Information processing device, information processing method, program, and recording medium

Abstract

Reduce the cost of generating static dialogue scenarios. [Solution] The information processing device (1) comprises an acquisition unit (11) that acquires an information group including a plurality of pieces of presentation information to be presented to a user, a clustering unit (12) that clusters the plurality of pieces of presentation information by referring to related information that is directly or indirectly associated with at least one of the plurality of pieces of presentation information, and a generation unit (13) that generates a static dialogue scenario including the plurality of pieces of presentation information by referring to the results of the clustering by the clustering unit.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, a program, and a recording medium for generating a static dialogue scenario. [Background technology]

[0002] Automated response systems (also called chatbots) that automatically engage in dialogue with users are known. Chatbots can be broadly divided into two types: those that generate responses using a trained generative model, and those that respond according to a predetermined static dialogue scenario. While the former type is capable of flexible responses based on user input, it has been noted that it may present incorrect information (the so-called hallucination problem). For this reason, in situations where accurate information needs to be conveyed to the user, the latter type, i.e., chatbots that respond according to a predetermined static dialogue scenario (also called scenario-based chatbots), are used.

[0003] As an example of a scenario-based chatbot, Patent Document 1 discloses a technology for generating a static dialogue scenario including partial dialogue scenarios specified by labels. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-310628 Summary of the Invention [Problem to be solved by the invention]

[0005] When using a scenario-based chatbot, it is necessary to acquire in advance information that can be presented to a user (also called presentation information) and generate a static dialogue scenario in advance using the presentation information. Therefore, as the amount of presentation information increases, there is a problem that the cost, including the developer's effort, for generating the static dialogue scenario increases rapidly, and this problem has been difficult to solve even with the technology described in Patent Document 1.

[0006] An object of one aspect of the present disclosure is to provide a technology that can reduce the cost of generating static dialogue scenarios. [Means for solving the problem]

[0007] In order to solve the above problem, an information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires an information group including a plurality of pieces of presentation information to be presented to a user, a clustering unit that clusters the plurality of pieces of presentation information by referring to related information that is directly or indirectly associated with at least one of the plurality of pieces of presentation information, and a generation unit that generates a static dialogue scenario including the plurality of pieces of presentation information by referring to the results of the clustering by the clustering unit.

[0008] In order to solve the above problem, an information processing method according to one embodiment of the present disclosure includes an acquisition step in which one or more processors acquire an information group including a plurality of pieces of presentation information to be presented to a user; a clustering step in which the plurality of pieces of presentation information are clustered by referring to related information that is directly or indirectly associated with at least any of the plurality of pieces of presentation information; and a generation step in which a static dialogue scenario including the plurality of pieces of presentation information is generated by referring to the results of the clustering in the clustering step.

[0009] The information processing device according to each aspect of the present invention may be realized by a computer. In this case, the information processing device program that causes the computer to operate as each part (software element) of the information processing device to realize the information processing device on the computer, and the computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention. [Effects of the Invention]

[0010] According to one aspect of the present disclosure, the cost of generating static dialogue scenarios can be reduced. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a configuration of an information processing system according to a first embodiment. [Figure 2] FIG. 3 is a diagram illustrating an example of information referred to by the information processing device according to the first embodiment. [Figure 3] 4 is a flowchart showing an example of a flow of processing executed by the information processing device according to the first embodiment. [Figure 4] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 5] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 6] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 7] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 8] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 9] FIG. 2 is a diagram for explaining processing by the information processing device according to the first embodiment. [Figure 10] FIG. 2 is a diagram showing an example of a static dialogue scenario generated by the information processing device according to the first embodiment. [Figure 11] 4 is a flowchart showing a specific example of the flow of processing executed by the information processing device according to the first embodiment. [Figure 12] 4 is a flowchart showing a specific example of the flow of processing executed by the information processing device according to the first embodiment. [Figure 13] FIG. 3 is a diagram showing an example of display screen information generated by the information processing device according to the first embodiment. [Figure 14] FIG. 2 is a diagram for explaining an example of the information processing device according to the first embodiment. [Figure 15] FIG. 2 is a diagram for explaining an example of the information processing device according to the first embodiment. [Figure 16] FIG. 2 is a diagram for explaining an example of the information processing device according to the first embodiment. [Figure 17] FIG. 2 is a diagram for explaining an example of the information processing device according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] [Embodiment 1] Hereinafter, one embodiment of the present disclosure will be described.

[0013] (Overview of information processing device 1) First, an overview of the information processing device 1 according to this embodiment will be described. In summary, the information processing device 1 according to this embodiment is a device that generates a dialogue scenario referenced by a dialogue execution unit (automatic response system, chatbot) that dialogues with a user. This dialogue scenario may be simply called a "scenario" or a "static dialogue scenario." Here, as an example, a "static dialogue scenario" refers to a scenario that is not subject to change in response to input from a user that dialogues with the information processing device 1. However, this does not limit this embodiment. The information processing device 1 may also be called a "dialogue scenario generation device" or a "scenario generation device." The information processing device 1 according to this embodiment is Acquire a group of information including multiple pieces of presentation information to be presented to the user, clustering the plurality of pieces of presentation information by referring to related information that is directly or indirectly associated with at least one of the plurality of pieces of presentation information; A static dialogue scenario including the plurality of pieces of presentation information is generated by referring to the clustering results. The following process is performed.

[0014] As described above, the information processing device 1 according to this embodiment clusters the plurality of pieces of presentation information and generates a static dialogue scenario including the plurality of pieces of presentation information by referring to the clustering results, thereby reducing costs, including the developer's effort, required for generating a static dialogue scenario. Furthermore, as described above, the information processing device 1 clusters the plurality of pieces of presentation information by referring to the related information, thereby obtaining appropriate clustering results. Therefore, the information processing device 1 according to this embodiment can generate an appropriate static dialogue scenario while reducing the cost required for generating a static dialogue scenario.

[0015] (Information processing system 100) Next, the configuration of an information processing system 100 including an information processing device 1 according to this embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram showing the configuration of the information processing system 100 according to this embodiment. As shown in FIG. 1, the information processing system 100 includes an information processing device 1, a server device 70, and one or more terminal devices 81, 82, etc. Examples of the information processing device 1 include a PC (Personal Computer), a smartphone, and a tablet. The information processing device 1 may be a server that cooperates with the server device 70. Examples of the terminal devices 81, 82, etc. include a smartphone, a tablet, and a PC. However, these examples do not limit this embodiment.

[0016] The information processing device 1, the server device 70, and the terminal devices 81, 82, etc. are connected to each other so as to be able to communicate with each other via a network, as shown in Fig. 1. The specific configuration of the network is not particularly limited, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these networks can be used.

[0017] (Server device 70) The server device 70 provides various types of data referenced by the information processing device 1 to the information processing device 1. As an example, the server device 70 provides at least a portion of the information included in the reference information group RGI, which will be described later, to the information processing device 1. However, this does not limit the present embodiment, and the information processing device 1 may be configured to acquire the reference information group RGI via its own input / output unit 40.

[0018] Furthermore, the server device 70 provides at least some of the models included in a model group MD, which will be described later, to the information processing device 1. However, this does not limit the present embodiment, and the information processing device 1 may provide input information for a model to the server device 70, and execute processing using the model in the server device 70. In this configuration, the server device 70 provides the execution results to the information processing device 1.

[0019] (Terminal devices 81, 82...) Each of the terminal devices 81, 82, etc. acquires user input from the user of the terminal device via a user interface such as a touch panel provided thereon, and performs various processes based on the acquired user input. As an example, each terminal device may be configured to acquire a static dialogue scenario DS generated by the information processing device 1, and present a response based on the static dialogue scenario DS and the user input to the user via the user interface.

[0020] Alternatively, each of the terminal devices 81, 82, etc. may be configured to provide the user input to the information processing device 1, and the information processing device 1 may generate display screen information DI including a response (presentation information) based on the static dialogue scenario DS and the user input. In this configuration, the terminal device acquires the display screen information DI from the information processing device 1 and presents it to the user via the user interface.

[0021] (Information processing device 1) As shown in FIG. 1, the information processing device 1 includes a control unit 10, a storage unit 20, a communication unit 30, and an input / output unit 40.

[0022] (Communication unit 30) The communication unit 30 is an interface for transmitting and receiving data via a network. As an example, the communication unit 30 acquires a user input from one of the terminal devices 81, 82, etc. The communication unit 30 also provides display screen information DI including a response (presentation information) generated based on the user input and the static dialogue scenario DS to one of the terminal devices. However, this does not limit the present embodiment, and the communication unit 30 may also provide the static dialogue scenario DS to each of the terminal devices 81, 82, etc. Examples of the communication unit 30 include, but are not limited to, communication chips for various communication standards such as Ethernet (registered trademark), Wi-Fi (registered trademark), and wireless communication standards for mobile data communication networks, and USB-compliant connectors.

[0023] (Input / output section 40) The input / output unit 40 is an interface with an input device that accepts data input and an output device that outputs data. Examples of input devices include, but are not limited to, a microphone, a camera, an eye-gaze input device, a keyboard, and a touchpad. Examples of output devices include, but are not limited to, a speaker and a display. When the information processing device 100 is used by a developer of a static dialogue scenario, the input / output unit 40 accepts input from the developer, who is different from the users of the terminal devices 81, 82, etc. The developer is sometimes referred to as the user of the information processing device 1.

[0024] (Storage unit 20) The storage unit 20 stores data referenced by the control unit 10, data derived (generated) by the control unit 10, and the like. ·Reference information group RGI ·Generation information group GGI Display screen information DI Model Group MD Examples of the storage unit 20 include, but are not limited to, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0025] (Reference information group RGI) The reference information group RGI is data that is mainly referenced by the control unit 10, and an example thereof is: ·Multiple presentation information RP Multiple related information RI Number of choices information NC Here, the presentation information RP included in the reference information group RGI is sometimes referred to as "referenced presentation information RP" to distinguish it from the presentation information GP included in the generated information group GGI, which will be described later.

[0026] The presentation information RP is information to be presented to a user in a dialogue with the user according to the static dialogue scenario DS. The upper part of Fig. 2 shows an example of the presentation information RP. In the example shown in the upper part of Fig. 2, the presentation information RP includes: -Title of the information: "How to sleep" -Description of the advertisement: "It's tough not being able to sleep. Here are some things you can try to help you get to sleep..." Contains:

[0027] The related information RI is information associated with the presentation information RP. In this embodiment, one or more pieces of related information RI can be associated with one piece of presentation information RP. In the example shown in the upper part of Figure 2, three pieces of related information RI (RI1, RI2, RI3) are associated with one piece of presentation information RP. The lower part of Figure 2 shows an example of the configuration of the related information RI1 and RI2. As shown in the lower part of Figure 2, each piece of related information RI includes supplemental information CI and explanatory information EI. Here, the supplemental information CI can also be considered to be the title of the related information RI. Furthermore, the explanatory information EI can also be considered to be information that explains the supplemental information CI, or can be considered to be descriptive information related to the supplemental information CI. Note that the terms supplemental information and explanatory information do not limit this embodiment.

[0028] In the example shown in the lower part of FIG. 2, more specifically, the related information RI1 includes: Supplementary information CI1: "I can't sleep" ·Explanatory information EI1: "I have trouble falling asleep when I want to, want to sleep, should sleep, or should sleep." Also, the related information RI2 includes: Supplementary information CI2: "I want to sleep soundly" Explanation EI2: "No matter how much I sleep, I feel like I'm still awake, and I feel like I'm not sleeping properly." Contains:

[0029] The option count information NC is information that specifies the number of options (number of branches) for each branch included in the static dialogue scenario DS. As an example, the option count information NC is set by the generating unit 13 (described later) in response to an input by the user of the information processing device 1 input via the input / output unit 40.

[0030] (Generation information group GGI) The generated information group GGI is data that is mainly derived (generated) by the control unit 10, and an example thereof is as follows: Clustering results CR ·Presentation information GP Static dialogue scenario DS etc. Here, the presentation information GP included in the generated information group GGI may be referred to as "generated presentation information GP" to distinguish it from the presentation information RP included in the reference information group RGI described above.

[0031] The clustering result CR is information indicating the result of a clustering process performed by the clustering unit 12, which will be described later. As an example, the clustering result CR includes a hierarchical branch structure including each of the above-described multiple pieces of presentation information RP as a node. Specific examples of the clustering result CR will be described later.

[0032] The presentation information GP is generated by the generating unit 13, which will be described later. Similar to the presentation information RP described above, the presentation information GP is information to be presented to a user in a dialogue with the user in accordance with the static dialogue scenario DS. Specific examples of the generated presentation information GP will be described later.

[0033] The static dialogue scenario DS is a static dialogue scenario generated by the generating unit 13, which will be described later, and includes the above-mentioned presentation information RP and presentation information GP, ​​for example. Specific examples of the static dialogue scenario DS will be described later.

[0034] The display screen information DI is information for display generated by the display control unit 15, which will be described later. Specific examples of the display screen information DI will be described later. The model group MD includes models for executing part of the processing of each unit included in the control unit 10. Such models include: A model for converting information contained in the reference information group RGI into a feature vector A model for executing the summarization process described below etc. are included.

[0035] (Control unit 10) 1, the control unit 10 includes an acquisition unit 11, a clustering unit 12, a generation unit 13, a dialogue execution unit 14, and a display control unit 15. Note that the control unit 10 may be configured not to include the dialogue execution unit 14 and the display control unit 15, and the terminal devices 81, 82, etc. may be configured to include the dialogue execution unit 14 and the display control unit 15, and such a configuration is also included in this embodiment.

[0036] (Acquisition part 11) The acquisition unit 11 acquires an information group including a plurality of pieces of presentation information RP to be presented to a user. Here, the user refers to, for example, a user of any of the terminal devices 81, 82, etc., or a user of the information processing device 1. In addition, the information group acquired by the acquisition unit 11 refers to, for example, at least a portion of the information included in the reference information group RGI described above. A specific example of the acquisition process by the acquisition unit 11 will be described later.

[0037] (Clustering section 12) The clustering unit 12 refers to related information RI associated directly or indirectly with at least one of the plurality of pieces of presentation information RP acquired by the acquisition unit 11, and performs clustering of the plurality of pieces of presentation information RP.

[0038] Here, the above-mentioned supplemental information CI is an example of related information RI directly associated with the presentation information RP. Furthermore, the above-mentioned explanatory information EI associated with the supplemental information CI is an example of related information RI indirectly associated with the presentation information RP. However, how the above-mentioned information is associated with each other does not limit this embodiment, and the explanatory information EI can also be considered as an example of related information RI directly associated with the presentation information RP. Therefore, unless there is any particular confusion, the expression "directly or indirectly associated" can also be simply expressed as "associated."

[0039] Furthermore, the clustering result CR, which is the result of the clustering process by the clustering unit 12, includes, as an example, a hierarchical branch structure including each of the plurality of pieces of presentation information RP acquired by the acquisition unit 11 as a node. The details of the clustering process by the clustering unit 12 do not limit the present embodiment, but as an example, the clustering unit 12 executes a hierarchical clustering process with reference to the distance (similarity) between pieces of information to be clustered. In such a hierarchical clustering process, the clustering unit 12 Each presentation information RP associated with one or more related information RI is represented as a vector in the feature space (embedded in the feature space), - Create pairs of vectors that fit a given rule (such as large / small distance (similarity) between vectors), A tree diagram containing each of the above pairs as a branch (each node) is generated as the clustering result CR. Here, if the hierarchical clustering process is an algorithm for generating a tree diagram with a binary tree structure, the set of vectors is a pair of vectors (a set of two vectors), and if the hierarchical clustering process is an algorithm for generating a tree diagram with a ternary tree structure, the set of vectors is a set of three vectors. A specific example of the clustering process by the clustering unit 12 will be described later.

[0040] (Generation part 13) The generation unit 13 generates a static dialogue scenario DS including the plurality of pieces of presentation information RP with reference to the clustering result CR by the clustering unit 12. As an example, the generation unit 13 generates the static dialogue scenario DS so that the number of options at each branch in the static dialogue scenario DS is greater than the number of branches at each branch (each node) included in the clustering result. The generation unit 13 stores the generated static dialogue scenario DS in the storage unit 20. The generated static dialogue scenario DS may be referenced by the dialogue execution unit 14 (described later) when performing dialogue processing with a user, or may be provided to terminal devices 81, 82, etc. and referenced when performing dialogue processing with a user on the terminal devices. A specific example of the generation process of the static dialogue scenario DS by the generation unit 13 will be described later.

[0041] The present invention also contemplates support for minority users, such as those with developmental disabilities, for example. Therefore, it is beneficial for the present invention to avoid the disadvantage of the number of options, names (described in detail later), etc. being changed for the majority based on the access history and frequency of other users who represent the majority. In other words, the generation unit 13 can generate static dialogue scenarios without relying on the input of the user (other users).

[0042] (Dialogue execution unit 14) The dialogue execution unit 14 executes a dialogue with the user based on the static dialogue scenario DS generated by the generation unit 13. As an example, the dialogue execution unit 14 acquires an input from the user, and determines a response content to the user based on the input and the static dialogue scenario DS. Note that the response content includes at least one of the presentation information RP and the presentation information GP included in the static dialogue scenario DS.

[0043] (Display control unit 15) The display control unit 15 generates a dialogue screen including the response content determined by the dialogue execution unit 14. In other words, the display control unit 15 controls the display of a dialogue screen including the content of the dialogue including the response content determined by the dialogue execution unit 14. The dialogue screen generated by the display control unit 15 may be presented, for example, via a display provided in the input / output unit 40, or may be provided to each of the terminal devices 81, 82, ... via the communication unit 30.

[0044] (Major effects of information processing device 1) In this way, the information processing device 1 according to this embodiment: Acquire a group of information including multiple presentation information RPs to be presented to the user, clustering the plurality of pieces of presentation information RP with reference to related information RI that is directly or indirectly associated with at least one of the plurality of pieces of presentation information RP; A static dialogue scenario DS including the plurality of pieces of presentation information RP is generated by referring to the clustering result CR. The following process is performed.

[0045] As described above, the information processing device 1 according to this embodiment clusters the plurality of pieces of presentation information RP and generates a static dialogue scenario DS including the plurality of pieces of presentation information RP by referring to the clustering results CR, thereby reducing costs, including the developer's effort, required for generating a static dialogue scenario DS. Furthermore, as described above, the information processing device 1 clusters the plurality of pieces of presentation information RP by referring to the related information RI, thereby obtaining appropriate clustering results. Therefore, the information processing device 1 according to this embodiment can generate an appropriate static dialogue scenario DS while reducing the cost required for generating a static dialogue scenario DS.

[0046] As described above, in the information processing device 1, The clustering result CR includes a hierarchical branch structure including each of the plurality of pieces of presentation information RP acquired by the acquisition unit 11 as a node, The generation unit 13 generates the static dialogue scenario DS so that the number of choices at each branch in the static dialogue scenario DS is greater than the number of branches at each branch included in the clustering result CR. The following process is performed.

[0047] According to the above configuration, a static dialogue scenario DS can be generated with fewer layers than the number of layers in the clustering result CR, thereby preventing the number of layers in the static dialogue scenario DS from becoming excessively large. Therefore, according to the above configuration, it is possible to improve the convenience (ease of use) for a user who engages in a dialogue in accordance with the static dialogue scenario DS.

[0048] (Processing flow by information processing device 1) Next, the flow of processing by the information processing device 1 will be described with reference to Fig. 3. Fig. 3 is a flow chart showing the flow of processing by the information processing device 1.

[0049] (Step S11) In step S11, the acquisition unit 11 acquires an information group including a plurality of pieces of presentation information RP to be presented to the user. The acquisition process by the acquisition unit 11 has been described above, so a duplicated description will be omitted. A specific example of the acquisition process by the acquisition unit 11 will be described later.

[0050] (Step S12) In step S12, the clustering unit 12 performs clustering of the plurality of pieces of presentation information RP with reference to related information RI associated directly or indirectly with at least any one of the plurality of pieces of presentation information RP acquired by the acquisition unit 11 in step S11. More specifically, the clustering unit 12 may perform clustering of the plurality of pieces of presentation information RP with reference to one or more pieces of supplemental information CI as related information RI associated with at least any one of the plurality of pieces of presentation information RP. Fig. 4 is a diagram illustrating an example of clustering processing by the clustering unit 12. In the example shown in Fig. 4, the information group (reference information group RGI) acquired by the acquisition unit 11 in step S11 includes presentation information RP1, presentation information RP2, ..., presentation information RPn. Furthermore, supplemental information CI_A and supplemental information CI_D are associated with the presentation information RP1, and supplemental information CI_A, supplemental information CI_C, and supplemental information CI_K are associated with the presentation information RP2. Furthermore, supplemental information CI_D and supplemental information CI_F are associated with the presentation information RPn.

[0051] The clustering unit 12 converts each of the pieces of presentation information RP1 to RPn into a feature vector by referring to the related information RI (more specifically, the supplementary information CI) associated with the presentation information. Generate a feature vector V1 from the presentation information RP1, supplementary information CI_A, and supplementary information CI_D, Generate a feature vector V2 from the presentation information RP2, supplementary information CI_A, supplementary information CI_C, and supplementary information CI_K, Generate a feature vector Vn from the presentation information RPn, supplementary information CI_D, and supplementary information CI_F. Here, the feature vector V1 may also be referred to as the feature vector of the presentation information RP1, the feature vector V2 may also be referred to as the feature vector of the presentation information RP2, and the feature vector Vn may also be referred to as the feature vector of the presentation information RPn.

[0052] Then, the clustering unit 12 performs hierarchical clustering processing by referring to each of the feature vectors V1 to Vn. By referring to each feature vector V1 to Vn, pairs of vectors that meet a predetermined rule (such as whether the distance (similarity) between vectors is large or small) are sequentially created. A tree diagram (a binary tree in the example in Figure 4) containing each of the above pairs as each branch is generated as the clustering result CR. The process is shown diagrammatically.

[0053] (Step S13) Subsequently, in step S13, the generation unit 13 generates a static dialogue scenario DS including the plurality of pieces of presentation information RP, with reference to the clustering result CR obtained by the clustering unit 12 in step S12. Hierarchical search processing Presentation information generation processing -Static dialogue scenario generation processing Includes:

[0054] (Hierarchical search process) The hierarchical search process is a process of searching for a hierarchy in which the number of options matches the option number information NC in the clustering result CR by the clustering unit 12. Fig. 5 is a diagram for explaining the hierarchical search process in the clustering result CR obtained by the clustering unit 12 with reference to the presentation information RP (RP1 to RP22) obtained by the acquisition unit 11. Here, the clustering result CR shown in Fig. 5 is a hierarchical branching structure (tree diagram) including each of the multiple pieces of presentation information (RP1 to RP22) obtained by the acquisition unit 11 as a node (for example, a terminal node). Note that the horizontal axis in the tree diagram showing the clustering result CR in Fig. 5 indicates an index obtained from the cosine distance (similarity) between each piece of presentation information RP and the group average.

[0055] In a tree diagram showing the clustering result CR, the generation unit 13 sequentially identifies the total number of branches (number of choices) from the top node (root node) side in the tree diagram, for example. In the example shown in Fig. 5, the total number of branches (number of choices) is 2 in the layer indicated by the leftmost vertical dotted line, but as one moves through the layers to the right (towards the lower nodes), the total number of branches (number of choices) changes to 3, 4, and 5. In the example shown in Fig. 5, the number of choices indicated by the choice number information NC is 5, and the generation unit 13 identifies the layer identified by the vertical dotted line indicating the number of choices of 5 as the layer of the search result. Note that the respective choices in the identified layer may also be referred to as choices C11 to C15, as shown in Fig. 5.

[0056] (Presentation information generation process) The presentation information generation process is a process for generating presentation information GP to be assigned to each of the options C11 to C15 in the hierarchy identified by the hierarchy search process. In the presentation information generation process, the generation unit 13 generates presentation information GP to be assigned to a certain option included in a certain branch in the static dialogue scenario DS by: In the clustering result CR, presentation information RP of a node lower than the certain option, and Related information RI associated with the presentation information RP of the lower node The generated image is generated by referring to at least one of the above.

[0057] FIG. 6 is a diagram showing an example of a presentation information generation process executed by the generation unit 13 for the presentation information group RPG1 including the presentation information RP1 to RP10 of nodes lower than the option C11 in the clustering result CR shown in FIG.

[0058] In the example shown in FIG. 6, for presentation information RP1 “Push yourself until the last moment” as an example of presentation information RP included in presentation information group RPG1, each related information RI: · Missing deadlines I don't know how to make a schedule Unable to estimate the time required In addition, for the presentation information RP2 "Finish before the deadline" which is another example of the presentation information RP included in the presentation information group RPG1, each related information RI: · Missing deadlines Forgetting deadlines Unable to estimate the time required I don't know how to make a schedule Each of these related information RI is more specifically related to each of the supplementary information CI: · Missing deadlines I don't know how to make a schedule Forgetting deadlines etc. and each explanatory information EI for each supplementary information CI: - Missing deadlines for work, homework, etc. - Missing deadlines for work, homework, etc. Forgetting deadlines for work, homework, etc. It should be noted that each of the supplementary information CI and each of the explanatory information EI is also included in the presentation information group RPG1.

[0059] The generation unit 13 generates, in the static dialogue scenario DS, presentation information GP to be assigned to an option C11 included in the hierarchical level identified by the hierarchical search process, by referring to a presentation information group RPG1 including presentation information RP1 to RP10 of nodes lower than the option C11. As an example, the generation unit 13 generates the presentation information GP to be assigned to the option C11 by referring to explanation information EI of each presentation information RP included in the presentation information group RPG1.

[0060] More specifically, as shown in Fig. 6, the generation unit 13 generates the presentation information GP to be assigned to the option C11 by applying a summarization process to the explanation information EI for each of the one or more pieces of supplemental information CI associated with the presentation information RP1 to RP10 of the lower nodes. In the example shown in Fig. 6, the explanation information EI for the supplemental information CI associated with the presentation information RP1 to RP10 of the lower nodes of the option C11: - Missing deadlines for work, homework, etc. - Missing deadlines for work, homework, etc. Forgetting deadlines for work, homework, etc. By performing a summary process on the option C11, the presentation information GP11 is assigned to the option C11: Work, homework, deadlines is generated.

[0061] Although the specific example of the summarization process executed by the generation unit 13 does not limit this embodiment, as an example, the summarization process can be configured to be executed by at least one of a topic model, a key phrase extraction process, and a generative model. Furthermore, the summarization process can use one or more models (machine-learned models) included in the above-mentioned model group MD.

[0062] The generation unit 13 performs the same process on at least one of the other options C12 to C15 in the layer identified by the above layer search process. Fig. 7 shows examples of presentation information GP11 to GP15 assigned by the generation unit 13 to the options C11 to C15 in the layer (denoted as layer 1) identified by the above layer search process. As shown in Fig. 7, option C13 has presentation information GP13: Missing, understanding, forgetting The presentation information GP13 is generated by the generation unit 13 with reference to the explanation information EI of each piece of presentation information RP included in the presentation information group RPG3 made up of the presentation information RP12 to RP20 of the subordinate nodes of the option C13.

[0063] On the other hand, in the example shown in Fig. 7, the lower nodes of the options C12, C14, and C15 are each composed of one terminal node. In such a case, the generation unit 13 may use the presentation information RP11, RP21, and RP22 of the terminal node as the presentation information GP12, GP14, and GP15 of the options C12, C14, and C15, respectively, as shown in Fig. 7. In the example shown in Fig. 7, the options C12, C14, and C15 each have the presentation information GP12, GP14, and GP15, and the presentation information RP: List your tasks · Site where you can search for lost items Paid cleaning service is granted.

[0064] 8 shows presentation information GP_N1 including presentation information GP11 to GP15 generated by the presentation information generation process for each option included in the hierarchical level (level 1) identified by the hierarchical search process. Presentation information GP_N1 is an example of a question included in the static dialogue scenario DS generated by the generation unit 13.

[0065] The generation unit 13 repeatedly applies the hierarchical search process and the presentation information generation process to the clustering result CR, thereby Identify the hierarchy that matches the number of options indicated by the option number information NC, Generate presentation information GP for each option included in the identified hierarchy 9 shows an example of another hierarchy (denoted as hierarchy 2) searched by the generation unit 13. The generation unit 13 also assigns the presentation information GP generated by the above-described presentation information generation process to each option included in these hierarchies.

[0066] (Dialogue scenario generation process) The generation unit 13 generates a static dialogue scenario DS using the results of the hierarchical search process and the presentation information generation process. FIG. 10 shows an example of a static dialogue scenario DS generated by the generation unit 13. As shown in FIG. 10, the generation unit 13 performs the hierarchical search process and the presentation information generation process to generate a static dialogue scenario DS such that the number of options at each branch in the static dialogue scenario DS (e.g., 5 in the example of FIG. 10) is greater than the number of branches at each branch included in the clustering result CR (e.g., 2 in the example above). In the example shown in FIG. 10, the presentation information RP1 to RP22 shown in FIG. 5 and the like can be included in a scenario with three hierarchical levels, which is significantly reduced compared to the number of hierarchical levels of the clustering result CR. Generally, the greater the number of hierarchical levels in a scenario, the greater the number of questions, resulting in reduced user convenience (ease of use). The above configuration can improve user convenience (ease of use) when engaging in a dialogue based on the static dialogue scenario DS.

[0067] Furthermore, the static dialogue scenario DS generated by the generation unit 13 may include, as part thereof, a branch to a scenario (also called a dynamic scenario) that generates response content using a trained generation model.

[0068] (Specific example of processing flow by information processing device 1) Next, a specific example of the flow of processing by the information processing device 1 will be described with reference to Fig. 11 and Fig. 12. Steps S111 to S115 shown in Fig. 11 correspond to step S11 shown in Fig. 3, and steps S131 to S133 shown in Fig. 11 correspond to steps S12 and S13 shown in Fig. 3. Furthermore, steps S121 to S123 shown in Fig. 12 correspond to step S12 shown in Fig. 3.

[0069] (Step S111) 11, the acquisition unit 11 acquires presentation information RP and stores (records) the acquired presentation information RP as part of the reference information group RGI in the storage unit 20. The acquisition unit 11 acquires, for example, the presentation information RP input by the user of the information processing device 1 via the input / output unit 40.

[0070] (Step S112) Subsequently, in step S112, the acquisition unit 11 Accepting a selection regarding the supplementary information CI and explanatory information EI to be associated with the presentation information RP obtained in step S111, or Acceptance of input regarding the above supplementary information CI and explanatory information EI As an example, the acquisition unit 11 presents the supplemental information CI and explanatory information EI included in the reference information group RGI at that time to the user of the information processing device 1 via the input / output unit 40. Then, the user selects the supplemental information CI and explanatory information EI to be associated with the presentation information RP input in step S111. Here, if the supplemental information CI and explanatory information EI to be associated with the presentation information RP are not included in the presentation via the input / output unit 40, the user inputs the supplemental information CI and explanatory information EI to be associated with the presentation information RP by text input or the like.

[0071] In this step, if the user performs "selection," the process proceeds to step S114, and if the user performs "input," the process proceeds to step S113.

[0072] (Step S113) In step S113, the acquisition unit 11 stores (records) the supplemental information CI and explanatory information EI input by the user in step S112 in the storage unit 20 as part of the reference information group RGI.

[0073] (Step S114) In step S114, the acquisition unit 11 associates (links) the supplemental information CI and explanatory information EI selected or input in step S112 with the presentation information RP acquired in step S111.

[0074] (Step S115) In step S115, the acquisition unit 11 determines whether there is other presentation information RP to be registered. If there is other presentation information RP to be registered, the process returns to step S111; otherwise, the process proceeds to step S131.

[0075] (Step S131) In step S131, a static dialogue scenario generation command is acquired from the user of the information processing device 1. Also, the number of options in the static dialogue scenario is acquired from the user. The acquired number of options is stored in the storage unit 20 as option number information NC.

[0076] (Step S132 (S12)) In step S132 (S12), the clustering unit 12 and the generation unit 13 generate a static dialogue scenario DS. The process of generating the static dialogue scenario DS has been described above, so a duplicated description will be omitted here. The process of generating the static dialogue scenario DS will also be described later with reference to FIG. 12.

[0077] (Step S133) In step S133, the generating unit 133 outputs the static dialogue scenario DS generated in step S132 (S12). As an example, step S132 (S12) is stored in the storage unit 20 as part of the generated information group GGI.

[0078] (Details of step S132 (S12)) FIG. 12 is a flowchart showing the detailed process flow in step S132 (S12) above.

[0079] (Step S121) In step S121, the acquisition unit 11 refers to the reference information group RGI and acquires the presentation information RP and supplemental information CI stored in steps S111 and S113.

[0080] (Step S122) In step S122, the clustering unit 12 creates feature vectors V1 to Vn from the acquired supplemental information CI as described with reference to Fig. 4. Here, the set of feature vectors V1 to Vn is also called a feature matrix.

[0081] (Step S123) In step S123, the clustering unit 12 references each of the feature vectors V1 to Vn and generates a tree diagram (clustering result CR) by the above-mentioned hierarchical clustering process. As the hierarchical clustering process, the above-mentioned cosine distance (similarity), group averaging method, etc. are used.

[0082] (Step S1321) In step S1321, the acquisition unit 11 acquires the number of options by referring to the option count information NC stored in step S131, and the generation unit 13 performs the dialogue scenario generation process based on the number of options and the tree diagram generated in step 123, to generate paths for the static dialogue scenario DS. As an example, a static dialogue scenario DS including the five paths shown in Fig. 10 is generated.

[0083] (Step S1322) In step S1322, the generation unit 13 generates the name (presentation information GP) of an option whose path in the static dialogue scenario continues below the option (for example, an option having a lower node) by applying a summarization process to the explanation information EI (or related information RI) (the above-mentioned presentation information generation process). As described with reference to Figure 6, the name of this option is automatically generated by the above-mentioned summarization process (topic model, key phrase extraction process, or generation model) from a list of explanation information EI linked to presentation information that can be an option at a lower node in the hierarchy of the specified option.

[0084] (Step S132 (Step S133)) In step S132 (step S133), the dialogue execution unit 14 associates the dialogue scenario path and the names of the options and records them in the generation information group GGI. Here, the relationship between the dialogue scenario path and the name of the option displayed at which level and for which option is recorded in the generation information group GGI as a linked static dialogue scenario DS.

[0085] (Notes regarding step S1321) The "story scenario generation process based on the number of options and the tree diagram that is the clustering result" in step S1321 may be performed as follows. Refer to the tree diagram generated in step S123 and determine the number of options so that the number of levels falls within a predetermined range. -Based on the determined number of options, a static dialogue scenario DS is generated.

[0086] By performing such processing, the number of options and the number of levels can be suitably determined according to the clustering results, and therefore it is possible to flexibly respond to changes in the presentation information GP.

[0087] (Example of display screen information) 13 shows an example of display screen information DI generated by the display control unit 15. The upper diagram is an example of a title screen, which is an example of display screen information DI, and the lower diagram is an example of an interactive screen, which is an example of display screen information DI.

[0088] The display control unit 15 of the information processing device 1 may visually present the display screen information DI to the users of the terminal devices 81, 82, etc. via the input / output unit 40. As an example, as shown in the title screen example in the upper diagram of Fig. 13, the display control unit 15 may output a title DI1 "Dialogue application 'Consultation desk'" and a UI button DI2 "Start dialogue" at the top center of the screen as the title screen of the static dialogue scenario, and output "Scenario generation date: 2025 / ** / ** Number of options: 5" at the bottom right of the screen as information DI3 related to clustering.

[0089] Furthermore, when the user selects (tap) "Start dialogue" DI2, as shown in the example dialogue screen in the lower part of Figure 13, as an example of an actual static dialogue scenario, presented information GP_N1 such as "Please select what you want to know: 1. Work, homework, deadlines 2. List tasks 3. Missed, understood, forgotten 4. Site where you can search for lost items 5. Paid cleaning services" may be output in a speech bubble from the left side of the screen.

[0090] If the user selects (tap) "1. Work, homework, deadlines," "1" may be output in a bubble from the right side of the screen, and then presentation information GP_N11 such as "Please select what you want to know: 1. Time, schedule, estimate 2. Get it done all at once 3. Deadline, things to do, forget 4. Priority, importance, deadline 5. Work on it a little bit every day" may be output in a bubble from the left side of the screen.

[0091] In this way, the display control unit 15 displays an interactive screen including the content of the dialogue, and the display control unit 15 may include information DI3 regarding the clustering performed by the generation unit 13 in the interactive screen or a display screen other than the interactive screen.

[0092] <Example> Next, an example of the process of generating a static dialogue scenario DS by the information processing device 1 will be described with reference to Figs. 14 to 17. Figs. 14 to 15 show the static dialogue scenario DS generated by the information processing device 1 in this example. · Site where you can search for lost items List your tasks ... etc. correspond to the presentation information RP (22 pieces in the example of FIGS. 14 and 15).

[0093] In this embodiment, the 22 pieces of presentation information shown in FIGS. 14 and 15 and new presentation information ·Manage with a calendar Use a planner Loss of items related to the incident The static dialogue scenario DS was updated by performing the above-mentioned clustering process and dialogue scenario generation process on a group of presentation information including the above. Figures 16 and 17 show the static dialogue scenario DS obtained by this update process. As shown in Figures 16 and 17, it was confirmed that an appropriate static dialogue scenario DS including this new presentation information was generated.

[0094] [Software implementation example] The functions of the information processing device 1 can be realized by a program that causes a computer to function as the device, and a program that causes a computer to function as each control block of the device (particularly each part included in the control unit 10).

[0095] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program, thereby realizing the functions described in each of the above embodiments.

[0096] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0097] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0098] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may run on the control device or on another device (for example, an edge computer or a cloud server).

[0099] [summary] The information processing device according to aspect 1 of this embodiment includes an acquisition unit that acquires an information group including a plurality of pieces of presentation information to be presented to a user, a clustering unit that performs clustering of the plurality of pieces of presentation information by referring to related information that is directly or indirectly associated with at least one of the plurality of pieces of presentation information, and a generation unit that generates a static dialogue scenario including the plurality of pieces of presentation information by referring to the results of the clustering by the clustering unit.

[0100] The above configuration can reduce costs, including the effort required by developers, to generate static dialogue scenarios.

[0101] In addition, an information processing device according to aspect 2 of this embodiment is an information processing device according to aspect 1, wherein the clustering result includes a hierarchical branching structure including each of the plurality of pieces of presentation information acquired by the acquisition unit as a node, and the generation unit generates the static dialogue scenario so that the number of options at each branch in the static dialogue scenario is greater than the number of branches at each branch included in the clustering result.

[0102] The above configuration can improve the convenience (ease of use) for users who engage in dialogue according to a static dialogue scenario.

[0103] In addition, an information processing device according to aspect 3 of this embodiment is an information processing device according to aspect 2, wherein the generation unit generates presentation information to be assigned to a certain option included in a certain branch in the static dialogue scenario by referring to at least one of the presentation information of a node lower than the certain option in the clustering results and related information associated with the presentation information of the lower node.

[0104] With the above configuration, the names of options (presentation information) in a scenario can be generated by summarizing the information of lower-level nodes.

[0105] In addition, an information processing device according to aspect 4 of this embodiment is an information processing device according to aspect 3, wherein the clustering unit performs the clustering by referring to one or more pieces of supplementary information as related information associated with at least one of the plurality of pieces of presentation information, and the generation unit generates presentation information to be assigned to a certain option included in a certain branch in the static dialogue scenario by applying a summarization process to explanatory information for each of the one or more pieces of supplementary information associated with the presentation information of the lower node.

[0106] Furthermore, an information processing device according to aspect 5 of this embodiment is the information processing device according to aspect 4, wherein the generation unit executes the summarization process using at least one of a topic model, a key phrase extraction process, and a generation model.

[0107] With the above configuration, the names of options (presentation information) in a scenario can be generated by summarizing the information of lower-level nodes.

[0108] Furthermore, an information processing device according to aspect 6 of this embodiment is the information processing device according to aspect 5, wherein the generation unit sets the number of options at each branch in the static dialogue scenario in accordance with input from a user.

[0109] With the above configuration, it is possible to set the number of options to be displayed to the user in a static dialogue scenario.

[0110] In addition, an information processing device according to aspect 7 of this embodiment is an information processing device according to any one of aspects 1 to 6, and is provided with a dialogue execution unit that executes a dialogue with a user based on the static dialogue scenario generated by the generation unit.

[0111] The above configuration makes it possible to execute a dialogue with a user based on a static dialogue scenario.

[0112] In addition, an information processing device according to aspect 8 of this embodiment is an information processing device according to aspect 7, which is provided with a display control unit that displays an interactive screen including the content of the dialogue, and the display control unit includes information regarding the clustering performed by the generation unit in the interactive screen or a display screen other than the interactive screen.

[0113] With the above configuration, an interactive screen including the content of the interaction and information regarding clustering can be displayed to a user who uses a static interaction scenario.

[0114] Furthermore, the information processing method according to aspect 9 of this embodiment includes an acquisition step in which one or more processors acquire an information group including a plurality of pieces of presentation information to be presented to a user, a clustering step in which the plurality of pieces of presentation information are clustered by referring to related information directly or indirectly associated with at least any of the plurality of pieces of presentation information, and a generation step in which a static dialogue scenario including the plurality of pieces of presentation information is generated by referring to the results of the clustering by the clustering unit.

[0115] The above configuration provides the same effects as in the first aspect.

[0116] Furthermore, a program according to aspect 10 of this embodiment is a program for causing a computer to function as the information processing device according to aspect 1, and causes the computer to function as the acquisition unit, the clustering unit, and the generation unit.

[0117] The above configuration provides the same effects as in the first aspect.

[0118] Furthermore, a computer-readable recording medium according to an eleventh aspect of this embodiment records the program according to the tenth aspect.

[0119] The above configuration provides the same effects as in the first aspect.

[0120] The present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0121] 100 Information Processing Systems 1. Information processing equipment 10 Control Unit 11 Acquisition Department 12 Clustering Department 13 Generation part 14 Dialogue execution unit 15 Display control unit 20 Memory section 30 Communications Department 40 Input / output section 70 Server equipment 81, 82... Terminal device

Claims

1. an acquisition unit that acquires an information group including a plurality of pieces of presentation information to be presented to a user; Related information directly or indirectly associated with at least one of the plurality of pieces of presented information a clustering unit that performs clustering of the plurality of pieces of presentation information by referring to a generation unit that generates a static dialogue scenario including the plurality of pieces of presentation information by referring to a result of the clustering by the clustering unit; It is equipped with the clustering result includes a hierarchical branch structure including each of the plurality of pieces of presentation information acquired by the acquisition unit as a node; The generation unit generates the static dialogue scenario so that the number of options at each branch in the static dialogue scenario is greater than the number of branches at each branch included in the clustering result. Information processing device.

2. The generation unit Presentation information to be assigned to a certain option included in a certain branch in the static dialogue scenario, Presentation information of a node lower than the certain option in the clustering result; and Related information associated with the presentation information of the lower node Generate it by referring to at least one of The information processing device according to claim 1 .

3. The clustering unit performing the clustering by referring to one or more pieces of supplementary information as related information associated with at least any of the plurality of pieces of presented information; The generation unit Generate presentation information to be assigned to a certain option included in a certain branch in the static dialogue scenario by applying a summarization process to explanatory information for each of the one or more pieces of supplementary information associated with the presentation information of the lower node. The information processing device according to claim 2 .

4. The generation unit executes the summarization process using at least one of a topic model, a key phrase extraction process, and a generation model. The information processing device according to claim 3 .

5. The generation unit sets the number of options at each branch in the static dialogue scenario in accordance with an input from a user. The information processing device according to claim 4 .

6. a dialogue execution unit that executes a dialogue with a user based on the static dialogue scenario generated by the generation unit; The information processing device according to claim 1 .

7. a display control unit that displays an interactive screen including the content of the interaction; The display control unit includes information about the clustering performed by the generation unit in the interactive screen or a display screen other than the interactive screen. The information processing device according to claim 6 .

8. one or more processors an acquisition step of acquiring an information group including a plurality of pieces of presentation information to be presented to a user; a clustering step of clustering the plurality of pieces of presentation information by referring to related information that is directly or indirectly associated with at least one of the plurality of pieces of presentation information; a generating step of generating a static dialogue scenario including the plurality of pieces of presentation information by referring to a result of the clustering in the clustering step; It contains In the generating step, the static dialogue scenario is generated so that the number of options at each branch in the static dialogue scenario is greater than the number of branches at each branch included in the clustering result. Information processing methods.

9. 2. A program for causing a computer to function as the information processing device according to claim 1, the program causing a computer to function as the acquisition unit, the clustering unit, and the generation unit.

10. A computer-readable recording medium on which the program according to claim 9 is recorded.

Images