JP7438479B1 - Automatic voice response device, automatic voice response method, automatic voice response program, and automatic voice response system - Google Patents

Abstract

[Problem] To realize automatic voice response that can respond according to the caller of a voice call. According to one embodiment, an automatic voice response device that performs voice interaction with a caller includes the steps of receiving a voice call request from a caller terminal, acquiring terminal information from the caller terminal, determining a response method based on the caller information including the terminal information; and when a voice call is started, performing a voice interaction with the caller according to the determined response method. automatic voice response device. [Selection diagram] Figure 6

Description

The present invention relates to an automatic voice response device, an automatic voice response method, an automatic voice response program, and an automatic voice response system.

2. Description of the Related Art In recent years, technology for automatically responding with voice to a caller of a voice call has become widespread. As such technology, for example, cited document 1 discloses an automatic voice response device that receives a call made by a caller and guides the caller to a desired service by exchanging voice or operations with the caller. a storage unit that stores a plurality of playback items in a predetermined playback order according to the type of interaction in order to prompt the caller to carry out the next interaction; and a storage unit that plays back the playback items in accordance with the playback order. a playback unit, a counting unit that counts the number of interactions for each type of interaction between the caller, and changing the playback order of the plurality of playback items according to the number of interactions counted by the counting unit. An automatic voice response device is disclosed which is characterized by having a playback change section.

JP2019-153835A

In automatic voice response, a response to a caller is made by outputting a preset message audibly. For this reason, only a uniform response can be made, and it is difficult to respond in accordance with the caller.

The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to realize an automatic voice response capable of responding according to the caller of a voice call.

According to one embodiment, an automatic voice response device that performs voice interaction with a caller includes the steps of receiving a voice call request from a caller terminal, acquiring terminal information from the caller terminal, and transmitting the terminal information. an automatic voice response that performs the following steps: determining a response method based on caller information included; and when a voice call is initiated, performing a voice interaction with the caller according to the determined response method. Device.

According to one embodiment, it is possible to realize an automatic voice response that can respond according to the caller of the voice call.

1 is a diagram showing an example of the configuration of an automatic voice response system 1000. FIG. 1 is a diagram showing an example of a hardware configuration of an automatic voice response device 1. FIG. 2 is a diagram showing an example of the hardware configuration of a caller terminal 2. FIG. 1 is a diagram showing an example of a functional configuration of an automatic voice response device 1. FIG. 2 is a diagram showing an example of a functional configuration of a caller terminal 2. FIG. It is a flowchart which shows an example of the process which the automatic voice response system 1000 based on 1st Embodiment performs. FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the first embodiment (1). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the first embodiment (1). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the first embodiment (2). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the first embodiment (3). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the first embodiment (4). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the second embodiment (1). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the second embodiment (2). FIG. 7 is a diagram illustrating an example of a method for determining a response method according to the second embodiment (3). It is a figure which shows an example of the determination method of the response method based on 3rd Example (1). It is a flowchart which shows an example of the process which the automatic voice response system 1000 based on 2nd Embodiment performs.

Hereinafter, each embodiment of the present invention will be described with reference to the accompanying drawings. Note that in the descriptions of the specifications and drawings related to each embodiment, the same reference numerals are given to the constituent elements having substantially the same functional configuration to omit redundant explanation.

[First embodiment]
<System configuration>
First, an overview of the automatic voice response system 1000 according to this embodiment will be explained. The automatic voice response system 1000 is an information processing system that automatically responds with voice to a caller of a voice call. The automated voice response system 1000 can realize a response tailored to the caller by determining a response method based on information about the caller. The automatic voice response system 1000 can be used for various services that require voice calls, such as making reservations for restaurants and accommodations, purchasing products, and applying for events.

FIG. 1 is a diagram showing an example of the configuration of an automated voice response system 1000. As shown in FIG. 1, the automated voice response system 1000 includes an automated voice response device 1 and a caller terminal 2, which are communicably connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination thereof. In the example of FIG. 1, the automatic voice response system 1000 includes one automatic voice response device 1 and one caller terminal 2, but it may include a plurality of each.

The automatic voice response device 1 is an information processing device that establishes a voice call with a speaker terminal 2 and executes a voice conversation with the caller on behalf of the receiver. The automatic voice response device 1 is, for example, a PC (Personal Computer), a smartphone, a tablet terminal, a server device, or a microcomputer, but is not limited thereto. In the example of FIG. 1, the automatic voice response device 1 is one information processing device, but it may be realized as a system consisting of a plurality of information processing devices connected via a network N.

The caller terminal 2 is an information processing device used by the caller to request a voice call from the receiver. A caller is a person requesting a voice call, and a recipient is any person receiving a request for a voice call. The recipient is, for example, a person, a corporation, or a store, but is not limited thereto. The sender requests a voice call to the receiver from a browser running on the caller terminal 2 or any application capable of making a voice call. The caller terminal 2 is, for example, a PC, a smartphone, or a tablet terminal, but is not limited thereto.

<Hardware configuration of automatic voice response device 1>
Next, the hardware configuration of the automatic voice response device 1 will be explained. FIG. 2 is a diagram showing an example of the hardware configuration of the automatic voice response device 1. As shown in FIG. As shown in FIG. 2, the automatic voice response device 1 includes a processor 101, a memory 102, a storage 103, a communication I/F 104, an input device 105, and an output device that are interconnected via a bus B1. 106 and a drive device 107.

The processor 101 controls each configuration of the automatic voice response device 1 by expanding various programs including an OS (Operating System) and an automatic voice response program stored in the storage 103 into the memory 102 and executing them. The functions of the automatic response device 1 are realized. The processor 101 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or a DSP (Digital Signal Processor), but is not limited thereto. .

The memory 102 is, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), or a combination thereof. The ROM is, for example, a PROM (Programmable ROM), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), or a combination thereof. The RAM is, for example, DRAM (Dynamic RAM) or SRAM (Static RAM), but is not limited thereto.

The storage 103 stores various programs and data including an OS and an automatic voice response program. The storage 103 is, for example, a flash memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an SCM (Storage Class Memories), but is not limited thereto.

The communication I/F 104 is an interface for connecting the automatic voice response device 1 to an external device via the network N and controlling communication. The communication I/F 104 is, for example, Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), or Ethernet (registered trademark), but is not limited thereto.

The input device 105 is a device for inputting information to the automatic voice response device 1. The input device 105 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a photographing device (camera), various sensors, or an operation button, but is not limited thereto.

The output device 106 is a device for outputting information from the automatic voice response device 1. The output device 106 is, for example, a display, a projector, a printer, a speaker, or a vibrator, but is not limited thereto.

The drive device 107 is a device that reads and writes data on the recording medium 108. The drive device 107 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or an SD card reader, but is not limited thereto. The recording medium 108 is, for example, a CD (Compact Disc), a DVD (Digital Versatile Disc), an FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray (registered trademark) Disc), or a USB (registered trademark). ) memory or SD card, but is not limited to this.

In this embodiment, the automatic voice response program may be written into the memory 102 or the storage 103 at the manufacturing stage of the automatic voice response device 1, or may be provided to the automatic voice response device 1 via the network N. Alternatively, the information may be provided to the automatic voice response device 1 via a non-transitory computer-readable recording medium such as the recording medium 108.

<Hardware configuration of caller terminal 2>
Next, the hardware configuration of the caller terminal 2 will be explained. FIG. 3 is a diagram showing an example of the hardware configuration of the caller terminal 2. As shown in FIG. As shown in FIG. 3, the caller terminal 2 includes a processor 201, a memory 202, a storage 203, a communication I/F 204, an input device 205, and an output device 206, which are interconnected via a bus B2. and.

The processor 201 controls each configuration of the caller terminal 2 and controls the functions of the caller terminal 2 by expanding various programs including the OS and automatic voice response program stored in the storage 203 into the memory 202 and executing them. Realize. The processor 201 is, for example, a CPU, MPU, GPU, ASIC, or DSP, but is not limited thereto.

Memory 202 is, for example, ROM, RAM, or a combination thereof. The ROM is, for example, a PROM, an EPROM, an EEPROM, or a combination thereof. RAM is, for example, DRAM or SRAM, but is not limited thereto.

The storage 203 stores various programs and data including an OS and an automatic voice response program. The storage 203 is, for example, a flash memory, an HDD, an SSD, or an SCM, but is not limited thereto.

The communication I/F 204 is an interface for connecting the caller terminal 2 to an external device via the network N and controlling communication. The communication I/F 204 is, for example, Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), or Ethernet (registered trademark), but is not limited thereto.

The input device 205 is a device for inputting information to the caller terminal 2. The input device 205 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a photographing device (camera), various sensors, or an operation button, but is not limited thereto. The caller terminal 2 includes a microphone 205C as the input device 205.

The output device 206 is a device for outputting information from the caller terminal 2. The output device 206 is, for example, a display, a projector, a printer, a speaker, or a vibrator, but is not limited thereto. The sender terminal 2 includes a display device 206D and a speaker 206S as the output device 206.

Note that in this embodiment, the automatic voice response program may be written into the memory 202 or the storage 203 during the manufacturing stage of the caller terminal 2, or may be provided to the caller terminal 2 via the network N. , may be provided to the caller terminal 2 via a non-transitory computer-readable recording medium, such as the recording medium 208.

<Functional configuration of automatic voice response device 1>
Next, the functional configuration of the automatic voice response device 1 will be explained. FIG. 4 is a diagram showing an example of the functional configuration of the automatic voice response device 1. As shown in FIG. As shown in FIG. 4, the automatic voice response device 1 includes a communication section 11, a storage section 12, and a control section 13.

The communication unit 11 is realized by the communication I/F 104. The communication unit 11 transmits and receives information to and from the caller terminal 2 via the network N.

The storage unit 12 is realized by a memory 102 and a storage 103. The storage unit 12 stores sender information 121, recipient DB 122, member DB 123, and response scenario information 124.

The sender information 121 is information regarding the sender. The sender information 121 includes terminal information 121a, member information 121b, voice information 121c, and procedure information 121d.

Terminal information 121a is information acquired from caller terminal 2. The terminal information 121a includes, for example, the session ID of the caller terminal 2, information about the page viewed by the caller (URL, title, query string, arbitrarily set identifier, etc.), information about the browser (browser type, version, settings, etc.). language, region, etc.), caller identification information (email address, phone number, name, membership number, etc.), device information (device type, version, language setting, region, etc.), or purpose of the voice call (reservation, etc.) Contains information indicating.

Member information 121b is member information corresponding to the sender. The member information 121b includes, for example, information indicating the sender's member ID, attributes (name, age, gender, address, family structure, occupation, membership rank, etc.), telephone number, email address, points held, or access log.

The voice information 121c is voice information of the voice uttered by the caller during the voice call.

The procedure information 121d is information regarding the procedure performed by the caller through voice dialogue. The procedure information 121d is extracted from the text obtained by converting the speech information 121c into text through speech recognition processing.

The recipient DB 122 is a DB (Database) of recipient information, which is information regarding persons registered as recipients in the automatic voice response system 1000. In the recipient DB 122, recipient information of a plurality of recipients is registered. The recipient information includes, for example, information indicating the recipient ID, name, address, telephone number, or email address.

The member DB 123 is a DB of member information that is information about people registered as members in the automatic voice response system 1000. Member information of a plurality of members is registered in the member DB 123. The member information includes, for example, information indicating a member ID, attributes (name, age, gender, address, family composition, occupation, member rank, etc.), telephone number, email address, points held, or access log.

The response scenario information 124 is information regarding a plurality of response scenarios prepared in advance for responses with the caller. A response scenario consists of a plurality of messages that are issued in sequence to the caller. The messages include, for example, messages corresponding to greetings, questions, or confirmations to the caller. Also,

The control unit 13 is realized by the processor 101 reading a program from the memory 102, executing it, and cooperating with other hardware configurations. The control unit 13 controls the entire operation of the automatic voice response device 1. The control unit 13 includes a voice call control unit 131, a caller information acquisition unit 132, a response method determination unit 133, and a voice interaction unit 134.

The voice call control unit 131 controls voice calls with the caller terminal 2.

The sender information acquisition unit 132 acquires the sender information 121.

The response method determination unit 133 determines a response method. The method for determining the response method includes, for example, selecting a response scenario to be used for voice dialogue, changing at least a part of the message included in the response scenario, selecting a message included in the response scenario, changing voice settings, or receiving terminal 3. including transfers to.

The voice interaction unit 134 executes voice interaction with the caller according to the response method determined by the response method determination unit 133.

Note that the functional configuration of the automatic voice response device 1 is not limited to the above example. For example, the automatic voice response device 1 may include part of the above functional configuration, and the caller terminal 2 may include the rest. Further, the automatic voice response device 1 may have a functional configuration other than the above. Further, each functional configuration of the automatic voice response device 1 may be realized by software as described above, or by hardware such as an IC chip, SoC (System on Chip), LSI (Large Scale Integration), or microcomputer. May be realized.

<Functional configuration of caller terminal 2>
Next, the functional configuration of the caller terminal 2 will be explained. FIG. 5 is a diagram showing an example of the functional configuration of the caller terminal 2. As shown in FIG. As shown in FIG. 5, the caller terminal 2 includes a communication section 21, a storage section 22, and a control section 23.

The communication unit 21 is realized by the communication I/F 204. The communication unit 21 transmits and receives information to and from the automatic voice response device 1 via the network N.

The storage unit 22 is realized by a memory 202 and a storage 203. The storage unit 22 stores terminal information 221.

The terminal information 221 is information regarding the caller terminal 2. The terminal information 221 includes, for example, the session ID of the caller terminal 2, information about the page viewed by the caller (URL, title, query string, arbitrarily set identifier, etc.), information about the browser (browser type, version, settings, etc.). language, region, etc.) or caller identification information (email address, phone number, name, membership number, etc.).

The control unit 23 is realized by the processor 201 reading a program from the memory 202, executing it, and cooperating with other hardware configurations. The control unit 23 controls the entire operation of the caller terminal 2. The control unit 23 includes a voice call control unit 231.

The voice call control unit 231 controls voice calls with the automatic voice response device 1 .

Note that the functional configuration of the caller terminal 2 is not limited to the above example. For example, the caller terminal 2 may include part of the above functional configuration, and the automatic voice response device 1 may include the rest. Further, the caller terminal 2 may have a functional configuration other than the above. Furthermore, each functional configuration of the caller terminal 2 may be realized by software as described above, or may be realized by hardware such as an IC chip, SoC, LSI, or microcomputer.

<Learning process executed by automatic voice response system 1000>
Next, the processing executed by the automatic voice response system 1000 will be explained. FIG. 6 is a flowchart illustrating an example of a process executed by the automatic voice response system 1000. In the following, a caller (For example, making a reservation) will be explained as an example. It is assumed that sender X is a member of web service Y, and provider Z is a recipient registered with web service Y.

(Step S101)
First, caller X displays web service Y on the display device 206D of caller terminal 2, logs in using his or her own member ID, and presses a call button provided on web service Y for provider Z. The caller terminal 2 accepts the operation of the call button (step S101).

(Step S102)
The communication unit 21 of the caller terminal 2 requests the automatic voice response device 1 to make a voice call to the operator Z. Further, the communication unit 21 of the caller terminal 2 transmits the terminal information 221 including the member ID of the caller X and the recipient ID of the provider Z to the automatic voice response device 1 (step S102).

(Step S103)
When the caller information acquisition unit 132 of the automatic voice response device 1 receives a voice call request from the caller terminal 2, it acquires the terminal information 221 from the caller terminal 2 and stores it in the storage unit 12 as the caller X's terminal information 121a. Save (step S103).

(Step S104)
The caller information acquisition unit 132 refers to the member ID of the caller X included in the terminal information 121a, obtains the member information of the caller Save (step S104).

(Step S105)
The response method determining unit 133 determines a response method based on the caller information 121 of the caller X and the response scenario information 124 (step S105). The method for determining the response method will be described in detail later.

(Step S106)
The voice call control unit 131 starts a voice call between the automatic voice response device 1 and the caller terminal 2 (step S106). The voice call may be started automatically, or may be started after the caller terminal 2 is notified of the start of the voice call and the caller responds to this notification.

(Step S107)
Thereafter, until the voice call ends, the voice interaction unit 134 of the automatic voice response device 1 executes voice interaction with the caller X according to the response method determined in step S105 (step S107).

(Step S108)
Specifically, the voice dialogue unit 134 transmits a message to the caller terminal 2 (step S108). The message may be text or audio.

(Step S109)
The voice call control unit 231 of the caller terminal 2 outputs the message received from the automatic voice response device 1 as a voice from the speaker 206S (step S109). When the message is text, the voice call control unit 231 synthesizes the text into speech and outputs the speech. If the message is voice, the voice call control unit 231 outputs the voice as is.

(Step S110)
When caller X speaks in response to the voice output message, caller terminal 2 transmits audio information of caller X's voice collected by microphone 205C to automatic voice response device 1 (step S110). .

(Step S111)
When the caller information acquisition unit 132 of the automatic voice response device 1 acquires the voice information from the caller terminal 2, it stores it in the storage unit 12 as the voice information 121c of the caller X (step S111).

Further, the caller information acquisition unit 132 converts the voice information 121c into text by voice recognition processing, extracts (acquires) the procedure information 121d from the obtained text, and stores it in the storage unit 12. As a result, information such as the reservation date and time, the name of the person making the reservation (caller), and the number of people making the reservation is acquired.

(Step S112)
The voice call control unit 131 determines whether the voice call termination condition is satisfied (step S112). The termination condition is, for example, that the voice call is disconnected from the caller terminal 2, that the voice call is disconnected due to communication failure, or that a termination message in the response scenario is sent. If the termination condition is not met (step S112: NO), the process returns to step S108, and the next message in the response scenario is transmitted (step S108). If the termination condition is satisfied (step S112: YES), the process proceeds to step S115.

(Step S113)
The voice call between the automatic voice response device 1 and the caller terminal 2 ends (step S113). After the voice call ends, the automatic voice response device 1 may transmit the procedure information 121d to the caller terminal 2 or to the operator Z, for example.

<How to determine response method>
Here, the method for determining the response method will be explained in detail.

[Example 1]
Based on the caller information 121, the response method determining unit 133 selects a response scenario to be used for voice dialogue from among a plurality of response scenarios prepared in advance. A plurality of response scenarios are prepared in association with caller information 121. A specific example will be explained below.

(1) The response method determining unit 133 can select a response scenario to be used for voice dialogue from among a plurality of response scenarios based on at least a part of the URL of the caller's viewing page (terminal information 121a). can.

For example, consider a case where web service Y is a reservation service for restaurants that lists a plurality of restaurants, and the URL of the page for each restaurant in web service Y includes an identifier for each restaurant. In this case, the response method determination unit 133 identifies the restaurant from the identifier included in the URL, and selects a response scenario corresponding to the restaurant.

In the example of FIG. 7, response scenarios 001 to 003 corresponding to restaurants 001 to 003, respectively, are prepared. When “http://xxx.com/xxx/001” is acquired as the URL of the caller's viewing page, the response method determining unit 133 responds based on the restaurant identifier (001) included in the URL. Select scenario 001.

Further, for example, consider a case where web service Y is a restaurant reservation service in which a plurality of restaurants are listed, and the URL of the inquiry page of web service Y includes an identifier of the content of the inquiry. In this case, the response method determining unit 133 identifies the content of the inquiry from the identifier included in the URL, and selects a response scenario corresponding to the content of the inquiry.

In the example of FIG. 8, response scenarios 001 to 003 are prepared respectively corresponding to reservations, changes in reservation details, and cancellations of reservations. When "http://xxx.com/xxx/reservation" is acquired as the URL of the caller's viewing page, the response method determining unit 133 responds based on the identifier (reservation) of the inquiry content included in the URL. Select scenario 001.

In this way, the automatic voice response system 1000 selects a response scenario to be used for voice interaction from a plurality of response scenarios based on at least part of the URL of the page the caller is viewing. Without having to prepare a telephone number for each inquiry content, it is possible to carry out a voice dialogue with the caller using a response message according to the recipient and the inquiry content.

(2) The response method determining unit 133 selects a response scenario to be used for voice dialogue from among a plurality of response scenarios based on at least a part of the query string (terminal information 121a) of the caller's viewing page. be able to.

For example, the response method determining unit 133 selects a response scenario corresponding to the keyword from the keyword included in the query string. The keyword is, for example, a reference source of a viewed page, a media name, a campaign name, a content name, or a keyword of a paid search advertisement, but is not limited thereto. Further, the response method determining unit 133 may select a response scenario corresponding to a combination of keywords from among a combination of keywords included in the query string.

In the example of FIG. 9, response scenarios 001 and 002 are prepared for a purchase application for product 001, corresponding to normal times and sale times, respectively. When "utm_campaign=sale&utm_content=product001" is acquired as the query string of the page viewed by the sender, the response method determining unit 133 determines the response method based on the campaign type (sale) and product identifier (product001) included in the query string. and select response scenario 001.

In this way, the automated voice response system 1000 selects a response scenario to be used for voice interaction from a plurality of response scenarios based on at least a part of the query string of the page viewed by the caller. It is possible to carry out voice dialogue with the caller by using a response message according to the recipient's viewing page without having to prepare a telephone number for each recipient's viewing page.

(3) The response method determining unit 133 can select a response scenario to be used for voice dialogue from among a plurality of response scenarios based on the language or region (terminal information 121a) set in the browser of the caller terminal 2. can.

In the example of FIG. 10, Japanese and English response scenarios 001 and 002 are prepared, respectively. When "Accept-Language=en" is acquired as the browser setting language, the response method determining unit 133 selects the English response scenario 002.

In this way, the automatic voice response system 1000 selects a response scenario to be used for voice dialogue from among a plurality of response scenarios based on information regarding the browser of the caller terminal 2. You can carry out voice dialogue with the caller using the response message according to the caller.

(4) The response method determining unit 133 can select a response scenario to be used for voice dialogue from among a plurality of response scenarios based on the caller's attributes (member information 121b).

In the example of FIG. 11, response scenarios 001 and 002 corresponding to member ranks A and B are prepared, respectively. If the caller's membership rank is "membership rank A," the response method determining unit 133 selects response scenario 001 corresponding to membership rank A.

In this way, by selecting a response scenario to be used for voice dialogue from a plurality of response scenarios based on information regarding the attributes of the caller, the automatic voice response system 1000 can respond in accordance with the attributes of the caller. Messages can be used to carry out a voice interaction with the caller. For example, it is possible to select response messages with different greetings depending on the caller's membership rank (see Figure 11), or select response messages with different speaking styles depending on the caller's age, gender, or occupation. It will be done.

[Example 2]
The response method determining unit 133 generates at least a portion of the message included in the response scenario based on the sender information 121. More specifically, the response method determining unit 133 generates a message to be used for voice dialogue by adding information according to the caller information 121 to the message template of the response scenario. Here, it is assumed that there is only one response scenario used for voice dialogue or that it has already been selected. A specific example will be explained below.

(1) The response method determining unit 133 generates a message to be used for voice dialogue by adding the title of the caller's viewing page (terminal information 121a) to the message template. The title corresponds to the recipient's name.

In the example of FIG. 12, a response scenario template is prepared that includes the message "Thank you for contacting [title]." [title] is a tag to which the title of the page viewed by the sender is added. When "xxx Shopping" is acquired as the title of the page viewed by the caller, the response method determining unit 133 generates a message "Thank you for contacting XXX Shopping." by adding the title to the template. do.

In this way, by generating at least a part of the message included in the response scenario based on the title of the page viewed by the caller, the automated voice response system 1000 can receive messages without preparing messages for each recipient. A message containing the person's name can be used to carry out a voice interaction with the caller.

(2) The response method determination unit 133 refers to the recipient DB 122, identifies the recipient's name from the recipient's identification information (terminal information 121a) set on the sender's viewing page, and sets it in the message template. By adding it, a message to be used for voice dialogue is generated. The recipient's identification information is included in the URL or query string of the viewing page.

In the example shown in FIG. 13, a response scenario template is provided that includes the message "Thank you for contacting [name]." [name] is a tag to which the recipient's name is added. When the recipient's name is identified as "xxx Co., Ltd." from the recipient's identification information, the response method determining unit 133 adds the recipient's name to the template, thereby adding "Thank you for contacting XXX Co., Ltd." ” message will be generated.

In this way, by generating at least a part of the message included in the response scenario based on the recipient's identification information set on the caller's viewing page, the automated voice response system 1000 generates a message for each recipient. Messages that include the recipient's name can be used to conduct a voice conversation with the caller without having to prepare a message.

(3) The response method determining unit 133 refers to the caller information 121b, identifies the caller's name from the caller's member ID, and adds it to the message template to generate a message to be used for voice dialogue. do.

In the example shown in FIG. 14, a response scenario template is provided that includes the message "Dear [name], thank you for calling." [name] is a tag to which the caller's name is added. When the caller's name is identified as "Taro Sato" from the member ID, the response method determining unit 133 adds the caller's name to the template to say "Mr. Taro Sato, thank you for calling." Generate a message.

In this manner, by generating at least a portion of the messages included in the response scenario based on the member ID, the automated voice response system 1000 utilizes the message that includes the caller's name to communicate with the caller via voice communication. Dialogue can be carried out.

[Example 3]
Based on the caller information 121, the response method determining unit 133 selects at least one message to be used for voice interaction from among the plurality of messages included in the response scenario. Here, it is assumed that there is only one response scenario used for voice dialogue or that it has already been selected. A specific example will be explained below.

(1) The response method determining unit 133 selects a message corresponding to a question whose answer is not included in the member information 121b from among a plurality of messages (question messages) corresponding to a question to the caller included in the response scenario, in a voice dialogue. Select as the message to be used for.

In the example of FIG. 15, the response scenario includes question messages 1 to 3. Since the sender's name (answer to question message 1) can be obtained as the member information 121b, the response method determining unit 133 requests an answer other than the caller's name among question messages 1 to 3 included in the response scenario. Question messages 1 and 2 are selected as messages to be used for voice dialogue.

In this way, by selecting a question message whose answer is not included in the member information 121b as a message to be used for voice dialogue, the automatic voice response system 1000 uses the question message according to the caller information 121 to send a message. You can carry out voice dialogue with other people.

[Example 4]
The response method determining unit 133 changes the audio settings used for audio dialogue based on the caller information 121. Here, it is assumed that there is only one response scenario used for voice dialogue or that it has already been selected. A specific example will be explained below.

(1) The response method determining unit 133 changes the audio settings used for audio dialogue based on the caller's attributes (member information 121b). The voice settings include at least one of voice gender, age, speed, pitch, and speaking style. The speaking style includes at least one of the following: simplicity of expression, politeness, presence or absence of technical terms, and dialect. For example, the gender of the voice may be matched to the gender of the caller, or the pitch of the voice may be lowered if the caller is over a predetermined age.

In this way, by changing the audio settings used for voice interaction based on the attributes of the caller, the automatic voice response system 1000 can perform voice interaction with the caller using the voice according to the attributes of the caller. can do.

(2) The response method determining unit 133 changes the audio settings used for audio dialogue based on the caller's audio (audio information 121c). In this embodiment, step S105 is additionally executed during execution of step S107. Specifically, the response method determining unit 133 performs voice analysis on the voice information 121c acquired through voice interaction with the caller to acquire elements of the caller's voice (volume, pitch, pitch, formant, etc.). , change the audio settings used for audio dialogue to audio settings that correspond to the elements of the caller's voice. For example, it is conceivable to match the pitch of the voice used for voice dialogue to the pitch of the caller's voice, or to match the volume of the voice used for voice dialogue to the volume of the caller's voice.

In this way, by changing the audio settings used for voice interaction based on the caller's voice, the automatic voice response system 1000 can execute voice interaction with the caller using a voice that corresponds to the caller's voice. can do.

Note that the response method determining unit 133 may determine a response method by combining two or more of the embodiments 1 to 4 described above. As a result, for example, the response method determining unit 133 selects a response scenario (Example 1), changes a message (Example 2), and selects a message (Example 3) based on the caller information 121. , the audio settings can be changed (Embodiment 4).

<Summary>
As described above, according to the present embodiment, the automatic voice response device 1 that performs a voice conversation with a caller includes step S103 of accepting a voice call request from the caller terminal 2, and receiving terminal information 121a from the caller terminal 2. Step S103 of acquiring, Step S105 of determining a response method to be used for voice dialogue based on caller information 121 including terminal information 121a, and when a voice call is started, the caller The automatic voice response device 1 is realized which executes step S107 of executing voice dialogue.

In this way, by determining the response method based on the caller information 121 (at least one of the terminal information 121a, the member information 121b, and the voice information 121c), the voice automation system can respond in accordance with the caller of the voice call. response can be realized.

Although the present embodiment has been described on the assumption that the storage unit 12 has the member DB 123, the storage unit 12 does not need to have the member DB 123. In this case, the automatic voice response device 1 may determine the response method using the caller information 121 other than the member information 121b. This also applies when the member information 121b of the sender does not exist in the member DB 123.

Further, the automatic voice response device 1 may acquire the member information 121b from the caller terminal 2. In this case, the caller inputs the member information 121b into the input form of the caller terminal 2, and the caller terminal 2 transmits the member information 121b to the automatic voice response device 1 together with the terminal information 121a. The automatic voice response device 1 can determine a response method using the member information 121b acquired from the caller terminal 2.

Furthermore, in this embodiment, when the caller operates the call button, the automatic voice response device 1 acquires all the terminal information 121a, but when the caller operates multiple buttons, the automatic voice response device 1 may acquire the terminal information 121a in stages.

For example, when a caller operates a call button, the automatic voice response device 1 acquires terminal information 121a such as a session ID, and transmits a preset message to the caller terminal 2. After that, a button for selecting the purpose of the voice call is displayed on the caller terminal 2, and when the caller selects the desired button, the automatic voice response device 1 displays information indicating the purpose of the voice call corresponding to the selected button, etc. The terminal information 121a is acquired and a response method is determined. That is, when the automatic voice response device 1 acquires the terminal information 121a in stages, the automatic voice response device 1 only needs to determine the response method after the terminal information 121a necessary for determining the response method is collected. The automatic voice response device 1 may acquire the terminal information 121a in three or more steps.

[Second embodiment]
In this embodiment, a case will be described in which the automatic voice response device 1 determines whether to perform a voice conversation with the caller or transfer the voice call to the receiver terminal 3 based on the caller information 121.

The receiver terminal 3 is an information processing device that the receiver uses for voice communication with the caller. The recipient uses the recipient terminal 3 to make a voice call with the caller. The recipient terminal 3 is, for example, a telephone, a PC, a smartphone, or a tablet terminal, but is not limited thereto.

FIG. 16 is a flowchart illustrating an example of processing executed by the automatic voice response system 1000. It is assumed that the recipient terminal 3 is a telephone.

Further, steps S201 to S204 in FIG. 16 are the same as steps S101 to S104 in FIG. 6, so the explanation will be omitted.

(Step S205)
The response method determination unit 133 determines a response method based on the caller information 121 of the caller X (step S205). More specifically, the response method determining unit 133 determines whether to perform a voice conversation with the caller or transfer the voice call to the receiver terminal 3 based on the caller information 121 of the caller X.

The response method determining unit 133 determines whether to perform a voice conversation with the caller or transfer the voice call to the receiver terminal 3, based on the caller's membership rank (member information 121b), for example. For example, if the member rank is lower than a predetermined rank, the response method determination unit 133 determines to perform a voice conversation, and if the member rank is equal to or higher than a predetermined rank, the response method determination unit 133 determines to transfer the voice call to the recipient terminal 3. . This makes it possible to respond in accordance with the caller's membership rank.

In step S205, if the response method determination unit 133 determines to perform a voice dialogue with the caller, the subsequent processing is the same as that from S106 onward in FIG. 6, so the description thereof will be omitted. On the other hand, if the response method determination unit 133 determines in step S205 to transfer the voice call to the recipient terminal 3, the process proceeds to step S206.

(Step S206)
The voice call control unit 131 transfers the voice call to the recipient terminal 3 (step S206). Specifically, the voice call control unit 131 makes a call (requests a voice call) to the recipient terminal 3 (step S206).

(Step S207)
The recipient receives a call (responses to the voice call request) at the recipient terminal 3 (step S207). Thereby, a telephone connection is established between the automatic voice response device 1 and the recipient terminal 3. Note that if the recipient does not receive a call at the recipient terminal 3 within a predetermined period of time, the process proceeds to S106 in FIG.

(Step S208)
The voice call control unit 131 starts a voice call between the sender terminal 2 and the receiver terminal 3 (step S208).

(Step S209)
During the voice call, the automatic voice response device 1 receives the recipient's uttered voice from the recipient terminal 3, and transfers it to the caller terminal 2 (step S209).

(Step S210)
Further, during the voice call, the automatic voice response device 1 receives the voice uttered by the caller from the caller terminal 2, and transfers it to the receiver terminal 3 (step S210). As a result, the caller and receiver have a voice conversation via the automatic voice response device 1.

(Step S211)
When the caller or the receiver performs an operation to end the call using the caller terminal 2 or the receiver terminal 3, the voice call between the caller terminal 2 and the receiver terminal 3 ends (step S211).

<Summary>
As explained above, according to the present embodiment, the determining step S205 determines whether to perform a voice dialogue or transfer the voice call to the receiver terminal 3 based on the caller information 121, and If it is determined that the voice call should be transferred to , the voice call between the sender terminal 2 and the receiver terminal 3 is started. Thereby, depending on the caller, it is possible to use the voice dialogue by the automatic voice response device 1 or the voice conversation with the recipient.

<Additional notes>
This embodiment includes the following disclosure.

(Additional note 1)
An automatic voice response device that performs voice dialogue with a caller,
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method to be used for voice dialogue based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
Automatic voice response device that performs.

(Additional note 2)
The automatic voice response device according to appendix 1, wherein the determining step selects a response scenario to be used for the voice dialogue from among a plurality of response scenarios based on the caller information.

(Additional note 3)
The automatic voice response device according to appendix 2, wherein the determining step selects a response scenario to be used for the voice dialogue based on the URL of the page viewed by the caller or a query string.

(Additional note 4)
The automatic voice response device according to appendix 2, wherein the determining step selects a response scenario in a language corresponding to the language setting of the browser of the caller terminal as the response scenario to be used for the voice dialogue.

(Appendix 5)
The automatic voice response device according to appendix 2, wherein the determining step selects a response scenario corresponding to the attribute of the caller as a response scenario to be used for the voice dialogue.

(Appendix 6)
The automatic voice response device according to appendix 1, wherein the determining step generates at least a part of the message included in the response scenario based on the caller information.

(Appendix 7)
The automatic voice response device according to appendix 6, wherein the determining step generates a message including the name of the sender or the recipient.

(Appendix 8)
The automatic voice response device according to appendix 1, wherein the determining step selects at least one message to be used for the voice interaction from among a plurality of messages included in the response scenario, based on the caller information.

(Appendix 9)
According to appendix 8, the determining step selects a message corresponding to a question whose answer is not included in the caller information, from among messages corresponding to questions to the caller, as a message to be used for the voice dialogue. Automatic voice response device.

(Appendix 10)
The automatic voice response device according to supplementary note 1, wherein the step of determining changes the voice settings used for the voice dialogue based on the caller information.

(Appendix 11)
The automatic voice response device according to appendix 10, wherein the voice setting includes at least one of voice gender, age, speed, height, and speaking style.

(Appendix 12)
The automatic voice response device according to appendix 10, wherein the step of determining changes the voice settings used for the voice dialogue during a voice call based on voice information of the caller.

(Appendix 13)
The determining step includes determining whether to perform a voice dialogue or transferring the voice call to the recipient terminal based on the caller information, and when it is determined to transfer the voice call to the recipient terminal, the caller The automatic voice response device according to supplementary note 1, which starts a voice call between a terminal and the recipient terminal.

(Appendix 14)
An automatic voice response method executed by an automatic voice response device that performs a voice conversation with a caller, the method comprising:
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method to be used for voice dialogue based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
automatic voice response methods including;

(Appendix 15)
A voice automatic response device that communicates with the caller by voice,
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method to be used for voice dialogue based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
A voice automatic response program that executes a voice automatic response method including.

(Appendix 16)
An automatic voice response system that performs voice dialogue with a caller,
Comprising a caller terminal and an automatic voice response device,
The automatic voice response device includes:
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method to be used for voice dialogue based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
An automatic voice response system that runs

The embodiments disclosed herein are illustrative in all respects and should not be considered restrictive. The scope of the present invention is indicated by the scope of the claims, not the meaning described above, and is intended to include meanings equivalent to the scope of the claims and all changes within the scope. Further, the present invention is not limited to the embodiments described above, and various modifications can be made within the scope of the claims, and can be obtained by appropriately combining technical means disclosed in different embodiments. The embodiments are also included in the technical scope of the present invention.

1: Automatic voice response device 2: Caller terminal 11: Communication unit 12: Storage unit 13: Control unit 121: Caller information 122: Receiver DB
123: Member DB
124: Response scenario information 131: Voice call control unit 132: Caller information acquisition unit 133: Response method determination unit 134: Voice dialogue unit

Claims (12)

An automatic voice response device that performs voice dialogue with a caller,
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
Run
In the step of determining, the automatic voice response device selects a response scenario to be used for the voice interaction from among a plurality of response scenarios having different contents, based on the URL of the viewing page of the caller or a query string . 2. The automatic voice response device according to claim 1, wherein the determining step selects a response scenario in a language corresponding to a language set in a browser of the caller terminal as a response scenario to be used for the voice dialogue. The automatic voice response device according to claim 1, wherein the determining step selects a response scenario corresponding to an attribute of the caller as a response scenario to be used for the voice dialogue. The automatic voice response device according to claim 1, wherein the step of determining generates at least a part of the message included in the response scenario based on the caller information. 5. The interactive voice response device of claim 4 , wherein the step of determining generates a message that includes the name of the sender or recipient. The automatic voice response device according to claim 1, wherein the step of determining selects at least one message to be used for the voice interaction from among a plurality of messages included in the response scenario, based on the caller information. The automatic voice response device according to claim 1, wherein the step of determining changes audio settings used for the voice interaction based on the caller information. The automatic voice response device according to claim 7 , wherein the voice settings include at least one of voice gender, age, speed, pitch, and speaking style. The determining step determines whether to perform a voice dialogue or transfer the voice call to the receiver terminal based on the caller information, and if it is determined to transfer the voice call to the receiver terminal, the caller The automatic voice response device according to claim 1, which initiates a voice call between a terminal and the recipient terminal. An automatic voice response method executed by an automatic voice response device that performs a voice conversation with a caller, the method comprising:
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
Run
In the automatic voice response method, the determining step selects a response scenario to be used for the voice dialogue from among a plurality of response scenarios having different contents based on the URL of the page viewed by the caller or a query string . A voice automatic response device that communicates with the caller by voice,
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
Run
The determining step executes an automatic voice response method that selects a response scenario to be used for the voice dialogue from among a plurality of response scenarios with different contents based on the URL of the page viewed by the caller or a query string. A voice automatic response program that allows you to An automatic voice response system that performs voice dialogue with a caller,
Comprising a caller terminal and an automatic voice response device,
The automatic voice response device includes:
accepting a voice call request from a caller terminal;
obtaining terminal information from the caller terminal;
determining a response method based on caller information including the terminal information;
When a voice call is initiated, performing a voice interaction with the caller according to the determined response method;
Run
In the automatic voice response system, the determining step selects a response scenario to be used for the voice dialogue from among a plurality of response scenarios having different contents, based on the URL of the page viewed by the caller or a query string .