JP3760761B2 - Information providing system and method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a system and method for providing information via an agent in a virtual space.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, as a system for providing standard information to a user, there is a system in which an agent such as a character displayed on a display of a terminal or a personal computer installed in a store or public facility provides the information (first conventional Technology). In such a system, information having a tree-like hierarchical structure stored in the storage device is sequentially read out and displayed on a display in accordance with a user operation.
[0003]
On the other hand, as a system that provides information according to the detailed request of the user, there is a system that connects to a call center or a help desk, and a person in charge individually gives detailed explanations by voice or videophone image (second case) Conventional technology).
[0004]
[Problems to be solved by the invention]
However, in the first prior art described above, since the prepared information has a hierarchical structure, the user cannot quickly access desired information. In addition, providing detailed information increases the amount of data, complicates the system, and increases the cost.
[0005]
In the second prior art, after a call center is connected, since a real person responds by voice or a photographed image, continuity with a character used as an agent cannot be maintained, and the user is confused or Or Further, in the video conference call center system, it is necessary to prepare a separate shooting room on the call center side, and it is also necessary for the person who handles the reception to correct the dress, which is expensive.
[0006]
The present invention has been made to solve the problems of the prior art, and the object of the present invention is not to be set as an agent that performs a pre-programmed fixed response to a user's action. This is to ensure the continuity with the agent that performs the fixed correspondence, and to increase the ability of the agent by providing information providers having various knowledge and ability through the same agent.
[0007]
[Means for Solving the Problems]
In order to achieve the above object, the present invention comprises one or a plurality of terminals and one or a plurality of center devices connected to the terminals via a network. An information providing system for providing information via an agent in a virtual space, an imaging means for photographing an information provider, a means for extracting a feature point from the photographed image, and at least the extracted feature point And an atypical image generating means for generating an image of the agent that operates in response to the operation of the information provider, and a fixed image generating means for generating an image of the agent that performs a preset operation. And question input means for the user to input question information, and whether or not the question information input by the input means is presumed question information. And when the question determination means determines that the question information is assumed in advance by the question determination means, the information stored in the fixed information storage means provided in the terminal or the center device is used to generate the fixed image. A fixed information output means for outputting via the agent image generated by the means, and if the question determination means determines that the question information is not assumed in advance, an answer to the question information is given as the atypical information. An atypical information output means for outputting via the image of the agent generated by the image generation means; and a display means for displaying the image; the output by the standard information output means; and the atypical information output means. Output through the same agent .
[0008]
In this way, the image of the agent that operates in response to the action of the information provider when the information provider performs the atypical action in addition to the case of the standard action assumed in the system. In addition to ensuring the continuity of the agent, it is possible to increase the number of agents by allowing information providers having various knowledge and capabilities to respond through the same agent.
[0009]
In addition, voice information synthesis means for synthesizing voice information is further provided, and the output by the standard information output means and the output by the non-standard information output means are performed by the same agent and the same voice .
[0012]
In addition, the present invention is composed of one or a plurality of terminals and one or a plurality of center devices connected to the terminals via a network, and imaging means for photographing the information provider, Means for extracting feature points from the image; and atypical image generation means for generating an image of the agent that operates in response to the operation of the information provider based on at least information about the extracted feature points; A method for providing information to a user via an agent in a virtual space in an information providing system, comprising: a fixed image generation unit configured to generate an image of an agent that performs a preset operation, the query information being provided to the user A step of inputting, a step of determining whether or not the inputted question information is question information assumed in advance, and the inputted question information is assumed in advance If it is determined that the information is question information, a fixed information output step for outputting the information stored in the fixed information storage means via the agent image generated by the fixed image generation means, and the input question If it is determined that the information is not presumed question information, an atypical information output step of outputting an answer to the question information via an agent image generated by the atypical image generation means; A method for providing information via an agent , wherein the output in the standard information output step and the output in the non-standard information output step are performed via the same agent. is there.
[0013]
DETAILED DESCRIPTION OF THE INVENTION
The present invention will be described below based on the illustrated embodiment.
[0014]
FIG. 1 is a block diagram showing a configuration of a call center which is an information providing system according to an embodiment of the present invention. The call center system allows users to receive services such as provision of various information through terminals installed in stores and public facilities, or through their own personal computers, and so on. When this happens, the person in charge can individually ask a question by connecting to a call center.
[0015]
The center device 1 of the call center mainly includes a CPU 3, a memory for storing programs and data 4, an input unit 5 for input by the operator, a VRAM 7 for storing image information taken by the camera 6, and a display based on commands from the CPU 3. 8, an image control circuit 9 that controls 8, a voice control circuit 12 that controls the microphone 10 and the speaker 11 based on a command from the CPU 3, a communication interface unit 13 that is connected to a network and communicates with an external device based on a command from the CPU 3, A voice information synthesis circuit 14 for synthesizing voice information is provided. These are connected to each other by a bus. Here, the memory is a ROM (Read Only Memory) that stores programs and data, a RAM (Randum Access Memory) that develops a program read from the ROM, or stores data temporarily and functions as a work area, In addition, it comprises a mass storage device such as an HDD (Hard Disc Drive) or a CD-ROM.
[0016]
The terminal 2 mainly includes a CPU 15, a memory 16, an input unit 17, a display 18 and an image control circuit 19, a microphone 20 and a speaker 21, an audio control circuit 22, and a communication interface unit 23. The terminal may be a so-called kiosk terminal installed in a store, public facility, street, or the like, or a personal computer. These terminals are connected to the center apparatus via a network such as the Internet or a LAN (Local Area Network).
[0017]
Although only one center device and one terminal are shown in FIG. 1, it is natural that a plurality of center devices and terminals may be provided. Although omitted in FIG. 1, when a system is configured from a plurality of center apparatuses, a server for managing connections from terminals is separately provided.
[0018]
In this system, when an information provider on the center apparatus 1 side responds, an avatar, which is an agent that provides information by being displayed on the display 18 of the terminal 2, is displayed by the information provider's facial expression and mouth taken by the camera. The movement similar to the movement of the head or the head is performed in real time. Such a technique is disclosed in WO99 / 53443. This system is a specific application of this technology. Feature points are extracted from the information of the information provider's raw image taken by the camera, and the movement of the feature points accompanying the movement of the information provider is tracked and analyzed. The processing result for such image information is transmitted to the terminal and synthesized with the image information of the avatar, which is a three-dimensional computer model (virtual head), so that the avatar corresponds to the movement of the information provider in real time. It became possible to move. FIG. 2 shows the characteristic point A extracted from the real image 30 of the person's face photographed by the camera and the corresponding point A ′ on the avatar 40 in association with each other. The amount of change at the point A is made to act as a change at the point A ′ on the avatar 40. In this way, by associating a plurality of feature points on the real image 30 with a plurality of points on the avatar 40, it is possible to replace a change in the face of the real image with a change in the animation. By operating the avatar on the terminal display in correspondence with the actual image thus captured, the amount of information transmitted between the center apparatus and the terminal can be reduced, and the communication cost can be reduced. it can. In addition, the response of moving images can be improved. A description of detailed processing such as computation on image data is left to the above-mentioned publication.
[0019]
FIG. 3 is a flowchart showing an information provision processing procedure in the present system.
[0020]
First, a user logs in to the terminal 2 (step 1).
[0021]
Next, the user inputs question information from the terminal 2 (step 2). At this time, the terminal 2 determines whether or not the input question information is fixed, that is, whether or not it is assumed (step 3). Here, if the question is a fixed question, a fixed answer is prepared, and this is acquired (step 4). In this case, when the standard answer information is on the center 1 side, the center 1 side is accessed to acquire it. The information acquired in this way is provided to the user through a display and a speaker. At this time, the agent displayed on the display 18 performs a predetermined operation. After providing the standard information, it is determined whether or not the process is finished (step 6). If finished, the process is finished. If not finished, the process returns to step 3.
[0022]
On the other hand, if the question information is not fixed, the terminal 2 transmits a connection request to the center device 1 side (step 7). The center device 1 that has received the connection request performs connection processing (step 9), and transmits an agent switching request to the terminal 2 (step 10). Upon receiving the agent switching instruction (step 11), the terminal 2 switches the agent (step 12) and transmits the question information to the center apparatus (step 13). The center device 1 receives the question information (step 14), and the information provider inputs an answer corresponding to the question by voice or the like (step 15). At this time, the operation of the information provider is photographed by the camera, and the processed image information is transmitted to the terminal 2 together with the reply information (step 16). The terminal 2 receives the response information and the processed image information (step 17), and the agent on the display 18 performs the same operation as that of the information provider and outputs the response information from the speaker 21 by voice. Provide to the user (step 18) and go to step 6. At this time, the voice inputted by the information provider through the microphone by the voice information synthesis circuit 14 may be converted into the synthesized voice output when providing the standard information, and transmitted to the terminal 2.
[0023]
FIG. 4 is a flowchart showing another information providing process.
[0024]
Here, when the user is logged in (step 21), the agent on the display 18 provides information by a predetermined operation. Here, when the user requests provision of fixed information by selecting an option displayed on the display 18 or the like (step 22), the fixed information is acquired and this is sent via an agent that performs a predetermined operation. Provided by voice, image, or the like (step 23). If there is no request for fixed information, it is determined whether there is a center connection request (step 24). That is, it is determined whether or not a connection with the center 1 is requested by pressing a help button or the like provided on the terminal. At this time, if there is a connection request with the center 1 side, it is transmitted to the center side (step 25). When the center device 1 receives this connection request (step 26), it performs connection processing (step 27), and transmits an agent switching request to the terminal 2 side (step 28). When the terminal 2 side receives the agent switching instruction (step 29), the agent to be displayed on the display 18 is switched accordingly (step 30).
[0025]
Next, the terminal 2 accepts an input of a user's question (step 31), and transmits the accepted question to the center device 1 (step 32). In the center apparatus 1 that has received the question (step 33), the information provider inputs an answer corresponding to the question by voice or the like (step 34). At this time, the operation of the information provider is photographed by the camera 6, and the processed image information is transmitted to the terminal together with the reply information (step 35). The terminal receives the response information and the processed image information (step 36), and the agent on the display 18 performs the same operation as that of the information provider and outputs the response information from the speaker 21 by voice. (Step 37), and it is determined whether or not the process is finished (step 38).
[0026]
In this way, if the user asks an unexpected question, or if a question or unknown matter arises during operation of the terminal and an attempt is made to connect to the center side, the information provider on the center device side answers this. Hey. Even if the information provider answers the information when connected to the center device, the agent displayed on the terminal display is the same agent that returns the expected answer to the standard question, so continuity is ensured. Detailed service can be provided. Also, since the person who provides information from the center device only needs to provide facial features, the same person does not need to respond, and another person may take over the service. In addition, a wide range of services can be provided through the same agent by providing information by a plurality of persons having knowledge in various different specialized fields. Further, since the information provider on the center apparatus side is only tracked on the facial features, it is not necessary to prepare a well-organized shooting room, uniform, etc., and an increase in cost can be suppressed.
[0027]
The above-described embodiment is a call center, but is not limited to this as long as the system provides information to a user via an agent on a display. For example, the present invention can be applied to an education system in which an agent on a display serves as a teacher and provides an education service to a user. Since the virtual teacher of the same character can teach various subjects continuously, the confidence and interest of the learner can be improved and the educational efficiency can be improved.
[0028]
【The invention's effect】
As described above, according to the present invention, the continuity between the agent that performs the pre-programmed fixed correspondence and the agent that performs the non-standard correspondence that is not set according to the user's action is ensured, In addition, it is possible to increase the number of agents by allowing information providers having various knowledge and abilities to respond through the same agent.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a call center system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a correspondence relationship between a feature point of an actual image and an avatar point;
FIG. 3 is a flowchart showing an information providing procedure in the call center system according to the embodiment of the present invention.
FIG. 4 is a flowchart showing another information providing procedure in the call center system according to the embodiment of the present invention.
[Explanation of symbols]
1 Center device 2 Terminals 3, 15 CPU
4,16 Memory 5,17 Input unit 7 VRAM
8, 18 Display 9, 19 Image control circuit 10, 20 Microphone 11, 21 Speaker 12, 22 Audio control circuit 13, 23 Communication control circuit 14 Audio information synthesis circuit

Claims (3)

Consists of one or a plurality of terminals and one or a plurality of center devices connected to the terminals via a network, and provides information to a user who uses the terminals via an agent in a virtual space An information providing system,
Imaging means for photographing the information provider;
Means for extracting feature points from the captured image;
Atypical image generation means for generating an image of the agent that operates in response to the operation of the information provider, based on at least information about the extracted feature points;
Fixed image generation means for generating an image of an agent that performs a preset operation;
Question input means for the user to input question information;
Question determination means for determining whether the question information input by the input means is question information assumed in advance;
If it is determined by the question determination means that the question information is assumed in advance, the information stored in the fixed information storage means provided in the terminal or the center device is converted into the agent generated by the fixed image generation means. Fixed form information output means for outputting via the image of
An atypical information output that outputs an answer to the question information via an agent image generated by the atypical image generation means when it is determined by the question determination means that the question information is not assumed in advance Means,
Display means for displaying an image;
With
An information providing system characterized in that the output by the standard information output means and the output by the non-standard information output means are performed through the same agent . Voice information synthesis means for synthesizing voice information;
2. The information providing system according to claim 1, wherein the output by the standard information output unit and the output by the non-standard information output unit are performed by the same agent and the same voice. Consists of one or more terminals and one or more center devices connected to the terminals via a network,
Imaging means for photographing the information provider;
Means for extracting feature points from the captured image;
Atypical image generation means for generating an image of the agent that operates in response to the operation of the information provider, based on at least information about the extracted feature points;
Fixed image generation means for generating an image of an agent that performs a preset operation;
A method for providing information to a user via an agent in a virtual space in an information providing system including :
Allowing the user to enter question information;
Determining whether the input question information is question information assumed in advance;
When it is determined that the input question information is presumed question information, the information stored in the fixed information storage means is output via the agent image generated by the fixed image generation means. A standard information output step;
Atypical information that outputs an answer to the question information via the agent image generated by the atypical image generation means when it is determined that the inputted question information is not the question information assumed in advance. An output step;
Have
The method for providing information through an agent, wherein the output in the standard information output step and the output in the non-standard information output step are performed through the same agent.

Images