SCENARIO GENERATION DEVICE, SCENARIO GENERATION METHOD, AND SCENARIO GENERATION PROGRAM

Abstract

To reduce the burden of generating scenarios to be executed by a chatbot. [Solution] A scenario generation device having a scenario generation unit that generates a scenario that specifies a series of conversational content to be executed by a chatbot to guide a user to purchase a product or service, wherein the scenario is composed of a plurality of objects that divide the series of conversational content according to purpose, and each of the plurality of objects includes a plurality of conversational sentences with a specified order.

Description

[Technical field]

[0001] The present invention relates to a scenario generation device, a scenario generation method, and a scenario generation program. [Background technology]

[0002] Conventionally, chatbots, which are communication robots that can automatically hold conversations with users over chat, have been known. In recent years, efforts have been made to utilize chatbot technology to provide information that is useful for decision-making such as purchasing various products and services, and to realize procedures required for purchases through automated conversations. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-77779 Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional technology, in order to realize a conversation with a user by a chatbot, a designer (communication designer) had to manually generate a scenario in advance that specifies a series of conversations with the user (see Patent Document 1). In such a scenario, the designer had to specify a conditional branch structure (tree-type structure) according to the expected content of the user's conversation so that the next conversation returned by the chatbot would be variable depending on the content of the conversation from the user, and specify a series of conversation flows separately for each condition. Depending on the purpose of using the chatbot, the scenario created in this way can become extremely complex, so the workload of preparing the scenario increases. In addition, in such a scenario, it is necessary to specify the conversation located downstream of the branch point without omission every time a conditional branch is added, so that overlapping conversation sentences also have to be defined individually in the conversation branched for each condition. For this reason, even when changing part of the conversation content included in the scenario, multiple corrections are required.

[0005] The present invention has been made in consideration of these circumstances, and one of its objectives is to provide a scenario generation device, a scenario generation method, and a program that can reduce the burden of generating scenarios to be executed by chatbots. [Means for solving the problem]

[0006] One aspect of the present invention is a scenario generation device that includes a scenario generation unit that generates a scenario that specifies a series of conversational content to be executed by a chatbot, such as for guiding a user to purchase a product or service, wherein the scenario is composed of a plurality of objects that divide the series of conversational content according to purpose, and each of the plurality of objects includes a plurality of conversational sentences in a specified order. Effect of the Invention

[0007] According to one aspect of the present invention, it is possible to reduce the load of generating a scenario to be executed by a chatbot. A scenario is composed of a plurality of objects in which a series of conversational content is divided according to purpose, and conversational text can be set for each of these objects. This simplifies the setting of conversational text included in a scenario. Also, overlapping conversational text that arises according to conversation branching can be set all at once. Also, when changing conversational text included in a scenario, it is necessary to modify only the necessary parts of the conversational text set for each object, improving maintainability. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a diagram illustrating an example of a configuration for implementing a chatbot service according to an embodiment. [Diagram 2] FIG. 2 is a functional block diagram showing an example of a configuration of a chatbot server 1 according to the embodiment. [Diagram 3] A figure showing an example of object type scenario data SD relating to the embodiment. [Figure 4] 1 is a functional block diagram showing an example of a configuration of a user terminal device 100 according to an embodiment. [Diagram 5] FIG. 2 is a diagram showing an example of a conversation screen P1 displayed on a user terminal device 100 according to the embodiment. [Figure 6] 11 is a flowchart showing an example of a sequence of steps in a scenario generation process performed by the chatbot server 1 according to the embodiment. [Figure 7] FIG. 2 is a diagram showing an example of an object structure setting screen P2 displayed on the operation terminal device 200 according to the embodiment. [Figure 8] FIG. 13 is a diagram showing an example of an entry object setting screen P3 displayed on the operation terminal device 200 according to the embodiment. [Figure 9] FIG. 13 is a diagram showing an example of a question object setting screen P4 displayed on the operation terminal device 200 according to the embodiment. [Figure 10]FIG. 13 is a diagram showing an example of an offer object setting screen P5 displayed on the operation terminal device 200 according to the embodiment. [Figure 11] FIG. 11 is a sequence diagram showing an example of a scenario display process according to the embodiment. [Figure 12] FIG. 2 is a diagram showing an example of user data UD according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, with reference to the drawings, an embodiment of a scenario generation device, a scenario generation method, and a scenario generation program of the present invention will be described. The scenario generation device of the embodiment can reduce the load required to generate a scenario that specifies a series of conversational contents to be executed by a chatbot, for example, to guide a user to purchase a product or service. A scenario is composed of multiple objects that classify (summarize) the series of conversational contents according to purpose (function, role). For example, a scenario has a structure in which multiple objects are associated with each other and arranged in a tree shape. Each of the multiple objects includes multiple conversational sentences in a specified order.

[0010] [Chatbot service] FIG. 1 is a diagram showing an example of a configuration for realizing a chatbot service according to an embodiment. In the chatbot service, a chatbot automatically converses with a user, such as a business providing a product or service (hereinafter referred to as "product, etc."), listens to the user's hobbies, preferences, and personal background, and proposes information on products, etc., appropriate for the user. Businesses include, for example, cosmetics sellers, food sellers, hospitals, human resources service providers, financial institutions, insurance companies, real estate agents, and communication companies. The chatbot service is realized mainly by a chatbot server 1. The chatbot server 1 communicates with, for example, one or more service servers 3, one or more message servers 5, one or more user terminal devices 100, and one or more operation terminal devices 200 via a communication network NW. The communication network NW includes, for example, the Internet, a LAN (Local Area Network), a wireless base station, a provider device, and the like.

[0011] [Device configuration] <Chatbot Server 1> The chatbot server 1 provides a function for generating a scenario to a designer D who operates an operation terminal device 200. The chatbot server 1 also provides a chatbot service to a user U who operates a user terminal device 100. FIG. 2 is a functional block diagram showing an example of a configuration of the chatbot server 1 according to an embodiment. The chatbot server 1 includes, for example, a communication unit 11, a control unit 13, and a storage unit 15. The chatbot server 1 is an example of a "scenario generation device." The communication unit 11 is a communication interface for connecting to a communication network NW. The communication unit 11 is, for example, a network interface card.

[0012] The control unit 13 includes, for example, an acquisition unit 131, a conversation generation unit 133, a transmission unit 135, a scenario generation unit 137, and a display control unit 139. The components of the control unit 13 are realized by, for example, a hardware processor such as a CPU executing a program (software). Some or all of these components may be realized by hardware such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a graphics processing unit (GPU), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (non-transitory computer-readable storage medium) such as a hard disk drive (HDD) or a flash memory, or may be stored in a removable storage medium (non-transitory computer-readable storage medium) such as a DVD or a CD-ROM, and installed in the storage device by mounting the storage medium in a drive device.

[0013] The acquisition unit 131 acquires various information (data) from each of the service server 3, the user terminal device 100, and the operation terminal device 200 via the communication network NW. For example, the acquisition unit 131 acquires information indicating conversation content input in response to an operation by a user U from the user terminal device 100. Also, for example, the acquisition unit 131 acquires instruction information regarding scenario generation input in response to an operation by a designer D from the operation terminal device 200. The acquisition unit 131 is an example of an "acquisition unit." The acquisition unit 131 acquires setting instructions from the scenario designer for a plurality of objects and a plurality of conversation sentences included in each of the plurality of objects.

[0014] The conversation generation unit 133 generates a conversation sentence to be transmitted to the user terminal device 100 (a conversation sentence to be presented to the user) based on information indicating the conversation content of the user U acquired from the user terminal device 100 and the object type scenario data SD pre-stored in the storage unit 15. The conversation generation unit 133 is an example of a "conversation generation unit".

[0015] The transmission unit 135 transmits conversation sentence data indicating the conversation sentence generated by the conversation generation unit 133 to the user terminal device 100. The transmission unit 135 is an example of a "transmission unit".

[0016] The scenario generating unit 137 generates a scenario based on setting instructions related to scenario generation acquired from the operation terminal device 200. The scenario generating unit 137 is an example of a “scenario generating unit.” The scenario generating unit 137 corrects dialogue sentences for each of a plurality of objects included in the scenario.

[0017] The display control unit 139 generates information for displaying various operation screens for generating a scenario, transmits the information to the operation terminal device 200, and causes the operation terminal device 200 to display the various operation screens. The display control unit 139 is an example of a "display control unit."

[0018] The storage unit 15 is a HDD, a flash memory, a RAM (Random Access Memory), etc. The storage unit 15 may be a NAS (Network Attached Storage) device that the chatbot server 1 can access via a network. The storage unit 15 stores information such as object type scenario data SD and user data UD. The object type scenario data SD specifies a series of conversation contents for realizing a conversation with a user. The user data UD is saved data such as answers obtained from a user in a conversation with the user.

[0019] FIG. 3 is a diagram showing an example of object type scenario data SD according to an embodiment. The object type scenario data SD is set, for example, in response to an operation by a designer D via an operation terminal device 200. The object type scenario data SD includes one or more scenarios SC defined for each business operator. Each scenario SC is composed of multiple objects. The objects include, for example, an entry object OB1, a question object OB2, an offer object OB3, a retention object OB4, etc. The multiple objects are not limited to these four objects, and may include other objects set according to other functions or purposes.

[0020] The entry object OB1 defines an initial conversation text to be carried out when starting a conversation with a user. The entry object OB1 includes, for example, a message such as a greeting, a question text for determining the attributes of the user, and the like. The question object OB2 defines a conversation text (question text) for requesting an answer from the user for determining a product or the like to be proposed to the user. The offer object OB3 defines a conversation text (proposal text) content for proposing a product or the like to the user based on the user's answer collected by the question object OB2. The retention object OB4 defines a conversation text for drawing a user who did not purchase a product or the like back into the conversation. The retention object OB4 includes, for example, a conversation text for push notification set for each user.

[0021] <Service Server 3> The service server 3 is managed by a business that provides products and the like. The service server 3 provides the user terminal device 100 with a site such as a homepage where the user can complete the purchase procedure for the product and the like. When the user U performs a preset trigger operation on this site, a process for providing a chatbot service is started. The trigger operation is, for example, pressing a button that starts the chatbot service and is displayed in a pop-up on the site.

[0022] <Message Server 5> The message server 5 provides a message service (chat service) that realizes a conversation function by sending and receiving messages to the user terminal device 100, the chatbot server 1, and the service server 3. The message server 5 provides the user terminal device 100 with a conversation application that can be installed in the user terminal device 100, and the user terminal device 100 executes this conversation application to send and receive messages with other user terminal devices 100 and various servers. The message server 5 also provides an API (Application Programming Interface) that enables the use of the message service from an external device (server), and the chatbot server 1 and the service server 3 send and receive messages with the user terminal device 100 by using this API.

[0023] <User Terminal Device 100> The user terminal device 100 is operated by a user U who uses a product or the like provided by a business operator. The user terminal device 100 is, for example, a portable terminal device such as a smartphone or a tablet terminal. FIG. 4 is a functional block diagram showing an example of the configuration of the user terminal device 100 according to the embodiment. The user terminal device 100 includes, for example, a communication unit 101, a display unit 103, an operation unit 105, a control unit 107, and a storage unit 109.

[0024] The communication unit 101 is a wireless communication module that performs wireless communication with a wireless base station connected to the communication network NW. The communication unit 101 communicates with the chatbot server 1, the service server 3, the message server 5, etc., via the wireless base station. The display unit 103 is a display device such as a liquid crystal display device. The operation unit 105 is an input interface that accepts operation instructions from the user U. The display unit 103 and the operation unit 105 may be configured as touch panel displays.

[0025] The control unit 107 controls the overall operation of the user terminal device 100. The functions of the control unit 13 are realized, for example, by a hardware processor such as a CPU executing a program (software). The control unit 107 starts a conversation application (program) AP stored in the storage unit 109 to realize a conversation function via a network. The conversation application may be an application dedicated to conversation, or may also have other functions (such as a call function, an image upload function, and a message upload function). For example, the conversation application may be an application on the business side that is provided by a business providing products and installed in the user terminal device 100 and has a conversation function. Alternatively, the conversation application may be realized using a general-purpose application program such as a web browser. For example, the conversation application may be realized by a chat function on the business side homepage provided by a service server 3 managed by the business.

[0026] Fig. 5 is a diagram showing an example of a conversation screen P1 displayed on the user terminal device 100 according to the embodiment. In the example of Fig. 5, a chatbot service provided by a business A is started, and a conversation screen P1 is shown in which a greeting message and questions are sent to a user U as a scenario. By having a conversation with a chatbot according to such a scenario, the user U can receive information suited to the user and suggestions for products, etc.

[0027] <Operation Terminal Device 200> The operation terminal device 200 is operated by a designer D who designs a scenario for a chatbot service. The operation terminal device 200 is, for example, a personal computer, a smartphone, a tablet terminal, etc. The operation terminal device 200 has at least a display function, an input function, a storage function, etc.

[0028] [Processing flow] <Scenario generation process> Next, various processes executed in the chatbot service will be described. First, the process on the operation side where the designer D generates a scenario will be described. FIG. 6 is a flowchart showing an example of a series of scenario generation processes by the chatbot server 1 according to the embodiment. The process shown in FIG. 6 is started, for example, when the designer D operates the operation terminal device 200 to input an instruction to start scenario generation, and the chatbot server 1 receives this start instruction.

[0029] (Step S101) First, the display control unit 139 of the chatbot server 1 causes the operation terminal device 200 to display an object structure setting screen. Then, the acquisition unit 131 acquires, from the operation terminal device 200, setting information input by the designer D to the object structure setting screen displayed on the operation terminal device 200. The scenario generation unit 137 sets the object structure according to this setting information and saves it in the storage unit 15.

[0030] FIG. 7 is a diagram showing an example of an object structure setting screen P2 displayed on the operation terminal device 200 according to the embodiment. The designer D can set the object structure by operating the input interface (keyboard, mouse, etc.) of the operation terminal device 200. The object structure specifies the type of objects included in each scenario, the number of objects, how the objects are connected to each other, etc. In the example shown in FIG. 7, an object structure including an entry object OB1, a question object (male) OB2-1 and a question object (female) OB2-2 each connected to the entry object OB1, an offer object (male) OB3-1 connected to the question object (male) OB2-1, and an offer object (female) OB3-2 connected to the question object (female) OB2-2 is shown. By pressing the object addition button BT1, it is possible to specify the type of object and set it at any position in the object structure. In the scenario, the conversation will proceed from the top to the bottom of the object structure set in this way.

[0031] (Step S103) Returning to FIG. 6, next, the display control unit 139 causes the operation terminal device 200 to display an entry object setting screen. Next, the acquisition unit 131 acquires, from the operation terminal device 200, setting information input by the designer D to the entry object setting screen displayed on the operation terminal device 200. The scenario generation unit 137 sets the conversation content included in the entry object according to this setting information and stores it in the storage unit 15. The process of this step S103 is executed, for example, when the designer D instructs editing of the entry object OB1 via the input interface on the object structure setting screen P2 displayed on the operation terminal device 200 as shown in FIG. 7 (for example, when the icon of the entry object OB1 is double-clicked).

[0032] FIG. 8 is a diagram showing an example of an entry object setting screen P3 displayed on the operation terminal device 200 according to the embodiment. The designer D can set the conversation content included in the entry object OB1 by operating the input interface of the operation terminal device 200. The conversation content is set by a plurality of actions. The actions include, for example, an action indicating the setting of the site of the business side of the transition source and a connection relationship with other objects, an action to display a simple message such as a greeting, an action to display an image, an action to display a conversation requesting an answer from the user such as a question, and the like. FIG. 8 shows an example in which actions AC1-1 to AC1-7 are set in order as the conversation content included in the entry object OB1. The action AC1-1 is an action indicating the setting of the site of the business side of the transition source. The action AC1-2 is an action to display a greeting, and the action AC1-3 is an action to display an image 1. The action AC1-4 is an action to display a question. The action AC1-5 is an action to display an answer option to the question of the action AC1-4. The actions AC1-6 and AC1-7 are actions indicating the setting of another object of the connection destination.

[0033] In the example shown in FIG. 8, action AC1-5 is described as displaying answer options to the question of action AC1-4 (smart reply function), but it is also possible to display a free input field for user U to answer the question.

[0034] (Step S105) Returning to FIG. 6, next, the display control unit 139 causes the operation terminal device 200 to display a question object setting screen. Then, the acquisition unit 131 acquires, from the operation terminal device 200, setting information input by the designer D to the question object setting screen displayed on the operation terminal device 200. The scenario generation unit 137 sets the content of the question object in accordance with this setting information and stores it in the storage unit 15. The process of this step S105 is executed, for example, when the designer D instructs editing of the question object OB2 via the input interface on the object structure setting screen P2 displayed on the operation terminal device 200 as shown in FIG. 7 (for example, when the icon of the question object OB2 is double-clicked).

[0035] FIG. 9 is a diagram showing an example of a question object setting screen P4 displayed on the operation terminal device 200 according to the embodiment. The designer D can set the conversation content included in the question object OB2 by operating the input interface of the operation terminal device 200. FIG. 9 shows an example in which actions AC2-1 to AC2-7 are set in order as the conversation content included in the question object. The action AC2-1 is an action indicating a connection setting with an entry object OB1, which is another object. The action AC2-2 is an action for displaying the first question. The action AC2-3 is an action for displaying answer options to the question of the action AC2-2. The action AC2-4 is an action for displaying the second question. The action AC2-5 is an action for displaying answer options to the question of the action AC2-4. The action AC2-6 is an action for displaying the third question, etc. Thereafter, the action for displaying answer options to the third question, etc. can be set arbitrarily. Action AC2-7 is an action that indicates the setting of another object as a connection destination.

[0036] In addition, in the question object OB2, the content of the next question may be made variable depending on the answer to the question from the user U. With such a configuration, it becomes possible to ask the user U personalized questions and to suggest subsequent products, etc.

[0037] (Step S107) Returning to FIG. 6, next, the display control unit 139 causes the operation terminal device 200 to display an offer object setting screen. Then, the acquisition unit 131 acquires, from the operation terminal device 200, setting information input by the designer D to the offer object setting screen displayed on the operation terminal device 200. The scenario generation unit 137 sets the conversation content included in the offer object according to this setting information and stores it in the storage unit 15. The processing of this step S107 is executed, for example, when the designer D instructs editing of the offer object OB3 via the input interface on the object structure setting screen P2 displayed on the operation terminal device 200 as shown in FIG. 7 (for example, when the icon of the offer object OB3 is double-clicked).

[0038] FIG. 10 is a diagram showing an example of an offer object setting screen P5 displayed on the operation terminal device 200 according to the embodiment. The designer D can set the conversation content included in the offer object OB3 by operating the input interface of the operation terminal device 200. FIG. 10 shows an example in which actions AC3-1 to AC3-3 are set in order as the conversation content included in the offer object OB3. The action AC3-1 is an action indicating a connection setting with a question object OB2, which is another object. The action AC3-2 is an action for displaying a message indicating that a product or the like is proposed. The action AC3-3 is an action for displaying proposed products A to D corresponding to the message of the action AC3-2. That is, the proposal text included in the offer object OB3 is defined to be variable according to the answer from the user U to the question text included in the question object OB2. That is, the proposal text included in the offer object OB3 is defined to be variable according to the answer or reaction from the user U to the question text included in the other object arranged above the offer object, even in the case where the proposal text does not visually form a tree structure (tree-type structure), based on each option included in each object.

[0039] (Step S109) Returning to FIG. 6, next, the display control unit 139 causes the operation terminal device 200 to display a retention object setting screen. Then, the acquisition unit 131 acquires, from the operation terminal device 200, setting information input by the designer D to the retention object setting screen displayed on the operation terminal device 200. The scenario generation unit 137 stores the setting contents of the retention object in the storage unit 15 according to this setting information. With this, the processing of this flowchart is completed.

[0040] <Scenario display process> Next, the process on the service side where the user U experiences the chatbot service will be described. Fig. 11 is a sequence diagram showing an example of a scenario display process according to the embodiment. Here, the process will be described by taking as an example a situation where the user U operates the user terminal device 100 and browses a provider's website using a web browser.

[0041] First, when a trigger operation is performed on a site in response to an operation by a user U, the user terminal device 100 transmits a trigger operation signal indicating that a trigger operation has been performed to the service server 3 (step S201). The trigger operation is, for example, pressing a button that starts a chatbot service displayed in a pop-up on the site.

[0042] Next, in response to the trigger operation signal received from the user terminal device 100, the service server 3 transmits a conversation start instruction for starting a series of conversations according to a scenario in the chatbot service to the chatbot server 1 (step S203).

[0043] Next, when the conversation generation unit 133 of the chatbot server 1 receives a conversation start instruction from the service server 3, it generates a conversation based on the object type scenario data SD stored in the storage unit 15 (step S205). Here, for example, the conversation generation unit 133 generates the first conversation (first conversation) of the entry object OB1 that is set as the conversation to be displayed first in the scenario associated with the business.

[0044] Next, the transmitting unit 135 of the chatbot server 1 transmits a request to transmit conversation data indicating the generated conversation to the message server 5 (step S207). The chatbot server 1 transmits the request to transmit conversation data to the message server 5, for example, by using an API provided by the message server 5. The message server 5, which has received the request to transmit conversation data from the chatbot server 1, transmits the conversation data to the user terminal device 100 (step S209).

[0045] Next, the user terminal device 100 starts the conversation application AP based on the conversation data received from the chatbot server 1 via the message server 5, and displays the conversation text based on the conversation data on the display unit 103 (step S211). This allows the user U to check the conversation text automatically sent from the chatbot server 1.

[0046] Next, if the conversation data received from the chatbot server 1 via the message server 5 is a question requesting an answer, the user terminal device 100 transmits answer data indicating the answer determined in response to the operation of the operation unit 105 by the user U to the message server 5 (step S213). Note that, if the conversation data received from the chatbot server 1 via the message server 5 is a simple message or image not requesting an answer, the user terminal device 100 may transmit receipt confirmation data indicating receipt to the message server 5. Having received the answer data from the user terminal device 100, the message server 5 transmits this answer data to the chatbot server 1 (step S215).

[0047] Next, the acquisition unit 131 of the chatbot server 1 stores the answer data received from the user terminal device 100 via the message server 5 in the user data UD of the storage unit 15 (step S217). Fig. 12 is a diagram showing an example of the user data UD according to the embodiment. The user data UD stores answer data acquired from users in each object, linked to a user ID that identifies each user.

[0048] A series of process QA from steps S205 to S217 above is repeatedly executed according to the scenario. That is, the transmission of conversations and the reception of responses of objects set in sequence in the scenario are repeatedly executed. Finally, when the acquisition unit 131 of the chatbot server 1 receives response data from the user U to the conversation proposing a product or the like in the offer object OB3, the transmission unit 135 transmits purchase request data indicating a desire to purchase to the service server 3 (step S219).

[0049] When the service server 3 receives the purchase request data from the chatbot server 1, it generates a purchase screen for performing payment processing and the like (step S221). Next, the service server 3 transmits purchase screen data for displaying the generated purchase screen to the user terminal device 100 (step S223).

[0050] Next, the user terminal device 100 displays the purchase screen on the display unit 103 based on the purchase screen data received from the service server 3 (step S225). Next, the user terminal device 100 transmits the purchase data input in response to the operation of the operation unit 105 by the user U to the service server 3 (step S227).

[0051] Next, the service server 3 performs purchase processing including settlement processing, shipping processing, etc. based on the purchase data received from the user terminal device 100 (step S229). With this, the processing in this sequence diagram ends.

[0052] Each object may be set so that a different conversation is displayed depending on the type of conversation application (type of platform).

[0053] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0054] 1... chatbot server, 11... communication unit, 13... control unit, 15... memory unit, 131... acquisition unit, 133... conversation generation unit, 135... transmission unit, 137... scenario generation unit, 139... display control unit, 100... user terminal device, 101... communication unit, 103... display unit, 105... operation unit, 107... control unit, 109... memory unit, 200... operation terminal device, NW... communication network

Claims

1. A scenario generation device including a scenario generation unit that generates a scenario that defines a series of conversation contents to be executed by a chatbot to induce a user to purchase a product or service, The scenario is composed of a plurality of objects that divide the series of conversation contents according to purpose, The plurality of objects include at least an entry object that defines an initial conversation with the user, a question object that defines a question to which the user is requested to answer, an offer object that defines a proposal for the product or service to the user, and a retention object that defines a conversation for drawing the user who did not purchase the product or service back into the conversation; each of the plurality of objects includes a plurality of dialogue sentences in a specified order; The scenario generation device comprises: a display control unit that displays on a display unit an operation screen for receiving inputs of a first setting instruction from a scenario designer regarding an object structure that specifies the types and number of objects that constitute the scenario and the connections between the objects, and a second setting instruction regarding the content and order of the plurality of conversation sentences included in each of the objects included in the object structure specified in the first setting instruction; an acquisition unit that acquires the first setting instruction and the second setting instruction input to the operation screen; Further equipped with the scenario generation unit generates the scenario based on the acquired first setting instruction and the acquired second setting instruction. Scenario generation device.

2. The proposal text included in the offer object is defined so that case classification based on each option included in each object can be changed even in the case where the proposal text does not visually form a tree structure in response to an answer or reaction from the user to a question text included in another object placed above the offer object. The scenario generating device according to claim 1 .

3. the scenario generation unit modifies the dialogue for each of the plurality of objects included in the scenario. The scenario generating device according to claim 1 .

4. a conversation generation unit that generates conversation sentences to be presented to the user based on the scenario; a transmission unit that transmits conversation sentence data indicating the generated conversation sentence to a terminal device of the user; Further comprising: The scenario generating device according to claim 1 .

5. The offer object includes a plurality of offer objects connected to the question object, the scenario generation unit generates the scenario based on the acquired second setting instruction such that each of the plurality of objects includes the suggestion sentence that is defined to be variable depending on an answer from the user to the question sentence included in the question object. The scenario generating device according to claim 1 .

6. The scenario generation unit generates the scenario based on the acquired second setting instruction such that the offer object includes the suggestion text indicating options for the product or service, the options being defined to be variable depending on an answer from the user to the question text included in the question object. The scenario generating device according to claim 1 .

7. The scenario generation unit generates the scenario having the object structure including the entry object, a plurality of question objects each connected to the entry object, and a plurality of offer objects each connected to the plurality of question objects, based on the acquired first setting instruction. The scenario generating device according to claim 1 .

8. The computer A scenario generation method for generating a scenario that specifies a series of conversation contents to be executed by a chatbot to induce a user to purchase a product or service, comprising: The scenario is composed of a plurality of objects that divide the series of conversation contents according to purpose, The plurality of objects include at least an entry object that defines an initial conversation with the user, a question object that defines a question to which the user is requested to answer, an offer object that defines a proposal for the product or service to the user, and a retention object that defines a conversation for drawing the user who did not purchase the product or service back into the conversation; each of the plurality of objects includes a plurality of dialogue sentences in a specified order; The scenario generation method further comprises the step of: displaying, on a display unit, an operation screen for receiving input from a scenario designer of a first setting instruction regarding an object structure that defines the types, number, and connections between objects constituting the scenario, and a second setting instruction regarding the contents and order of the plurality of conversation sentences included in each of the objects included in the object structure specified in the first setting instruction; acquiring the first setting instruction and the second setting instruction inputted to the operation screen; generating the scenario based on the acquired first setting instruction and the acquired second setting instruction; Scenario generation method.

9. On the computer, A scenario generation program for generating a scenario that defines a series of conversation contents to be executed by a chatbot and guide a user to purchase a product or service, The scenario is composed of a plurality of objects that divide the series of conversation contents according to purpose, The plurality of objects include at least an entry object that defines an initial conversation with the user, a question object that defines a question to which the user is requested to answer, an offer object that defines a proposal for the product or service to the user, and a retention object that defines a conversation for drawing the user who did not purchase the product or service back into the conversation; each of the plurality of objects includes a plurality of dialogue sentences in a specified order; The scenario generation program further causes the computer to displaying, on a display unit, an operation screen for receiving input from a scenario designer of a first setting instruction regarding an object structure that defines the types, number, and connections between objects constituting the scenario, and a second setting instruction regarding the contents and order of the plurality of conversation sentences included in each of the objects included in the object structure specified in the first setting instruction; acquiring the first setting instruction and the second setting instruction inputted to the operation screen; generating the scenario based on the acquired first setting instruction and the acquired second setting instruction; Scenario generator.

Images