JP6817056B2 - Servers, information processing methods, network systems, and terminals - Google Patents

Description

The present invention relates to technologies for servers, information processing methods, network systems, and terminals for outputting voice such as messages.

Conventionally, a technique for outputting a message suitable for a user has been known. For example, Japanese Patent Application Laid-Open No. 2016-24636 (Patent Document 1) discloses a control device, a control method, and a control program. According to Patent Document 1, the control device is searched by a search unit that searches for advertisement information, which is information about an advertisement to be output as a response message, based on the characteristics of sound in a conversation between the dialogue agent system and the user. It is characterized by including an output control unit that controls to output an advertisement related to the advertisement information as a response message. Therefore, the control device can output a message suitable for the user.

Japanese Unexamined Patent Publication No. 2016-24636

An object of the present invention is to provide a technique for realizing a more suitable dialogue with a 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 communication interface for exchanging a message with a user to the terminal. A server is provided with a processor for causing the terminal to start outputting another type of message when it is determined to execute and the exchange of messages 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 to the terminal via the communication interface. Is executed, and when the exchange of messages is stopped for a predetermined time or longer, a server including a processor for causing the terminal to start outputting another type of message is provided.

Preferably, the processor causes the terminal to output advertising information via the communication interface when certain conditions for exchanging messages with the user are met.

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

Preferably, the processor makes the conditions for causing the terminal to start outputting another type of message differ between the first time zone and the other time zone for each user.

Preferably, the processor changes another type of message that is output based on past message exchanges with the user.

According to another aspect of the invention, there is provided a method of information processing in a server that includes a communication interface, memory, and a processor. The information processing method includes a step in which the processor causes the terminal to exchange a message with the user via the communication interface, and when the processor determines that the message exchange is completed or the message exchange is stopped for a predetermined time or longer. When this happens, it includes a step of causing the terminal to start outputting another type of message.

According to another aspect of the present invention, it is determined that a terminal having a speaker for outputting a message and a microphone for acquiring a message from the user and the terminal execute a message exchange with the user, and the message exchange is completed. A network system is provided that includes a server that causes the terminal to start outputting another type of message when the message is exchanged or when the exchange of messages is stopped for a predetermined time or longer.

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

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

It is a figure which shows the whole structure of the network system 1 which concerns on 1st Embodiment. It is a figure which shows the 1st operation outline of the network system 1 which concerns on 1st Embodiment. It is a figure which shows the 2nd operation outline of the network system 1 which concerns on 1st Embodiment. It is a figure which shows the 3rd operation outline of the network system 1 which concerns on 1st Embodiment. It is a block diagram which shows the structure of the voice service server 100 which concerns on 1st Embodiment. It is an image diagram which shows the theme table 121 which concerns on 1st Embodiment. It is an image diagram which shows the dialogue scenario database 122 which concerns on 1st Embodiment. It is a block diagram which shows the functional structure of the voice service server 100 in 1st Embodiment. It is a flowchart which shows information processing in voice service server 100 which concerns on 1st Embodiment. It is a block diagram which shows the structure of the electric apparatus 300 which concerns on 1st Embodiment. It is a flowchart which shows the 1st information processing in the voice service server 100 which concerns on 2nd Embodiment. It is a flowchart which shows the 2nd information processing in the voice service server 100 which concerns on 2nd Embodiment. It is a figure which shows the golden time of the 3rd Embodiment. It is a flowchart which shows the 1st information processing in the voice service server 100 which concerns on 3rd Embodiment. It is a flowchart which shows the 2nd information processing in the voice service server 100 which concerns on 3rd Embodiment. It is a flowchart which shows the 3rd information processing in the voice service server 100 which concerns on 3rd Embodiment. It is an image diagram which shows the reaction table 123 which concerns on 4th Embodiment. It is a flowchart which shows the information processing in the voice service server 100 which concerns on 4th Embodiment. It is a flowchart which shows the information processing in the voice service server 100 which concerns on 5th Embodiment. It is an image diagram which shows the dialogue scenario database 122B which concerns on 6th Embodiment. 6 is a flowchart showing information processing in the voice service server 100 according to the sixth embodiment. It is a figure which shows the operation outline of the electric apparatus 300 which concerns on 7th Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are designated by the same reference numerals. Their names and functions are the same. Therefore, the detailed description of them 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 an electric device (communication terminal) such as a robot 300A, a refrigerator, and an air conditioner. The electric device according to the present embodiment voice-outputs a message based on data from the voice service server 100 in response to a message from the user.

The electrical equipment (communication terminal) is not limited to the robot 300A, but also includes refrigerators, microwave ovens, air conditioners, washing machines, vacuum cleaners, air purifiers, humidifiers, dehumidifiers, rice cookers, home appliances such as lighting, and mobile phones. AV (audio / visual) equipment such as smartphones, TVs, hard disk recorders, projectors, music players, game machines, personal computers, built-in lighting, solar generators, interphones, water heaters, housing equipment such as hot water washing toilet seat controllers, etc. It may be. Hereinafter, these electric devices (communication terminals) are collectively referred to as an electric device 300.
<Outline of operation 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. 2 to 4. Regarding the network system 1 according to the present embodiment, a dialogue, that is, a voice message is exchanged by a user talking to an electric device 300 such as a robot 300A or the electric device 300 talking 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 previously output voice message according to the reaction of the user, and relates to the previously output voice message or the message. Determine if the user is interested in the topic.

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

Further, as shown in FIG. 4, the voice service server 100 elapses a predetermined time while the dialogue with the user regarding a certain theme is completed based on the data of the messages of a plurality of types of themes and scenarios prepared in advance. When that happens, start a dialogue on another topic based on the scenario data of another topic.

As described above, the voice service server 100 according to the present embodiment can facilitate the dialogue 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 becomes easy to make the user comfortable or maintain 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, one aspect of the hardware configuration of the voice service server 100 constituting the network system 1 according to the present embodiment will be described. Since the other information providing servers 100B and 100C also have the same configuration as the voice service server 100, the description will not be repeated here.

With reference to FIG. 5, the 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 part of the voice service server 100 by executing a program stored in the memory 120. For example, the CPU 110 executes a program 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 includes a program executed by the CPU 110, data generated by executing the program by the CPU 110, input data, the theme table 121, the dialogue scenario database 122, and the user being interested in the message. A database used for voice services such as data of a plurality of types of keywords of the first level indicating that the user has simply heard a message and data of a plurality of types of keywords of the second level indicating that the user has simply heard a message is stored. As a matter of course, these data may not be stored in the voice service server 100 itself, but may be stored in another device accessible to the voice service server 100.

Here, referring to FIG. 6, the theme table 121 stores the correspondence between the theme ID and the theme name for each theme. Further, referring to FIG. 7, the dialogue scenario database 122 stores the correspondence between the dialogue scenario ID, the theme ID, and the text data or the voice data for each scenario or each message. In the following, a series of messages for interacting with the user is also referred to as a scenario.

Therefore, in the present embodiment, the CPU 110 executes the program of the memory 120 to execute the dialogue scenario selection unit 110A, the dialogue scenario execution processing unit 110B, and the dialogue scenario execution processing unit 110B, as shown in FIG. 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 the exchange of messages with the user. The dialogue scenario execution processing unit 110B causes the electrical device 300 to execute a dialogue with the user by transmitting a message included in the scenario to the electrical device 300 via the communication interface 160.

Then, when the dialogue of the scenario ends, or when the dialogue ends and the silence continues for a predetermined time, or when the message following the current scenario is not prepared, the associative scenario search unit 110C selects the theme first. Search for scenarios related to or scenarios and messages, and extract new messages from the dialogue scenario database 122. As a result, the dialogue scenario execution processing unit 110B again transmits the message included in the scenario to the electric device 300 via the communication interface 160 in response to the message from the user, thereby causing the electric device 300 to interact with the user. To execute.

Returning to FIG. 5, the operation unit 140 receives an instruction from the service administrator or the like and inputs the instruction to the CPU 110.

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

The configurations of the other information providing servers 100B and 100C differ in the processing of the data in the memory 120 and the CPU 110, but the hardware configuration is almost the same as that of the voice service server 100, so the description is not repeated here.
<Information processing in the 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 periodically executes the following processing for each user or each electric device 300, and for each electric device 300. First, the CPU 110 determines whether or not the conversation is currently in progress (step S102). During the dialogue (when YES in step S102), the CPU 110 extracts the user's message from the voice data from the electric device 300 and analyzes the message (step S104).

The CPU 110 refers to the data in the memory 120 and determines whether or not the user is interested in the message output by the electric device 300 or the theme thereof (step S112). For example, the CPU 110 is interested in a series of messages when the extracted message contains first-level keywords such as "I love you !!", "Like", and a question from the user. If the message does not contain the first level keyword, it is determined that the user is not interested in the series of messages. Alternatively, when the CPU 110 gives a quiz to the user via the electric device 300, determines that the user is interested in a series of messages when the user answers, and does not answer the quiz. It may be determined that the user was not interested in the series of messages. Alternatively, when the user answers "Yes" or "Yeah" after asking the user "Are you interested?", It is determined that the user is interested in the series of messages, and the relevant message is applicable. If the question is answered with "No." or "Yeah." Or if there is no answer, it is determined that the user is not interested in the message.

When it is determined that the user is interested in the message (YES in step S112), the CPU 110 determines the user's specific information, the specific information of the message output by the electric device 300, the specific information of the theme, and the time zone. And, in association with, data indicating that the user is interested is stored in the memory 120 (step S114). The CPU 110 executes the process from step S132.

When it is determined that the user is not interested in the message (NO in step S112), the CPU 110 refers to the data in the memory 120 and determines whether or not the user has heard the message from the electric device 300. (Step S122). For example, if the extracted user's message contains a second-level keyword, such as "Yeah." Or "Hey.", The CPU 110 determines that the user has heard the message and puts the second level in the message. If the keyword at the level of is not included, it is determined that the user did not hear the message. Alternatively, when the user is asked "Hey, are you listening?" And then the user answers "Yes." Or "Yeah.", It is determined that the user has heard the message, and the question is answered. On the other hand, if there is an answer such as "No." Or "Yeah." Or if there is no answer, it is determined that the user did not hear the message.

When it is determined that the user has heard the message (YES in step S122), the CPU 110 determines the user's specific information, the specific information of the message output by the 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). The CPU 110 executes the process from step S132.

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

Preferably, the CPU 110 performs "per user, per user group such as age, address, gender, or whole user", "per message, or per theme, or per time zone", "message The ratio of listening or the ratio of showing interest in a 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, the CPU 110 refers to the dialogue scenario database 122 and determines whether or not a message following the message output by the electric device 300 is prepared. When the continuation message is prepared (YES in step S132), the CPU 110 causes the electric device 300 to continue the dialogue 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 electric device 300 every first predetermined time, for example, every second.

When the subsequent message is not prepared (NO in step S132), the CPU 110 refers to the theme table 121 and specifies the next theme (step S144). The CPU 110 may determine the next theme in the order of the theme ID of the theme table 121, may determine the next theme based on popular news, or may use user settings or a user as described later. The next theme may be decided based on the past history or the like.

The CPU 110 refers to the dialogue scenario database 122, reads the message corresponding to the specified theme, and transmits the message data to the electric device 300 via the communication interface 160 (step S146). As a result, the CPU 310 of the electric 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, for each electrical device 300, step S102 is repeated after the lapse of the first predetermined time.

On the other hand, when the dialogue is not in progress (YES in step S102), the CPU 110 determines whether or not a second predetermined time, for example, 20 seconds has elapsed since the dialogue was stopped (step S142). When the second predetermined time has elapsed (YES in step S142), the CPU 110 executes the process from step S144.

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

Next, with reference to FIG. 10, one aspect of the configuration of the electric device 300 constituting 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 drive unit 390 as main components.

The CPU 310 controls each part 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 provided via a device drive program, a conversation program, or other program executed by the CPU 310, data generated by executing the program by the CPU 310, data received from the voice service server 100 or another server, and an operation unit 340. And memorize the input data.

The display 330 outputs characters, images, and the like based on the signal from the CPU 310. As shown in FIG. 1, the display 330 may be simply the lights 330A and 330B.

The operation unit 340 is realized by a button, a touch panel, or 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 form a touch panel.

Further, 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 holds his / her hand over the electric device 300 via the proximity sensor or the temperature sensor as the operation unit 340, and starts various operations. For example, the electric device 300 may detect that the user is stroking or hitting the electric device 300 by arranging the proximity sensor near the forehead when the electric device 300 is a robot.

The camera 350 takes an image and passes 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 so that the server 100 can 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 another device 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, the CPU 310 causes the speaker 370 to output a voice message based on the voice data received from the server 100 via the communication interface 360. Alternatively, the CPU 310 creates a voice signal based on the text data received from the server 100 via the communication interface 360, and causes the speaker 370 to output a voice message. Alternatively, the CPU 310 reads the voice data of the message from the memory 320 based on the message ID received from the server 100 via the communication interface 360, and causes the speaker 370 to output the voice message.

The microphone 380 creates a voice signal based on the voice from the outside and inputs it to the CPU 310.

The device drive unit 390 controls each part (motor, heater, etc.) of the electric device 300 based on the signal from the CPU 310.

As described above, in the voice service according to the present embodiment, another topic is started when the message data for the subsequent dialogue is not prepared, or another topic is started when the dialogue is stopped and a predetermined time elapses. Since the topic of the above is started, the user of the electric device 300 is less likely to get bored and feel comfortable and comfortable. Further, in the voice service according to the present embodiment, for example, the voice service is provided with the provider of conversation information or advertisement information, "for each user, for each user group such as age, address, gender, or for the entire user. , "By message, by topic, by theme, or by time of day", "Percentage of listening to the message, or Percentage of interest in the message" and so on. Then, such information can be used for calculation of charges collected from advertisement providers, calculation of charges paid to other information providers, various marketing, and the like.
<Second Embodiment>

The voice service server 100 further outputs an advertisement for a company, a product, or a service from the electric device 300 when the user shows interest, speaks a positive message, or has a lively dialogue (see FIG. 2 and the like). ), It may have a function of not outputting an advertisement of a company, a product, or a service from the electric device 300 when the user does not show interest, speaks a negative message, or does not have a lively dialogue.

More specifically, referring to FIG. 11, if it is determined that the user is interested in the message (yes in step S112), the CPU 110 will be charged via the communication interface 160 in addition to step S114. Data for advertising is transmitted to the device 300 (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, when it is determined that the user is not interested in the message (NO in step S112), the CPU 110 determines whether or not the user has heard the message of the electric device 300 (step S122). In this case, the electric device 300 does not output the advertisement.

Alternatively, when it is determined that the user is interested in the message with reference to FIG. 12 (YES in step S112), the CPU 110, in addition to step S114, causes the user to perform electricity for the first predetermined number of times or more. It is determined whether or not the device 300 is responding to the message output, for example, whether or not the user has input the message to the electric device 300 more than the first predetermined number of times (step S116). When the user has input a message to the electric device 300 more than the first predetermined number of times (YES in step S116), the CPU 110 transmits the advertising data to the electric device 300 via the 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, when the user has not yet input the message to the electric device 300 more than the first predetermined number of times (NO in step S116), or when it is determined that the user is not interested in the message (in step S112). If NO), the CPU 110 does not cause the electric device 300 to output an advertisement.

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 determine that the user is negative if 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's message includes the second message, and the user's message. May determine that the user is positive if does not include the second message.

A positive first message and a negative second message are set in advance, and the CPU 110 of the voice service server 100 is positive when the user's message includes the first message. If the user's message contains the second message, the user is judged to be negative, and if the user's message does not contain any of the messages, the judgment is suspended until the next message. Good.

Alternatively, affirmative points indicating the degree of affirmation are given to each message. Positive messages such as "I love you" and "Highest" are given a large "positive" point, and negative messages such as "I hate you" and "No" are given "negative". Large points will be awarded. Then, the CPU 110 may determine that the points or accumulated points of the user's message are affirmative when they are equal to or more than a predetermined value, and may determine that they are not affirmative when they are less than a predetermined value.

Further, in the above embodiment, the advertisement information is output in response to the message of the positive user, and the advertisement information is not output in response to the message of the negative user, but the present embodiment is limited to such a form. 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's message and output the second advertisement information in response to a negative user's message. .. The first advertisement information includes more detailed contents than the second advertisement information. Alternatively, the first advertising information includes the company name and the product, and the second advertising information includes either the company name and the product.

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

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

The voice service server 100 may further change the method of switching the theme of the dialogue, various determination methods, and the like according to the time zone, the 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 that the message of the electric device 300 for each user can be concentrated, in other words, a time zone in which each user is not busy is referred to as a golden time. For example, the CPU 110 of the voice service server 100 has a large proportion of the determination results of "interested" based on the proportion of the determination results of "interested" for the message for each user or each electric device 300, for example, 30. Set the time zone such as% or more as the golden time for each user. Alternatively, the CPU 110 has a large sum of both ratios, for example, 40, based on the ratio of the "interested" judgment result and the "heard" judgment result ratio for the message for each user or each electric device 300. Set the time zone such as% or more as the golden time for each user. Alternatively, the CPU 110 may set a time zone in which the number of catch balls for dialogue with the user is large for each user or each electric device 300 as the golden time.

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

When it is determined that the user is interested in the message with reference to FIG. 14 (YES in step S112), the CPU 110, in addition to step S114, is currently present to the target electrical device 300 or the user. It is determined whether or not it is the golden time (step S116).

When the present is the golden time (YES in step S116), the CPU 110 transmits data for advertisement via the 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. The CPU 110 stores the time when the user is interested in the message of the electric device 300, and makes a correction to increase the reaction frequency for determining the golden time (step S119). The CPU 110 executes the process from step S132.

On the other hand, when it is determined that the user is not interested in the message (NO in step S112), the CPU 110 refers to the data in the memory 120 and determines whether or not the user has heard the message (step). S122). When it is determined that the user has heard the message (YES in step S122), the CPU 110 stores the time when the user heard the message of the electric device 300 in addition to step S124, and determines the golden time. Maintain the reaction frequency for (step S126). The CPU 110 executes the process from step S132.

When it is determined that the user has not heard the message (NO in step S122), the CPU 110 stores the time when the user did not hear the message of the electric device 300, and makes a correction to reduce the frequency of the golden time. (Step S128). The CPU 110 executes the process from step S132.

Alternatively, referring to FIG. 15, the CPU 110 refers to the dialogue scenario database 122, and when a message following the message output by the electric device 300 is not prepared (NO in step S132), When a second predetermined time, for example, 20 seconds has elapsed since the dialogue stopped (YES in step S142), the CPU 110 determines whether or not the current golden time is for the target electric device 300 or the user. Is determined (step S143).

When the current time is the golden time (YES in step S143), the CPU 110 executes the process from step S144. On the other hand, when the current time is not the golden time (NO in step S143), the CPU 110 waits for the next message from the electric device 300 via the communication interface 160. Alternatively, for each electrical device 300, step S102 is repeated after the lapse of the first predetermined time.

Alternatively, a case where the dialogue is not in progress in step S102 will be described with reference to FIG. 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). When the present is the golden time (YES in step S152), the CPU 110 determines whether or not the first predetermined time, for example, 10 seconds has elapsed since the dialogue stopped (step S154). When the first predetermined time has elapsed (YES in step S154), the CPU 110 executes the process from step S144.

On the other hand, when the current time is not the golden time (NO in step S152), the 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 dialogue was stopped. Determine (step S156). When the second predetermined time has elapsed (YES in step S156), the CPU 110 executes the process from step S144.

On the contrary, when the first predetermined time has not elapsed (NO in step S154) or the second predetermined time has not elapsed (NO in step S156), the CPU 110 is in step. The process from S102 is repeated.

As a result, the voice service according to the present embodiment is likely to have a new topic as soon as the talk is interrupted when the user can afford to focus on the dialogue with the electric device 300, that is, during the golden time. When it is highly likely that the message is provided to the user and the user cannot afford to be aware of the dialogue with the electrical device 300, that is, when it is not the golden time, even if the talk is interrupted, the next topic is provided to the user. 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 a form in which the themes are simply selected in the order of the theme IDs of the theme table 121 and the scenarios are extracted, or the themes randomly selected and the scenarios are extracted. For example, the CPU 110 of the voice service server 100 listens to themes and topics that the user is likely to be interested in, based on the history of past interests and the history of listening in the past for each user or each electric device 300. It is preferable to prioritize and select themes and topics that are likely to be available.

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 has a correspondence relationship such as a theme ID, the number of dialogue starts, the number of round trips of a message in an actual dialogue, and the average number of round trips of a message for one dialogue, that is, one scenario, for each theme. Including. The number of dialogue starts is the number of times the dialogue of a new scenario is started. The user reaction table 123 is used when selecting the next theme, but it can also be used by an advertisement provider or the like for various marketing or the like.

Then, as shown in FIG. 18, when it is determined that the user is interested in the message (YES in step S112), the CPU 110, in addition to step S114, counts the number of round trips of the message related to this dialogue. It is added to the reaction table 123 and the average is updated (step S119B). The CPU 110 executes 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 this dialogue to the reaction table 123 in addition to step S124. The average is updated (step S126B). The CPU 110 executes the process from step S132.

Then, 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 weights 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 specified theme, and transmits the message data to the electric device 300 via the communication interface 160 (step S146). At this time, the CPU 110 increments the number of dialogue starts of the theme newly specified this time in the reaction table 123.

In the theme table 121, the dialogue scenario database 122, and the reaction table 123, it is preferable that not only the themes of the major classification but also the topics and keywords of the smaller classification are set. As a result, the CPU 110 of the voice service server 100 can further select a scenario suitable for the user.

In this way, when the dialogue with the user is about to be delayed, the voice service server 100 may select a theme different from the previous theme, or continuously select another scenario of the same theme. In some cases. Then, since the CPU 110 of the voice service server 100 according to the present embodiment determines the next theme based on the user reaction table 123, there is a possibility that a theme of interest, for example, a theme having a large average number of catch balls of a message is selected. Is likely to be selected and another scenario with the same theme is likely to be selected.
<Fifth Embodiment>

As shown in FIG. 3 or 4, when starting a dialogue on a new theme or topic, the CPU 110 of the voice service server 100 inserts words for calling "yes" or "by the way", and then inserts words for calling. It is preferable to output a message of a new theme from the electric device 300.

More specifically, as shown in FIG. 19, the CPU 110 identifies the next theme with reference to the reaction table 123 and the theme table 121 (step S144). Then, the CPU 110 reads a message corresponding to the specified theme, and adds words for calling "so-so" or "by the way" before the message (step S145). The CPU 110 transmits message data to the electric device 300 via the communication interface 160 (step S146). As a result, the CPU 310 of the electric device 300 starts to output the message after issuing the words "so-so" and "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 the scenario database 122B as shown in FIG. That is, the first message of the scenario may include words for calling "yes" or "by the way" in the scenario database 122B in advance. 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 a message from the user, but the configuration is not limited to this. For example, the CPU 110 of the voice service server 100 may make various determinations based on the image from the electric device 300 instead of the 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. Then, as shown in FIG. 21, the CPU 110 of the voice service server 100 may analyze the image data from the electric device 300 (step S604).

For example, when the user makes a big nod (YES in step S612), the CPU 110 associates the user with specific information such as a message or theme and stores data indicating that he / she is interested. It is stored in 120 (step S114). Further, when the user makes a small nod or shakes his / her head (YES in step S622), the CPU 110 associates the user with specific information such as a message or theme, and the user listens to the message. Data indicating that 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 simply heard the message when the user nods but is not smiling. Or you may not output advertisements.

Alternatively, based on the data from the proximity sensor or the temperature sensor as the operation unit 340 of the electric device 300, the user holds his / her hand over the electric device 300 or strokes / hits the head of the electric device 300. It may be detected and sent 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 or that the user has heard the message, based on such data from the electrical device 300. 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, that 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 or that the user has heard the message, based on such data from the electrical device 300. Conversely, if the user does not touch the electrical device 300, the CPU 110 determines that the user is not interested in the message.
<7th Embodiment>

The structure, function, and operation of the server 100 and the electric device 300 as in the first to sixth embodiments are not limited, and for example, the role of each device is shared by a plurality of devices such as other servers and databases. May be done. Conversely, some or all of the roles of the 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 the update data of the dialogue service from the voice service server 100, or may use the information of the other servers 100B and 100C. Further, 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 when it is achieved by supplying a program to a system or device. Then, a storage medium (or memory) storing a program represented by software for achieving the present invention is supplied to the system or device, and the computer (or CPU or MPU) of the system or device stores the storage medium 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 function 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 embodiment are realized, but also the OS (operating system) running on the computer based on the instruction of the program code, etc. Needless to say, there is a case where a part or all of the actual processing is performed, and the processing realizes the function of the above-described embodiment.

Further, the program code read from the storage medium is written to another storage medium provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, and then based on the instruction of the program code. Needless to say, there are cases where the function expansion board, the CPU provided in the function expansion unit, or the like performs a part or all of the actual processing, and the processing realizes the functions of the above-described embodiment.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown by the scope of claims, not the above description, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1: Network system 100: Voice service server 100B: Information providing server 100C: Information providing server 110: CPU
110A: Dialogue scenario selection unit 110B: Dialogue scenario execution processing unit 110C: Associative scenario search unit 120: Memory 121: Theme table 122: Dialogue scenario database 122B: Dialogue scenario database 123: User reaction table 140: Operation unit 160: Communication interface 300 : Electrical 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: Equipment drive unit

Claims (7)

A communication interface for communicating with a terminal having a speaker and a microphone,
A memory that stores multiple types of message information, information in the first time zone, and a control program,
According to the control program, the terminal is made to exchange a message with a user via the communication interface, and when the exchange of the message is stopped for a first predetermined time or more in the first time zone, the terminal is separated. When the output of a message of the above type is started and the exchange of the message is stopped for a second predetermined time longer than the first predetermined time when it is not in the first time zone, another type of message is sent to the terminal. A server with a processor to initiate the output of. The server according to claim 1, wherein the processor outputs advertisement information to the terminal via the communication interface when a predetermined condition for exchanging a message with a user is satisfied. The server according to claim 2, wherein the processor outputs the advertisement information based on the first time zone set for each user. The server according to any one of claims 1 to 3, wherein the processor changes the message of the other type to be output based on the past exchange of messages with the user. An information processing method in a server including a communication interface, a memory, and a processor.
A step in which the processor causes a terminal to exchange messages with a user via the communication interface.
In the first time zone, when the processor stops exchanging the message for the first predetermined time or more, the step of causing the terminal to start outputting another type of message.
When the processor is not in the first time zone and the exchange of the message is stopped for a second predetermined time longer than the first predetermined time, the processor starts outputting another type of message to the terminal. An information processing method that includes steps to make it. A terminal having a speaker for outputting a message and a microphone for acquiring a message from the user,
The terminal is made to exchange messages with the user, and in the first time zone, when the exchange of the message is stopped for the first predetermined time or more, the terminal is started to output another type of message. A server that causes the terminal to start outputting another type of message when the exchange of the message is stopped for a second predetermined time or longer longer than the first predetermined time when it is not in the first time zone. Network system with. With speakers
With Mike
A memory that stores multiple types of message information, information in the first time zone, and a control program,
According to the control program, the speaker is made to output a message, and in the first time zone, when the exchange of the message is stopped for a first predetermined time or more, the speaker is made to start outputting another type of message. When the exchange of the message is stopped for a second predetermined time longer than the first predetermined time when it is not in the first time zone, a processor for starting the output of another type of message. A terminal to be equipped.

Images