JP2016103270A - Information processing system, receiving server, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve efficiency of an operation for receiving an inquiry from a customer.SOLUTION: In an information processing system 1, a voice recognition section 104 receives an inquiry from a terminal device 70, and an intention/state interpretation section 107 determines whether an answer for the inquiry can be searched from an FAQ search database 154, executes complementary processing for complementing information for the answer when the answer cannot be searched, and generates an answer on the basis of a result of the complementary processing. The intention/state interpretation section 107 determines whether the answer for the inquiry has been generated or not, and transmits the answer searched or the answer generated when a determination is made that the answer can be searched or the answer has been generated for the inquiry. A communicator call section 112 executes call processing of a communicator when the intention/state interpretation section 107 determines that the answer cannot be generated.SELECTED DRAWING: Figure 4

Description

  The present invention relates to an information processing system, a reception server, an information processing method, and a program.

Conventionally, a technology for automating call center operations for receiving inquiries from customers is known.
For example, a system is known that responds to inquiries by telephone from a customer to a call center by using an automatic voice response (IVR). There is also known a system that accepts an inquiry from a customer to a call center via the Internet or the like using a virtual operator (VO).
A technique for automating call center operations is described in Patent Document 1, for example.

Japanese Patent Application Laid-Open No. 2014-178381

  However, in the conventional technology for automating the call center business, the actual situation is that the usage form is limited, for example, the business to be automated is limited to Q & A distribution. Therefore, the business of receiving inquiries from customers has not been made sufficiently efficient.

  The present invention has been made in view of such a situation, and an object of the present invention is to further improve the efficiency of operations for receiving inquiries from customers.

In order to achieve the above object, an information processing system according to one embodiment of the present invention includes:
An information processing system including a terminal device that transmits an inquiry and a reception server that receives the inquiry transmitted from the terminal device,
The reception server is
Accepting means for accepting the inquiry from the terminal device;
First determination means for determining whether or not an answer to the inquiry can be searched from a response database in which a plurality of prepared questions and answers are stored;
When it is determined by the first determination means that an answer to the inquiry cannot be searched, a replenishment process for replenishing information for performing an answer to the inquiry is executed, and the inquiry is answered based on the result of the replenishment process An answer generating means for generating an answer;
Second determination means for determining whether or not an answer to the inquiry has been generated by the answer generation means;
The answer retrieved by the first determination means when the first determination means determines that the answer to the inquiry can be searched and when the second determination means determines that the answer to the inquiry can be generated. Or answering means for sending the answer generated by the second determining means;
Call means for executing a call process of a communicator corresponding to the inquiry when the second determination means determines that an answer to the inquiry could not be generated;
It is characterized by including.

  According to the present invention, it is possible to further improve the efficiency of operations for receiving inquiries from customers.

It is a figure showing the system configuration of the information processing system concerning the present invention. It is a figure which shows the hardware constitutions of the server computer which comprises each server. It is a figure which shows the hardware constitutions of a terminal device. It is a block diagram which shows the main function structures implement | achieved in an information processing system. It is a flowchart which shows the flow of the reception process which an information processing system performs. It is a figure which shows the example of a display screen displayed on a terminal device in a reception process. It is a flowchart which shows the flow of a VOC collection process. It is a flowchart which shows the flow of the knowledge management process which an information processing system performs. It is a block diagram which shows the main function structures implement | achieved in the information processing system which concerns on 2nd Embodiment. It is a flowchart which shows the flow of the cooperation process which the information processing system which concerns on 2nd Embodiment performs. It is a figure which shows the example of a display screen displayed on a terminal device in a cooperation process. It is a figure which shows the example of a display screen displayed on PC for communicators in a cooperation process.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[First Embodiment]
[Constitution]
[System configuration]
FIG. 1 is a diagram showing a system configuration of an information processing system 1 according to the present invention.

  The information processing system 1 constitutes a proxy call center system that integrates and processes call center operations of a plurality of companies. In the information processing system 1, primary inquiries are made using a virtual operator (VO) capable of voice recognition in response to an inquiry from a customer, and a virtual operator answers a fixed inquiry in which an answer is prepared in advance. Answer. Further, in the information processing system 1, when a virtual operator executes a process of supplementing information for generating an answer (supplement process) in response to an inquiry for which no answer is prepared in advance, Answer by virtual operator. Furthermore, in the information processing system 1, an inquiry that needs to be handled by a human communicator is connected to a call center of each company and processed.

  Further, in the information processing system 1, based on the history of correspondence performed by a human communicator, a query that can be standardized and an answer are sequentially added to the corresponding standard query by a virtual operator.

  In the information processing system 1, the virtual operator presents a topic to the customer who has inquired and performs a conversation, thereby presenting recommended information to the customer based on the information grasped through the conversation.

  As shown in FIG. 1, the information processing system 1 includes a VO server 10, an IVR server 20, a plurality of CTI (Computer Telephony Integration) servers 30, an IP-PBX (Internet Protocol Private Exchange exchange) server 40, and a screen. The server includes a linkage server 50, a CRM (Customer Relationship Management) server 60, and a terminal device 70. The terminal device 70 and the IVR server 20 are configured to be communicable via a public telephone network 80A, and the terminal device 70, the VO server 10, and the CRM server 60 are capable of communicating with each other via a public communication network 80B such as the Internet. Connected to. The VO server 10 and the CTI server 30 are connected to each other via a VPN (Virtual Private Network) 80C so as to communicate with each other. Furthermore, the CTI server 30 transmits and receives IP voice (voice communication using the Internet protocol) to and from the IVR server 20 via the IP-PBX server 40.

  The VO server 10 responds to an inquiry through a public communication network from a terminal device 70 (such as a smartphone or a PC) equipped with a browser, in response to primary reception using a virtual operator. Specifically, the VO server 10 recognizes the voice transmitted from the terminal device 70 and makes a response by voice according to the utterance content. Further, the VO server 10 records the conversation between the customer who made the inquiry and the virtual operator, and executes machine learning based on the recorded conversation. As a result of the machine learning, the VO server 10 changes the speech recognition method or changes the interpretation method of the customer's intention. In addition, the VO server 10 standardizes responses to similar inquiries by virtual operators based on the history of inquiries handled by the communicator.

  The IVR server 20 responds to an inquiry from the terminal device 70 via the public telephone network by an automatic voice response.

  The CTI server 30 is installed in each of a plurality of companies (here, company A to company C), and inquiries exceeding the scope of primary reception by the VO server 10 are passed on to reception by human communicators in each company. Make it. Specifically, a communicator PC used by the communicator is connected to the CTI server 30 and a communicator telephone is connected via the PBX. The CTI server 30 stores documents, URLs, PDF files, FAQ text data, and the like provided to customers as a database. In addition, when the CTI server 30 performs reception by the communicator, the display of the screen is controlled via the screen cooperation server 50 that links the screen of the terminal device 70 used by the customer and the screen of the communicator PC. The communicator and the customer can make a call by transmitting / receiving IP voice or voice communication via the public telephone network 80A.

The IP-PBX server 40 performs conversion between IP voice transmitted from the IVR server 20 or the terminal device 70 and voice on the telephone line.
The screen linkage server 50 controls the terminal device 70 used by the customer and the communicator terminal device used by the communicator, and the screen of the terminal device 70 used by the customer and the screen of the communicator terminal device used by the communicator. Link.

  The CRM server 60 stores information related to customer attributes such as purchase history, behavior history, or preference information. Note that these pieces of information stored in the CRM server 60 are hereinafter referred to as “personal information” as appropriate. The CRM server 60 refers to the personal information in response to a request from the VO server 10 or the CTI server 30 and provides information that enables individually adapted responses to each customer.

  The terminal device 70 is a terminal device 70 used by a customer who makes an inquiry to a call center system configured by the information processing system 1, and is configured by, for example, a smartphone, a PC, or a mobile phone. Among the terminal devices 70, devices capable of displaying guidance on the screen by the VO server 10, such as smartphones or PCs, display guidance on the screen in addition to voice responses by the virtual operator. In addition, about the terminal device 70 which cannot perform guidance display by a screen, a voice response by a virtual operator is performed.

  The terminal device 70 performs communication of page data such as text and images and IP voice via the public communication network 80B. It is also possible to use a terminal device 70 that performs voice communication on a telephone line via the public telephone network 80A. The terminal device 70 communicates an inquiry to the VO server 10 or the IVR server 20, and displays a screen of a response transmitted from the VO server 10 or the IVR server 20 and outputs a sound.

[Hardware configuration]
Next, the hardware configuration of the server and the terminal device 70 in the information processing system 1 will be described.

[Hardware configuration of server]
In the information processing system 1, the VO server 10, the IVR server 20, the CTI server 30, the IP-PBX server 40, the screen cooperation server 50, and the CRM server 60 are installed with software that realizes the function of each server in the server computer. Consists of.

FIG. 2 is a diagram illustrating a hardware configuration of a server computer 800 configuring each server.
As shown in FIG. 2, a server computer 800 constituting each server includes a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, a RAM (Random Access Memory) 813, a bus 814, and an input unit. 815, an output unit 816, a storage unit 817, a communication unit 818, and a drive 819.

The CPU 811 executes various processes (processes for realizing the functions of each server) according to a program recorded in the ROM 812 or a program loaded from the storage unit 817 to the RAM 813.
The RAM 813 appropriately stores data necessary for the CPU 811 to execute various processes.

  The CPU 811, ROM 812, and RAM 813 are connected to each other via a bus 814. An input unit 815, an output unit 816, a storage unit 817, a communication unit 818, and a drive 819 are connected to the bus 814.

The input unit 815 is configured with various buttons and the like, and inputs various information according to an instruction operation.
The output unit 816 includes a display, a speaker, and the like, and outputs an image and sound.
The storage unit 817 is configured by a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data managed by each server.
The communication unit 818 controls communication performed with other devices via a network.

  A removable medium 821 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately attached to the drive 819. The program read from the removable medium 821 by the drive 819 is installed in the storage unit 817 as necessary.

[Hardware Configuration of Terminal Device 70]
In the information processing system 1, the terminal device 70 is configured by a terminal device 70 in which a browser such as a smartphone or a PC (Personal Computer) is mounted, a mobile phone or a fixed phone capable of voice communication, and the like.

FIG. 3 is a diagram illustrating a hardware configuration of the terminal device 70.
In FIG. 3, a hardware configuration of a smartphone is illustrated as an example of the terminal device 70.

  As illustrated in FIG. 3, the terminal device 70 includes a CPU 911, a ROM 912, a RAM 913, a bus 914, a touch operation input unit 915, an output unit 916, a voice input unit 917, an imaging unit 918, and a storage unit. 919, a communication unit 920, and a drive 921.

The CPU 911 executes various processes (processes for realizing the functions of the terminal device 70) in accordance with a program recorded in the ROM 912 or a program loaded from the storage unit 919 to the RAM 913.
The RAM 913 appropriately stores data necessary for the CPU 911 to execute various processes.

  The CPU 911, the ROM 912, and the RAM 913 are connected to each other via a bus 914. A touch operation input unit 915, an output unit 916, an audio input unit 917, an imaging unit 918, a storage unit 919, a communication unit 920, and a drive 921 are connected to the bus 914.

The touch operation input unit 915 includes, for example, a capacitance type or resistance film type position input sensor stacked in the display area of the output unit 916, and detects the coordinates of the position where the touch operation is performed. Here, the touch operation refers to a contact or proximity operation of an object (such as a user's finger or a touch pen) with respect to the touch operation input unit 915.
The output unit 916 includes a display, a speaker, and the like, and outputs an image and sound.
In other words, in this embodiment, the touch operation input unit 915 and the display of the output unit 916 constitute a touch panel.

The voice input unit 917 is constituted by a microphone, for example, and converts the input voice into an analog electric signal.
The audio analog signal is subjected to A / D (Analog / Digital) conversion processing and converted into a digital signal representing the audio data. The execution subject of the A / D conversion processing is not particularly limited, and may be the CPU 911 or dedicated hardware (not shown). However, in the present embodiment, for convenience of explanation, the voice input unit 917 is used. It shall be.
That is, in this embodiment, the voice input unit 917 outputs voice data based on the input voice to the CPU 911 or the like.

Although not shown, the imaging unit 918 includes an optical lens unit and an image sensor.
The optical lens unit is configured with a lens that collects light, such as a focus lens, for photographing a subject. In addition to the focus lens, a zoom lens that freely changes the focal length within a certain range may be provided in the optical lens unit.
The optical lens unit is also provided with a peripheral circuit for adjusting setting parameters such as focus, exposure, and white balance as necessary.

The image sensor includes a photoelectric conversion element, AFE (Analog Front End), and the like.
The photoelectric conversion element is composed of, for example, a CMOS (Complementary Metal Oxide Semiconductor) type photoelectric conversion element or the like. In the present embodiment, a Bayer color filter is attached to the image sensor. The image sensor photoelectrically converts (images) the optical signal of the subject image incident and accumulated during a certain time interval, and sequentially supplies analog electric signals obtained as a result to the AFE.
The AFE performs various signal processing such as A / D conversion processing on the analog electric signal. Through various signal processing, a digital signal is generated and output as an output signal of the imaging unit 918. The image data indicated by the output signal of the imaging unit 918 is hereinafter referred to as “captured image data” as appropriate. The captured image data is stored in the RAM 913 or the storage unit 919 in accordance with an instruction from the CPU 911.

The storage unit 919 includes a storage device such as a DRAM and stores various data.
The communication unit 920 controls communication performed with other devices via a network.
A removable medium 931 is appropriately attached to the drive 921 as necessary. The program read from the removable medium 931 by the drive 921 is installed in the storage unit 919 as necessary. The removable medium 931 can also store various data stored in the storage unit 919 in the same manner as the storage unit 919.

[Functional configuration]
Next, main functional configurations realized in the information processing system 1 will be described.
FIG. 4 is a block diagram illustrating a main functional configuration realized in the information processing system 1.

As shown in FIG. 4, the information processing system 1 includes a VO server 10 as a database, a character database 151, a personal database 152, a scenario database 153, a FAQ search database 154, a speech synthesis database 155, a marketing template. A database 156, a VOC database 157, a topic submission database 158, a communicator history database 159, and a dialogue history database 160 are provided. The CTI server 30 is provided with a document database 351 and a FAQ text database 352. Further, the CRM server 60 is provided with a CRM personal database 651 and a meta database 652.
In FIG. 4, the database is abbreviated as “DB”.

The character database 151 stores data representing various expressions and gestures of the virtual operator.
For each user (customer) specified by the user information, the personal database 152 stores user-specific information such as past inquiry contents and a part of CRM personal data acquired from the CRM server 60.

The scenario database 153 stores a scenario (response pattern) in which a virtual operator regularly answers or interacts with an inquiry.
The FAQ search database 154 stores FAQ (Frequently Asked Questions) data.
The speech synthesis database 155 stores speech data for synthesizing sentences as speech.

The marketing template database 156 stores template data in which questions relating to various marketing and questionnaires are assumed in advance.
The VOC database 157 stores customer opinions and requests (VOC: Voice Of Customer) sent to the information processing system 1 as voice or text data.

The topic suggestion database 158 stores topic data to be proposed according to the contents of the inquiry to the customer who made the inquiry.
The communicator history database 159 stores history data of dialogue between the customer and the communicator.

The dialogue history database 160 stores the history data of dialogue between the customer and the virtual operator.
The document database 351 stores data such as documents, URLs, and PDFs that the communicator presents to the customer.
The FAQ text database 352 stores FAQ text data presented to the customer by the communicator.

The CRM personal database 651 stores user's personal attribute information and related information such as purchase history, behavior history, or preference information.
The metadata database 652 stores purchase information, behavior information, SNS information, and preference information of a large number of users in summary (that is, as metadata).

  As shown in FIG. 4, the information processing system 1 includes an inquiry voice receiving unit 201, an answer request unit 202, an answer receiving unit 203, and an answer voice transmitting unit 204 as functions of the IVR server 20. ing. The functions of the VO server 10 include an IP communication unit 101, an utterance cutout unit 102, a user information acquisition unit 103, a voice recognition unit 104, an emotion analysis unit 105, a language determination unit 106, an intention / state interpretation. Unit 107, dialogue processing unit 108, speech synthesis unit 109, screen control unit 110, supplement processing unit 111, communicator calling unit 112, machine learning processing unit 113, stylization processing unit 114, and communicator Data support unit 115. Furthermore, as a function of the CTI server 30, a response management unit 301 and a screen control unit 302 are provided.

The IP communication unit 101 transmits the IP voice transmitted from the terminal device 70 to the IP-PBX server 40.
The utterance cutout unit 102 performs utterance cutout by detecting a silent portion of the input voice.
The user information acquisition unit 103 is a user information (user-specific number, etc.) that uniquely identifies a user who is a user of the terminal based on information on the accessed terminal (IP address, user ID and password, terminal number, etc.) To get.

The voice recognition unit 104 recognizes the utterance input from the utterance cutout unit 102 and converts it into a character string.
The emotion analysis unit 105 analyzes the emotion of the speaker based on the utterance and the silent portion input from the utterance cutout unit 102, and outputs data obtained by quantifying the emotion. For example, the emotion analysis unit 105 calculates a numerical value for each parameter such as joy, anger, sadness, fun, calmness, or impatience about the emotion of the speaker based on the speaking speed of the speaker, the level of inflection, and the like.

  The language discriminating unit 106 discriminates the spoken language based on the character string input from the voice recognition unit 104. For example, the language discriminating unit 106 is assumed to be a plurality of languages supported by the information processing system 1, and from the results of speech recognition performed by the speech recognition unit 104, the language with the highest accuracy of the analysis result is spoken It is determined that

  The intention / state interpreter 107 interprets the intention of the speaker and the current state of dialogue based on the character string whose language is determined by the language determiner 106 and the numerical value data of the emotion input from the emotion analyzer 105. . Specifically, the intention / state interpreting unit 107 determines the content of a character string whose language is determined by the language determining unit 106 (that is, a character string in which the speech of the speaker is converted into text), and the conversation of the speaker Interpret the intent (meaning content of the utterance). At this time, based on the user information acquired by the user information acquiring unit 103, the intention / state interpreting unit 107 stores the user's personal data stored in the CRM server 60 and the user stored in the personal database 152. Interpret the intention of the speaker's conversation by referring to the past inquiries. For example, when a speech-recognized speaker's word includes a word having a plurality of homonyms, the intention / state interpreting unit 107 refers to the content inquired by the speaker in the past, purchase history, etc. Then narrow down the meaning of the word and interpret it as the most likely meaning. As a result, the intention of the inquiry can be accurately determined according to the speaker (customer) who made the inquiry, and the inquiry can be answered. In addition, when interpreting the intention of the speaker, the intention / state interpreting unit 107 interprets the intention when the speaker repeats the same question with an increased feeling of “anger” in response to the virtual operator. It is possible to determine that this is an error and change the interpretation of the intention.

  In addition, the intention / state interpreting unit 107 interprets a speaker's current conversation precondition as an element of the current conversation state from the flow of conversation from when the inquiry is made to the present. For example, if the speaker has specified a specific condition in the previous utterance (for example, if Shinjuku is specified as the area), the conversation that the speaker has already spoken in the next utterance has already been specified It is interpreted as assuming a specific condition.

  The intention / state interpreting unit 107 interprets the type of the terminal device 70 used by the speaker as an element of the current dialog state. For example, the intention / state interpreting unit 107 interprets whether or not the terminal device 70 used by the speaker is the terminal device 70 capable of guidance by screen display as an element of the current dialog state. When the terminal device 70 used by the speaker is a terminal device 70 that cannot be guided by screen display, the intention / state interpretation unit 107 selects a dialog that does not use an image.

The intention / state interpreting unit 107 searches the FAQ search database 154 on the basis of the intention of the speaker interpreted as described above and the state of the current dialogue, and determines whether or not the content of the dialogue can be determined (first step). Judgment). If the dialog content can be determined as a result of the first determination, the intention / state interpretation unit 107 determines the content of the dialog for the utterance. For example, when the speaker utters “What is a delicious restaurant in Shinjuku?”, The intention / state interpretation unit 107 determines the content of the dialog to answer a popular restaurant in Shinjuku. On the other hand, when the dialog content cannot be determined, the intention / state interpretation unit 107 requests the supplement processing unit 111 to perform information supplement processing (described later) for determining the dialog content. Then, the intention / state interpretation unit 107 performs determination (second determination) as to whether or not the content of the dialogue can be determined based on the result of the supplement process. Specifically, the FAQ search database 154 is searched using the result of the replenishment process, and it is determined whether the dialog content can be determined, or whether information that can determine the dialog content is obtained from an information source other than the FAQ search database 154. The As a result of the second determination, when the conversation content can be determined, the intention / state interpretation unit 107 determines the conversation content for the utterance. On the other hand, when the dialogue content cannot be determined, the intention / state interpreting unit 107 calls the communicator of the inquired company via the communicator calling unit 112.
When the inquiry is made by chat (conversation using only characters) from the terminal device 70, the character string transmitted by the chat is directly input to the intention / state interpreting unit 107, and thereafter the content of the dialogue is similar to the inquiry by voice. Is determined. However, in this case, the response to the terminal device 70 is performed by chat using a character string.

  The dialogue processing unit 108 refers to the scenario database 153 based on the dialogue contents interpreted by the intention / state interpretation unit 107, and determines a dialogue to respond to the speaker. For example, if the intention / state interpretation unit 107 determines that the content of the dialogue is to answer a popular restaurant in Shinjuku, the dialogue processing unit 108 follows the scenario stored in the scenario database 153 and reads “ Select the dialogue "Popular restaurants within ...".

  Further, the dialogue processing unit 108 associates the utterance of the speaker and the dialogue responded to the speaker with the user information of the speaker and the terminal device 70 of the speaker, and stores it in the dialogue history database 160 as a dialogue history. Remember.

The speech synthesizer 109 synthesizes speech determined by the dialogue processing unit 108 and transmits it to the speaker's terminal device 70.
The screen control unit 110 refers to the character database 151 based on the conversation content interpreted by the intention / state interpretation unit 107 and determines the virtual operator character data to be displayed on the terminal device 70 of the speaker. Specifically, the screen control unit 110 selects the facial expression and gesture character data corresponding to the conversation contents interpreted by the intention / state interpretation unit 107, and the screen data on which the virtual operator talks with the facial expression and gesture is displayed. Generate. Then, the screen control unit 110 transmits the generated screen data to the terminal device 70 of the speaker.

  The replenishment processing unit 111 executes a replenishment process of information for determining the content of dialogue when a request for a replenishment process is received from the intention / state interpretation unit 107. Specifically, the supplement processing unit 111 transmits a question for supplementing the inquiry content to the terminal device 70 when there are a plurality of answers to the inquiry, and the FAQ search database 154 does not include the answer to the inquiry. In some cases, information related to the inquiry content is searched from an information source (communication history database 159 or the Internet) other than the FAQ search database 154. Then, the replenishment processing unit 111 outputs an answer to the question and a search result to the intention / state interpretation unit 107 as a result of the replenishment processing.

  The communicator calling unit 112 calls the communicator of the inquired company when a request for calling the communicator is received from the intention / state interpreting unit 107. Further, when an operation for calling the communicator is performed on the terminal device 70 (for example, pressing a “call” button in FIG. 6A described later), the communicator calling unit 112 selects the communicator. Execute the process to call. At this time, the communicator calling unit 112 may notify the communicator of the speaking rate of the speaker and the numerical value data of the emotion acquired in the dialogue with the virtual operator in addition to the inquiry contents of the customer who is the speaker. Good.

  The machine learning processing unit 113 refers to the dialogue history stored in the dialogue history database 160 and determines whether or not an inappropriate response is made in the dialogue history. For example, the machine learning processing unit 113 determines whether or not there is a situation in which the speaker denies the response of the virtual operator or instructs the communicator instead of the virtual operator in the conversation history. Then, the machine learning processing unit 113 notifies the system administrator PC used by the system administrator of the conversation history determined that an inappropriate response has been made.

  If the dialogue history that the machine learning processing unit 113 determines that an inappropriate response is made is recognized as inappropriate by the system administrator PC, the content of speech recognition (from voice to text) in the dialogue history Conversion) or interpretation of the intention of the speaker (result of determination of the contents of the character string) is fed back to the processing in the speech recognition unit 104 and the intention / state interpretation unit 107.

  The stylization processing unit 114 refers to the communicator history database 159 by executing the knowledge management process, and when the communicator has made a plurality of responses to the same inquiry, the inquiry processing and the response to the inquiry are performed. Standardize and add to FAQ search database 154. At this time, the system administrator PC is notified of the standardized inquiry and answer, and when approved, the addition to the FAQ search database 154 may be executed.

  Here, in this embodiment, inquiries and responses to communicators in call centers of a plurality of companies are referred to in a unified manner, and standardization is performed according to whether or not a plurality of responses to similar inquiries are made. . Thereby, since the same inquiry and answer in a plurality of companies can be standardized, it is possible to increase the frequency with which the inquiry and answer can be standardized as compared with the case where a call center is operated in a single company. However, refer to the communicator inquiries and responses at each call center for each company, and standardize the answers to the inquiries for each company according to whether or not there are multiple responses to similar inquiries at that company. It is good.

  When the communicator responds to an inquiry from a customer, the communicator support unit 115 recognizes the dialogue by the voice recognition unit 104 and supports the communicator based on the text data that is the voice recognition result. I will provide a. For example, the communicator support unit 115 displays information on “NISA” on the communicator PC when the inquiry content by the customer is “NISA (small investment tax exemption system)”. The communicator support unit 115 analyzes the interaction between the customer and the communicator by the emotion analysis unit 105, and displays the change in the customer's emotion on the communicator PC based on the data obtained by quantifying the emotion. Also good.

The inquiry voice receiving unit 201 of the IVR server 20 receives the voice transmitted from the terminal device 70 and outputs it to the answer request unit 202.
The answer request unit 202 transmits the voice data input from the inquiry voice receiving unit 201 to the VO server 10 and requests the answer voice.
The answer receiving unit 203 receives answer voice data transmitted from the VO server 10.
The answer voice transmitting unit 204 transmits the answer voice data received by the answer receiving unit 203 to the terminal device 70 as voice.

The response management unit 301 of the CTI server 30 manages and manages a customer and a communicator that has responded to an inquiry connected to the communicator.
The screen control unit 302 controls the screen of the terminal device 70 via the screen cooperation server 50 according to the operation of the communicator.

[Operation]
Next, the operation of the information processing system 1 will be described.
FIG. 5 is a flowchart showing a flow of acceptance processing executed by the information processing system 1.

The acceptance process is started when the information processing system 1 is activated.
FIG. 6 is a diagram showing an example of a display screen displayed on the terminal device 70 in the acceptance process. FIG. 6A is an example of an initial reception screen, FIG. 6B is an example of a display screen in a standard response, and FIG. 6 (C) is an example of a communicator screen, and FIG. 6 (D) is a diagram showing an example of a display screen in VOC collection. Hereinafter, the flow of the reception process will be described with reference to FIG. 6 as appropriate.

In step S <b> 1, the voice recognition unit 104 of the VO server 10 determines whether there is an inquiry from the terminal device 70.
When there is no inquiry from the terminal device 70, it is determined as NO in step S1, and the process of step S1 is repeated.
On the other hand, when there is an inquiry from the terminal device 70, it is determined as YES in Step S1, and the process proceeds to Step S2.

In step S2, the screen control unit 110 causes the terminal device 70 to display an initial reception screen (see FIG. 6A).
In step S3, the utterance cutout unit 102 cuts out the utterance, the voice recognition unit 104 recognizes the voice input from the utterance cutout unit 102, and the emotion analysis unit 105 performs the voice input from the utterance cutout unit 102. Perform emotion analysis.
In step S4, the language discrimination unit 106 discriminates the spoken language.

In step S5, the intention / state interpreting unit 107 interprets the intention of the speaker and the state of the current dialogue.
In step S6, the intention / state interpretation unit 107 searches the FAQ search database 154 based on the utterance content specified from the intention of the speaker interpreted in step S5 and the current conversation state.
In step S <b> 7, the intention / state interpreting unit 107 determines whether or not the dialog content can be determined (that is, whether or not the FAQ search database 154 has an answer).

If the dialog content can be determined, YES is determined in step S7, and the process proceeds to step S8.
On the other hand, if the dialog contents cannot be determined, NO is determined in step S7, and the process proceeds to step S10.
In step S8, the intention / state interpretation unit 107 determines the content of the dialogue based on the response retrieved from the FAQ search database 154, and makes a response (standard response) by the dialogue processing unit 108 (see FIG. 6B).

In step S9, the intention / state interpretation unit 107 determines whether or not the response to the inquiry has been completed.
If the response to the inquiry has not been completed, the process proceeds to step S3.
On the other hand, when the response to the inquiry is completed, the process proceeds to step S18.

  In step S <b> 10, the intention / state interpretation unit 107 requests the replenishment processing unit 111 to perform replenishment processing. Specifically, when there are a plurality of answer candidates for the inquiry, the replenishment processing unit 111 transmits a question for replenishing the inquiry contents to the terminal device 70, and the answer to the inquiry is not included in the FAQ search database 154. In some cases, information related to the inquiry content is searched from an information source (communication history database 159 or the Internet) other than the FAQ search database 154.

In step S <b> 11, the intention / state interpretation unit 107 determines whether the content of the dialogue can be determined as a result of the supplement process.
If the dialog contents can be determined as a result of the replenishment process, YES is determined in step S11, and the process proceeds to step S12.
On the other hand, if the dialog content cannot be determined as a result of the replenishment process, NO is determined in step S11, and the process proceeds to step S13.

In step S <b> 12, the intention / state interpretation unit 107 determines the content of the dialogue using the result of the supplement processing, and makes a response by the dialogue processing unit 108.
After step S12, the process proceeds to step S9.

  In step S <b> 13, the intention / state interpretation unit 107 calls the communicator of the inquired company via the communicator call unit 112. At this time, the screen controller 110 may respond to the virtual operator that the communicator is being called on the screen of the terminal device 70. If an operation for calling the communicator is performed in the terminal device 70, the process jumps to the process of step S13 by the interrupt process to call the communicator.

In step S14, the screen control unit 110 of the CTI server 30 displays the communicator screen on the screen of the terminal device 70 using the communicator's photograph as a background, and the conversation content is converted into text by voice recognition (see FIG. 6C). Is displayed. By displaying the communicator screen, the customer feels closer to the person (communicator) who is responding, and can make inquiries and responses more smoothly.
In step S15, the voice recognition unit 104 recognizes a dialogue between the customer and the communicator.

In step S <b> 16, the intention / state interpretation unit 107 determines whether or not the dialogue between the customer and the communicator has ended.
If the conversation between the customer and the communicator has not ended, NO is determined in step S16, and the process proceeds to step S14.
On the other hand, when the dialogue between the customer and the communicator is completed, YES is determined in step S16, and the process proceeds to step S17.

In step S17, the intention / state interpretation unit 107 executes a VOC collection process (see FIG. 6D).
In step S <b> 18, the dialogue processing unit 108 stores a series of dialogue histories for the inquiry in the dialogue history database 160.
After step S18, the acceptance process is repeated until an end instruction is issued.

By such processing, in the information processing system 1, when an inquiry is made from the terminal device 70, the FAQ search database 154 is referred to, and when an answer is prepared in the FAQ search database 154, a routine by a virtual operator is used. A response is made. On the other hand, when the answer is not prepared in the FAQ search database 154, the VO server 10 executes a supplement process of information for determining the content of the dialogue, and uses the result of the supplement process to receive an answer from the FAQ search database 154. Processing such as searching or acquiring information from an information source other than the FAQ search database 154 is performed, and a response by the virtual operator is made to the inquiry. Furthermore, even if the result of the replenishment process is used, if a response to the inquiry cannot be made by the virtual operator, the communicator is called and a response is made by the communicator.
Therefore, in the information processing system 1, a response by the virtual operator is tried as much as possible, and the frequency of calling the communicator is reduced.
Therefore, it is possible to further improve the efficiency of operations for receiving inquiries from customers.

Next, the VOC collection process executed as a subflow in step 17 of the reception process will be described.
FIG. 7 is a flowchart showing the flow of the VOC collection process.
When the VOC collection process is started, in step S21, the intention / state interpretation unit 107 refers to the marketing template database 156, acquires a questionnaire template regarding the response of the communicator, and the screen control unit 110 uses the terminal device 70. A questionnaire is displayed on the screen.

  In step S22, the intention / state interpretation unit 107 receives an answer to the questionnaire. Note that the answer to the questionnaire can be input by characters in the terminal device 70 in addition to being input by voice.

In step S <b> 23, the intention / state interpretation unit 107 refers to the topic suggestion database 158, and proposes a topic corresponding to the inquiry content to the terminal device 70.
In step S <b> 24, the voice recognition unit 104 recognizes a response voice to the topic transmitted from the terminal device 70.

  In step S <b> 25, the intention / state interpreting unit 107 searches the topic suggestion database 158 for a dialog for presenting cell information based on the keyword included in the answer acquired by speech recognition. Note that the cell information is advertisement information intended for up-sell or cross-sell. In the case of presenting cell information, it is possible to present cell information limited to a customer inquiry company or present cell information across a plurality of companies using the information processing system 1.

In step S26, the intention / state interpretation unit 107 determines whether or not a dialog for presenting cell information has been searched.
If a dialog for presenting cell information can be searched, YES is determined in step S26, and the process proceeds to step S27.
On the other hand, when the dialog for presenting the cell information cannot be searched, it is determined as NO in Step S26, and the process proceeds to Step S28.

In step S27, the intention / state interpreting unit 107 performs a dialog for presenting cell information and presents the cell information to the customer.
After step S27, the process proceeds to step S29.
In step S <b> 28, the intention / state interpretation unit 107 searches the terminal device 70 for a topic that continues from the topic suggestion database 158 and submits it.

In step S29, the intention / state interpretation unit 107 determines whether or not the end condition of the VOC collection process is met. The end condition of the VOC collection process can be defined when the customer gives an instruction to end the VOC collection process or when the customer requests product guidance according to the cell information.
If the VOC collection process termination condition is not met, NO is determined in step S29, and the process proceeds to step S24.
On the other hand, if the VOC collection process end condition is met, YES is determined in step S29, and the VOC collection process ends.

By such processing, the virtual operator and the customer perform related conversations (chat conversations) other than the inquiry itself, so that cell information corresponding to the content of the conversation is presented to the customers.
Therefore, cell information that matches the customer's condition can be presented to the customer who has made an inquiry due to some event or the like.
Therefore, more effective marketing can be performed using the call center business.

Next, the knowledge management process will be described.
FIG. 8 is a flowchart showing the flow of knowledge management processing executed by the information processing system 1.
The knowledge management process is executed as a batch process or the like at a preset time.

In step S31, the stylization processing unit 114 refers to the communicator history database 159.
In step S32, the stylization processing unit 114 analyzes the history of the communicator history database 159.

In step S <b> 33, the stylization processing unit 114 determines whether there is a dialog that can be standardized in the history of the communicator history database 159. Whether or not there is a dialogue that can be standardized can be determined, for example, by whether or not an answer to a similar inquiry has been made a predetermined number of times or more.
If there is no dialogue that can be standardized in the history of the communicator history database 159, it is determined as NO in step S33, and the knowledge management process is ended.
On the other hand, if there is a dialog that can be standardized in the history of the communicator history database 159, it is determined YES in step S33, and the process proceeds to step S34.

In step S <b> 34, the stylization processing unit 114 adds the stylized inquiry and answer to the FAQ search database 154.
After step S34, the knowledge management process ends.

As a result of such processing, when a similar inquiry is made a plurality of times for a non-standardized inquiry to which the communicator has responded, a FAQ search database is used as the inquiry that can be standardized. Added to 154. Thereafter, when a similar inquiry is made, an answer is made by the virtual operator instead of the communicator.
Therefore, as the information processing system 1 is operated, the range of inquiries that can be regularly answered increases, so that the efficiency of call center operations using the information processing system 1 can be improved.

[Second Embodiment]
Next, a second embodiment of the present invention will be described.
[Constitution]
FIG. 9 is a block diagram illustrating a main functional configuration realized in the information processing system 1 according to the second embodiment.
The information processing system 1 according to the second embodiment further includes a cooperation server 90 that realizes cooperation between the VO server 10 and the IVR server 20 in the information processing system 1 according to the first embodiment. In FIG. 9, the functions of each server shown in the first embodiment are omitted.

The cooperation server 90 includes a cooperation processing unit 901 that executes processing for cooperation between the VO server 10 and the IVR server 20. When the VO server 10 is handling the primary reception, the cooperation processing unit 901 calls the IVR server 20 in response to an operation for calling a communicator by a customer who uses the terminal device 70. Make a call. Then, the cooperation processing unit 901 automatically makes a voice inquiry according to the content of the previous dialogue with the customer, and responds to the automatic voice response provided by the IVR server 20 while calling the communicator. Proceed with conversation automatically.
By such processing, even when the VO server 10 and the CTI server 30 cannot directly cooperate, it is possible to call the communicator from the VO server 10 using the automatic voice response function of the IVR server 20. .
Note that the VO server 10 may have the function of the cooperation server 90 as described above.

[Operation]
Next, the operation will be described.
Similar to the first embodiment, the information processing system 1 according to the second embodiment executes the reception process illustrated in FIG.
Then, when an operation for calling the communicator is performed in the terminal device 70, a cooperation process is executed as a sub-flow of step S13.
FIG. 10 is a flowchart illustrating the flow of the cooperation processing executed by the information processing system 1 according to the second embodiment.
FIG. 11 is a diagram showing an example of a display screen displayed on the terminal device 70 in the cooperation process. FIG. 11A is an example of a telephone number input screen, and FIG. FIG. 11C is a diagram showing an example of a screen displayed during calling of the communicator.
Further, FIG. 12 is a diagram showing an example of a display screen displayed on the communicator PC in the cooperation process, FIG. 12A is an example of a dialog history search screen, FIG. 12B is an example of a dialog history confirmation screen, FIG. 12C shows an example of a screen during power reception, and FIG. 12D shows an example of a screen after completion of response.
Hereinafter, the flow of the cooperation process will be described with reference to FIGS. 11 and 12 as appropriate.

In step S41, the intention / state interpreting unit 107 of the VO server 10 makes a response to prompt the customer to input his / her telephone number by the dialogue processing unit 108 (see FIG. 11A). At this time, the input of the telephone number by the customer can be either input by voice or input by character string. Thereby, the customer's own telephone number is acquired in the VO server 10.
In step S42, the communicator calling unit 112 acquires a contact list of the communicator estimated to be the customer's inquiry destination from the cooperation processing unit 901 of the cooperation server 90, and transmits it to the terminal device 70 (FIG. 11). (See (B)). In FIG. 11B, three contact points that are likely to be customer inquiries and buttons for displaying all the contacts are displayed. The contact information of the communicator can be provided from the CTI server 30 to the cooperation processing unit 901, or the cooperation processing unit 901 can collect and acquire information from a general Web server. Further, as the contact information of the communicator, it is possible to indicate the department name and telephone number of the inquiry destination, or to indicate only the department name of the inquiry destination. In step S42, the data of the conversation history between the customer and the virtual operator so far is transmitted to the cooperation server 90.

In step S <b> 43, the communicator calling unit 112 acquires the contact address selected by the terminal device 70.
In step S <b> 44, the communicator calling unit 112 requests the cooperation processing unit 901 to make a call to the contact selected in the terminal device 70. In step S44, the data of the conversation history between the customer and the virtual operator so far is transmitted to the cooperation server 90.
In step S45, the cooperation processing unit 901 makes a call to the IVR server 20, and automatically makes a voice inquiry according to the content of the previous dialogue with the customer. At this time, the cooperation processing unit 901 automatically advances the conversation up to the call of the communicator while corresponding to the automatic voice response provided by the IVR server 20. A message indicating that the communicator is being called is notified to the customer terminal device 70 by the virtual operator (see FIG. 11C).

In step S46, the IVR server 20 calls the communicator as a response result to the automatic conversation by the cooperation processing unit 901.
In step S47, the response management unit 301 of the CTI server 30 executes a power reception process that is executed when a call is made to the communicator. In the power receiving process, a dialog history search screen for searching for inquiry contents is displayed on the communicator PC (see FIG. 12A), and the communicator inputs an ID notified from the cooperation server 90. Then, on the dialog history confirmation screen, the dialog history with the calling customer (dialog data managed by the cooperation server 90) is displayed as a character string, and the communicator calls the customer. Button (power receiving button) is displayed (see FIG. 12B).
In step S48, in response to the communicator operating the power receiving button, the cooperation processing unit 901 shifts to a “power receiving standby state” in which the communicator is ready for a call. At this time, on the communicator PC, a power reception screen for inputting the result after the power reception button operation is displayed (see FIG. 12C).

In step S49, the cooperation processing unit 901 sends a call from the communicator telephone to the telephone number input by the customer via the IP-PBX server 40.
In step S50, when the customer answers the phone, a call between the communicator and the customer is started.
After step S50, the process returns to the acceptance process.
In addition, after the call between the communicator and the customer ends, the communicator displays on the screen when receiving power, "Call was completed", "Did not answer", "Out of service area", "Voice mail", "Busy" Or, the result of contact with the customer such as “illegal phone number” is input. When input by the communicator is performed, a screen after response completion displayed after the response to the customer by the communicator is completed is displayed (see FIG. 12D).

By such processing, when the customer requests to call the communicator, the cooperation processing unit 901 of the cooperation server 90 advances the input of the conversation for the automatic voice response in the IVR server 20 and communicates via the IVR server 20. Can be called.
Therefore, even when the VO server 10 and the CTI server 30 cannot directly cooperate, it is possible to call the communicator from the VO server 10 using the automatic voice response function of the IVR server 20.

[Application Example 1]
In the above-described embodiment, the character or clothes of the virtual operator can be made different depending on the inquired company. For example, if multiple types of characters with different personalities are stored in the character database, if the content of the inquiry is technical, the virtual operator will be a character that seems to be familiar with the technology, and if it is related to banking operations, the virtual operator will be solid It can be a character of clothes.
Thereby, it is possible to make the customer who has inquired feel the virtual operator atmosphere suitable for the contents of the inquiry.

[Application 2]
In the above embodiment, the character or clothes of the virtual operator can be made different depending on the customer who made the inquiry. For example, a plurality of types of characters having different personalities are stored in the character database, and the virtual operator can be an anime character when the customer who has made the inquiry is interested in animation.
As a result, it is possible to make a response at the call center by a virtual operator who gives a favorable impression to the customer, so that customer satisfaction can be improved.

[Application Example 3]
In the above-described embodiment, when a customer who has made an inquiry performs similar procedures such as address change for a plurality of companies, the procedures for the plurality of companies may be performed collectively by receiving a virtual operator.
Thereby, the customer can reduce the trouble of performing the same procedure a plurality of times.

[Application Example 4]
In the above embodiment, the virtual operator may propose a procedure other than the content inquired by the customer and related to the content inquired so that these procedures can be performed together.
As a result, the customer can reduce the possibility of omission of necessary procedures.

As described above, the information processing system 1 according to the present embodiment includes the terminal device 70 and the VO server 10 as a reception server.
The VO server 10 includes a voice recognition unit 104, an intention / state interpretation unit 107, and a communicator calling unit 112.
The voice recognition unit 104 receives an inquiry from the terminal device 70.
The intention / state interpretation unit 107 determines whether or not an answer to the inquiry can be searched from the FAQ search database 154 in which a plurality of prepared questions and answers are stored.
Further, when it is determined that the answer to the inquiry cannot be searched, the intention / state interpreting unit 107 executes a supplement process for supplementing information for answering the inquiry, and an answer to the inquiry based on the result of the supplement process Is generated.
In addition, the intention / state interpretation unit 107 determines whether an answer to the inquiry has been generated.
In addition, the intention / state interpretation unit 107 transmits the searched answer or the generated answer when it is determined that the answer to the inquiry can be searched and when it is determined that the answer to the inquiry can be generated.
When the intention / state interpreting unit 107 determines that the answer to the inquiry could not be generated, the communicator calling unit 112 executes a communicator calling process corresponding to the inquiry.
Thereby, when an inquiry is made from the terminal device 70, the FAQ search database 154 is referred to, and when an answer is prepared in the FAQ search database 154, a standard response is made. On the other hand, when the answer is not prepared in the FAQ search database 154, a supplement process of information for answering the inquiry is executed, and an answer is generated based on the result of the supplement process. Furthermore, if an answer to the inquiry cannot be generated even after the replenishment process is performed, the communicator is called and a response by the communicator is performed.
Therefore, in the information processing system 1, an automatic response by the system is attempted as much as possible, and the frequency of calling the communicator is reduced.
Therefore, it is possible to further improve the efficiency of operations for receiving inquiries from customers.

In addition, the intention / state interpretation unit 107 transmits a question for supplementing the content of the inquiry to the terminal device 70 as the supplement processing.
Thereby, when the answer to the inquiry cannot be narrowed down, a question for narrowing down the answer can be made.

In addition, the intention / state interpreting unit 107 searches information related to the contents of the inquiry from information sources other than the FAQ search database 154 as a supplement process.
Thereby, even if a reply to the inquiry is not prepared, information can be obtained from the searchable information source and the reply can be made.

Further, the voice recognition unit 104 receives an inquiry from the terminal device 70 by an automatic response using voice recognition.
In addition, the intention / state interpretation unit 107 transmits the retrieved answer or the generated answer as a response by voice data.
Thereby, an automatic response by voice can be performed in response to an inquiry from the terminal device.

The VO server 10 also includes a stylization processing unit 114.
The stylization processing unit 114 generates a combination of inquiry and answer to be standardized based on the response history of the communicator.
As a result, when a similar inquiry is made a plurality of times for a non-standardized inquiry to which the communicator has responded, the inquiry and answer are determined as a standardized inquiry.
Therefore, as the information processing system 1 is operated, the range of inquiries that regularly answer is expanded, so that the efficiency of work using the information processing system 1 can be improved.

The communicator calling unit 112 executes a calling process for calling the communicator of the organization corresponding to the inquiry among the communicators installed corresponding to each of the plurality of organizations.
The voice recognition unit 104 accepts inquiries to a plurality of organizations as a representative.
The stylization processing unit 114 generates a combination of a query and a response that can be standardized by a plurality of organizations based on a history of responses from the communicator in response to the query to each organization.
As a result, when inquiries corresponding to inquiries in multiple organizations are integrated, similar inquiries and responses in multiple organizations can be standardized, compared to operating inquiries corresponding to inquiries in a single organization. It is possible to increase the frequency at which inquiries and answers can be standardized.

The VO server 10 also includes a personal database 152.
The personal database 152 manages personal information related to individual customers who make inquiries.
The intention / state interpreting unit 107 refers to the personal information and determines whether or not an answer to the inquiry can be searched from the FAQ search database 154.
As a result, the intent of the inquiry can be accurately determined according to the customer who has made the inquiry, and the inquiry can be answered.

In addition, the intention / state interpretation unit 107 provides a topic related to the content of the inquiry as a voice.
In addition, the intention / state interpreting unit 107 recognizes a response from the user of the terminal device 70 to the topic and provides recommended information (cell information or the like) related to the response content as a sound.
As a result, when the system and the customer conduct a related conversation other than the inquiry itself (chat conversation), recommended information corresponding to the content of the conversation is presented to the customer.
Therefore, it is possible to present recommended information that matches a customer's condition to a customer who has made an inquiry due to some event or the like.
Therefore, it is possible to perform more effective marketing by utilizing the business for responding to inquiries.

Further, the information processing system 1 includes an IVR server 20 as an automatic voice response server and a cooperation server 90.
The IVR server 20 responds to a preset inquiry from the terminal device 70 by an automatic voice response, and executes a communicator call process for a query other than the preset inquiry.
When the linking server 90 calls the communicator from the VO server 10, it makes an inquiry to the IVR server 20 based on the inquiry and response made between the VO server 10 and the terminal device 70, and the communicator The conversation is automatically advanced until the call processing is performed, and the communicator is called.
Thereby, when the customer requests to call the communicator, the cooperation server 90 can advance the input of the conversation for the automatic voice response in the IVR server 20 and can call the communicator via the IVR server 20. .
Therefore, it is possible to call the communicator from the VO server 10 using the automatic voice response function of the IVR server 20.

In addition, this invention is not limited to the above-mentioned embodiment, The deformation | transformation in the range which can achieve the objective of this invention, improvement, etc. are included in this invention.
For example, in the above-described embodiment, the organization represented by the information processing system 1 is described as a company, but the present invention is not limited to this.
That is, the present invention can be applied to schools, administrative institutions, medical institutions, etc., as well as corporations, as long as it is an organization that handles inquiries.

  In the above-described embodiment, the configuration of each server is shown as an example. If the information processing system 1 as a whole has the functions of each server, the functions of a plurality of servers can be integrated, The functions of one server can be divided.

The series of processes described above can be executed by hardware or can be executed by software.
In other words, the functional configuration of FIG. 4 is merely an example, and is not particularly limited. That is, it is sufficient that the information processing system 1 has a function capable of executing the above-described series of processing as a whole, and what functional block is used to realize this function is not particularly limited to the example of FIG. .
In addition, one functional block may be constituted by hardware alone, software alone, or a combination thereof.

When a series of processing is executed by software, a program constituting the software is installed on a computer or the like from a network or a recording medium.
The computer may be a computer incorporated in dedicated hardware. The computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

  The recording medium including such a program is not only configured by the removable medium 821 shown in FIG. 2 distributed separately from the apparatus main body in order to provide the user with the program, but is also incorporated in the apparatus main body in advance. It is comprised with the recording medium etc. which are provided in this. The removable medium 821 is configured by, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), or the like. The magneto-optical disk is configured by an MD (Mini-Disk) or the like. Further, the recording medium provided to the user in a state of being incorporated in advance in the apparatus main body is configured by, for example, the ROM 812 in FIG. 2 in which the program is recorded, the DRAM included in the storage unit 817 in FIG.

In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in chronological order according to the order, but is not necessarily performed in chronological order, either in parallel or individually. The process to be executed is also included.
Further, in the present specification, the term “system” means an overall apparatus configured by a plurality of devices, a plurality of means, and the like.

  DESCRIPTION OF SYMBOLS 1 ... Information processing system, 10 ... VO server, 20 ... IVR server, 30 ... CTI server, 40 ... IP-PBX server, 50 ... Screen cooperation server, 60 ... CRM server, 70 ... terminal device, 80A ... public telephone network, 80B ... public communication network, 80C ... VPN, 90 ... cooperation server, 800 ... server computer, 811, 911 ..CPU, 812, 912 ... ROM, 813, 913 ... RAM, 814, 914 ... Bus, 815 ... Input unit, 816, 916 ... Output unit, 817, 919 ... Storage unit, 818, 920 ... Communication unit, 819, 921 ... Drive, 821, 931 ... Removable media, 915 ... Touch operation input unit, 917 ... Voice input unit, 918 ... imaging unit, 151 ... character database, 152 ... personal database, 153 ... scenario database, 154 ... FAQ search database, 155 ... speech synthesis database, 156 ..Marketing template database, 157... VOC database, 158... Topic submission database, 159 .. communicator history database, 160 .. dialogue history database, 351 ... document database, 352 ... FAQ Text database, 651... CRM personal database, 652 .. meta database, 201... Inquiry voice reception unit, 202 .. response request unit, 203 .. response reception unit, 204. Part, 101 ... IP , Utterance extraction unit, 103 user information acquisition unit, 104 voice recognition unit, 105 emotion analysis unit, 106 language discrimination unit, 107 intention / State interpreting unit, 108 ... Dialog processing unit, 109 ... Speech synthesis unit, 110, 302 ... Screen control unit, 111 ... Replenishment processing unit, 112 ... Communicator calling unit, 113 ...・ Machine learning processing unit, 114... Stylization processing unit, 115... Communicator support unit, 301 .. response management unit, 901.

Claims (12)

An information processing system including a terminal device that transmits an inquiry and a reception server that receives the inquiry transmitted from the terminal device,
The reception server is
Accepting means for accepting the inquiry from the terminal device;
First determination means for determining whether or not an answer to the inquiry can be searched from a response database in which a plurality of prepared questions and answers are stored;
When it is determined by the first determination means that an answer to the inquiry cannot be searched, a replenishment process for replenishing information for performing an answer to the inquiry is executed, and the inquiry is answered based on the result of the replenishment process An answer generating means for generating an answer;
Second determination means for determining whether or not an answer to the inquiry has been generated by the answer generation means;
The answer retrieved by the first determination means when the first determination means determines that the answer to the inquiry can be searched and when the second determination means determines that the answer to the inquiry can be generated. Or answering means for sending the answer generated by the second determining means;
Call means for executing a call process of a communicator corresponding to the inquiry when the second determination means determines that an answer to the inquiry could not be generated;
An information processing system comprising:   The information processing system according to claim 1, wherein the answer generation unit transmits a question for supplementing the content of the inquiry to the terminal device as the supplement processing.   The information processing system according to claim 1, wherein the answer generation unit searches the information regarding the content of the inquiry from an information source other than the response database as the supplement process. The accepting means accepts the inquiry from the terminal device by an automatic response using voice recognition,
4. The response means transmits the answer searched by the first determination means or the answer generated by the second determination means as a response by voice data. 5. The information processing system according to item 1. The reception server is
5. The information processing system according to claim 1, further comprising: a stylization processing unit that generates a combination of a query and a response to be standardized based on a response history of the communicator. The calling means executes the calling process for calling a communicator of an organization corresponding to the inquiry among communicators installed corresponding to each of a plurality of organizations,
The accepting means accepts an inquiry to the plurality of organizations on behalf of the organization;
The stylization processing unit generates a combination of a query and a response that can be standardized by the plurality of organizations based on a history of responses from the communicator in response to the query to each organization. The information processing system according to claim 5. The reception server includes personal information management means for managing personal information related to an individual customer who makes the inquiry,
The said 1st determination means determines whether the reply with respect to the said inquiry can be searched from the said response database with reference to the said personal information, The any one of Claim 1 to 6 characterized by the above-mentioned. Information processing system. The reception server is
A topic providing means for providing a topic related to the content of the inquiry as audio;
A recommended information providing means for recognizing a response from the user of the terminal device to the topic and providing recommended information related to the response content as a voice;
The information processing system according to any one of claims 1 to 7, further comprising: An automatic voice response server that responds to a preset inquiry from the terminal device by an automatic voice response, and executes a call process of a communicator other than the preset inquiry,
When calling the communicator from the reception server, an inquiry is made to the automatic voice response server based on the inquiry and response made between the reception server and the terminal device, and the communicator call processing A server that automatically advances the conversation until the call is made and executes the communicator call,
The information processing system according to claim 1, comprising: A reception server in an information processing system including a terminal device that transmits an inquiry and a reception server that receives the inquiry transmitted from the terminal device;
Accepting means for accepting the inquiry from the terminal device;
First determination means for determining whether or not an answer to the inquiry can be searched from a response database in which a plurality of prepared questions and answers are stored;
When it is determined by the first determination means that an answer to the inquiry cannot be searched, a replenishment process for replenishing information for performing an answer to the inquiry is executed, and the inquiry is answered based on the result of the replenishment process An answer generating means for generating an answer;
Second determination means for determining whether or not an answer to the inquiry has been generated by the answer generation means;
The answer retrieved by the first determination means when the first determination means determines that the answer to the inquiry can be searched and when the second determination means determines that the answer to the inquiry can be generated. Or answering means for sending the answer generated by the second determining means;
Call means for executing a call process of a communicator corresponding to the inquiry when the second determination means determines that an answer to the inquiry could not be generated;
A reception server comprising: An information processing method executed in an information processing system including a terminal device that transmits an inquiry and a reception server that receives the inquiry transmitted from the terminal device,
An accepting step for accepting the inquiry from the terminal device;
A first determination step of determining whether or not an answer to the inquiry can be searched from a response database storing a plurality of questions and answers prepared in advance;
In the first determination step, when it is determined that an answer to the inquiry cannot be searched, a replenishment process for replenishing information for performing an answer to the inquiry is executed, and the inquiry is answered based on the result of the replenishment process An answer generation step for generating an answer;
A second determination step of determining whether an answer to the inquiry has been generated in the answer generation step;
The answer searched in the first determination step when it is determined that the answer to the inquiry can be searched in the first determination step and when the answer to the inquiry can be generated in the second determination step Or an answer step of transmitting the answer generated in the second determination step;
In the second determination step, when it is determined that an answer to the inquiry could not be generated, a calling step for executing a communicator calling process corresponding to the inquiry;
An information processing method comprising: A computer that constitutes a reception server in an information processing system including a terminal device that transmits an inquiry and a reception server that receives the inquiry transmitted from the terminal device,
A reception function for receiving the inquiry from the terminal device;
A first determination function for determining whether or not an answer to the inquiry can be searched from a response database storing a plurality of questions and answers prepared in advance;
When it is determined by the first determination function that an answer to the inquiry cannot be searched, a replenishment process for replenishing information for making an answer to the inquiry is executed, and the inquiry is answered based on the result of the replenishment process An answer generation function for generating an answer;
A second determination function for determining whether or not an answer to the inquiry has been generated by the answer generation function;
The answer searched by the first determination function when it is determined that the answer to the inquiry can be searched by the first determination function and when the answer to the inquiry can be generated by the second determination function Or an answer function for transmitting the answer generated by the second determination function;
A call function for executing a call process of a communicator corresponding to the inquiry when it is determined by the second determination function that an answer to the inquiry cannot be generated;
A program characterized by realizing.

Images