine that the user is affirmative if does not include the second message.

  Note that a positive first message and a negative second message are set in advance, and the CPU 110 of the voice service server 100 determines that the user is positive when the user's message includes the first message. If the user's message includes the second message, it is determined that the user is negative. If the user's message does not include any message, the determination is suspended until the next message. Good.

  Alternatively, an affirmation point indicating the degree of affirmation is given for each message. Positive messages such as “I love you” and “Highest” are given a large “positive” point, and negative messages such as “I hate” and “No.” are “negative”. Big points are awarded. Then, CPU 110 may determine that the user's message point or accumulated point is positive when it is greater than or equal to a predetermined value, and may determine that the user's message point or cumulative point is not positive when it is less than the predetermined value.

  In the above embodiment, the advertisement information is output in response to a positive user message, and the advertisement information is not output in response to a negative user message. I can't.

  For example, the CPU 110 of the voice service server 100 may output the first advertisement information in response to a positive user message and output the second advertisement information in response to a negative user message. . Note that the first advertisement information includes more detailed content than the second advertisement information. Alternatively, the first advertisement information includes a company name and a product, and the second advertisement information includes either the company name or the product.

  In addition to the advertisement information, the CPU 110 of the voice service server 100 outputs information such as news in response to a positive user message and does not output information such as news in response to a negative user message. It may be. Alternatively, detailed information may be output according to a positive user message, and simple information may be output according to a negative user message.

Further, by combining them, the CPU 110 of the voice service server 100 determines that the user message points or accumulated points are greater than or equal to the first predetermined value, or the user message includes the first positive message. Then, it is determined that the state is the first affirmative state, and the detailed information and the advertisement information are output to the electric device 300. CPU 110 determines that the point or cumulative point of the user's message is equal to or greater than a second predetermined value that is less than the first predetermined value and smaller than the first predetermined value, or the user message includes a second positive message. If so, it is determined to be in the second affirmative state, and simple information and advertisement information are output to the electric device 300. CPU 110 determines that the state is negative when the user's message points or accumulated points are less than the second predetermined value, or when the user's message does not include the first and second positive messages. Then, only the simple information may be output to the electric device 300.
<Third Embodiment>

  The voice service server 100 may further change the conversation theme switching method, various determination methods, and the like according to the time zone, day of the week, and the like.

  In the following, as shown in FIG. 13, a time zone in which there is a high possibility of being able to concentrate on messages of the electric device 300 for each user, in other words, a time zone that is not busy for each user is referred to as a golden time. For example, the CPU 110 of the voice service server 100 has a high ratio of determination results of “interesting” based on the ratio of determination results of “interesting” to a message for each user or each electrical device 300, for example, 30 Set a time zone such as% or more as the golden time for each user. Alternatively, the CPU 110 has a large sum of both ratios based on the ratio of the determination result of “interested” and the ratio of the determination result of “listening” for each message for each user or each electric device 300, for example, 40 Set a time zone such as% or more as the golden time for each user. Or CPU110 is good also considering the time zone with many frequency | counts of the catch ball of the dialog with a user for every user or every electric equipment 300 as a golden time.

  However, the golden time does not need to be set for each user and may be common to all users, or may be set for each attribute such as age, sex, and address.

  Referring to FIG. 14, when it is determined that the user is interested in the message (YES in step S112), CPU 110 adds the current state to target electric device 300 or the user in addition to step S114. It is determined whether it is a golden time (step S116).

  When the current time is the golden time (YES in step S116), CPU 110 transmits data for advertisement via communication interface 160 (step S118). Then, as shown in FIG. 2, the electric device 300 outputs an advertisement based on the data from the voice service server 100. CPU110 memorize | stores the time when the user was interested in the message of the electric equipment 300, and correct | amends which raises the reaction frequency for judgment of golden time (step S119). CPU110 performs the process from step S132.

  On the other hand, if it is determined that the user has not shown interest in the message (NO in step S112), CPU 110 refers to the data in memory 120 to determine whether the user has heard the message (step). S122). If it is determined that the user has heard the message (YES in step S122), CPU 110 stores the time when the user listened to the message from electric device 300 in addition to step S124, and determines the golden time. The reaction frequency is maintained (step S126). CPU110 performs the process from step S132.

  If it is determined that the user has not heard the message (NO in step S122), CPU 110 stores the time when the user did not hear the message from electric device 300, and corrects to reduce the frequency of the golden time. (Step S128). CPU110 performs the process from step S132.

  Alternatively, referring to FIG. 15, CPU 110 refers to dialog scenario database 122, and if a message subsequent to the message output by electric device 300 is not prepared (NO in step S <b> 132), If the second predetermined time, for example, 20 seconds has elapsed since the conversation stopped (YES in step S142), CPU 110 determines whether the current time is the golden time for the target electrical device 300 or the user. Is determined (step S143).

  If the current time is the golden time (YES in step S143), CPU 110 executes the processing from step S144. On the other hand, if the current time is not the golden time (NO in step S143), CPU 110 waits for the next message from electrical device 300 via communication interface 160. Alternatively, Step S102 is repeated for each electrical device 300 after the first predetermined time has elapsed.

  Or with reference to FIG. 16, the case where it is not in dialog in step S102 is demonstrated. First, the CPU 110 determines whether or not the current time is the golden time for the target electric device 300 or the user (step S152). If the current time is the golden time (YES in step S152), CPU 110 determines whether or not a first predetermined time, for example, 10 seconds has elapsed since the conversation stopped (step S154). CPU110 performs the process from step S144, when 1st predetermined time passes (when it is YES in step S154).

  On the other hand, if the current time is not the golden time (NO in step S152), CPU 110 determines whether or not a second predetermined time, for example, 30 seconds, which is longer than the first predetermined time, has elapsed since the conversation stopped. Judgment is made (step S156). CPU110 performs the process from step S144, when 2nd predetermined time passes (when it is YES in step S156).

  Conversely, if the first predetermined time has not elapsed (NO in step S154), or the second predetermined time has not elapsed (NO in step S156), CPU 110 performs step. The processing from S102 is repeated.

As a result, the voice service according to the present embodiment has a high possibility that the user can afford to pay attention to the dialogue with the electric device 300, that is, during the golden time, a new topic is immediately created when the talk is interrupted. When a message is provided to the user and there is a high possibility that the user cannot afford to pay attention to the dialogue with the electric device 300, that is, when it is not the golden time, the next topic is provided to the user even if the talk is interrupted Wait for a while. As a result, it is possible to create a more comfortable situation for the user.
<Fourth embodiment>

  The voice service server 100 is not limited to simply extracting a scenario by selecting a theme in the order of theme IDs in the theme table 121, or extracting a scenario by selecting a randomly selected theme. For example, the CPU 110 of the voice service server 100 listens to a theme or topic that the user is likely to be interested in, or a user's question based on a history of past interest or a history of past hearing for each user or each electric device 300. It is preferable to prioritize themes and topics that are likely to be received.

  For example, the memory 120 of the voice service server 100 stores a user reaction table 123 as shown in FIG. 17 for each user or each electric device 300. The user reaction table 123 shows a correspondence relationship such as the theme ID, the number of conversation starts, the number of round trips of messages in an actual dialogue, and the average number of round trips of messages for one dialogue, that is, one scenario. Including. Note that the number of dialogue start times is the number of times a new scenario dialogue is started. The user reaction table 123 is used when selecting the next theme, but can also be used for various types of marketing by an advertisement provider.

  Then, as shown in FIG. 18, when it is determined that the user has shown interest in the message (YES in step S112), CPU 110 determines the number of round-trip messages related to the current conversation in addition to step S114. Add to the reaction table 123 or update the average (step S119B). CPU110 performs the process from step S132.

  Also, when it is determined that the user has heard the message (YES in step S122), the CPU 110 adds the number of round trips of the message related to the current dialogue to the reaction table 123 in addition to step S124. The average is updated (step S126B). CPU110 performs the process from step S132.

  In step S144, the CPU 110 specifies the next theme with reference to the reaction table 123 and the theme table 121 (step S144). For example, the CPU 110 performs weighting based on the average number of times, and then selects the next theme from all the themes. The CPU 110 refers to the dialogue scenario database 122, reads a series of messages corresponding to the identified theme, and transmits message data to the electrical device 300 via the communication interface 160 (step S146). At this time, the CPU 110 increments the number of dialog start times of the theme newly specified this time in the reaction table 123 by one.

  In addition, it is preferable that the theme table 121, the dialogue scenario database 122, and the reaction table 123 are set not only with the major classification theme but also with a smaller classification topic or keyword. Thereby, the CPU 110 of the voice service server 100 can further select a scenario suitable for the user.

As described above, when the dialogue with the user is likely to be delayed, the voice service server 100 may select a theme different from the previous theme or continuously select different scenarios of the same theme. In some cases. Then, since CPU 110 of voice service server 100 according to the present embodiment determines the next theme based on user reaction table 123, a theme of interest, for example, a theme with a high average number of catch balls of messages may be selected. And another scenario with the same theme is likely to be selected.
<Fifth embodiment>

  As shown in FIG. 3 or FIG. 4, the CPU 110 of the voice service server 100 puts a word for calling “Yes” or “By the way” when starting a conversation about a new theme or topic, It is preferable to output a new theme message from the electric device 300.

  More specifically, as shown in FIG. 19, the CPU 110 refers to the reaction table 123 and the theme table 121 to identify the next theme (step S144). Then, the CPU 110 reads a message corresponding to the identified theme, and adds a word for calling “yes” or “by the way” before the message (step S145). CPU 110 transmits message data to electrical device 300 via communication interface 160 (step S146). As a result, the CPU 310 of the electrical device 300 starts outputting a message after issuing a word for calling “Look” or “By the way” from the speaker 370 based on the data from the voice service server 100.

However, the memory 120 of the voice service server 100 may store a scenario database 122B as shown in FIG. That is, a scenario database 122B may include a scenario message 122B in which a word for calling “yes” or “by the way” is included in advance in the first message of the scenario. In this case, the CPU 110 may execute step S146 without executing the process of step S145.
<Sixth Embodiment>

  In the first to fifth embodiments, the CPU 110 of the voice service server 100 makes various determinations based on messages from the user, but is not limited to such a configuration. For example, the CPU 110 of the voice service server 100 may make various determinations based on images from the electrical device 300 instead of voice.

  Specifically, the CPU 310 of the electric device 300 may transmit the captured image of the camera 350 to the voice service server 100. And as shown in FIG. 21, CPU110 of the audio | voice service server 100 may analyze the image data from the electric equipment 300 (step S604).

  For example, when CPU 110 nods greatly (when YES at step S612), CPU 110 stores data indicating that the user is interested in association with the user and specific information such as a message or theme. 120 (step S114). When CPU 110 nods or swings his head (YES in step S622), CPU 110 correlates the user with specific information such as a message or a theme and listens to the user's message. Data indicating this is stored in the memory 120 (step S124).

  Alternatively, the CPU 110 determines that the user is interested in the message or outputs an advertisement when the user is smiling, and determines that the user has just heard the message when the user nods but is not smiling. Or may not output an advertisement.

  Alternatively, based on data from a proximity sensor or a temperature sensor serving as the operation unit 340 of the electric device 300, the user holds the hand over the electric device 300 or strokes or strikes the head of the electric device 300. It may be detected and transmitted to the voice service server 100 to that effect. The CPU 110 of the voice service server 100 may determine that the user is interested in the message based on such data from the electrical device 300 or may determine that the user has heard the message. Conversely, if the user does not touch the electrical device 300, the CPU 110 determines that the user is not interested in the message.

Alternatively, when the user presses a button as the operation unit 340 of the electric device 300, the fact may be transmitted to the voice service server 100. The CPU 110 of the voice service server 100 may determine that the user is interested in the message based on such data from the electrical device 300 or may determine that the user has heard the message. Conversely, if the user does not touch the electrical device 300, the CPU 110 determines that the user is not interested in the message.
<Seventh embodiment>

  In addition, it is not restricted to the structure, function, and operation | movement of the server 100 or the electric equipment 300 like the 1st-6th embodiment, For example, the role of each apparatus is shared with several apparatuses, such as another server and a database. May be. Conversely, some or all of the roles of a plurality of devices may be integrated into one device.

For example, as shown in FIG. 22, the stand-alone electric device 300A may have all the roles of the voice service server 100 according to the first to sixth embodiments. Alternatively, the electric device 300 may acquire only a part of update data of the interactive service from the voice service server 100, or may use information of the other servers 100B and 100C. Moreover, the electric device 300 may have only a part of the voice service server 100 according to the first to seventh embodiments.
<Other application examples>

  It goes without saying that the present invention can also be applied to a case where it is achieved by supplying a program to a system or apparatus. Then, a storage medium (or memory) storing a program represented by software for achieving the present invention is supplied to the system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores it in the storage medium. The effect of the present invention can also be enjoyed by reading and executing the program code.

  In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

  Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) running on the computer based on the instruction of the program code However, it is needless to say that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

  Furthermore, after the program code read from the storage medium is written to another storage medium provided in the function expansion board inserted into the computer or the function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that the CPU of the function expansion board or function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

1: Network system 100: Voice service server 100B: Information providing server 100C: Information providing server 110: CPU
110A: Dialog scenario selection unit 110B: Dialog scenario execution processing unit 110C: Association scenario search unit 120: Memory 121: Theme table 122: Dialog scenario database 122B: Dialog scenario database 123: User reaction table 140: Operation unit 160: Communication interface 300 : Electric equipment 300A: Robot 310: CPU
320: Memory 330: Display 330A: Light 330B: Light 340: Operation unit 350: Camera 360: Communication interface 370: Speaker 380: Microphone 390: Device driving unit

Claims (9)

A communication interface for communicating with a terminal having a speaker and a microphone;
A memory for storing multiple types of message information;
A processor for causing the terminal to perform message exchange with a user via the communication interface and causing the terminal to start outputting another type of message when it is determined that the message exchange is completed; A server comprising A communication interface for communicating with a terminal having a speaker and a microphone;
A memory for storing multiple types of message information;
A processor for causing the terminal to exchange messages with a user via the communication interface, and causing the terminal to start outputting another type of message when the message exchange is stopped for a predetermined time or more; Server to provide.   The server according to claim 1 or 2, wherein the processor causes the terminal to output advertisement information via the communication interface when a predetermined condition regarding message exchange with a user is satisfied.   The server according to claim 3, wherein the processor outputs the advertisement information based on a first time zone for each user.   5. The processor according to claim 1, wherein the processor changes a condition for causing the terminal to start outputting another type of message in a first time zone and a time zone other than that for each user. Server as described in the section.   The server according to claim 1, wherein the processor changes the another type of message to be output based on a message exchange with the user in the past. An information processing method in a server including a communication interface, a memory, and a processor,
The processor causing the terminal to exchange messages with a user via the communication interface;
An information processing method comprising: causing the terminal to start outputting another type of message when the processor determines that the message exchange ends or when the message exchange stops for a predetermined time or longer. . A terminal having a speaker for outputting a message and a microphone for obtaining a message from the user;
Allow the terminal to exchange messages with the user and start outputting another type of message to the terminal when it is determined that the exchange of messages has ended or when the exchange of messages has stopped for a predetermined time or longer A network system. Speakers,
With a microphone,
When the message is output to the speaker and the message exchange is determined to end based on the voice acquired through the microphone, or when the message exchange is stopped for a predetermined time or longer, another type of message is sent to the speaker. And a processor for starting output of the message.

Images