Support device, support method, and program
The support device and method improve chatbot usage by generating and demonstrating frequently asked questions and answers, addressing low usage rates through interactive learning models.
Patent Information
- Application Number
- JP2024024676
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-02-21
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2044-02-21
AI Technical Summary
Existing question answering methods using chatbots have low usage rates due to user unfamiliarity, leading to unanswered questions.
A support device and method that utilizes a learning model to generate and demonstrate frequently asked questions and answers based on user interactions with chatbots, promoting their usage by providing interactive demonstrations.
Enhances user understanding and promotes the use of chatbots by displaying common questions and answers, increasing their engagement and effectiveness.
Smart Images

Figure 0007606024000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an assistance device, an assistance method, and a program. [Background technology]
[0002] In recent years, chatting has become known in which questions posed by users are answered via a computer. For example, Patent Document 1 proposes a question answering method that uses artificial intelligence to provide answers to questions posed by users. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2022-166260 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, in the above-mentioned question answering method, if the behavior of the chatbot is unclear, the utilization rate of the chatbot may be low, and as a result, the user's question may not be resolved. In other words, from the viewpoint of promoting the utilization of chatbots, this method is still insufficient.
[0005] The present invention is intended to solve the above-mentioned problems, and aims to provide an assistance device, an assistance method, and a program that can promote the use of chatbots. [Means for solving the problem]
[0006] The support device according to a first aspect of the present invention comprises: a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demonstration execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; It is characterized by:
[0007] In addition, in the support device according to the above aspect, the question and answer generation unit generates a first combination, which is a combination of a question and an answer corresponding to the page indicated by the viewed page information, and then generates a second combination, which is a combination of a question and an answer different from the first combination, which is corresponding to the page indicated by the viewed page information; the demonstration execution unit provides the user with a demonstration corresponding to the first combination, and then provides the user with a demonstration corresponding to the second combination; This may be done.
[0008] In addition, in the support device according to the above aspect, The combination of the question and answer indicated by the first combination is a question and answer that has been asked more frequently by each user who viewed the page indicated by the viewed page information acquired by the viewed page information acquisition unit than the combination of the question and answer indicated by the second combination. This may be done.
[0009] In addition, in the support device according to the above aspect, an icon display unit that displays an icon superimposed on a page currently being viewed by the user; a chatbot activation unit that activates the chatbot by displaying a question and answer area superimposed on the currently viewed page when the icon displayed by the icon display unit is selected by the user, the demonstration execution unit displays the question and answer area when a predetermined start condition is satisfied after the icon is displayed by the icon display unit, and displays a combination of questions and answers generated by the question and answer generation unit in the question and answer area as a demonstration of a case where the chatbot is used. This may be done.
[0010] An assistance device according to another aspect of the present invention comprises: a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; an answer generation unit that, when a question is input by the user, generates an answer corresponding to the question using an artificial intelligence for answer generation; a question generation unit that generates a question corresponding to the page indicated by the viewed page information acquired by the viewed page information acquisition unit, using an artificial intelligence for generating questions; a demonstration execution unit that provides a combination of the question and the answer to the user as a demonstration of a case where a chatbot is used; the answer generation unit generates an answer corresponding to the question generated by the question generation unit, using the question generated by the question generation unit as the question input by the user. It is characterized by:
[0011] In addition, in the support device according to the above aspect, the demonstration execution unit repeatedly generates the question by the question generation unit and generates the answer by the answer generation unit, and provides a combination of the question and the answer to the user as a demonstration of the use of the chatbot; The question generation unit and the answer generation unit generate the questions and the answers based on a learning model that is trained using a history of questions and answers for each page being browsed by the chatbot until each user obtains a final answer as training data. This may be done.
[0012] In addition, in the support device according to the above aspect, a re-learning unit that further learns a history of the questions and answers repeatedly generated by the question generating unit and the answer generating unit as training data; Further, it may be provided.
[0013] A support method according to a second aspect of the present invention comprises: A method for assisting a user using an assisting device, comprising: a browsing page information acquiring step of acquiring browsing page information indicating a page currently being browsed by a user; a question and answer generating step of generating a question and answer combination corresponding to a page indicated by the browsed page information acquired in the browsed page information acquiring step, the question and answer combination being a combination of questions and answers to be performed when using a chatbot; a demonstration step of providing the user with a combination of questions and answers generated in the question and answer generating step as a demonstration of the use of the chatbot; In the question and answer generating step, a combination of questions and answers corresponding to the page indicated by the viewed page information is generated based on a learning model that is trained using a history of questions and answers for each page viewed by the chatbot that each user has made until obtaining a final answer as training data. A support method comprising: It is characterized by:
[0014] A program according to a third aspect of the present invention comprises: Computer, a browsing page information acquisition unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demo execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; It is characterized by:
[0015] The above program may be recorded on a non-transitory recording medium. The non-transitory recording medium can be distributed and sold independently of the computer. Here, the non-transitory recording medium refers to a tangible recording medium. Examples of the non-transitory recording medium include a compact disc, a flexible disc, a hard disk, a magneto-optical disk, a digital video disk, a magnetic tape, and a semiconductor memory. In addition, the transitory recording medium refers to the transmission medium (propagation signal) itself. Examples of the transitory recording medium include an electric signal, an optical signal, and an electromagnetic wave. In addition, the temporary storage area is an area for temporarily storing data and programs, and is, for example, a volatile memory such as a RAM (Random Access Memory). Effect of the Invention
[0016] According to the present invention, it is possible to provide an assistance device, an assistance method, and a program that can promote the use of chatbots. [Brief description of the drawings]
[0017] [Figure 1] FIG. 2 is a diagram showing the relationship between a support device and an information terminal. [Diagram 2] FIG. 2 is a block diagram showing an example of a support device. [Diagram 3] FIG. 13 is an explanatory diagram showing an example of a display operation of chat support. [Figure 4] FIG. 2 is an explanatory diagram showing an example of the learning content of a learning model. [Diagram 5] 13 is a flowchart illustrating an example of a demo display process. [Figure 6] FIG. 11 is an explanatory diagram showing an example of a demo display based on a browse page. [Figure 7] FIG. 11 is an explanatory diagram showing an example of a display operation during a demo display. [Figure 8] FIG. 13 is an explanatory diagram showing an example of a demo display in a modified example. [Figure 9] FIG. 13 is an explanatory diagram showing an example of the learning content of a learning model in a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] (Overall composition) A support device, a support method, and a program according to an embodiment of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are given the same reference numerals. As shown in Fig. 1, a support device 100 according to an embodiment of the present invention is communicably connected to an information terminal 200 via a computer communication network 400 such as the Internet.
[0019] The support device 100 is, for example, a PC (Personal Computer) or a server (so-called computer) that manages and operates an online shopping mall, an online supermarket, a reservation site for accommodation facilities, a reservation site for a sports facility, a reservation site for a beauty facility, a sales site for betting tickets for public races, an online bank, an online securities company, or other websites, and can communicate with the information terminal 200 via a computer communication network 400. For ease of understanding, the support device 100 in this embodiment will be described below as a server device that manages and operates an online securities company. Specifically, the support device 100 is a device that supports the use of a chatbot by providing the user with a flow of questions and answers corresponding to the page the user is viewing as a demonstration of the use of the chatbot, in order to improve the utilization rate of the chatbot used in the online securities company. In addition, the support device 100 also has normal functions for operating an online securities company, such as user management and asset management. The support device 100 also has a function of providing the user with the functions of a normal chatbot.
[0020] The information terminal 200 is an information terminal (so-called computer) owned by a user, such as a smartphone, tablet, or PC. The information terminal 200 has a function of transmitting trading instructions and questions about the online securities to the support device 100 in response to an operation by the user.
[0021] (Functional configuration of the support device) Next, the configuration of the support device 100 will be described with reference to FIG.
[0022] As shown in FIG. 2, the support device 100 includes a storage unit 110, a control unit 120, an input / output unit 130, a communication unit 140, and a system bus (not shown) that interconnects these units.
[0023] The storage unit 110 includes a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The ROM stores a program 111 to be executed by the control unit 120, various data (not shown) required in advance for executing the program 111, and a learning model 112.
[0024] The program 111 is a program for executing a demo display process, which will be described later, and is stored in the storage unit 110 in advance.
[0025] The learning model 112 is a learning model that is machine-learned based on the page information currently being viewed by the user using the chatbot, and the questions and answers asked.
[0026] Here, the operation of the chatbot will be described. First, as shown in FIG. 3(a), an icon (button) such as "Chat inquiry" is displayed superimposed on the page being viewed. Specifically, when the support device 100 provides a viewed page requested by the user, the support device 100 displays the icon superimposed on the viewed page. Then, when the user selects the "Chat inquiry" button, the support device 100 is notified of the selection, and the support device 100 starts the chatbot. That is, as shown in FIG. 3(b), the chatbot "chat support" is started. Then, as shown in FIG. 3(b), three options are displayed as question 1, and as shown in FIG. 3(c), the user selects a desired question from these options as answer 1. Then, as shown in FIG. 3(d), three options are displayed as question 2 as a lower level question, and the user answers them one after another. By repeating this process, the user can obtain the final answer he or she desires. These questions and answers are provided to the user by the support device 100.
[0027] The learning model 112 is a learning model that learns the chatbot operation history performed by each user on the currently viewed page until the user obtains the final answer as teacher data. Specifically, the learning model 112 includes a learning model that performs machine learning using currently viewed page information indicating the page currently viewed by each user and the history of questions displayed on the page and selected answers as teacher data, and a learning model that learns the currently viewed page and the final answer (final answer X) as teacher data, as shown in FIG. 4. For example, as shown in FIG. 3(a), when the "chat inquiry" button is pressed while the page A is being viewed, and question 1 is displayed as shown in FIG. 3(b), as shown in FIG. 4, for the pair of "page A" and "no question answer", the supervised data in which question 1 is the answer is used as the learning data. Then, as shown in FIG. 3(c), when "option A-1-2" is selected (answer 1), and as shown in FIG. 3(d), question 2 is displayed as a result of the answer being made, and as shown in FIG. 4, for the pair of "page A" and the history of "question 1 answer 1", the supervised data in which question 2 is the answer is used as the learning data. Thus, the learning model 112 includes a learning model that has learned answers to pairs of page information currently being viewed and a history of questions and answers until the final answer was obtained, using as training data. As shown in Fig. 4, the learning model 112 also includes a learning model that has learned a final answer X to the page currently being viewed, using as training data. In this way, the learning model 112 is a machine learning model that has learned questions and answer histories made by many users by associating them with page information.
[0028] Returning to Fig. 2, the control unit 120 is composed of a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), etc. The control unit 120 operates in accordance with a program 111 stored in the storage unit 110, and executes processing in accordance with the program 111. The control unit 120 includes a demonstration start determination unit 121, a browsed page information acquisition unit 122, a question and answer generation unit 123, and a demonstration execution unit 124 as main functional units provided by the program 111 stored in the storage unit 110.
[0029] The demonstration start determination unit 121 is a functional unit that determines whether or not it is time to start a demonstration showing a flow of questions and answers corresponding to a page that the user is viewing. Specifically, the demonstration start determination unit 121 determines that it is time to start a demonstration when it determines that a preset period has passed without any input from the user since the user started viewing the same page. Note that the input from the user does not include, for example, mouse operation or scroll operation by the user. In other words, when a preset period has passed while the same page is being viewed (during an idle state) without any input operation other than mouse operation or scroll operation (for example, an input operation of the purchase amount or the purchase quantity, etc.), the demonstration start determination unit 121 determines that it is time to start a demonstration.
[0030] The viewed page information acquisition unit 122 is a functional unit that acquires viewed page information that identifies a page being viewed by a user. Specifically, the viewed page information acquisition unit 122 has a function of acquiring page information of a page being viewed by a user, thereby identifying a page being viewed by a user. The page information is, for example, a URL (Uniform Resource Locator).
[0031] The question and answer generating unit 123 is a functional unit that generates a demonstration showing a flow of questions and answers corresponding to the page specified by the viewed page information acquiring unit 122. Specifically, the question and answer generating unit 123 has a function of generating a demonstration combining questions and answers frequently asked by users in the past on the page specified by the viewed page information acquiring unit 122, using the learning model 112. Note that the question and answer generating unit 123 can generate a plurality of demonstrations, such as a demonstration showing a flow of questions and answers most frequently asked by a user viewing the page specified by the viewed page information acquiring unit 122 using a chatbot, and a demonstration showing a flow of questions and answers second most frequently asked by a user viewing the page specified by the viewed page information acquiring unit 122 using a chatbot. Also, the question and answer generating unit 123 may generate a flow of questions and answers until the final answer X is obtained as one demonstration.
[0032] The demonstration execution unit 124 is a functional unit that executes the demonstration generated by the question and answer generation unit 123. Specifically, the demonstration execution unit 124 has a function of presenting the operation contents of the chatbot and the contents of the questions and answers to the user by sequentially displaying the demonstrations generated by the question and answer generation unit 123 on the display screen of the information terminal 200, thereby deepening the user's understanding of the chatbot and promoting the use of the chatbot. Note that, when multiple demonstrations are generated by the question and answer generation unit 123, the demonstration execution unit 124 may sequentially display them starting from the demonstration showing the most frequently asked question and answer flow.
[0033] The input / output unit 130 is composed of a keyboard, a mouse, a camera, a microphone, a liquid crystal display, an organic EL (Electro-Luminescence) display, and the like, and is a device for inputting and outputting various types of data.
[0034] The communication unit 140 is a device that enables the support device 100 to communicate with other information terminals such as the information terminal 200 via the computer communication network 400. The configuration of the support device 100 has been described above.
[0035] (operation) Next, the operation of the support device 100 will be described with reference to FIG. 5 to FIG. 7. FIG. 5 is a flowchart showing an example of a demo display process in the support device 100. The demo display process shown in FIG. 5 is a process for deepening the user's understanding of the chatbot and promoting the use of the chatbot by presenting the operation contents of the chatbot when the chatbot is used to the user. As described above, the demo display process in this embodiment shows a demo display example of a chatbot used in an online securities company, but it can also be applied to chatbots in other websites such as online shopping malls, online supermarkets, accommodation reservation sites, sports facility reservation sites, beauty facility reservation sites, public sports betting ticket sales sites, online banks, etc. The demo display process starts when the user accesses the online securities company. It may start when the user logs in. It may also start when an icon (button) such as "enquire by chat" is displayed superimposed on the page being viewed.
[0036] In the demonstration display process, the control unit 120 of the support device 100 first determines whether it is time to start a demonstration by using the function of the demonstration start determination unit 121 (step S11). Specifically, in the process of step S11, the demonstration start determination unit 121 determines whether a preset period has passed while the same page is viewed without performing any input operation (e.g., input operation of the purchase amount or input operation of the purchase quantity) other than mouse operation or scroll operation. If it is determined that it is not time to start a demonstration (step S11; No), or if a preset period has not passed while the same page is viewed without performing any input operation other than mouse operation or scroll operation, the support device 100 repeats the process of step S11 until it is time to start a demonstration.
[0037] When it is determined in the process of step S11 that it is time to start a demonstration (step S11; Yes), that is, when a preset period has elapsed while the same page is being viewed without any input operation other than mouse operation or scroll operation, the control unit 120 acquires page information indicating the page currently being viewed by the user through the function of the viewed page information acquisition unit 122 (step S12). Specifically, in the process of step S12, the viewed page information acquisition unit 122 acquires the URL of the page currently being viewed by the user as page information, and identifies the page currently being viewed.
[0038] After executing the process of step S12, the control unit 120 generates a question and an answer corresponding to the page identified in the process of step S12 by using the function of the question and answer generation unit 123 (step S13), thereby generating a demonstration corresponding to the page. Specifically, in the process of step S13, the question and answer generation unit 123 generates a question and an answer corresponding to the page identified in the process of step S12 by using the learning model 112. For example, if the page identified in the process of step S12 is "page A", then as shown in FIG. 6(a), "question A" corresponding to the "page A" is generated in the process of step S13; if the page identified in the process of step S12 is "page B", then as shown in FIG. 6(b), "question B" corresponding to the "page B" is generated; and if the page identified in the process of step S12 is "page C", then as shown in FIG. 6(c), "question C" corresponding to the "page C" is generated in the process of step S13, and the subsequent answers are generated. As described above, in the processing of step S13, it is possible to generate multiple demonstrations, such as a demonstration showing the sequence of questions and answers that the user most frequently posed using the chatbot, as well as a demonstration showing the sequence of questions and answers that the user second most frequently posed using the chatbot.
[0039] 5, after executing the process of step S13, the control unit 120 executes the demonstration (step S14) by providing the questions and answers generated in the process of step S13, i.e., a demonstration of the case where the chatbot is used, to the information terminal 200 through the function of the demonstration execution unit 124, and ends the demonstration display process. As a result, the operation contents of the chatbot and the contents of the questions and answers are displayed on the information terminal 200, which allows the user to deepen their understanding of the chatbot and promotes the use of the chatbot.
[0040] FIG. 7 is a diagram showing an example of a demonstration performed on information terminal 200 by executing the demonstration display process of FIG. 5, that is, an example of a display operation during demonstration display.
[0041] As shown in FIG. 7(a), when a preset period of time has elapsed while viewing “Page A” without any input operations other than mouse operations and scrolling operations, and the start condition is met, the result is determined to be “Yes” in the processing of step S11 in FIG. 5, and it is determined that it is time to start the demonstration.
[0042] 5 is executed, the page being viewed is identified as "Page A," and a demonstration showing the flow of questions and answers corresponding to "Page A" is generated in step S13. Then, the process of step S14 is executed, and the questions and answers are displayed in sequence, as shown in Figures 7(b) to 7(h).
[0043] That is, in this example, the contents of the demonstration generated in the process of step S13 in FIG. 5 are as shown in FIG. 7(b) to FIG. 7(h). Specifically, as shown in FIG. 7(b), "Question A-1" corresponding to "Page A" is displayed first, then, as shown in FIG. 7(c), "Answer A-1" is given, and then, as shown in FIG. 7(d), "Question A-2" is displayed. Then, when "Answer A-2" is given, as shown in FIG. 7(e), "Question A-3" is displayed, as shown in FIG. 7(f), and "Answer A-3" is given, as shown in FIG. 7(g). After this flow continues, finally, "Final Answer X" is displayed, as shown in FIG. 7(h). In step S13 in FIG. 5, the learning model 112 is used to generate the demonstrations shown in FIG. 7(b) to FIG. 7(h) corresponding to "Page A".
[0044] If "Page A" continues to be viewed without any input operations other than mouse operations and scroll operations being performed even after the demonstration has ended, a demonstration showing the sequence of questions and answers that was the second most frequently asked by the user viewing "Page A" may be displayed. The timing for executing the second demonstration after the first demonstration has ended may be immediately after the first demonstration has ended, or after a predetermined period of time has elapsed. The period of time may be shorter than the period of the start condition for the first demonstration (it may be a short idle state).
[0045] The above is the operation of the demo display process in the support device 100. By performing the demo display process by the support device 100, a flow of questions and answers corresponding to the page the user is browsing can be displayed as a demonstration of the case where a chatbot is used. Therefore, the user can understand the operation content when using a chatbot, deepen his / her understanding of the chatbot, and promote the use of the chatbot. In addition, by presenting the user with the flow of questions and answers that were frequently asked in the past on the browsing page, the probability of obtaining the final answer X desired by the user is increased, and the user can also understand what questions and answers to select in order to obtain the final answer X desired, thereby promoting the use of the chatbot.
[0046] (Modification) It should be noted that the present invention is not limited to the above-mentioned embodiment, and various modifications and applications are possible. For example, the support device 100 according to the above-mentioned embodiment does not need to have all the technical features described above, and may have some of the configurations described in the above-mentioned embodiment so as to solve at least one problem in the conventional technology. In addition, at least a part of each of the following modifications may be combined.
[0047] In the above embodiment, since the questions and answers of the chatbot are selected by the user as shown in FIG. 3, an example in which questions and answers are also selected for the demonstration as shown in FIG. 6 and FIG. 7 has been shown, but this is just an example. For example, the questions in the chatbot may be freely input by the user as shown in FIG. 8. In addition, when one demonstration is completed from the start of the demonstration to the display of the final answer X, a scroll display may be performed as shown in FIG. 8 so that the user can check the history of options from the first combination of question and answer to the final answer X. Furthermore, for example, when the mouse pointer is positioned by a user's operation in the question input area, which is the area of "Please enter your question" shown in the figure, even if the demonstration is in progress, that is, even if the final answer X is not displayed, a scroll display may be performed so that the user can check the history of options in the demonstration. Note that the scroll display may be performed when a condition other than the mouse pointer being positioned in the question input area is met, and for example, the start condition of the scroll display may be that the area in which the demonstration is displayed is selected by the user.
[0048] Also, as shown in FIG. 8, when a question in a chatbot is freely input by a user, the learning model 112 may be a learning model that has learned using the page information being viewed, the content of the question and the history of the answer, and the newly input question as teacher data, as shown in FIG. 9. In FIG. 9, answer 1, answer 2, ... answer n may be omitted from the learning data. Also, as in the case shown in FIG. 4, the learning model 112 shown in FIG. 9 may also include a learning model that has learned using the final answer X to the page being viewed as teacher data. In the aspect in which questions and answers are made in free text (using a generation AI), the generation AI generates questions that are frequently asked on the page being viewed by the user, inputs the questions into an existing Q&A system to be answered, and the generation AI generates new questions based on the page and the history of questions and answers generated so far, and the process is repeated, so that the user can see the interaction from the question to the answer. That is, an AI that generates questions to be asked on the page being viewed may be used. Also, the existing Q&A system (program) may be stored in advance in the storage unit 110, for example. In addition, an AI that generates an answer when a question is input may be used. For example, a learning model 112 that clusters the question content input by the user by unsupervised learning and then learns the answers corresponding to each cluster as supervised data may be used. Then, in the process of step S13 shown in FIG. 5, the learning model 112 may be used to generate an answer corresponding to the question content most frequently input by the user in the past as a demonstration. More specifically, an answer corresponding to the cluster to which the question most frequently input by the user who viewed the viewed page belongs may be generated as the content of the demonstration. According to this, it is possible to provide the user with the question content to obtain the desired answer, so that the use of the chatbot can be promoted. Furthermore, both an AI that generates a question to be asked on the currently viewed page and an AI that generates an answer when the question is input may be used. That is, a process in which a question generating AI generates a question that is frequently asked on the currently viewed page, and an answer to the question is generated by an answer generating AI may be repeated.The answer generating AI may be an AI that, when a question is input by a user, generates an answer corresponding to the question. Furthermore, the questions and answers generated by the question generating AI and the answer generating AI may be re-learned in the learning model 112.
[0049] The support device 100, the information terminal 200, and the information terminal 300 according to the above-mentioned embodiment can be realized by using a normal computer, not by a dedicated device. For example, the support device 100 that executes the above-mentioned processes may be configured by installing a program for executing any of the above-mentioned processes on a computer from a recording medium storing the program. Also, one support device 100, the information terminal 200, and the information terminal 300 may be configured by a plurality of computers operating in cooperation with each other.
[0050] Furthermore, when the above-mentioned functions are realized by sharing the functions between an OS (Operating System) and an application, or by cooperation between the OS and the application, only the parts other than the OS may be stored on the medium.
[0051] It is also possible to superimpose the program on a carrier wave and distribute it via a communication network. For example, the program may be posted on a bulletin board (BBS, Bulletin Board System) on the communication network and distributed via the network. These programs may then be started and executed under the control of the operating system in the same way as other application programs, thereby enabling the above-mentioned processing to be performed.
[0052] Various aspects of the present disclosure are summarized below as appendices.
[0053] (Appendix 1) a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demonstration execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; 13. An assistance device comprising:
[0054] (Appendix 2) the question and answer generation unit generates a first combination, which is a combination of a question and an answer corresponding to the page indicated by the viewed page information, and then generates a second combination, which is a combination of a question and an answer different from the first combination, which is corresponding to the page indicated by the viewed page information; the demonstration execution unit provides the user with a demonstration corresponding to the first combination, and then provides the user with a demonstration corresponding to the second combination; 2. The assistance device according to claim 1 .
[0055] (Appendix 3) The combination of the question and answer indicated by the first combination is a question and answer that has been asked more frequently by each user who viewed the page indicated by the viewed page information acquired by the viewed page information acquisition unit than the combination of the question and answer indicated by the second combination. 3. The assistance device according to claim 2,
[0056] (Appendix 4) an icon display unit that displays an icon superimposed on a page currently being viewed by the user; a chatbot activation unit that activates the chatbot by displaying a question and answer area superimposed on the currently viewed page when the icon displayed by the icon display unit is selected by the user, the demonstration execution unit displays the question and answer area when a predetermined start condition is satisfied after the icon is displayed by the icon display unit, and displays a combination of questions and answers generated by the question and answer generation unit in the question and answer area as a demonstration of a case where the chatbot is used. 4. The support device according to claim 1, wherein:
[0057] (Appendix 5) a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; an answer generation unit that, when a question is input by the user, generates an answer corresponding to the question using an artificial intelligence for answer generation; a question generation unit that generates a question corresponding to the page indicated by the viewed page information acquired by the viewed page information acquisition unit, using an artificial intelligence for generating questions; a demonstration execution unit that provides a combination of the question and the answer to the user as a demonstration of a case where a chatbot is used; the answer generation unit generates an answer corresponding to the question generated by the question generation unit, using the question generated by the question generation unit as the question input by the user. 13. An assistance device comprising:
[0058] (Appendix 6) the demonstration execution unit repeatedly generates the question by the question generation unit and generates the answer by the answer generation unit, and provides a combination of the question and the answer to the user as a demonstration of the use of the chatbot; The question generation unit and the answer generation unit generate the questions and the answers based on a learning model that is trained using a history of questions and answers for each page being browsed by the chatbot until each user obtains a final answer as training data. 6. The assistance device according to claim 5,
[0059] (Appendix 7) a re-learning unit that further learns a history of the questions and answers repeatedly generated by the question generating unit and the answer generating unit as training data; The assistance device according to claim 6, further comprising:
[0060] (Appendix 8) A method for assisting a user using an assisting device, comprising: a browsing page information acquiring step of acquiring browsing page information indicating a page currently being browsed by a user; a question and answer generating step of generating a question and answer combination corresponding to a page indicated by the browsed page information acquired in the browsed page information acquiring step, the question and answer combination being a combination of questions and answers to be performed when using a chatbot; a demonstration step of providing the user with a combination of questions and answers generated in the question and answer generating step as a demonstration of the use of the chatbot; In the question and answer generating step, a combination of questions and answers corresponding to the page indicated by the viewed page information is generated based on a learning model that is trained using a history of questions and answers for each page viewed by the chatbot that each user has made until obtaining a final answer as training data. A support method comprising:
[0061] (Appendix 9) Computer, a browsing page information acquisition unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demo execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; A program characterized by:
[0062] Various embodiments and modifications of the present disclosure are possible without departing from the broad spirit and scope of the present disclosure. The above-described embodiments are for explaining the present disclosure and do not limit the scope of the present disclosure. That is, the scope of the present disclosure is indicated by the claims, not the embodiments. Various modifications made within the scope of the claims and the scope of the disclosure equivalent thereto are considered to be within the scope of the present disclosure. [Industrial Applicability]
[0063] According to the present invention, it is possible to promote the use of chatbots. [Explanation of symbols]
[0064] 100 Support equipment 110 Storage section 111 Program 112 Learning Model 120 Control section 121 Demo start judgment section 122 Viewed page information acquisition unit 123 Question and answer generation section 124 Demonstration Department 130 Input / output section 140 Communications Department 200 Information terminal 400 Computer Communication Network
Claims
1. a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demonstration execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; 13. An assistance device comprising:
2. the question and answer generation unit generates a first combination, which is a combination of a question and an answer corresponding to the page indicated by the viewed page information, and then generates a second combination, which is a combination of a question and an answer different from the first combination, which is corresponding to the page indicated by the viewed page information; the demonstration execution unit provides the user with a demonstration corresponding to the first combination, and then provides the user with a demonstration corresponding to the second combination.
2. The support device according to claim 1 .
3. the combination of the question and answer indicated by the first combination is a question and answer that has been made more frequently by each user who viewed the page indicated by the viewed page information acquired by the viewed page information acquisition unit than the combination of the question and answer indicated by the second combination; 3. The support device according to claim 2.
4. an icon display unit that displays an icon superimposed on a page currently being viewed by the user; a chatbot activation unit that activates the chatbot by displaying a question and answer area superimposed on the currently viewed page when the icon displayed by the icon display unit is selected by the user, the demonstration execution unit displays the question and answer area when a predetermined start condition is satisfied after the icon is displayed by the icon display unit, and displays a combination of questions and answers generated by the question and answer generation unit in the question and answer area as a demonstration of a case where the chatbot is used.
4. The support device according to claim 1, wherein the support device is a computer.
5. a browsing page information acquiring unit that acquires browsing page information indicating a page currently being browsed by a user; an answer generation unit that, when a question is input by the user, generates an answer corresponding to the question using an artificial intelligence for answer generation; a question generation unit that generates a question corresponding to the page indicated by the viewed page information acquired by the viewed page information acquisition unit, using an artificial intelligence for question generation; a demonstration execution unit that provides a combination of the question and the answer to the user as a demonstration of a case where a chatbot is used; the answer generation unit generates an answer corresponding to the question generated by the question generation unit, using the question generated by the question generation unit as the question input by the user.
13. An assistance device comprising:
6. the demonstration execution unit repeatedly generates the question by the question generation unit and generates the answer by the answer generation unit, and provides a combination of the question and the answer to the user as a demonstration of using the chatbot; The question generation unit and the answer generation unit generate the questions and the answers based on a learning model that is trained using a history of questions and answers for each page being browsed by the chatbot until each user obtains a final answer as training data.
6. The support device according to claim 5.
7. a re-learning unit that further learns a history of the questions and answers repeatedly generated by the question generating unit and the answer generating unit as training data; The support device according to claim 6, further comprising:
8. A method for assisting a user using an assisting device, comprising: a browsing page information acquiring step of acquiring browsing page information indicating a page currently being browsed by a user; a question and answer generating step of generating a question and answer combination corresponding to a page indicated by the viewed page information acquired in the viewed page information acquiring step, the question and answer combination being a combination of questions and answers to be performed when using a chatbot; a demonstration step of providing the user with a combination of questions and answers generated in the question and answer generating step as a demonstration of the use of the chatbot; In the question and answer generating step, a combination of questions and answers corresponding to the page indicated by the viewed page information is generated based on a learning model that is trained using a history of questions and answers for each page viewed by the chatbot that each user has made until obtaining a final answer as training data. A support method comprising:
9. Computer, a browsing page information acquisition unit that acquires browsing page information indicating a page currently being browsed by a user; a question and answer generating unit that generates a combination of questions and answers to be asked when using a chatbot, the combination of questions and answers corresponding to a page indicated by the viewed page information acquired by the viewed page information acquiring unit; a demo execution unit that provides the user with a combination of questions and answers generated by the question and answer generation unit as a demonstration of the use of the chatbot; the question and answer generation unit generates a combination of questions and answers corresponding to the page indicated by the viewed page information, based on a learning model trained using a history of questions and answers for each page viewed by the chatbot until each user obtains a final answer as training data; A program characterized by:
Citation Information
Patent Citations
Communication control program, communication control method, and communication control device
JP2018194920A
Intelligent question response method based on multi-system, device, and apparatus
JP2022166260A
Information processing device, information processing method, and program
JP2023048877A
Automatic generation of question answer pairs
US20230133392A1
