Information processing apparatus, information processing method, and program

Abstract

To provide an information processor or the like capable of acquiring information related to a user's action to a chat.SOLUTION: According to an aspect of the present invention, there is provided an information processing apparatus including a processor, wherein the processor is configured to execute the following steps by reading a program, in the screen display control step, a chat screen is displayed in an entire dominated area allocated to the processor in a display area of an output unit of the user terminal, the chat screen includes only a chat field in which information is sequentially displayed in a chat format, in the question step, a question to the user is displayed in the chat field, and in the answer reception step, an input of an answer to the question in the chat field is received from an input unit of the user terminal, there is provided an information processing apparatus in which the answer is displayed in a chat field, and in the association step, association information corresponding to the answer is displayed in the chat field on the basis of the answer and the reference information, the association information is provision information or a question for the user, and the reference information includes a correlation between the answer and the association information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] As disclosed in Patent Document 1, a system that uses a chatbot to obtain answers from users is known. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-080944 Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned system, the chat field where users enter their responses is displayed as part of the app screen along with a search field, etc. Therefore, the user's view and operation are not limited to the chat field, making it difficult to obtain information for analyzing user behavior in chat.

[0005] In view of the above circumstances, the present invention provides an information processing device and the like that can acquire information about user behavior in chat. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing device comprising a processor, the processor being configured to execute each of the following steps by reading a program, wherein in a screen display control step, a chat screen is displayed in the entire control area allocated to the processor out of the display area of ​​the output unit of the user terminal, the chat screen including only a chat box in which information is displayed sequentially in chat format, in a question step, a question for the user is displayed in the chat box, in a response receiving step, input of an answer to the question in the chat box is accepted from an input unit of the user terminal and the answer is displayed in the chat box, in a response step, response information corresponding to the answer is displayed in the chat box based on the answer and reference information, in which the response information is information to be provided to the user or a question, and the reference information includes a correlation between the answer and the response information.

[0007] According to this aspect, by displaying a chat screen on the user terminal that is composed only of a chat field and does not include any other information display other than the chat field, it is possible to obtain information (such as the time of input) when a user inputs an answer to a question in association with the state of the chat field. As a result, it is possible to present supplemental information, additional questions, etc., tailored to each individual user, and to perform accurate statistics and analysis of user behavior. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] 2 is a block diagram showing the hardware configuration of the server device 10. FIG. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of the user terminal 20. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (controller 11) and a user terminal 20 (controller 21). [Figure 5] FIG. 10 is a diagram showing an example of a chat screen CD displayed on the user terminal 20. [Figure 6]FIG. 10 is a diagram showing an example of a chat screen CD in which a reply is displayed in a chat field. [Figure 7] FIG. 10 is a diagram showing an example of a chat screen CD when accepting text input in a chat field CF. [Figure 8] FIG. 10 is a diagram showing an example of a chat screen CD in which corresponding information is displayed in a chat field. [Figure 9] FIG. 10 is a diagram showing an example of a chat screen CD displayed on the user terminal 20 upon transition from the referrer website. [Figure 10] 10 is a diagram showing an example of a chat screen CD displayed on the user terminal 20 upon transition from a referral source website different from that shown in FIG. 9. FIG. [Figure 11] FIG. 10 is a diagram showing an example of a graph (funnel) showing the dropout rate for each question. [Figure 12] 1 is an activity diagram showing an example of the flow of information processing (answer acquisition processing) executed by the information processing system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a generative AI such as a large-scale language model or a visual language model that can output a desired result in response to a prompt input.

[0012] In one embodiment, a "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] 1. Hardware Configuration This section explains the hardware configuration.

[0015] <Information Processing System 1> 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes a communication line 2, a server device 10 (an example of an information processing device), and a plurality of user terminals 20. The server device 10 and the user terminals 20 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10 and the user terminals 20 may be wired or wireless.

[0016] In one embodiment of the information processing system 1, the information processing system 1 is made up of one or more devices or components. These components will be described below.

[0017] <Server device 10> Fig. 2 is a block diagram showing the hardware configuration of server device 10. As shown in Fig. 2, server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. Control unit 11, storage unit 12, and communication unit 13 are electrically connected within server device 10 via communication bus 14.

[0018] <Control unit 11> The control unit 11 processes and controls the overall operations related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out predetermined programs stored in the storage unit 12. In other words, information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have multiple control units 11 for each function. Alternatively, a combination of these may be used.

[0019] <Storage section 12> The memory unit 12 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The memory unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0020] <Communications Department 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), or wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, or BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a collection of multiple communication means. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The server device 10 may be an on-premise server or a cloud server. The cloud server device 10 may provide the above-described functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <User terminal 20> The user terminal 20 is an information processing terminal used by a user who uses the interaction service provided by the server device 10. Fig. 3 is a block diagram showing the hardware configuration of the user terminal 20. As shown in Fig. 3, the user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the storage unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected via the communication bus 26 inside the user terminal 20. The description of the control unit 21, the storage unit 22, and the communication unit 23 is omitted because they are the same as the description of each unit in the server device 10.

[0023] <Input section 24> The input unit 24 accepts an action input made by the user. The action input is transferred as a command signal to the control unit 21 via the communication bus 26. The control unit 21 can execute predetermined control or calculation based on the transferred command signal as necessary. The input unit 24 may be included in the housing of the user terminal 20 or may be externally attached. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input a tap action, a swipe action, or the like to the input unit 24. Instead of a touch panel, a switch button, a mouse, a trackpad, a QWERTY keyboard, or the like can be used as the input unit 24.

[0024] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) on which the user can perform actions. The output unit 25 may be included in the housing of the user terminal 20 or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are used appropriately depending on the type of user terminal 20.

[0025] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (a processor provided in the information processing system 1).

[0026] FIG. 4 is a block diagram showing functions realized by the server device 10 (controller 11) and the user terminal 20 (controller 21).

[0027] 4A, the server device 10 (control unit 11) includes a display instruction receiving unit 111, an information acquisition unit 112, a screen display control unit 113, a questioning unit 114, an answer receiving unit 115, a correspondence unit 116, a data recording unit 117, and an artificial intelligence unit 120. As shown in FIG. 4B, the user terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212.

[0028] <Display instruction receiving unit 111> The display instruction receiving unit 111 is configured to receive a display instruction from the user terminal 20 for a chat screen to be displayed on the user terminal 20 by a screen display control unit 113 (to be described later).

[0029] For example, the display instruction receiving unit 111 receives an instruction to display a chat screen by inputting a predetermined URL (a specific URL assigned to each chat screen as a communication page) in the user terminal 20. According to this embodiment, it is possible to guide the user to the chat screen without going through other access sites or screens.

[0030] Examples of methods for inputting the specific URL include reading a two-dimensional code indicating the specific URL using the user terminal 20, selecting a link to the specific URL displayed on a website or the like, and directly inputting the URL using the input unit 24 of the user terminal 20. The specific URL may be displayed as a two-dimensional code in an advertisement introducing a product or service, for example. This allows a user who is interested in a product or service to easily access a chat screen for purchasing or using the product or service on the spot. Typically, when a user reads the two-dimensional code with the user terminal 20, a chat screen is displayed on the display of the user terminal 20 (the display screen on the display of the user terminal 20 transitions to the chat screen).

[0031] The display instruction receiving unit 111 may receive an instruction to display a chat screen from the user terminal 20 via a referencing website (a transition source website) displayed on the user terminal 20. The display instruction receiving unit 111 receives, for example, an input to an object including a link to a specific URL displayed on the referencing website from the user terminal 20. The display instruction receiving unit 111 may also receive an instruction to display a chat screen by reading a two-dimensional code indicating the specific URL displayed on the referencing website.

[0032] There are no particular restrictions on the referring website, as long as it contains a link to the chat screen. Typical examples of referring websites are websites that introduce specific products or services, such as social networking services (SNS), social media, and corporate owned media. These websites, for example, stream real-time or archived videos (live commerce) in which hosts introduce products or services.

[0033] If the referring website contains a video, the link to the chat screen may be displayed on the referring website at all times, or may be displayed after the video on the referring website has been viewed (after playback of the video has been completed).

[0034] <Information acquisition unit 112> The information acquisition unit 112 is configured to acquire various information from the user terminal 20, other information processing devices (servers), etc. The information acquisition unit 112 acquires, for example, information such as personal information of a user who uses an interaction service (chatbot service) for purchasing or using a product or service provided by the server device 10, a purchase history or browsing history of the product or service, etc.

[0035] When the display instruction receiving unit 111 receives an instruction to display a chat screen via a referrer website, the information acquiring unit 112 acquires referrer information related to the referrer website that received the display instruction. According to this embodiment, a chat linked to the referrer website of the chat screen can be developed on the chat screen. Therefore, a consistent experience can be provided to the user from the referrer website.

[0036] The referrer information is information indicating the attributes of the referrer website, and includes, for example, information about the administrator (operator) of the referrer website, the host (YouTuber, influencer, etc.) introducing the product or service, the provider (sales agent) of the product or service, etc. In particular, the referrer information may include the attributes of the host of the referrer website (e.g., gender, age, personality, hobbies, appearance, etc.). The host of the referrer website may be a real person or a virtual character (e.g., a VTuber).

[0037] The information acquisition unit 112 acquires or determines the referrer information based on, for example, the URL of the referrer website acquired from the web browser used in the user terminal 20. Furthermore, if an individual specific URL (individual URL of the chat screen) is prepared for each referrer website, the information acquisition unit 112 may acquire or determine the referrer information based on the specific URL.

[0038] <Screen display control unit 113> The screen display control unit 113 is configured to cause the user terminal 20 to display a usage screen for the interaction service provided by the server device 10. Specifically, the screen display control unit 113 causes the chat screen to be displayed in the entire control area allocated to the processor of the server device 10 out of the display area of ​​the output unit 25 (display) of the user terminal 20.

[0039] The "control area assigned to the processor" is an area exclusively used by an application (hereinafter referred to as a "specific application") controlled by the control unit 11 (which can cause display or processing to be executed by the control unit 11 sending commands to the user terminal 20) among the applications executed in the user terminal 20. Examples of specific applications include a dedicated application for an interaction service provided by the server device 10, a web browser capable of providing the interaction service, etc.

[0040] For example, if the specific application is a dedicated application, the "control area assigned to the processor" corresponds to the exclusive area of ​​the dedicated application (the execution area of ​​the dedicated application). Also, if the specific application is a web browser, the "control area assigned to the processor" corresponds to the exclusive area of ​​the tag in which the interaction service is executed in the web browser.

[0041] In particular, when the user terminal 20 is a mobile terminal such as a smartphone or tablet, the "control area assigned to the processor" is typically the area excluding the functional display portion of the application (display portion of the application's outer frame, menu, etc.) from the entire display area of ​​the output unit 25 of the user terminal 20.

[0042] The screen display control unit 113 receives the display instruction for the chat screen received by the display instruction receiving unit 111 and displays the chat screen on the output unit 25 of the user terminal 20. In particular, when the display instruction receiving unit 111 receives the display instruction for the chat screen via the referrer website, the screen display control unit 113 displays the chat screen on the user terminal 20 based on the display instruction from the referrer website. As a result, the web browser running on the user terminal 20 transitions from the display screen of the referrer website to the chat screen.

[0043] The chat screen that the screen display control unit 113 displays on the user terminal 20 includes only a chat field where information is displayed sequentially in a chat format. Specifically, the chat field includes only a main area showing the history of chat messages (characters, images, etc. showing statements), a chat input field (UI for inputting characters or images), and icons for operating the chat screen (for example, a UI for operating screen switching).

[0044] In the chat field, the user and the chatbot chat. In the chat field, chat messages (messages by the chatbot) output by the question unit 114 and the response unit 116 (to be described later) and chat messages input by the user on the user terminal 20 are displayed in chronological order along the vertical direction.

[0045] On the chat screen, information (text, images, etc.) about products or services to be presented to the user is not displayed outside the main area. In other words, on the chat screen, new information is presented only in chat messages, and new information is not displayed in any form other than chat messages.

[0046] A chat screen is prepared for each product or service to be presented to the user. Configuration information of the chat screen (products or services handled, screen design, question list, etc.) is stored, for example, in the storage unit 12. Each chat screen is assigned a unique URL.

[0047] <Question 114> The question unit 114 is configured to display an initial question for the user in the chat box along with the initial information.

[0048] The question unit 114 first displays initial information in the chat field in the initial state of the chat screen displayed on the user terminal 20 by the screen display control unit 113. The initial information includes, for example, commercial information (an introduction to the product or service, an outline of the campaign, conditions, target audience, etc.) relating to the product or service to be presented to the user on the chat screen accessed by the user (displayed on the user terminal 20), a guide message on the chat screen, etc.

[0049] The question unit 114 displays at least one piece of initial information in the chat field, and then subsequently displays an initial question in the chat field. The initial question is a question prepared in advance for each product or service handled by the chat screen. The question unit 114 may select an initial question to be displayed in the chat field from a plurality of prepared initial questions based on the user's personal information, etc. The initial question includes, for example, a question to confirm the user's intention to apply for the purchase or use of a product or service, to apply for a campaign, etc. Furthermore, the question unit 114 may display answer options for the initial question in the chat field following the initial question.

[0050] FIG. 5 is a diagram showing an example of a chat screen CD displayed on the user terminal 20. As shown in FIG. 5, the entire area of ​​the chat screen CD is a chat field CF in which chat messages are displayed sequentially. The chat field CF displays an initial information message IM1, an initial question message QM1, and an initial option message OM1. The initial information message IM1 includes text, images, videos, etc. of the initial information output by the question unit 114. The initial question message QM1 includes text of the initial question output by the question unit 114. The initial option message OM1 includes answer options to the initial question output by the question unit 114.

[0051] When the display instruction receiving unit 111 receives an instruction to display a chat screen via the source website, the questioning unit 114 adjusts at least one of the content and expression of the question to the user based on the source information acquired by the information acquiring unit 112. For example, the questioning unit 114 changes the question (inquiry content), the types of options, the presentation order of the options, etc., depending on the attributes of the host included in the source information. Furthermore, the questioning unit 114 changes the tone of the question (whether honorific language is used, the frequency of use of decorative characters or emoticons, etc.) depending on the attributes of the host included in the source information. Therefore, if there are two different websites A and B (which have different hosts) that introduce the same product or service, the content or expression of the question displayed on the chat screen will change depending on whether the user transitions from website A or website B. The same applies to the correspondence information described below.

[0052] The question unit 114 creates a question message based on the source information and the first reference information. For example, the question unit 114 may adjust the content or wording of the question by selecting a question message with reference to a combination table (an example of first reference information) prepared in advance that defines correlations (correspondences) between host attributes and question messages. The question unit 114 may also input a prepared question message template and the host attributes into a message creation model (an example of first reference information) and cause the message creation model to output a question message with the content or wording adjusted. The message creation model is a learning model that has been machine-learned so as to input a question message template and the host attributes and output a question message according to the host attributes, and is typically a large-scale language model.

[0053] Furthermore, when the display instruction receiving unit 111 receives an instruction to display a chat screen via the source website, the questioning unit 114 displays a speaker icon corresponding to the source information in association with the question to the user. According to this aspect, a speaker icon representing the host, administrator, etc. of the source website is displayed on the chat screen, thereby improving the consistency of the user experience from the source website to the chat screen.

[0054] For example, the question unit 114 sets a speaker icon to be displayed according to the attributes of the host included in the source information. The speaker icon is, for example, prepared in advance for each host, and is, for example, a photograph of the host's face, an avatar, or the like.

[0055] Furthermore, the question unit 114 may change information (e.g., product or service price, availability of discount coupons, etc.) presented to the user on the chat screen according to the referrer information. An example of the chat screen CD based on the referrer information will be described later.

[0056] <Answer Reception Section 115> The answer receiving unit 115 is configured to receive input of an answer to a question in the chat box from the input unit 24 of the user terminal 20 and to display the input answer in the chat box. "Questions in the chat box" include initial questions output by the questioning unit 114 and follow-up questions output by the response unit 116, which will be described later.

[0057] Answers are input in the user terminal 20 by inputting an answer to an option presented by the questioning unit 114 or the response unit 116, or by manually inputting text. Whether an answer is given by selecting an option or manually inputting text depends on the type of question. When manually inputting text, the answer receiving unit 115 displays an area for receiving text input in the chat box.

[0058] Fig. 6 is a diagram showing an example of a chat screen CD in which an answer is displayed in the chat field. In the example of Fig. 6, an answer message AM to an initial question message QM1 by the question unit 114 is displayed in the chat field CF following the initial question message QM1 and the initial choice message OM1. The answer message AM includes an answer entered by the user (in the example of Fig. 6, an answer selected from the choices in the initial choice message OM1).

[0059] 7A and 7B are diagrams showing an example of a chat screen CD when accepting text input in the chat box CF. As shown in FIG. 7A, an input area IA for inputting an answer to an initial question message QM1 by the question unit 114 is displayed at the bottom of the chat box CF. After inputting text in the input area IA, the user sends the answer by performing an input operation on the send button SB. As a result, the display of the input area IA is cleared, and an answer message AM is displayed in the chat box, as shown in FIG. 7B.

[0060] <Corresponding Department 116> The response unit 116 is configured to display response information corresponding to the answer entered by the user in the chat box based on the answer entered by the user and the second reference information. The response information is information to be provided to the user or a question. For example, the response unit 116 selects the type and content of the response information according to the answer entered by the user. In addition, the "information to be provided" includes a message to the user, an image and a video to be presented to the user, etc.

[0061] The second reference information is information including a correlation between a user's answer and the corresponding information. The second reference information is stored in, for example, the storage unit 12. The second reference information is an estimator constructed to be able to output the corresponding information using the user's answer as input. The second reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates a correlation between a feature extracted from the user's answer (e.g., identification information of the option selected by the user, vector data obtained by vectorizing the answer content, etc.) and a feature extracted from the corresponding information (e.g., identification information of pre-prepared corresponding information, vector data obtained by vectorizing the corresponding information, etc.). The correlation included in the second reference information can be constructed, for example, by statistically analyzing data recording actual interactions with users (combinations of user answers and responses to the answers (corresponding information)).

[0062] The second reference information may include a sentence creation model that has been trained to input the user's answer and output corresponding information. In this case, the correspondence unit 116 inputs the user's answer to the sentence creation model of the artificial intelligence unit 120 and causes the sentence creation model to output corresponding information. According to this embodiment, it is possible to generate corresponding information based on examples of corresponding information (supplementary information, additional questions, etc.) for many answers or natural language processing.

[0063] The writing model is a learning model that is trained using combinations of answers for learning and corresponding information for the answers as training data. In the writing model, parameters calculated, tuned, etc. through learning constitute correlations of the second reference information.

[0064] The writing model may be a generative AI including a large-scale language model. In this case, the correspondence unit 116 inputs the user's answer, inputs a prompt including an instruction to output corresponding information to the writing model, and causes the writing model to output the corresponding information. In addition to the instruction to create and output the corresponding information and the user's answer, the correspondence unit 116 may input a prompt into the writing model that includes, as input and output samples, one or more samples of the user's answer and one or more corresponding samples of corresponding information.

[0065] The correspondence unit 116 may create or select correspondence information using accompanying information about the user in addition to the user's answer. The accompanying information includes, for example, supplementary information about the user's answer, personal information about the user, and behavior history information about the user.

[0066] The supplemental information about the answer includes at least one of the speed at which the answer is input at the user terminal 20, the directionality of the input answer, and the number of times the same user has input an answer to one question.

[0067] The "answer input speed" is the time from when the question unit 114 or the response unit 116 displays a question in the chat box to when the user sends the answer. The "answer directionality" is information indicating whether the input or selected answer is positive (affirmative) or negative (negative). The answer directionality may be defined in advance for each option presented in the chat box, or may be determined by text data analysis. The "number of answer inputs" is the number of times the user re-enters the answer to one question. The re-entry of the answer is performed, for example, by the response unit 116 displaying an option message (for example, a message including an option such as "revise answer") in the chat box after the answer acceptance unit 115 accepts the answer and accepts the answer revision.

[0068] The response unit 116 may create or select response information based on one piece of information included in the supplemental information, or may create or select response information based on a combination of multiple pieces of information. For example, when the input speed of the answer is high and the direction of the answer is positive, the response unit 116 creates or selects response information that results in positive conversation content and displays it in the chat box. Also, for example, when the input speed of the answer is slow and the direction of the answer is negative, the response unit 116 creates or selects response information that results in modest conversation content and displays it in the chat box.

[0069] The correspondence unit 116 may refer only to the supplemental information of the immediately preceding answer, or may cumulatively refer to the supplemental information of previous answers. For example, the correspondence unit 116 may set a conversation score that increases each time a positive answer is input and decreases each time a negative answer is input, and create or select correspondence information based on the value of the conversation score. The conversation score may increase or decrease depending on the answer input speed.

[0070] When supplemental information is used, the sentence creation model of the artificial intelligence unit 120 may be trained so as to be able to input the user's answer and supplemental information related to the answer and output corresponding information. In this case, the response unit 116 inputs the user's answer and the supplemental information to the sentence creation model and causes the sentence creation model to output the corresponding information. According to this aspect, it is possible to respond (present supplemental information, additional questions, etc.) according to the user's preferences, personality, etc., and therefore it is possible to prevent the user from dropping out before all questions are completed.

[0071] When supplemental information is used as input, the writing model is a learning model that has learned using a combination of a learning answer and supplemental information, and corresponding information for the answer, as training data. Also, when the writing model is a generative AI that includes a large-scale language model, the correspondence unit 116 inputs the user's answer and supplemental information, inputs a prompt including an instruction to output corresponding information to the writing model, and causes the writing model to output the corresponding information.

[0072] The response unit 116 may increase the number of questions to be asked to a user as the number of times an answer to one question is input increases. According to this embodiment, in a chat intended to obtain answers from a user, it is possible to adjust the number of questions to be asked according to the user's loyalty. Specifically, the response unit 116 sets a question score that increases according to the number of times an answer is input, and displays additional questions in the chat field according to the level of the question score. This makes it possible to obtain detailed answers from users with a high question score (high loyalty) by asking additional questions. On the other hand, by reducing the number of questions asked to users with a low question score (low loyalty), it is possible to prevent users from dropping out.

[0073] In addition to the supplemental information, the correspondence unit 116 may create or select correspondence information based on the user's personal information and the user's behavioral history information. The user's personal information and the user's behavioral history information referred to by the correspondence unit 116 are acquired, for example, by the information acquisition unit 112. The user's personal information includes, for example, gender, age, etc. The user's behavioral history information includes a product or service purchase history (including, for example, a payment method, a contract date, etc.) or a browsing history, an access route to an interaction service (chat screen) provided by the server device 10, etc.

[0074] The user's answer to the follow-up question that the response unit 116 has displayed in the chat box is received by the answer receiving unit 115.

[0075] 8 is a diagram showing an example of a chat screen CD in which response information is displayed in the chat box. In the example of FIG. 8, an additional information message IM2, an additional question message QM2, and an additional option message OM2 are displayed following the user's answer message AM. The additional information message IM2 includes provided information (text, images, videos, etc.) output by the response unit 116 in response to the answer message AM. The additional question message QM2 includes the text of the additional question output by the response unit 116 in response to the answer message AM. The additional option message OM2 includes answer options for the additional question output by the response unit 116.

[0076] When the display instruction receiving unit 111 receives an instruction to display a chat screen via the source website, the response unit 116 adjusts at least one of the content and expression of the response information based on the source information acquired by the information acquiring unit 112. For example, the questioning unit 114 changes the reaction to a question, whether or not to ask a follow-up question, etc., depending on the attributes of the host included in the source information. Furthermore, the questioning unit 114 changes the tone of voice of the response information to the same tone of voice as the question displayed by the questioning unit 114, depending on the attributes of the host included in the source information.

[0077] The correspondence unit 116 creates an additional message (an additional information message or an additional question message) based on the source information and the third reference information. The third reference information is obtained by replacing the question message of the first reference information referred to by the question unit 114 with the additional message.

[0078] Furthermore, when the display instruction receiving unit 111 receives an instruction to display a chat screen via the source website, the response unit 116 displays a speaker icon in association with the response information. For example, the response unit 116 sets a speaker icon to be displayed according to the attributes of the host included in the source information. This speaker icon is the same as the one that the question unit 114 displays in association with a question. Note that the response unit 116 may display a speaker icon in which the host's facial expression is different from that of the speaker icon when asking a question. For example, the response unit 116 may change the facial expression of the speaker icon according to the content of the response information (the emotion of the message).

[0079] FIG. 9 is a diagram showing an example of a chat screen CD displayed on the user terminal 20 upon transition from the referrer website. On the chat screen CD in FIG. 9, the initial information message IM1, the initial question message QM1, the additional information message IM2, and the follow-up question message QM2 are each accompanied by a speaker icon SI (specifically, located to the left of the message). The speaker icon SI in FIG. 9 is a facial photograph (face image) of the host of the referrer website. The initial information message IM1, the initial question message QM1, the additional information message IM2, and the follow-up question message QM2 are each arranged with content and expression that matches the attributes (image) of the host. Note that in FIG. 9, a price suggestion message PM presenting the price of a product or service is displayed between the initial question message QM1 and the initial option message OM1.

[0080] FIG. 10 is a diagram showing an example of a chat screen CD displayed on the user terminal 20 upon transition from a referencing website different from that shown in FIG. 9. The host of the referencing website in FIG. 10 is different from that shown in FIG. 9. On the chat screen CD in FIG. 10, a speaker icon SI is displayed accompanying each of the initial information message IM1, the initial question message QM1, and the additional information message IM2. The speaker icon SI in FIG. 10 is a photograph of the host of the referencing website, different from the speaker icon in FIG. 9. Furthermore, the initial information message IM1, the initial question message QM1, and the additional information message IM2 are each arranged with content and expression that are in line with the attributes of the host different from those in FIG. 9.

[0081] <Data Recording Unit 117> The data recording unit 117 is configured to record various information acquired from the content of chats on the chat screen, user actions, etc. The data recording unit 117 outputs the recorded information or the results of analyzing the information to the terminal of the provider of the product or service handled in the interaction service provided by the server device 10.

[0082] The data recording unit 117 may record the timing of withdrawal when the chat screen is closed on the user terminal 20 in association with the question displayed in the chat field. According to this aspect, by analyzing the timing when the user withdraws from the chat, it is possible to improve the flow of questions for acquiring information from the user.

[0083] The data recording unit 117 may calculate the dropout rate for each question displayed in the chat box based on the dropout timings of multiple users. According to this aspect, it is possible to quantitatively grasp which questions users are likely to drop out of.

[0084] FIG. 11 shows an example of a graph (funnel) showing the dropout rate for each question. In FIG. 11, questions are plotted on the horizontal axis. Question A corresponds to the initial question, and questions are presented to users in the order of Question A, Question B, Question C, etc. The graph shows the number of users to whom the question was displayed (the number of users who responded to the question) above the reference line P, and the graph shows the remaining percentage, which is the number of users to whom the question was displayed divided by the initial number of users (the number of users targeted by the initial question), below the reference line P. The dropout rate is calculated, for example, by the difference in the remaining percentage between two consecutive questions. In the example of FIG. 11, it can be seen that the number of users significantly decreased (the dropout rate increased) after Question I was presented. This indicates that improvements are needed for Question I, such as the question content and timing.

[0085] The data recording unit 117 may store input information input by the user on the chat screen in the user terminal 20. This allows the user to resume chatting based on the previously input information when the user displays the chat screen again on the user terminal 20. The input information is linked to, for example, a user account (domain) and stored in the local storage of the web browser. For example, if the stored input information includes basic information such as name and address, input of the basic information on the next displayed chat screen is omitted.

[0086] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0087] The artificial intelligence unit 120 may include a learning model such as a language model including a generative AI, such as a Transformer or a Recurrent Neural Network (RNN).

[0088] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor algorithms, naive Bayes algorithms, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0089] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of pairs of input data for learning and output data (correct answer data). Furthermore, the language model may not only be trained for a specific task, but may also be a general-purpose model that can be used for a wide range of tasks. The learning model included in the artificial intelligence unit 120 can undergo additional training as transfer learning or fine tuning.

[0090] <Display section 211> The display unit 211 of the user terminal 20 is configured to display on the output unit 25 a screen indicated by the screen data transmitted from the server device 10.

[0091] <Operation acquisition unit 212> The operation acquisition unit 212 of the user terminal 20 is configured to accept operations by the user of the user terminal 20.

[0092] 3. Information Processing Method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0093] Specifically, this information processing method includes a screen display control step, a question step, an answer receiving step, and a response step. In the screen display control step, a chat screen is displayed in the entire control area allocated to the processor out of the display area of ​​the output unit 25 of the user terminal 20. In the question step, a question for the user is displayed in the chat box. In the response receiving step, an answer to the question in the chat box is input from the input unit 24 of the user terminal 20, and the answer is displayed in the chat box. In the response step, response information corresponding to the answer is displayed in the chat box based on the answer and the first reference information.

[0094] 12 is an activity diagram showing an example of the flow of information processing (answer acquisition processing) executed by the information processing system 1. Below, the information processing will be described along with each activity in this activity diagram.

[0095] The response acquisition process begins with a user accessing the chat screen. The user inputs the URL of the chat screen into the user terminal 20, for example, by reading a two-dimensional code (activity A110). The server device 10 receives an access request from the user terminal 20 and outputs the chat screen to the user terminal 20 (activity A120). As a result, the chat screen is displayed on the user terminal 20 (activity A130).

[0096] Next, the server device 10 outputs the initial question to the user terminal 20 (activity A140). As a result, the initial question is displayed in the chat field of the chat screen on the user terminal 20 (activity A150). Note that the chat screen and the initial question may be displayed simultaneously. In other words, the server device 10 may cause the user terminal 20 to display a chat screen on which the initial question is displayed.

[0097] The user inputs an answer to the initial question on the user terminal 20 (activity A160). The server device 10 accepts the answer to the initial question from the user terminal 20 (activity A170). After accepting the answer to the initial question, the server device 10 outputs a follow-up question in accordance with the answer (activity A180). As a result, the follow-up question is displayed in the chat field on the chat screen on the user terminal 20 (activity A190). The user inputs an answer to the follow-up question on the user terminal 20 (activity A200). The server device 10 accepts the answer to the follow-up question from the user terminal 20 (activity A210).

[0098] After receiving the answer to the additional question, the server device 10 determines whether or not to ask another additional question (activity A220). If there is an additional question (if all questions have not been completed), the server device 10 repeats the process from outputting the additional question in activity A180. On the other hand, if there is no additional question (if all questions have been completed), the server device 10 does not output any additional question.

[0099] 4. Effect The operation of this embodiment can be summarized as follows: That is, by displaying a chat screen on the user terminal 20 that is composed only of a chat field and does not include any information display other than the chat field, it is possible to acquire information (such as the time of input) when a user inputs an answer to a question, in association with the state of the chat field. As a result, it is possible to present supplemental information, additional questions, etc., tailored to each individual user, and to perform accurate statistics and analysis of user behavior.

[0100] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention.

[0101] 5.Other In the above embodiment, the server device 10 performs various storage and control operations, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like.

[0102] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0103] At least one of the devices included in the information processing system 1 may be installed outside the country in which the functions of the information processing system 1 are performed.

[0104] It may be provided in the following manner.

[0105] (1) An information processing device comprising a processor, the processor being configured to execute each of the following steps by reading a program: a screen display control step displays a chat screen in the entire control area assigned to the processor of a display area of ​​an output unit of a user terminal, wherein the chat screen includes only a chat field in which information is displayed sequentially in chat format; a question step displays a question for the user in the chat field; a response receiving step accepts input of an answer to the question in the chat field from an input unit of the user terminal and displays the answer in the chat field; and a response step displays response information corresponding to the answer in the chat field based on the answer and reference information, wherein the response information is information to be provided to the user or a question, and the reference information includes a correlation between the answer and the response information.

[0106] According to this aspect, by displaying a chat screen on the user terminal that is composed only of a chat field and does not include any other information display other than the chat field, it is possible to obtain information (such as the time of input) when a user inputs an answer to a question in association with the state of the chat field. As a result, it is possible to present supplemental information, additional questions, etc., tailored to each individual user, and to perform accurate statistics and analysis of user behavior.

[0107] (2) In the information processing device described in (1) above, the processor is configured to further execute the following steps, and in the display instruction receiving step, an instruction to display the chat screen is received by inputting a predetermined URL in the user terminal.

[0108] According to this aspect, the user can be guided to the chat screen without going through other access sites or screens.

[0109] (3) In the information processing device described in (1) or (2) above, the processor is configured to further execute the following steps, and in the data recording step, the timing of withdrawal when the chat screen is closed on the user terminal is recorded in association with the question displayed in the chat box.

[0110] According to this aspect, by analyzing the timing at which a user leaves a chat, it is possible to improve the flow of questions for acquiring information from the user.

[0111] (4) In the information processing device described in (3) above, in the data recording step, the information processing device calculates a dropout rate for each question displayed in the chat box based on the dropout timings of multiple users.

[0112] According to this embodiment, it is possible to quantitatively grasp what kind of questions users are likely to drop out of the conversation.

[0113] (5) In the information processing device described in any one of (1) to (4) above, the reference information includes a writing model that has been trained to be able to use the answer as input and the corresponding information as output, and in the corresponding step, the answer is input to the writing model and the writing model is caused to output the corresponding information.

[0114] According to this aspect, it is possible to generate response information based on examples of response information (supplementary information, additional questions, etc.) to a large number of answers, or based on natural language processing.

[0115] (6) In the information processing device described in (5) above, the writing model is trained to be able to input the answer and supplementary information related to the answer and output the corresponding information, wherein the supplementary information includes at least one of the input speed of the answer, the directionality of the answer, and the number of times the answer is input for one question, and in the corresponding step, the answer and the supplementary information are input into the writing model and the writing model is caused to output the corresponding information.

[0116] According to this aspect, it is possible to respond to the user's preferences, personality, etc. (by presenting supplementary information, additional questions, etc.), thereby preventing the user from leaving before all questions are completed.

[0117] (7) In the information processing device according to any one of (1) to (6) above, in the response step, the more times the answer to one question is input, the more questions are asked to the user.

[0118] According to this aspect, in a chat intended to obtain answers from users, it is possible to adjust the number of questions asked according to the user's loyalty.

[0119] (8) In the information processing device described in any one of (1) to (7) above, the processor is configured to further execute the following steps: in the display instruction receiving step, a display instruction for the chat screen is received from the user terminal via a website displayed on the user terminal; in the information acquisition step, source information regarding the website that received the display instruction is acquired; in the screen display control step, the chat screen is displayed on the user terminal based on the display instruction; in the questioning step, at least one of the content and expression of a question to the user is adjusted based on the source information; and in the response step, at least one of the content and expression of the response information is adjusted based on the source information.

[0120] According to this aspect, a chat linked to the website from which the chat screen was accessed can be developed on the chat screen, thereby providing the user with a consistent experience from the website from which the chat screen was accessed.

[0121] (9) In the information processing device described in (8) above, in the questioning step, a speaker icon corresponding to the source information is displayed in association with a question to the user, and in the response step, the speaker icon is displayed in association with the response information.

[0122] According to this aspect, a speaker icon representing the host, administrator, etc. of the source website is displayed on the chat screen, thereby improving the consistency of the user experience from the source website to the chat screen.

[0123] (10) An information processing method, comprising steps executed by an information processing device according to any one of (1) to (9) above.

[0124] (11) A program for causing a computer to execute each step of the information processing device described in any one of (1) to (9) above. Of course, this is not the case. [Explanation of symbols]

[0125] 1: Information processing system 2: Communication line 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: User terminal 21: Control unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 111: Display instruction reception unit 112: Information acquisition department 113: Screen display control unit 114: Questions 115: Answer Reception Department 116: Corresponding department 117: Data recording section 120: Artificial Intelligence Department 211: Display section 212: Operation acquisition section AM: Reply message CD: Chat screen CF: Chat box IA: Input Area IM1: Initial information message IM2: Additional information message OM1: Initial Choice Message OM2: Additional Choice Message PM: Price message QM1: Initial question message QM2: Additional question message SB: Send button SI:Speaker Icon

Claims

1. An information processing device, a processor; The processor is configured to execute the following steps by reading the program: In the screen display control step, a chat screen is displayed in the entire control area allocated to the processor among the display areas of the output unit of the user terminal, wherein the chat screen includes only a chat field in which information is sequentially displayed in a chat format; In the question step, a question for the user is displayed in the chat box; In the answer receiving step, an input of an answer to the question in the chat box is received from an input unit of the user terminal, and the answer is displayed in the chat box; In the response step, response information corresponding to the answer is displayed in the chat box based on the answer and reference information, wherein the response information is information to be provided to the user or a question, and the reference information includes a correlation between the answer and the response information.

2. 2. The information processing device according to claim 1, The processor is further configured to perform the steps of: In the display instruction receiving step, the information processing device receives an instruction to display the chat screen by inputting a predetermined URL into the user terminal.

3. 2. The information processing device according to claim 1, The processor is further configured to perform the steps of: In the data recording step, the information processing device records the timing at which the chat screen is closed on the user terminal in association with the question displayed in the chat field.

4. 4. The information processing device according to claim 3, In the data recording step, an information processing device calculates a dropout rate for each question displayed in the chat box based on the dropout timings of a plurality of users.

5. 2. The information processing device according to claim 1, the reference information includes a sentence creation model that has been trained to use the answer as an input and the corresponding information as an output; In the corresponding step, the answer is input to the writing model, and the writing model is caused to output the corresponding information.

6. 6. The information processing device according to claim 5, the writing model is trained to be able to use the answer and supplemental information related to the answer as input and to use the corresponding information as output, wherein the supplemental information includes at least one of an input speed of the answer, a directionality of the answer, and a number of times the answer is input for one question; In the corresponding step, the answer and the supplementary information are input to the writing model, and the writing model is caused to output the corresponding information.

7. 2. The information processing device according to claim 1, In the responding step, the information processing device increases the number of questions posed to the user as the number of times the answer to one question is input increases.

8. 2. The information processing device according to claim 1, The processor is further configured to perform the steps of: In the display instruction receiving step, a display instruction for the chat screen is received from the user terminal via a website displayed on the user terminal; In the information acquisition step, source information regarding the website that has received the display instruction is acquired; In the screen display control step, the chat screen is displayed on the user terminal based on the display instruction, In the questioning step, at least one of content and expression of a question to the user is adjusted based on the inflow source information; In the responding step, the information processing device adjusts at least one of the content and expression of the response information based on the source information.

9. 9. The information processing device according to claim 8, In the questioning step, a speaker icon corresponding to the source information is displayed in association with the question to the user; In the corresponding step, the information processing device displays the speaker icon in association with the corresponding information.

10. An information processing method, comprising: An information processing method, comprising the steps executed by the information processing device according to any one of claims 1 to 9.

11. A program, A program for causing a computer to execute each step of the information processing device according to any one of claims 1 to 9.

Images