TW201738830A - Information processing system, receiving server, information processing method and program wherein the information processing system includes a voice recognition sector, an intention and state interpretation sector, and an FAQ search database - Google Patents

Abstract

The problem of the present invention is to make the business that accepts inquiries from customers more efficient. To solve this problem, in the information processing system 1, the voice recognition sector 104 receives an inquiry from the terminal device 70. The intention and state interpretation sector 107 determines whether the answer to the inquiry can be retrieved from the FAQ search database 154, and when it is determined that the answer cannot be retrieved, a supplementary process is carried out to supplement the information for making the answer, and an answer is generated based on the result of the supplementary process. The intention and state interpretation sector 107 determines whether or not an answer to the inquiry can be generated, and when determining that the answer can be retrieved and that the answer to the inquiry can be generated, the intention and state interpretation sector 107 transmits the retrieved answer or the generated answer. The customer service stall call sector 112 performs the customer service staff calling process when it is determined that the answer cannot be generated by the intention and state interpretation sector 107.

Description

Information processing system, receiving server, information processing method and program

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

Previously, a technique for automating the service of a call center, which is a service that accepts an inquiry from a customer, is known.

For example, a system for responding is known which responds to an inquiry made by a customer to a customer service center in a telephone by an automatic voice response (IVR). Further, a system for accepting reception is known in which a virtual operator (VO: Virtual Operator) accepts an inquiry made by a customer to a customer service center on a network or the like.

Further, for example, Patent Document 1 describes a technique for automating a service of a customer service center.

[Previous Technical Literature]

(Patent Literature)

Patent Document 1: Japanese Patent Laid-Open Publication No. 2014-178381

However, the current situation is that in the prior art of automating the customer service center, the automated business is limited to the allocation of Q & A, etc., so that the utilization pattern is utilized. Limited. Therefore, the business that accepts the inquiry from the customer is not sufficiently streamlined.

The present invention has been made in view of such a situation, and an object thereof is to make it more efficient to accept a business from an inquiry by a customer.

In order to achieve the above object, an information processing system according to an aspect of the present invention includes: a terminal device that transmits an inquiry: and a receiving server that accepts the inquiry transmitted from the terminal device; the information processing system is characterized in that The receiving server includes: receiving means for accepting the inquiry transmitted from the terminal device; and the first determining means determining whether or not the response data library of the plurality of questions and answers prepared in advance can be retrieved from The answer to the inquiry; the answer generation means, when it is determined by the first determining means that the answer to the inquiry cannot be retrieved, the supplementary processing is performed to supplement the information for performing the answer to the inquiry, and based on the aforementioned supplementary processing The result is an answer to the query; the second determining means determines whether the answer to the query can be generated by the answer generating means; and the answering means determines that the query can be retrieved by the first determining means When answering, and when judging by the second judgment means Can be generated for the query answer, the sending by the first judging means is retrieved by the answer or answers the generated second judging means; and, The calling means, when it is determined by the second determining means that the answer to the inquiry cannot be generated, performs the call processing of the agent corresponding to the inquiry.

According to the present invention, it is possible to make the business of accepting an inquiry from a customer more efficient.

1‧‧‧Information Processing System

10‧‧‧VO server (receiving server)

20‧‧‧IVR server (automatic voice response server)

30‧‧‧CTI server

40‧‧‧IP-PBX Server

50‧‧‧ Screen Collaboration Server

60‧‧‧CRM server

70‧‧‧ Terminal devices

80A‧‧‧ Public telephone network

80B‧‧‧Communication Network

80C‧‧‧VPN

90‧‧‧Synchronized server

101‧‧‧IP Communications Department

102‧‧‧Speaking Department

103‧‧‧User Information Acquisition Department

104‧‧‧Voice Identification Department (acceptance means)

105‧‧‧Affective Analysis Department

106‧‧‧Language Discrimination Department

107‧‧‧Intentions and Status Interpretation Department (first means of judgment, means for generating answers, second means of judgment, means of answering, means of providing topics, means of providing information for recommendation)

108‧‧‧Dialog Processing Department

109‧‧‧Sound Synthesis Department

110, 302‧‧‧ Screen Control Department

111‧‧‧Additional Processing Department

112‧‧‧Customer Service Calling Department (calling means)

113‧‧‧Mechanical Learning Processing Department

114‧‧‧Formation Processing Department (formation processing means)

115‧‧‧Customer Support Department

151‧‧‧ Character database

152‧‧‧Personal database (personal information management means)

153‧‧‧ script database

154‧‧‧FAQ Search Database (Response Database)

155‧‧‧Sound Synthesis Database

156‧‧‧ City Sample Library

157‧‧‧VOC database

158‧‧‧Topic database

159‧‧‧ Customer Service CV Database

160‧‧‧Dialogue database

201‧‧‧Inquiry voice receiving department

202‧‧‧Responding to the Requesting Department

203‧‧‧Response to the receiving department

204‧‧‧Response to the voice transmission department

301‧‧‧Response Management Department

351‧‧ ‧Document Database

352‧‧‧FAQ document database

651‧‧‧CRM Personal Database

652‧‧ ‧ database

800‧‧‧ server computer

811, 911‧‧‧ CPU

812, 912‧‧‧ROM

813, 913‧‧‧RAM

814, 914‧‧ ‧ busbar

815‧‧‧ Input Department

816, 916‧‧‧ Output Department

817, 919‧‧‧ Memory Department

818, 920‧‧ Department of Communications

819, 921‧‧‧ drive

821, 931‧‧‧Removable media

901‧‧‧Cooperative Processing Department

915‧‧‧Touch operation input

917‧‧‧Sound Input Department

918‧‧·Photography Department

Fig. 1 is a view showing a system configuration of an information processing system according to the present invention.

Fig. 2 is a view showing a hardware configuration of a server computer constituting each server.

Fig. 3 is a view showing a hardware configuration of the terminal device.

Figure 4 is a block diagram showing the main functions of the information processing system.

Fig. 5 is a flow chart showing the flow of the acceptance processing executed by the information processing system.

Fig. 6 is a view showing an example of a display screen displayed on the terminal device in the receiving process.

Fig. 7 is a flow chart showing the flow of VOC (Voice of Customer) collection processing.

Fig. 8 is a flow chart showing the flow of knowledge management processing executed by the information processing system.

Fig. 9 is a block diagram showing the main functional configuration realized in the information processing system according to the second embodiment.

Fig. 10 is a flow chart showing the flow of the cooperative processing performed by the information processing system of the second embodiment.

Fig. 11 is a view showing an example of a display screen displayed on the terminal device in the cooperative processing.

Fig. 12 is a view showing an example of a display screen displayed on a PC (personal computer) for a customer service person in the cooperative processing.

Hereinafter, embodiments of the present invention will be described using the drawings.

[First Embodiment]

[composition]

[System Components]

Fig. 1 is a view showing a system configuration of an information processing system 1 according to the present invention.

The information processing system 1 constitutes a proxy customer service center, which integrates the services of a plurality of enterprise customer service centers and processes them. In the information processing system 1, the inquiry from the customer is initially accepted by the virtual operator (VO) that recognizes the voice, and the inquiry is made by the virtual operator for the inquiry (fixed type) in which the preset answer is prepared. Answer it. Further, in the information processing system 1, for the inquiry that the preset answer is not prepared, the virtual operator performs supplementary processing to supplement the information for generating the answer, and when the answer can be generated, the virtual operator answers. Further, in the news In the processing system 1, for the inquiry that needs to be responded by the real person's customer service person, the customer service center of each company is contacted for processing.

Further, in the information processing system 1, the inquiry and the answer that can be finalized (which can be made into a fixed type) can be sequentially added to the virtual operator based on the history of the corresponding person. Styling inquiry.

Further, in the information processing system 1, the virtual operator raises a topic with the customer who made the inquiry and conducts a conversation, and proposes the recommendation information to the customer based on the information grasped through the conversation.

As shown in FIG. 1, the information processing system 1 includes the following components: a VO server 10, an IVR server 20, a plurality of CTIs (Computer Telephony Integration) servers 30, and IP-PBXs (Internet). A network protocol-user exchange (Internet Protocol Private Branch eXchange) server 40, a screen collaboration server 50, a CRM (Customer Relationship Management) server 60, and a terminal device 70. Further, the terminal device 70 and the IVR server 20 are configured to be communicable via the public telephone network 80A, and the terminal device 70, the VO server 10, and the CRM server 60 are connected via the Internet or the like. The public communication network 80B communicates with each other. Further, the VO server 10 and the CTI server 30 are connected to each other via a VPN (Virtual Private Network) 80C. Further, the CTI server 30 and the IVR server 20 transmit and receive IP sound (voice communication by the Internet Protocol) via the IP-PBX server 40.

The VO server 10 performs a preliminary acceptance of the inquiry by the virtual operator for an inquiry from the public communication network and from the terminal device 70 (smartphone or PC) that configures the browser. Specifically, the VO server 10 recognizes the sound transmitted from the terminal device 70 and responds with a sound corresponding to the spoken content. Further, the VO server 10 records a conversation between the customer who made the inquiry and the virtual operator, and performs mechanical learning based on the recorded session. The VO server 10 changes the method of voice recognition based on the result of the mechanical learning, and changes the interpretation method of the customer's intention. Further, the VO server 10 initializes the answer to the same inquiry based on the history of the inquiry corresponding to the agent, so as to create a correspondence that can be made by the virtual operator.

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

The CTI server 30 is provided for a plurality of enterprises (here, Company A to Company C), and the inquiry of the corresponding range in which the VO server 10 can perform preliminary acceptance is referred to the live agent of the real person in each company. To continue to accept. Specifically, on the CTI server 30, a PC for the customer service person used by the agent is connected, and a telephone for the customer service is connected via the PBX. Further, in the database of the CTI server 30, the URL (Uniform Resource Locator) or PDF (Portable Document Format) file of the document to be provided to the customer is memorized, or the FAQ is used. Documentation, etc. Further, when the CTI server 30 performs the reception by the agent, the screen is controlled via the screen cooperation server 50 to cooperatively display the screen of the terminal device 70 used by the customer. Use the screen of the PC with the customer service staff. In addition, the agent and the customer can use voice communication to make a call via the transmission of the IP voice or via the public telephone network 80A.

The IP-PBX server 40 performs conversion of IP sounds transmitted from the IVR server 20 or the terminal device 70 and sounds in the telephone line.

The screen cooperation server 50 controls the terminal device 70 used by the customer and the agent terminal device used by the agent to cooperatively display the screen of the terminal device 70 used by the customer and the agent terminal used by the agent. The screen of the device.

The CRM server 60 stores information on customer attributes such as purchase history, action history, or preference information. In addition, the information stored in the CRM server 60 is appropriately referred to as "personal information" hereinafter. The CRM server 60, which may correspond to requests from the VO server 10 or the CTI server 30, and refers to personal information to provide suitable information to the customers.

The terminal device 70 is a terminal device 70 used by a customer who inquires about the customer service center system configured by the information processing system 1, and is configured by, for example, a smart phone, a PC, or a mobile phone. A smartphone, a PC, or the like among the terminal devices 70 is a device that can display a guidance screen of the VO server 10, and can display a guidance screen in addition to a voice response by a virtual operator. Further, for a terminal device that cannot display a guidance screen, a voice response is performed by a virtual operator.

The terminal device 70 communicates page data such as files and images or IP voices via the public communication network 80B. In addition, the terminal device 70 can also use the public telephone network 80A and utilize the telephone line. To make voice communication. The terminal device 70 performs communication for the inquiry of the VO server 10 or the IVR server 2, and performs screen display or sound output of the response transmitted from the VO server 10 or the IVR server 20.

[Hardware composition]

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

[Server hardware structure]

The information processing system 1 is composed of a VO server 10, an IVR server 20, a CTI server 30, an IP-PBX server 40, a screen cooperative server 50, and a CRM server 60, and is installed in the server computer. The software of each server can be realized.

Fig. 2 is a view showing a hardware configuration of a server computer 800 constituting each server.

As shown in FIG. 2, the server computer 800 constituting each server includes a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, and a RAM (random access memory). (Random Access Memory) 813, bus bar 814, input unit 815, output unit 816, memory unit 817, communication unit 818, and driver 819.

The CPU 811 executes various processes (for realizing the processing of the functions of the respective servers) in accordance with the program recorded in the ROM 812 or the program loaded from the memory unit 817 into the RAM 813.

In the RAM 813, the data and the like necessary for the CPU 811 to perform various processes are also appropriately stored.

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

The input unit 815 is configured by various buttons and the like, and inputs various information in response to an instruction operation.

The output unit 816 is configured by a display, a speaker, or the like, and outputs an image or a sound.

The memory unit 817 is constituted by a hard disk or a DRAM (Dynamic Random Access Memory) or the like, and stores various materials managed by the respective servers.

The communication unit 818 controls communication with other devices via the network.

In the drive 819, a removable medium 821 is suitably mounted, which is constituted by a magnetic disk, a optical disk, an optical disk, or a semiconductor memory or the like. The program read from the removable medium 821 by the drive 819 is attached to the storage unit 817 in response to the need.

[Hardware Configuration of Terminal Device 70]

The terminal device 70 in the information processing system 1 is constituted by a terminal device 70 equipped with a browser such as a smart phone or a PC (Personal Computer), or a mobile phone or a fixed telephone that can perform voice communication.

FIG. 3 is a view showing a hardware configuration of the terminal device 70.

In addition, the hardware configuration of the smartphone is shown in FIG. 3 as an example of the terminal device 70.

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

The CPU 911 executes various processes (for performing the function processing of the terminal device 70) in accordance with a program recorded in the ROM 912 or a program loaded from the memory unit 919 into the RAM 913.

In the RAM 913, the data and the like necessary for the CPU 911 to perform various processes are also appropriately stored.

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

The touch operation input unit 915 is configured by, for example, a capacitive input type or a resistive film type position input sensor stacked on the display area of the output unit 916, and detects a coordinate at a position at which the touch operation is performed. Here, the touch operation refers to an operation of contacting or approaching an object (a user's finger or a touch pen, etc.) that touches the operation input portion 915.

The output unit 916 is configured by a display, a speaker, or the like to output an image or a sound.

That is, in the present embodiment, the touch panel is configured by touching the display of the operation input unit 915 and the output unit 916.

The sound input unit 917 is configured by, for example, a microphone, and converts the input sound into an analog electrical signal.

In addition, the analog signal of the sound is converted into a digital signal representing the sound data after being converted by A/D (Analog/Digital). The main body of the A/D conversion processing is not particularly limited, and may be a CPU 911 or a dedicated hardware (not shown). However, in the present embodiment, the sound input unit 917 is provided for convenience of explanation.

In other words, in the present embodiment, the voice input unit 917 outputs an audio signal 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 imaging sensor.

The optical lens unit is configured by a lens that collects light for capturing an object, and is configured by, for example, a focus lens. Further, in the optical lens unit, in addition to the focus lens, a zoom lens that can freely change the focal length within a certain range may be provided.

Further, in the optical lens unit, a peripheral circuit is provided to adjust setting parameters such as focus, exposure, white balance, and the like, as needed.

The imaging sensor is constituted by a photoelectric conversion element, an AFE (Analog Front End), or the like.

The photoelectric conversion element is configured by, for example, a CMOS (Complementary Metal Oxide Semiconductor) type photoelectric conversion element. In the image pickup element of this embodiment, a Bayer array color filter is mounted. The imaging element photoelectrically converts (images) the optical signals of the images of the subject that are incident and accumulated during the period, and sequentially supplies the resultant analog signals to the AFE.

The AFE performs various signal processing such as A/D conversion processing for such specific signals. The digital signal is generated by various signal processing and output as an output signal of the imaging unit 918. Hereinafter, the image data indicated by the output signal of the imaging unit 918 is appropriately referred to as "capture image data". 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 memory unit 919 is configured by a memory device such as a DRAM and stores various materials.

The communication unit 920 controls communication with other devices via the network.

The drive 921 is appropriately mounted with the removable medium 931 corresponding to the need. The program read from the removable medium 931 by the drive 921 is attached to the memory unit 919 as needed. Further, various materials stored in the storage unit 919 can be similarly stored in the removable medium 931.

[Structure of function]

Next, the main functional configuration realized in the information processing system 1 will be described.

Fig. 4 is a block diagram showing the main functional configuration realized in the information processing system 1.

As shown in FIG. 4, in the VO server 10 of the information processing system 1, the following database is provided: a character database 151, a personal database 152, a script database 153, a FAQ (Frequently Asked). The search database 154, the voice synthesis database 155, the market adjustment (market survey) template database 156, the VOC database 157, the topic filing database 158, the customer service resume database 159, and the conversation history database 160. Further, the CTI server 30 includes a document database 351 and a FAQ file database 352. Further, the CRM server 60 includes a CRM personal database 651 and a metadata repository 652.

In addition, in the fourth figure, the database is omitted as "DB".

The character database 151 stores information about various expressions and behaviors of the virtual operator.

The personal database 152 stores user-specific information such as the past inquiry content of each user (customer) specified by the user information or a part of the CRM personal data acquired from the CRM server 60.

The script database 153 stores an answer to the stereotype of the inquiry by the virtual operator or a dialog script (a template for the response).

The FAQ searches the database 154, which stores information on the FAQ (Frequently Asked Questions).

The sound synthesis database 155 stores the sound data used to synthesize the sound of the article.

The city sample library database 156, which stores information on pre-thinking samples of questions about various marketing or questionnaires.

The VOC database 157 stores the opinions or wishes (Voice of Customer) collected by the information processing system 1 as sound or file materials.

The topic mentioning database 158 stores information for the customer who made the inquiry and raises the topic corresponding to the content of the inquiry.

The customer service resume database 159 stores information on the history of the conversation between the customer and the customer service.

The conversation history database 160 stores information on the history of the conversation between the customer and the virtual operator.

The document database 351 stores information such as a URL or a PDF file of a document presented to the customer by the customer service staff.

The FAQ document database 352 stores the documents of the FAQ prompted by the customer service staff to the customer.

The CRM personal database 651 stores related information such as attribute information of a user, a purchase history, an action history, or a preference information.

The meta-database 652 summarizes and memorizes the purchase history, action history, SNS (Social Networking Service) information, and hobby information (i.e., summarized and memorized as metadata) of a majority of users.

Further, as shown in FIG. 4, the information processing system 1 includes an inquiry sound receiving unit 201, an answer request unit 202, an answer receiving unit 203, and an answer voice transmitting unit 204 in order to realize the function of the IVR server 20. Further, in order to realize the function of the VO server 10, the IP communication unit 101, the speech capture unit 102, the user information acquisition unit 103, the voice recognition unit 104, the emotion analysis unit 105, the language determination unit 106, the intention and the state explanation are provided. The unit 107, the dialog processing unit 108, the voice synthesizing unit 109, the screen control unit 110, the supplementary processing unit 111, the agent call unit 112, the machine learning processing unit 113, the finalization processing unit 114, and the agent support unit 115. Further, in order to achieve the function of the CTI server 30, the response management unit 301 and the 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 speech capture unit 102 performs the capture of the speech content by detecting the unvoiced portion of the input sound.

The user information acquisition unit 103 obtains user information uniquely identifying the user of the terminal device based on the information (IP address, user ID and password, terminal device number, etc.) of the accessed terminal. (a number unique to the user, etc.).

The voice recognition unit 104 recognizes the voice input from the speech capturing unit 102 and converts the voice into a character string.

The emotion analysis unit 105 analyzes the emotion of the speaker based on the speech content and the unvoiced portion input from the speech capturing unit 102, and outputs the data obtained by digitizing the emotion. For example, the emotion analysis unit 105 is based on the speaker's The value of each parameter of the joy, anger, sadness, happiness, calmness, anxiety, etc. of the speaker's feelings is calculated by the speed of speech or the magnitude of the swaying (tone).

The language determination unit 106 determines the spoken language based on the character string input from the voice recognition unit 104. For example, the language determination unit 106 determines a language in which a plurality of languages corresponding to the information processing system 1 are the most accurate in the result of the voice recognition by the voice recognition unit 104. .

The intention and state interpretation unit 107 interprets the intention of the speaker and the state of the current conversation based on the character string determined by the language determination unit 106 and the numerical data of the emotion input from the emotion analysis unit 105. Specifically, the intention and state interpretation unit 107 discriminates and interprets the contents of the character string of the language (that is, the character string filed by the speaker's voice) determined by the language determination unit 106. The intention of the conversation (the meaning of the speech). At this time, the intention and state interpretation unit 107 refers to the user information acquired by the user information acquisition unit 103, and refers to the user's personal data stored in the CRM server 60 and in the personal data repository 152. The stored user's past inquiry content is used to explain the intent of the speaker's conversation. For example, when there are a plurality of homonyms in the word included in the utterance of the speaker who has performed the voice recognition, the intention and state interpretation unit 107 refers to the past inquiry content of the speaker or the purchase history or the like to specify the word. The meaning is explained in the most likely sense. Thereby, it is possible to appropriately determine the intention of the inquiry and answer the inquiry in accordance with the speaker (customer) who makes the inquiry. Again, the intention and state solution The interpretation unit 107, when interpreting the speaker's intention, repeats the same question when the speaker answers the virtual operator with a strong "angry" feeling, and then determines that the interpretation of the intention is erroneous and can change the interpretation of the intention.

Further, the intention and state interpretation unit 107 interprets the precondition of the current conversation of the speaker as the element of the current conversation state based on the trend of the conversation from the start of the inquiry until now. For example, when the speaker specifies a specific condition in the speech before one sentence (for example, when designating Shinjuku as a region, etc.), the specific condition specified is used as a premise in the next sentence to explain what the speaker said. Conversation.

Further, the intention and state interpretation unit 107 interprets the type of the terminal device 70 used by the speaker as an element of the state of the current conversation. For example, the intention and state interpretation unit 107 explains whether or not the terminal device 70 used by the speaker is the terminal device 70 that can be guided by the screen display, and interprets the current state of the conversation. When the terminal device 70 used by the speaker is not the terminal device 70 that can be guided by the screen display, the intention and state interpretation unit 107 selects a dialogue in which the portrait is not used.

The intention and state interpretation unit 107 searches the FAQ search database 154 based on the intention of the speaker thus explained and the state of the current conversation to determine whether or not the content of the conversation can be determined (first determination). When the result of the first determination is that the content of the conversation can be decided, the intention and state interpretation unit 107 determines the content of the conversation for the conversation. For example, when the speaker's speech is "Which restaurant is there in Shinjuku?", the intention and state interpretation unit 107 determines that the popular restaurant in Shinjuku is the content of the conversation to be answered. On the other hand, when the content of the conversation cannot be decided, then the intention and the shape The state interpretation unit 107 relies on the supplementary processing unit 111 to perform a supplementary process (described later) for determining the information of the conversation content. Then, the intention and state interpretation unit 107 determines whether or not the content of the conversation can be determined based on the result of the supplementary processing (second determination). Specifically, it is determined whether or not the FAQ search database 154 can be searched for using the result of the supplementary processing to determine the content of the conversation, or whether information for determining the content of the conversation can be obtained from an information source other than the FAQ search database 154. When the result of the second determination is that the content of the conversation can be determined, the intention and state interpretation unit 107 determines the content of the conversation for the conversation. On the other hand, when the content of the conversation cannot be determined, the intention and status interpretation unit 107 calls the agent of the company at the inquiry via the agent call unit 112.

The dialog processing unit 108 refers to the scenario database 153 based on the content of the conversation explained by the intention and state interpretation unit 107 to determine the line of the response to the speaker. For example, when the conversation processing unit 108 determines that the popular restaurant of Shinjuku is the content of the conversation to be answered by the intention and state interpretation unit 107, it selects "at the Shinjuku station based on the script stored in the script database 153. The popular restaurant which is within ○○m is the line of...".

Further, the dialog processing unit 108 stores the speaker's speech and the line of the speaker's response in the conversation history database 160 in association with the speaker's user information and the speaker's terminal device 70. Dialogue history.

The speech synthesizing unit 109 synthesizes the speech by the speech determined by the dialog processing unit 108 and transmits it to the terminal device 70 of the speaker.

The screen control unit 110 determines the character profile of the virtual operator displayed on the terminal device 70 of the speaker based on the content of the conversation explained by the intention and state interpretation unit 107 and referring to the character database 151. Specifically, the screen control unit 110 selects the character data of the expression and the behavior corresponding to the content of the conversation explained by the intention and state interpretation unit 107, and displays the screen material of the session in which the virtual operator performs the conversation according to the expression and behavior. Then, the screen control unit 110 transmits the generated screen material to the terminal device 70 of the speaker.

When there is a dependency of the supplementary processing from the intention and state interpretation unit 107, the supplementary processing unit 111 performs supplementary processing of the information to determine the content of the conversation. Specifically, when there are a plurality of candidates for the answer to the inquiry, the supplementary processing unit 111 transmits the question of the supplementary inquiry content to the terminal device 70, and when the answer to the inquiry is not included in the FAQ search database 154. Then, information about the inquiry content is retrieved from an information source other than the FAQ search database 154 (a customer service resume database 159 or the Internet). Then, the supplementary processing unit 111 outputs the answer to the question or the search result to the intention and state interpretation unit 107 as a result of the supplementary processing.

The agent caller 112 calls the agent of the company at the inquiry when there is a dependency of the call from the agent of the intent and status interpretation section 107. Further, when the terminal device 70 performs an operation of calling the agent (for example, pressing the "call" button of the sixth (A) diagram described later), the agent caller 112 performs the process of calling the agent. At this time, the agent call unit 112 can also be combined with the content of the inquiry of the speaker's customer. The customer's speech speed or emotional data obtained in the virtual operator's conversation is notified to the customer service staff.

The machine learning processing unit 113 refers to the conversation history stored in the conversation history database 160 to determine whether or not an inappropriate response has been made in the conversation history. For example, the machine learning processing unit 113 determines whether or not the speaker denies the response of the virtual operator in the conversation history, and indicates that the virtual operator is not required to contact the agent. Then, the machine learning processing unit 113 notifies the system administrator PC used by the system administrator to determine the history of the conversation in which the inappropriate response has been made.

When the system administrator determines that the response history of the inappropriate response has been determined by the machine learning processing unit 113 as an inappropriate response, the content of the voice recognition in the conversation history (self-sound) The degree of accuracy of the interpretation of the intention of the speaker (the result of the determination of the content of the character string) is set to be low, and is fed back to the process of the voice recognition unit 104 and the intention and state interpretation unit 107.

When the knowledge management process is executed and the customer service staff history database 159 is used to learn that the customer service has answered the same inquiry a plurality of times, the finalization processing unit 114 adds the inquiry and the answer to the inquiry. The model is added and added to the FAQ search database 154. Further, at this time, the customized inquiry and the answer may be notified to the system administrator PC first, and may be added to the FAQ search database 154 when the approval is obtained.

Here, in the present embodiment, the inquiry and the answer to the agent in the customer service center of a plurality of companies are collectively referred to, and the answer is made based on whether or not the answer to the same inquiry has been performed plural times. borrow Since the same inquiry and answer can be finalized in a plurality of companies, the frequency of inquiring and answering can be improved compared with the case where the customer service center is used in a separate company. However, it is also possible to refer to the inquiry and the answer to the customer service staff in the customer service center of each enterprise, and to finalize the answer to the inquiry in each enterprise according to whether the answer to the same inquiry has been repeated in the enterprise. .

When the agent responds to the inquiry by the customer, the agent support unit 115 performs voice recognition on the session by the voice recognition unit 104, and provides support information to the agent based on the file data as a result of the voice recognition. For example, when the inquiry content of the customer is "NISA (Nippon Individual Saving Account)", the customer service support unit 115 displays the information about "NISA" on the PC for the customer service. Further, the agent support unit 115 may analyze the relationship between the customer and the agent by the emotion analysis unit 105, and display the change in the feeling of the customer on the PC for the customer service based on the data obtained by digitizing the feeling.

The inquiry sound receiving unit 201 of the IVR server 20 receives the sound transmitted from the terminal device 70 and outputs it to the answer request unit 202.

The answer request unit 202 transmits the data of the voice input from the inquiry sound receiving unit 201 to the VO server 10 to request the voice of the answer.

The answer receiving unit 203 receives the data of the voice of the answer transmitted from the VO server 10.

The answer voice transmitting unit 204 transmits the data of the voice of the answer received from the answer receiving unit 203 to the terminal device 70 as a voice.

The response management unit 301 of the CTI server 30 manages the inquiry to contact the customer service agent in such a manner that the customer corresponds to the corresponding customer service agent.

The screen control unit 302 controls the screen of the terminal device 70 via the screen cooperation server 50 in accordance with the operation of the agent.

[action]

Next, the operation of the information processing system 1 will be described.

Fig. 5 is a flowchart showing the flow of the acceptance processing executed by the information processing system 1.

The processing is accepted, which starts with the activation of the information processing system 1.

6 is a view showing an example of a display screen displayed on the terminal device 70 in the receiving process, FIG. 6(A) is an example of accepting an initial screen, and FIG. 6(B) is a display screen in a stereotype response. For example, the 6th (C) figure is an example of a guest screen, and the 6th (D) is an example of a display screen in VOC collection. Hereinafter, the flow of the acceptance processing will be described with reference to Fig. 6 as appropriate.

In step S1, the voice recognition unit 104 of the VO server 10 determines whether or not there is an inquiry from the terminal device 70.

When there is no inquiry from the terminal device 70, the determination is 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, the determination in step S1 is YES, and the process proceeds to step S2.

In step S2, the screen control unit 110 displays the acceptance initial screen on the terminal device 70 (see FIG. 6(A)).

In step S3, the speech capturing unit 102 extracts the speech content, and the speech recognition unit 104 recognizes the sound input from the speech capturing unit 102, and the emotion input by the emotion analyzing unit 105 for the self-speaking capturing unit 102. Conduct emotional analysis.

In step S4, the language determination unit 106 determines the spoken language.

In step S5, the intention and state interpretation section 107 explains the speaker's intention and the state of the current conversation.

In step S6, the intention and state interpretation unit 107 searches the FAQ search database 154 based on the speech content specified by the speaker's intention explained in step S5 and the state of the current conversation.

In step S7, the intention and state interpretation unit 107 determines whether or not it is possible to determine the content of the conversation (that is, whether or not there is an answer in the FAQ search database 154).

When the content of the conversation can be determined, it is determined to be YES in step S7, and the process proceeds to step S8.

On the other hand, when the content of the conversation cannot be determined, the determination in step S7 is NO, and the process proceeds to step S10.

In step S8, the intention and state interpretation unit 107 determines the content of the conversation by the response retrieved from the FAQ search database 154, and responds by the dialog processing unit 108 (typed response) (see section 6 (B). )))).

In step S9, the intention and state interpretation unit 107 makes a determination as to whether or not the response to the inquiry is completed.

When 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 has been completed, the process proceeds to step S18.

In step S10, the intention and state interpretation unit 107, which relies on the supplementary processing unit 111, performs supplementary processing. Specifically, when there are a plurality of candidates for the answer to the inquiry, the supplementary processing unit 111 transmits the question of the supplementary inquiry content to the terminal device 70, and when the answer to the inquiry is not included in the FAQ search database 154. Then, information about the inquiry content is retrieved from an information source other than the FAQ search database 154 (a customer service resume database 159 or the Internet).

In step S11, the intention and state interpretation unit 107 determines whether or not the result of the supplementary processing can determine the content of the conversation.

When the result of the supplementary processing can determine the content of the conversation, the determination in step S11 is YES, and the process proceeds to step S12.

When the result of the supplementary processing cannot determine the content of the conversation, the determination is NO in step S11, and the processing proceeds to step S13.

In step S12, the intention and state interpretation unit 107 determines the content of the conversation using the result of the supplementary processing, and the dialogue processing unit 108 performs the correspondence.

After step S12, the process proceeds to step S9.

In step S13, the intention and status interpretation unit 107 calls the agent of the company at the inquiry via the agent call unit 112. At this time, the virtual operator on the screen of the terminal device 70 may express the response of the calling agent by the screen control unit 110. In addition, when When the operation of calling the agent is performed on the terminal device 70, the process of step S13 for calling the agent is jumped by the interrupt processing.

In step S14, the screen control unit 110 of the CTI server 30 displays a guest agent screen on the screen of the terminal device 70, which displays the document as a background and displays the document by voice recognition. Conversation content (refer to Figure 6(C)). By displaying the customer service screen, the customer is made to feel that the corresponding person (customer agent) is in the vicinity, and the inquiry and the answer can be performed more smoothly.

In step S15, the voice recognition unit 104 performs voice recognition on the conversation between the customer and the agent.

In step S16, the intention and state interpretation unit 107 determines whether or not the conversation between the customer and the customer service has ended.

When the conversation between the customer and the agent has not been completed, the determination is NO in step S16, and the process proceeds to step S14.

When the conversation between the customer and the agent has ended, the determination in step S16 is YES, and the process proceeds to step S17.

In step S17, the intention and state interpretation unit 107 executes VOC collection processing (see FIG. 6(D)).

In step S18, the dialog processing unit 108 stores a series of conversation histories for the inquiry in the conversation history database 160.

After the step S18, the acceptance processing is repeated until the instruction to end the release.

With this processing, in the information processing system 1, when the inquiry has been made by the terminal device 70, the FAQ search database 154 is referred to, if When an answer is prepared in the FAQ search database 154, the virtual operator performs a final response. On the other hand, if an answer is not prepared in the FAQ search database 154, the VO server 10 performs supplementary processing of the information to determine the content of the conversation, and retrieves the answer from the FAQ search database 154 using the result of the supplementary processing, or The process of obtaining information from the information source other than the FAQ search database 154 is performed so that the virtual operator can respond to the inquiry. Further, when the virtual operator cannot respond to the inquiry even if the result of the supplementary processing is used, the customer service agent is called and the customer service person responds.

Therefore, in the information processing system 1, it is attempted to respond by a virtual operator as much as possible to reduce the frequency of calling the agent.

Therefore, the business that accepts the inquiry from the customer can be made more efficient.

Next, the VOC collection processing executed as a subroutine in step S17 of the acceptance processing will be described.

Fig. 7 is a flow chart showing the flow of VOC collection processing.

When the VOC collection process is started, in step S21, the intention and state interpretation unit 107 refers to the market sample library 156 to obtain a template of the questionnaire regarding the response of the agent, and displays it on the terminal by the screen control unit 110. On the screen of device 70.

In step S22, the intention and state interpretation unit 107 receives the answer to the questionnaire. Further, in the terminal device 70, the answer to the questionnaire may be input by a character in addition to the voice input.

In step S23, the intention and state interpretation unit 107 refers to the topic mentioning library 158 and raises the topic corresponding to the inquiry content to the terminal device 70.

In step S24, the voice recognition unit 104 recognizes the voice of the response to the topic transmitted from the terminal device 70.

In step S25, the intention and state interpretation unit 107 searches for a dialogue for prompting the sales information from the topic filing database 158 based on the keyword included in the answer obtained by the voice recognition. In addition, sales information refers to advertising information intended to be up-selling or cross-selling. When the sales information is prompted, the sales information in the company limited to the customer's inquiry may be prompted, or the sales information of the plurality of companies using the information processing system 1 may be prompted.

In step S26, the intention and state interpretation unit 107 performs a determination as to whether or not the dialog for presenting the sales information can be retrieved.

When it is possible to retrieve the information for prompting the sales, the determination in step S26 is YES, and the process proceeds to step S27.

When the sales information for prompting cannot be retrieved, the determination is NO in step S26, and the process proceeds to step S28.

In step S27, the intention and state interpretation unit 107 performs a dialog for presenting sales information and prompts the customer for sales information.

After step S27, the process proceeds to step S29.

In step S28, the intention and state interpretation unit 107 retrieves the continued topic from the topic filing database 158 and lifts it up to the terminal device 70.

In step S29, the intention and state interpretation unit 107 makes a determination as to whether or not the end condition of the VOC collection processing coincides. The end condition of the VOC collection process is defined as a case where the customer has instructed the end of the VOC collection process, or a case where the customer requests the product guidance in response to the sales information.

When it does not coincide with the end condition of the VOC collection processing, the determination is NO in step S29, and the processing proceeds to step S24.

On the other hand, when it coincides with the end condition of the VOC collection processing, the determination in step S29 is YES, and the VOC collection processing is ended.

By this processing, it is possible to perform an associated session (a chat-like session) other than the inquiry by the virtual operator and the customer, and present the sales information to the customer in accordance with the content of the session.

Therefore, the customer who inquires about the occurrence of any event or the like can present the sales information in accordance with the state of the customer.

Therefore, the use of the customer service center business can be more effective in marketing.

Next, the knowledge management process will be described.

Fig. 8 is a flow chart showing the flow of knowledge management processing executed by the information processing system 1.

The knowledge management process refers to batch processing and the like performed at a predetermined time.

In step S31, the finalizing processing unit 114 refers to the customer service provider history database 159.

In step S32, the finalization processing unit 114 analyzes the customer service provider history database 159.

In step S33, the finalization processing unit 114 determines whether or not there is a session that can be finalized in the customer service provider history database 159. Whether or not there is a session that can be finalized can be determined, for example, by whether or not the answer to the same inquiry has been performed a predetermined number of times or more.

When there is no session that can be finalized in the history of the customer service provider history database 159, the determination is NO in step S33, and the knowledge management process is ended.

On the other hand, when there is a session that can be finalized in the history of the customer service provider history database 159, the determination in step S33 is YES, and the process proceeds to step S34. .

In step S34, the finalizing processing unit 114 adds the customized query and answer to the FAQ search database 154.

After step S34, the knowledge management process is ended.

As a result of such a process, the inquiry that the customer service agent has responded but has not been finalized is added to the FAQ search database 154 as a formable inquiry when the same inquiry has been performed plural times. . Later, when the same inquiry is made, the answer is not made by the agent but by the virtual operator.

Therefore, the more the information processing system 1 is used, the more the range of the inquiry that enables the stereotyped response is expanded, so that the efficiency of the service using the customer service center of the information processing system 1 can be improved.

[Second embodiment]

Next, a second embodiment will be described.

[composition]

Fig. 9 is a block diagram showing the main functional configuration realized in the information processing system 1 of the second embodiment.

The information processing system 1 of the second embodiment further includes a cooperative server 90 for realizing cooperation between the VO server 10 and the IVR server 20 in the information processing system 1 of the first embodiment. Further, in the ninth diagram, the functions of the respective servers shown in the first embodiment are omitted.

The cooperative server 90 includes a cooperative processing unit 901 for performing cooperative processing for the VO server 10 and the IVR server 20. When the cooperation processing unit 901 performs preliminary reception by the VO server 10, the call is made in the IVR server 20 in response to the customer's operation of calling the agent by the terminal device 70. Then, the cooperative processing unit 901 automatically makes an inquiry by voice corresponding to the conversation content with the customer to date, and automatically performs a session corresponding to the automatic voice response provided by the IVR server 20 until the call to the agent. .

By this processing, even if the VO server 10 and the CTI server 30 cannot directly cooperate, the automatic voice answering function of the IVR server 20 can be utilized, and the VO server 10 can call the agent.

Further, the VO server 10 may have the function of the cooperative server 90.

[action]

Next, the operation will be described.

In the information processing system 1 of the second embodiment, the acceptance processing shown in Fig. 6 is executed in the same manner as in the first embodiment.

Further, when an operation for calling a customer service person is performed in the terminal device 70, step S13 is taken as a sub-flow to perform cooperative processing.

Fig. 10 is a flowchart showing the flow of the cooperative processing performed by the information processing system 1 of the second embodiment.

11 is a view showing an example of a display screen displayed on the terminal device 70 in the cooperative processing, and FIG. 11(A) is an example of an input screen of a telephone number, and FIG. 11(B) is a contact point of a customer service person. An example of a display screen of a list, and FIG. 11(C) is an example of a display screen indicating that a customer service person is calling.

Further, Fig. 12 is a view showing an example of a display screen displayed on the PC for the agent in the cooperative processing. Fig. 12(A) is an example of a dialog history search screen, Fig. 12(B) is an example of a dialog history confirmation screen, Fig. 12(C) is an example of a screen when a call is received, and Fig. 12(D) is an example after the response is completed. Example of the screen.

Hereinafter, the flow of the cooperative processing will be described with reference to FIGS. 11 and 12 as appropriate.

In step S41, the intention and state interpretation unit 107 of the VO server 10 performs a response prompting the customer to input the telephone number by the dialog processing unit 108 (refer to Fig. 11(A)). At this time, the customer can also input the telephone number by any of the input of the voice input or the character string. Thereby, the customer's own telephone number can be obtained in the VO server 10.

In step S42, the agent call unit 112 obtains a list of liaisons of the agent who is estimated to be the customer's inquiry from the cooperation processing unit 901 of the cooperation server 90, and transmits it to the terminal device (refer to item 11(B)). Figure). In the 11th (B) diagram, three liaison offices that are highly likely to be the customer's inquiry are displayed, and buttons for displaying all the liaison offices are displayed. The cooperation processing unit 901 can obtain the contact person of the customer service person from the CTI server 30, or can collect information from a general Web server to obtain the contact person of the customer service. In addition, the deployment name and phone number of the inquiry can be displayed, or only the deployment name of the inquiry office can be displayed as the contact point of the customer service staff. Further, in step S42, the information of the conversation history of the customer and the virtual operator up to the present is transmitted to the cooperation server 90.

In step S43, the agent call unit 112 obtains the contact location selected in the terminal device 70.

In step S44, the agent call unit 112 requests the cooperation processing unit 901 to make a call toward the contact point selected in the terminal device 70. Further, in step S44, the information of the conversation history of the customer and the virtual operator up to the present is transmitted to the cooperation server 90.

In step S45, the cooperation processing unit 901 makes a call in the IVR server 20, and automatically makes an inquiry by voice based on the content of the conversation with the customer so far. At this time, the cooperative processing unit 901 automatically performs the session until the call to the agent is corresponding to the automatic voice response provided by the IVR server 20. Further, on the terminal device 70, the virtual operator is notified of the message that the customer service person is calling (see FIG. 11(C)).

In step S46, the IVR server 20 calls the agent at the result of the response of the session automatically performed by the cooperation processing unit 901 (for example, the content of the conversation such as the contact point input by the customer).

In step S47, the response management unit 301 of the CTI server 30 performs a call processing to assist the called agent. The call processing is to display a dialog history search screen for searching the content of the inquiry on the PC for the customer service (see Fig. 12(A)). The agent, who enters the ID notified by the collaborative server 90. Then, on the dialogue history confirmation screen, the conversation history of the customer who has made the call (the data of the conversation history managed by the cooperation server 90) is displayed in a character string, and the button used by the agent to call the customer is displayed. (Receive the phone button) (Refer to Figure 12(B)).

In step S48, the cooperation processing unit 901 shifts to the "waiting call state" in a state in which the agent is ready to make a call in response to the operation of the call button by the agent. At this time, the screen of the answering call is displayed on the PC by the customer service staff (refer to FIG. 12(C)) for the customer service staff to input the result of the operation of receiving the telephone button.

In step S49, the cooperation processing unit 901, via the IP-PBX server 40, dials the telephone number input by the customer with the telephone set by the agent.

In step S50, if the customer picks up the call, the call of the customer service agent and the customer is started.

After step S50, the process returns to the acceptance process.

In addition, after the call between the customer service staff and the customer, the customer service staff enters "Already able to call", "The customer does not answer the call", "No" in the screen when answering the call. Contact results with customers for "signal", "telephone answering machine", "in-call", or "incorrect phone number". Once the agent completes the input, the answer completion screen is displayed (refer to Figure 12(D)) to indicate that the agent has completed the response to the customer.

With this processing, when the customer requests to call the agent, the cooperative processing unit 901 of the cooperative server 90 performs the session by the automatic voice response provided by the IVR server 20, and based on the input by the customer in the session. The liaison office calls the agent at the IVR server 20.

Therefore, even when the VO server 10 and the CTI server 30 do not directly cooperate, the automatic voice answering function of the IVR server 20 can be utilized, and the VO server 10 can be used to call the agent.

[Application Example 1]

In the above embodiment, the role of the virtual operator, the clothing, and the like can be changed in accordance with the company in the inquiry. For example, a character with a different personality can be memorized in the character database in advance. If the content of the inquiry is technical, the virtual operator is set to a role of a detailed technology, and if the content of the inquiry is about banking, the virtual operation is performed. The player is set to a character in a suit.

Thereby, the customer who made the inquiry can feel that the virtual operator has the temperament that matches the content of the inquiry.

[Application Example 2]

In the above embodiment, the roles, clothing, and the like of different virtual operators can be set in accordance with the customer who makes the inquiry. For example, it is possible to memorize a plurality of characters having different personalities in the character database in advance. When the customer inquiring about the animation, the virtual operator can be set to the role in the movement.

Thereby, it is possible to respond to the customer service center by the virtual operator who can bring a good feeling to the customer, and it is possible to improve the satisfaction of the customer.

[Application Example 3]

In the above-described embodiment, when the customer who makes the inquiry needs to perform the same procedure as the address change in a plurality of companies, the procedure can be collectively performed in a plurality of companies by the acceptance of the virtual operator.

Thereby, it is possible to reduce the time required for the customer to perform the same procedure multiple times.

[Application Example 4]

In the above-described embodiment, the virtual operator may submit the procedures related to the inquiry content in addition to the procedures inquired by the customer, and the procedures may be collectively performed.

Thereby, it is possible to reduce the possibility that the customer misses the necessary procedures.

As described above, the information processing system 1 of the present embodiment includes the terminal device 70 and the VO server 10 as the receiving server.

The VO server 10 includes a voice recognition unit 104, an intention and state interpretation unit 107, and a customer service call unit 112.

The voice recognition unit 104 accepts an inquiry from the terminal device 70.

The intention and state interpretation unit 107 determines whether or not the answer to the inquiry can be retrieved from the FAQ search database 154 in which a plurality of questions and answers prepared in advance are stored.

Further, the intention and state interpretation unit 107, when it is determined that the answer to the inquiry cannot be retrieved, performs supplementary processing to supplement the information for performing the answer to the inquiry, and generates an answer to the inquiry based on the result of the supplementary processing.

Further, the intention and state interpretation unit 107 determines whether or not an answer to the inquiry can be generated.

Further, the intention and state interpretation unit 107 transmits the retrieved answer or the generated answer when it is determined that the answer to the inquiry can be retrieved and the answer to the inquiry can be generated.

The agent call unit 112, when the intention and status interpretation unit 107 determines that the answer to the inquiry cannot be generated, executes the call processing corresponding to the inquirer.

Thereby, when the inquiry is made by the terminal device 70, the FAQ search database 154 is referred to, and if there is a preparation for answering in the FAQ search database 154, a fixed answer is made. On the other hand, if there is no prepared answer in the FAQ search database 154, the supplementary processing of the information is performed to perform an answer to the dialogue, and an answer is generated based on the result of the supplementary processing. Further, when the answer to the inquiry cannot be generated even if the result of the supplementary processing is used, the agent is called and the responder responds.

Therefore, in the information processing system 1, an automatic response by the system is attempted as much as possible to reduce the frequency of calling the agent.

Therefore, the business that accepts the inquiry from the customer can be made more efficient.

Further, as a supplementary process, the intention and state interpretation unit 107 transmits a question of supplementing the inquiry content to the terminal device 70.

Thereby, when the answer to the inquiry is not completely specified, the question of the specific answer is made.

Further, as a supplementary process, the intention and state interpretation unit 107 retrieves information on the content of the inquiry from an information source other than the FAQ search database 154.

Thereby, even when the answer to the inquiry is not prepared, the information can be obtained from the searchable information source to answer.

Further, the voice recognition unit 104 accepts an inquiry from the terminal device 70 using an automatic response of voice recognition.

Further, the intention and state interpretation unit 107 transmits the retrieved answer or the generated answer as a response to the voice material.

Thereby, it is possible to automatically respond to the inquiry from the terminal device with sound.

Further, the VO server 10 includes a finalizing processing unit 114.

The finalization processing unit 114 generates a combination of the finalized inquiry and the answer based on the history of the response of the agent.

Thereby, the inquiry that the customer service agent has responded but has not been finalized is used as the inquiry that can be finalized when the same inquiry has been performed plural times.

Therefore, the more the information processing system 1 is used, the more the range of the inquiry that enables the stereotyped response is expanded, so that the efficiency of the service using the customer service center of the information processing system 1 can be improved.

Further, the customer service call unit 112 performs call processing to call a customer service person corresponding to the inquiry organization among the customer service agents set up by each of the plurality of organizations.

The voice recognition unit 104 accepts an inquiry about a plurality of organizations on behalf of the voice recognition unit 104.

The finalization processing unit 114 generates a combination of a query and an answer that can be finalized by a plurality of organizations based on the history of the customer's response to the inquiry of each organization.

In this way, when the corresponding service for the inquiry is integrated in a plurality of organizations, the same inquiry and answer in a plurality of enterprises can be finalized, so that the corresponding business for the inquiry is used in a separate company. In comparison, the frequency with which queries and answers can be finalized can be improved.

Further, the VO server 10 includes a personal data library 152.

A personal database 152 that manages personal information about the individual of the customer making the inquiry.

The intention and state interpretation unit 107 refers to the personal information to determine whether or not the answer to the inquiry can be retrieved from the FAQ search database 154.

Thereby, the intention of the inquiry can be appropriately determined in accordance with the customer who made the inquiry, and the inquiry can be answered.

Further, the intention and state interpretation unit 107 vocally provides a topic related to the inquiry content.

Further, the intention and state interpretation unit 107 performs voice recognition on the response of the user from the terminal device 70 to the topic, and provides recommendation information (sales information, etc.) associated with the response content by voice.

Thereby, the recommendation information corresponding to the content of the session is presented to the customer by the system and the associated conversation (quiet conversation) other than the customer's own inquiry.

Therefore, the customer who makes an inquiry because of the occurrence of any event or the like can present advice information that matches the state of the customer.

Therefore, marketing can be performed more effectively with the corresponding business for the inquiry.

Further, the information processing system 1 includes an IVR server 20 as an automatic voice response server and a cooperative server 90.

The IVR server 20, when the inquiry from the terminal device 70 is a predetermined inquiry, is answered by an automatic voice response, and when an inquiry other than the preset is made, the call of the agent is performed.

The cooperative server 90, when calling the agent through the VO server 10, makes an inquiry to the IVR server 20 based on the inquiry and response between the VO server 10 and the terminal device 70, and automatically performs the session until the customer service is completed. The call processing of the member is used to carry out the call of the customer service staff.

Thereby, when the customer requests to call the agent, the automatic voice answering machine in the IVR server 20 can be input by the cooperative server 90 and the call of the agent can be carried out via the IVR server 20.

Therefore, the automatic voice response function of the IVR server 20 can be utilized, and the VO server 10 is used to call the agent.

Further, the present invention is not limited to the above-described embodiments, and variations, improvements, and the like within a scope that can achieve the object of the present invention are also included in the present invention.

For example, in the above embodiment, the case where the organization represented by the information processing system 1 is an enterprise will be described, but the present invention is not limited thereto.

That is to say, in addition to the company, it is applicable to organizations that are inquiring about conducting business, such as schools, administrative agencies, or medical institutions.

Further, in the above-described embodiment, the configuration of each server is merely an example. As long as the information processing system 1 as a whole has the functions of the above-described servers, it is also possible to integrate the functions of a plurality of servers. Split the function of one server.

The series of processes described above can be implemented by hardware or by software.

In other words, the configuration of the function of Fig. 4 is merely an example and is not particularly limited. In other words, as long as the components included in the information processing system 1 as a whole can perform the functions of the above-described series of processes, it is not limited to the example of FIG. 4 to realize which functions are used.

Further, one functional block may be configured only by a hard body, or may be constituted only by a soft body, or may be configured by a combination of a hard body and a soft body.

When a series of processing is executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium.

A computer can also be a computer that is assembled in dedicated hardware. Moreover, the computer can also be a computer that can be implemented by installing various programs, such as a general-purpose personal computer.

The recording medium including such a program may be constituted not only by the removable medium 821 of the second figure which is provided to the user by the program separately from the apparatus body, but also may be pre-assembled to the apparatus body. In the state, the program is provided to the user's memory medium and the like. The removable media 821 is constructed, for example, by a magnetic disk (including a floppy disk), a compact disk, or a magnetic disk. The optical disc is constituted by, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), or the like. The optical disk is composed of MD (Mini-Disk). The memory medium supplied to the user in a state of being pre-assembled to the apparatus body is constituted by, for example, the ROM 812 of the second drawing in which the program has been recorded, or the DRAM included in the memory unit 817 of the second drawing.

Further, the steps of recording the program in the recording medium described in the present specification may of course be processed in time series in the order, but also include processing not in time series, but in parallel or individually. Case.

Further, the term "system" in the present specification means an entire device constituted by a plurality of devices or a plurality of means.

10‧‧‧VO server (receiving server)

20‧‧‧IVR server (automatic voice response server)

30‧‧‧CTI server

40‧‧‧IP-PBX Server

50‧‧‧ Screen Collaboration Server

60‧‧‧CRM server

70‧‧‧ Terminal devices

101‧‧‧IP Communications Department

102‧‧‧Speaking Department

103‧‧‧User Information Acquisition Department

104‧‧‧Voice Identification Department (acceptance means)

105‧‧‧Affective Analysis Department

106‧‧‧Language Discrimination Department

107‧‧‧Intentions and Status Interpretation Department (first means of judgment, means for generating answers, second means of judgment, means of answering, means of providing topics, means of providing information for recommendation)

108‧‧‧Dialog Processing Department

109‧‧‧Sound Synthesis Department

110‧‧‧Screen Control Department

111‧‧‧Additional Processing Department

112‧‧‧Customer Service Calling Department (calling means)

113‧‧‧Mechanical Learning Processing Department

114‧‧‧Formation Processing Department (formation processing means)

115‧‧‧Customer Support Department

151‧‧‧ Character database

152‧‧‧Personal database (personal information management means)

153‧‧‧ script database

154‧‧‧FAQ Search Database (Response Database)

155‧‧‧Sound Synthesis Database

156‧‧‧ City Sample Library

157‧‧‧VOC database

158‧‧‧Topic database

159‧‧‧ Customer Service CV Database

160‧‧‧Dialogue database

201‧‧‧Inquiry voice receiving department

202‧‧‧Responding to the Requesting Department

203‧‧‧Response to the receiving department

204‧‧‧Response to the voice transmission department

301‧‧‧Response Management Department

302‧‧‧Screen Control Department

351‧‧ ‧Document Database

352‧‧‧FAQ document database

651‧‧‧CRM Personal Database

652‧‧ ‧ database

Claims (12)

An information processing system includes: a terminal device that transmits an inquiry: and a receiving server that accepts the inquiry transmitted from the terminal device; the information processing system is characterized in that the receiving server includes: a receiving means, Receiving the inquiry sent from the terminal device; the first determining means determines whether the answer to the inquiry can be retrieved from the response database storing a plurality of questions and answers prepared in advance; the answer generating means When it is determined by the first determining means that the answer to the inquiry cannot be retrieved, the supplementary processing is performed to supplement the information for performing the answer to the inquiry, and the answer to the inquiry is generated based on the result of the supplementary processing; a second determining means for determining whether the answer to the query can be generated by the answer generating means; and the answering means, when the first determining means determines that the answer to the query can be retrieved, and when the second When the determination means determines that an answer to the aforementioned inquiry can be generated Transmitting the answer retrieved by the first determining means or the answer generated by the second determining means; and the calling means, when the second determining means determines that the answer to the inquiry cannot be generated The call processing of the agent corresponding to the aforementioned inquiry is performed. The information processing system according to claim 1, wherein, in the supplementary processing, the answer generating means transmits a question supplementing the content of the inquiry to the terminal device. The information processing system according to claim 1 or 2, wherein, in the supplementary processing, the answer generation means retrieves information on the content of the inquiry from an information source other than the response information base. The information processing system according to claim 1 or 2, wherein the receiving means receives the inquiry from the terminal device by using an automatic response to voice recognition; and the answering means transmits the message by the foregoing The aforementioned answer retrieved by a determination means or the aforementioned answer generated by the second determination means is used as a response by the voice material. The information processing system according to claim 1 or 2, wherein the receiving server includes a sizing processing means for generating a combination of the customized inquiry and the answer based on the history of the response of the agent. The information processing system of claim 5, wherein the call means performs the foregoing call processing, and the call processing is a caller of an organization corresponding to the inquiry in the customer service staff corresponding to each of the plurality of organizations. And the receiving means, the representative accepts an inquiry about the plurality of organizations; The stereotyped processing means generates a combination of an inquiry and an answer that can be commonly formed for the plurality of organizations based on the history of the customer's response to the inquiry of each organization. The information processing system according to claim 1 or 2, wherein the receiving server includes personal information management means for managing personal information about a customer who performs the inquiry; and the first determining means Referring to the aforementioned personal information, it is determined whether the answer to the aforementioned inquiry can be retrieved from the aforementioned response database. The information processing system according to claim 1 or 2, wherein the receiving server includes: a topic providing means for providing a topic related to the content of the inquiry by voice; and a recommendation information providing means for The user from the terminal device performs voice recognition on the response to the topic and provides the recommendation information associated with the response content in an audible manner. The information processing system according to claim 1 or 2, further comprising: an automatic voice response server that answers the inquiry from the terminal device as a predetermined inquiry by an automatic voice response, and Execute the call processing of the customer service staff after the inquiry other than the pre-set inquiry; and, The cooperative server automatically queries the automatic voice response server based on the inquiry and the response between the receiving server and the terminal device when the client is called by the receiving server. The session is not completed until the caller's call processing is completed, thereby performing the call of the agent. A receiving server is a receiving server in an information processing system, the information processing system includes: a terminal device that transmits an inquiry; and a receiving server that accepts the inquiry sent from the terminal device; the receiving The server is characterized in that it includes: receiving means for accepting the inquiry transmitted from the terminal device; and the first determining means determining whether or not the search is possible based on the response database storing a plurality of questions and answers prepared in advance The answer to the inquiry; the answer generation means, when it is determined by the first determining means that the answer to the inquiry cannot be retrieved, the supplementary processing is performed to supplement the information for performing the answer to the inquiry, and based on the foregoing The result of the supplementary processing is used to generate an answer to the inquiry; the second determining means determines whether the answer to the inquiry can be generated by the answer generating means; and the answering means determines that the pair can be retrieved by the first determining means The answer to the above inquiry, and when the second judgment hand is used Can determine When the answer to the inquiry is generated, the answer retrieved by the first determining means or the answer generated by the second determining means is transmitted; and the calling means is provided by the second determining means When it is determined that the answer to the above inquiry cannot be generated, the call processing of the agent corresponding to the above inquiry is performed. An information processing method is an information processing method implemented in an information processing system, the information processing system including: a terminal device that transmits an inquiry: and a receiving server that accepts the inquiry sent from the terminal device; The information processing method includes a receiving step of accepting the inquiry transmitted from the terminal device, and a first determining step of determining whether or not the response database of the plurality of questions and answers prepared in advance is stored Retrieving an answer to the aforementioned inquiry; an answer generating step of performing supplementary processing to supplement information for performing an answer to the aforementioned inquiry when it is determined in the foregoing first determining step that the answer to the aforementioned inquiry cannot be retrieved, and based on The result of the aforementioned supplementary processing is to generate an answer to the aforementioned inquiry; a second determining step of determining whether an answer to the inquiry can be generated in the aforementioned answer generating step; and an answering step of determining that the search can be retrieved in the aforementioned first determining step For the answer to the above inquiry, and the second sentence mentioned above It can be determined in step When the answer to the inquiry is generated, the foregoing answer retrieved in the first determining step or the aforementioned answer generated in the second determining step is transmitted; and a calling step is determined in the second determining step When the answer to the aforementioned inquiry cannot be generated, the call processing of the agent corresponding to the aforementioned inquiry is performed. A program for causing a computer to implement a function of a receiving server in an information processing system, the information processing system comprising: a terminal device that transmits an inquiry; and a receiving server that receives the transmission from the terminal device The foregoing function; the function includes: receiving the function, and accepting the inquiry sent from the terminal device; and the first determining function, determining whether the self-supplied response database of the plurality of questions and answers prepared in advance is stored To the answer to the inquiry; the answer generation function, when the first judgment function determines that the answer to the inquiry cannot be retrieved, the supplementary processing is performed to supplement the information for performing the answer to the inquiry, and based on the foregoing The result of the supplementary processing is used to generate an answer to the aforementioned inquiry; the second determining function determines whether the function for generating the inquiry can be generated by the foregoing answer generating function; the answering function, which can be retrieved by the first determining function The answer to the above inquiry, and when the second judgment is made by the aforementioned Function can determine When the answer to the foregoing inquiry is generated, the foregoing answer retrieved by the first determining function or the answer generated by the second determining function is transmitted; and the calling function is enabled by the second determining function When it is determined that the answer to the above inquiry cannot be generated, the call processing of the agent corresponding to the above inquiry is performed.