Information processing system, its control method and program

Abstract

To provide a system which generates an answer to a question and outputs it according to a content being viewed by a questioner.SOLUTION: An information processing device which allows data to be displayed and includes: question accepting means for accepting a question from a user; acquisition means for acquiring a category of data being displayed; and output means for outputting an answer generated on the basis of the accepted question and the acquired category.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique for providing information. [Background technology]

[0002] Traditionally, explanatory materials for life insurance, etc. were printed on paper and sales representatives visited customers to explain the contents face-to-face. However, face-to-face meetings were time- and place-constrained for both the customer and the sales representative, which was a burden for both. Therefore, digital content that allows customers to view explanatory materials stored on a server using a web browser or a dedicated app is becoming more popular.

[0003] However, because customers themselves view the explanatory materials at any time and place, there is a problem in that if a question or concern arises, it is not possible to immediately confirm with a sales representative or other person.

[0004] As a result, systems are being developed to automatically answer questions using AI (artificial intelligence) and other technologies.

[0005] Patent Document 1 discloses a technique for identifying attributes of an accessing user, creating an answer suited to the user's attributes in response to a question received from the user, and displaying the answer on the user's terminal.

[0006] Patent Document 2 discloses a technology for categorizing multiple questions associated with answers, identifying the classification category of input text, and selecting a question that belongs to the identified classification category to obtain an answer. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2019-28646 A [Patent Document 2] JP 2006-85381 A Summary of the Invention [Problem to be solved by the invention]

[0008] However, the user (questioner) can freely browse the provided content by manipulating the pages, etc., and even for the same question, the appropriate answer may change depending on the content being viewed.

[0009] In both Patent Document 1 and Patent Document 2, it is not possible to generate an answer by taking into consideration the content that the user is viewing.

[0010] Therefore, an object of the present invention is to provide a mechanism for generating and outputting an answer to a question in accordance with the content being viewed by the questioner. [Means for solving the problem]

[0011] The present invention is characterized by the following. Effect of the Invention

[0012] According to the present invention, it is possible to provide a mechanism for generating and outputting an answer to a question in accordance with the content being viewed by the questioner. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram showing an example of a configuration of an information processing system according to an embodiment of the present invention. [Diagram 2] FIG. 1 shows an example of a hardware configuration applicable to a server 101 and clients 102 and 103. [Diagram 3] 1 is a flowchart showing an example of an overall process in an information processing system. [Figure 4] Flowchart showing an example of an answer generation process [Diagram 5] Flowchart showing an example of a template embedding process [Figure 6] An example of a page display and question input reception screen [Figure 7]A diagram showing an example of a template [Figure 8] A diagram showing an example of a template [Figure 9] A diagram showing an example of various data tables and answer text creation [Figure 10] An example of a screen showing answers [Figure 11] An example of a screen showing answers [Figure 12] An example of a screen showing answers [Figure 13] An example of a screen showing how to input answer evaluations [Figure 14] An example of a notification to a person in charge DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

[0015] As shown in FIG. 1, the information processing system of this embodiment has a configuration in which a server 101, clients 102 and 103 are communicatively connected via a network 104.

[0016] The server 101 receives a viewing request from the client 102, generates viewing content, and transmits it to the client 102 for display. Also, the server 101 receives a question from the client 102, generates an answer to the question, and transmits it to the client 102 for display.

[0017] The customer client 102 accesses the server 101 using a web browser or a dedicated application, transmits a viewing request to the server 101 in response to a viewing instruction from the user, and displays the viewing content received from the server 101 in the web browser or the dedicated application. Also, the customer client 102 accepts questions from the user on each occasion, transmits the questions to the server 101, and displays the answers received from the server 101.

[0018] A client 103 for the person in charge receives and displays notifications (such as emails) from the server 101 when necessary.

[0019] FIG. 2 is a diagram showing an example of a hardware configuration applicable to the server 101 and the clients 102 and 103 shown in FIG.

[0020] Reference numeral 201 denotes a CPU, which performs overall control of each device and controller connected to a system bus 204 .

[0021] The ROM 202 or the external memory 211 stores the BIOS (Basic Input / Output System), which is the control program of the CPU 201, an operating system program (hereinafter, OS), and various programs described below that are necessary to realize the functions executed by each server or each PC.

[0022] Reference numeral 203 denotes a RAM (storage unit) which functions as a main memory, a work area, etc. of the CPU 201. The CPU 201 loads programs and the like required for executing processing from the ROM 202 or the external memory 211 into the RAM 203 and executes the loaded programs to realize various operations.

[0023] An input controller 205 controls input from a keyboard (KB) 209 and a pointing device such as a mouse (not shown).

[0024] Reference numeral 206 denotes a video controller, which controls the display on the display unit 210. The display unit 210 may be not only a CRT but also other display devices such as a liquid crystal display. These are used by the administrator as necessary. The display unit may also include a touch panel function that allows the user to specify a target position on the display screen with a finger, a pen, or the like.

[0025] Reference numeral 207 denotes a memory controller, which controls access to an external memory 211 such as a hard disk (HD) for storing boot programs, various applications, font data, user files, edited files, various data, etc., a flexible disk (FD), or a compact flash (registered trademark) memory connected to a PCMCIA card slot via an adapter.

[0026] A communication I / F controller 208 connects to and communicates with external devices via a network (LAN) 300 and executes communication control processing on the network. For example, communication using TCP / IP is possible.

[0027] The CPU 201 enables display on a CRT by, for example, executing a process of expanding (rasterizing) an outline font in a display information area in the RAM 203. The CPU 201 also enables user instructions using a mouse cursor (not shown) on the CRT.

[0028] Various programs for implementing the present invention, which will be described later, are recorded in the external memory 211, and are executed by the CPU 201 by being loaded into the RAM 203 as necessary. Furthermore, data files and data tables, etc., used when executing the above programs are also stored in the external memory 211, and these will also be described in detail later.

[0029] FIG. 3 is a flowchart showing an example of the overall process in the information processing system.

[0030] The overall process in FIG. 3 will now be described.

[0031] In step S101, the client 102 accepts a content viewing instruction from a user (customer) and transmits a content viewing request to the server 101. The user has previously performed a login process to enable access to the server 101, and the content viewing instruction is executed from a menu screen (not shown) displayed on a web browser or a menu screen (not shown) of a dedicated application.

[0032] In step S102, the server 101 receives a content browsing request transmitted from the client 102. The content browsing request includes a content name or ID, a customer ID, and the like.

[0033] In step S103, the server 101 generates content in accordance with the content browsing request and transmits it to the client 102. The content data is stored in a content database, and the data is extracted by searching based on the content name and customer ID. Here, the data of all the content may be transmitted, or only the data of some pages may be transmitted.

[0034] In step S104, the client 102 receives the content from the server 101 and displays it using a web browser, a dedicated application, or the like.

[0035] In step S105, the client 102 accepts a page operation from the user and displays the target page. If data for only a portion of the pages is transmitted in step S103, a request is made to the server to transmit the pages that have not yet been transmitted each time they are displayed.

[0036] In step S106, the client 102 accepts an input of a question from the user.

[0037] In step S107, the client 102 acquires the category of the page being viewed by the user, that is, the page being displayed. Here, a category is a classification of the content being viewed by the user, and for example, in the case of explanatory materials for life insurance, categories include "XX insurance in general," "XX special clause," and "contract precautions." The category is embedded as tag data for each page of content, and can be acquired from the displayed page. Note that a category may be assigned to the entire content, each chapter, or each paragraph, as long as it classifies the content being viewed. Also, a category may be specified and acquired by reading and analyzing text, etc. from the displayed content, without assigning a category in advance.

[0038] In step S108, the client 102 transmits to the server 101 the question accepted in step S106 and the browsing category acquired in step S107.

[0039] FIG. 6 shows an example of the screen display on the client 102 in steps S105 to S108.

[0040] The page display screen 610 includes a page display window 611, a page operation button 612, and a question start button 613, and the previous or next page is displayed by operating the page operation button 612. The page display operation may be realized by a scroll bar, a page specification input, etc. By pressing the question start button 613, a question input acceptance screen 620 is displayed.

[0041] On question input reception screen 620, a message 621 prompting the user to input a question is displayed. By inputting a question (text) in question input field 622 and pressing send button 623, the entered question and the category of the page being viewed are sent to server 101.

[0042] Returning to the explanation of Figure 3.

[0043] In step S109, the server 101 receives the question and the browse category sent from the client 102.

[0044] In step S110, the server 101 generates an answer based on the question and the browsing category received in step S108. The answer generation process will be described in detail with reference to FIG.

[0045] FIG. 4 is a flowchart showing an example of the answer generating process.

[0046] In step S201, the server 101 acquires a question received from the client 102. Specifically, the server 101 stores the question in RAM for use in subsequent processing.

[0047] In step S202, the server 101 acquires the viewing category received from the client 102. Specifically, the server 101 stores the viewing category in the RAM for use in subsequent processing.

[0048] In step S203, the server 101 uses the acquired question and browsing category as input data to identify an answer template through AI processing using the learning model 401. The templates are stored in the template database 402, and the identified template is used in subsequent processing.

[0049] The learning model 401 used in this process is, for example, a model trained using a learning question, a browsing category, and a corresponding template (or its ID), and by inputting a question and a browsing category, the corresponding template (or its ID) is obtained as an output. Note that the learning model may have any configuration or learning method as long as it receives a question and a browsing category as input and obtains a corresponding template as an output.

[0050] Here, an example of the template will be described with reference to FIG. 7 and FIG.

[0051] Template 1 (710 in FIG. 7) is a template that is identified when the viewing category is "cancer special" and the representative question is "What are the benefits of signing up for this special?" In other words, when a page in the category "cancer special" is viewed and a question that matches or is similar to the representative question is entered, the learning model 401 will identify this template. In 710, the parts surrounded by boxes 711, 712, 713, 714, and 715 are display items that change depending on the user attributes.

[0052] Template 2 (720 in FIG. 7) is a template that is identified when the viewing category is "Injury Special Clause" and the representative question is "What are the benefits of signing up for this special clause?". The details are the same as for template 1 described above, but even if the representative question is the same, the identified template will change depending on the viewing category.

[0053] Template 3 (810 in Fig. 8) is a template that is specified when the viewing category is "Disaster Special Clause" and the representative question is "What are the benefits of taking out this special clause?". It differs from templates 1 and 2 in that there is no part enclosed in a square, that is, there are no display items that change depending on user attributes, so it is a template common to all users.

[0054] Returning to the explanation of Figure 4.

[0055] In step S204, the server 101 determines whether a template was identified in step S203. Depending on the content of the question and the browsing category, the AI ​​processing may not be able to identify the template. If the template was identified (Yes), proceed to step S205. If the template was not identified (No), proceed to step S207. In step S205, the server 101 determines whether the accuracy when the template was identified in step S203 is equal to or greater than a threshold. Even if a template can be identified by AI processing, the accuracy may be low. The accuracy is output as a result of the AI ​​processing. The threshold is set in advance on a setting screen (not shown). If it is equal to or greater than the threshold (Yes), proceed to step S206; if it is less than the threshold (No), proceed to step S207.

[0056] In step S206, server 101 determines whether the identified template is one that requires embedding processing based on user attributes. In the above-mentioned example of templates, template 1 and template 2 are templates that require embedding based on user attributes, and template 3 is a template that does not require embedding based on user attributes. If embedding based on user attributes is required (Yes), proceed to step S208, and if embedding based on user attributes is not required (No), proceed to step S209.

[0057] In step S207, the server 101 creates a response indicating that the response is not possible. Alternatively, the server 101 may contact the person in charge and add that the person in charge will respond separately. Also, since no embedding of user attributes is performed, the content will be the same for all users, but the user's name, etc. may be embedded.

[0058] In step S208, the server 101 executes a template embedding process. The template embedding process will be described in detail with reference to FIG.

[0059] FIG. 5 is a flowchart showing an example of the template embedding process. This processing example is a process when the above-mentioned template 1 is specified. The configuration of the process changes depending on the template specified. The process will be described with reference to the data example in FIG. 9.

[0060] In step S301, the server 101 acquires the identified template and extracts the portion that needs to be filled with the user attribute. The template in question in this example is template 1 (710 in FIG. 7).

[0061] In step S302, the server 101 acquires user attributes of the user who is the questioner from a user information database 501 managed by itself or externally. The user attributes to be acquired may be only the user attributes corresponding to the portion extracted in step S301, or may be all the user attributes that can be acquired. Fig. 9 shows an example of a user information table 950 stored in the user information database 501. The user information table 950 includes user attributes such as health risk, age, and whether or not the user has children for each user.

[0062] The processes from steps S303 to S307 depend on template 1. Moreover, the processes from steps S303 to S306 are executed by referring to each table stored in the answer candidate database 502.

[0063] In step S303, the server 101 embeds an answer sentence depending on the presence or absence of a health risk in the item 711 of the template 1. That is, an answer sentence is selected from the answer sentence table 910 according to health risks in Fig. 9 according to the attribute of the user's health risk and embedded.

[0064] In step S304, the server 101 embeds the cancer morbidity rate of the same age group into the item 712 of the template 1. That is, the cancer morbidity rate is selected and embedded from the cancer morbidity rate table 920 by age group in accordance with the user's age attribute.

[0065] The same embedding process as described above is also carried out in steps S305 and S306.

[0066] In step S307, the server 101 embeds the content itself or a link in the item 715 of the template 1 so that the content of the detailed explanation of the guarantee suited to the user is displayed as a reference material (attachment).

[0067] As described above, the template 1 is filled with user attributes and an answer is generated. In Fig. 9, an answer sentence 960 to person A and an answer sentence 970 to person B are shown as examples.

[0068] This completes the description of the template embedding process in FIG. 5, and we return to the description of FIG.

[0069] In step S209, the server 101 creates a response by using the content of the template as the response content as is. Since no user attribute embedding is performed, the content will be the same for all users, but the user's name, etc. may be embedded.

[0070] This completes the explanation of the answer generation process in FIG. 4, and we will return to the explanation of FIG.

[0071] In step S111, server 101 determines whether or not a notification to the person in charge is necessary depending on the generation status of the answer in step S110. Here, the determination is made based on pre-set conditions, such as when a template could not be identified in step S110, when the accuracy was low, when the person in charge needs to follow up on the generated answer, etc. If a notification to the person in charge is necessary (Yes), proceed to step S112, and if a notification to the person in charge is not necessary (No), proceed to step S114.

[0072] In step S112, the server 101 creates a notification for the person in charge and transmits it to the client 103. The transmission method may be any form, such as email, SNS, or push notification by a dedicated app.

[0073] In step S113, the client 103 receives the notification to the person in charge from the server 101 and displays it.

[0074] An example of a notification to the person in charge is shown in Fig. 14. An example of a notification 1410 is a notification when a template cannot be specified in answer generation, and an example of a notification 1420 is a notification when the accuracy is below a threshold in answer generation.

[0075] Returning to the explanation of Figure 3.

[0076] In step S114, the server 101 transmits to the client 102 the response generated in step S110.

[0077] In step S115, the client 102 receives the response sent from the server 101 and displays it.

[0078] Here, examples of displaying answers will be described with reference to Figs.

[0079] 1010 in FIG. 10 is an example of a reply to Person A using template 1 that requires embedding of user attributes. The reply text is displayed in 1011, and part of the detailed explanation content of the coverage, which is reference material, is displayed in 1012. By clicking or tapping the link to the coverage content in 1011 or the display area of ​​1012, all of the detailed explanation content of the coverage is displayed. The reference material may be displayed in a pop-up window.

[0080] 10 shows an example of a reply to person A using template 1, which requires embedding of user attributes. The details are the same as 1010.

[0081] 11 shows an example of a reply to C using template 2 that requires embedding of user attributes. The details are the same as for 1010.

[0082] 11 shows an example of a common answer for all users using template 3, which does not require embedding of user attributes. Since embedding of user attributes is not performed, the content will be the same for all users.

[0083] 1210 in Fig. 12 is an example of a response when a template cannot be identified or the accuracy is below a threshold. Since no embedding based on user attributes is performed, the content is the same for all users.

[0084] Returning to the explanation of Figure 3.

[0085] In step S116, the client 102 accepts an input of an evaluation for the answer.

[0086] In step S117, the client 102 transmits the answer evaluation that has been input to the server 101.

[0087] Here, a display example when accepting an evaluation of an answer will be described with reference to Fig. 13. In the display example of 1310 in Fig. 13, a message prompting an evaluation of the answer is displayed in 1311. By inputting an evaluation in the input field and pressing the send button, the contents of the answer evaluation are transmitted to the server 101.

[0088] In step S118, the server 101 receives and registers the answer evaluation transmitted from the client 102. Here, the received answer evaluation is registered in an answer history table (not shown), and the learning model 401 is subjected to reinforcement learning based on the registered answer evaluation, thereby making it possible to improve the accuracy of AI processing.

[0089] In this way, it becomes possible to generate and output an answer to a question according to the content being viewed by the asker.

[0090] Although several embodiments have been described above, the present invention can be embodied, for example, as a system, an apparatus, a method, a computer program, or a recording medium, and specifically, the present invention may be applied to a system made up of multiple devices, or may be applied to an apparatus made up of a single device.

[0091] The computer program of the present invention is a computer program that enables a computer to execute the processing method of each flowchart, and the storage medium of the present invention stores a computer program that enables a computer to execute the processing method of each flowchart. Note that the computer program of the present invention may be a computer program for each processing method of each device of each flowchart.

[0092] As described above, it goes without saying that the object of the present invention can be achieved by supplying a recording medium on which a program that realizes the functions of the above-mentioned embodiments is recorded to a system or device, and having the computer (or CPU or MPU) of that system or device read and execute the program stored on the recording medium.

[0093] In this case, the program itself read out from the recording medium will realize the novel functions of the present invention, and the recording medium on which the program is recorded will constitute the present invention.

[0094] Examples of recording media for supplying the program include flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, magnetic tapes, non-volatile memory cards, ROMs, EPROMs, silicon disks, etc.

[0095] Furthermore, it goes without saying that the functions of the above-mentioned embodiments are not only realized by the computer executing a program it has read, but also includes cases where an OS (operating system) running on the computer performs some or all of the actual processing based on the instructions of the program, and the functions of the above-mentioned embodiments are realized through that processing.

[0096] Furthermore, it goes without saying that this also includes cases where a program read from a recording medium is written into a memory provided on a function expansion board inserted into a computer or a function expansion unit connected to a computer, and then a CPU or the like provided on the function expansion board or function expansion unit performs some or all of the actual processing based on the instructions of the program code, thereby realizing the functions of the above-mentioned embodiments.

[0097] The present invention may be applied to a system consisting of multiple devices, or to an apparatus consisting of a single device. Needless to say, the present invention can also be applied to a case where the object is achieved by supplying a program to a system or apparatus. In this case, the effect of the present invention can be enjoyed by the system or apparatus by reading a recording medium storing a program for achieving the present invention into the system or apparatus.

[0098] The program may be in the form of object code, program code executed by an interpreter, script data supplied to an OS (operating system), or the like.

[0099] Furthermore, by downloading and reading a program for achieving the present invention from a server, database, etc. on a network using a communication program, the system or device can enjoy the effects of the present invention. Note that the present invention also includes configurations that combine the above-mentioned embodiments and their modified examples. [Explanation of symbols]

[0100] 101 Server 102 Client (Customer) 103 Client (for personnel) 104 Network

Claims

1. A question receiving means for receiving questions; an acquisition means for acquiring, upon receiving the question, information relating to a component displayed on the display unit from among components constituting the content displayed on the display unit; an output means for outputting an answer generated based on the question received by the question receiving means and the information acquired by the acquisition means. An information processing system characterized by:

2. The constituent elements of the content are information that identifies the content.

2. The information processing system according to claim 1, wherein:

3. The information for identifying the content is a category related to the content.

3. The information processing system according to claim 2, wherein:

4. The content of the content is at least one of a page, a chapter, or a paragraph that constitutes the content.

4. The information processing system according to claim 2 or 3, wherein:

5. 2. The information processing system according to claim 1, wherein said output means controls the display of said output answer on said display unit.

6. A display instruction receiving means for receiving an instruction to display content, The acquisition means acquires information relating to a component displayed on a display unit among the components of the content for which a display instruction has been received by the display instruction receiving means.

4. The information processing system according to claim 1, wherein:

7. A response generation control means for controlling the generation of a response based on the question received by the question receiving means and the information related to the component acquired by the acquiring means, The output means outputs the answer generated by the answer generation control means.

4. The information processing system according to claim 1, wherein:

8. The information processing system described in Claim 7, characterized in that the answer generation control means selects an answer template based on the question received by the question receiving means and the information acquired by the acquisition means, and generates the answer based on the answer template.

9. The information processing system described in Claim 8, characterized in that the answer generation control means generates the answer by embedding information associated with user information related to the question into the answer template.

10. The information processing system described in Claim 7, characterized in that the answer generation control means generates the answer using a learning model, using the question received by the question receiving means and the information acquired by the acquisition means as input.

11. The information processing system described in Claim 10 is characterized in that it accepts evaluations of the output answers, registers a history, and performs reinforcement learning on the learning model based on the history.

12. The information processing system described in Claim 10, characterized in that the answer generation control means operates a notification unit that notifies the responsible party's terminal when it determines that the accuracy of answer generation is below a predetermined threshold.

13. A display control step of controlling the display of the content on a display unit; a question receiving step for receiving a question; an acquisition step of acquiring, upon receiving the question, information relating to the component displayed on the display unit among the components constituting the content; an output step of outputting an answer generated based on the question received in the question receiving step and the information acquired in the acquisition step. A method for controlling an information processing system, comprising:

14. A program for causing at least one computer to function as each means of the information processing system described in any one of claims 1 to 3.

Images