Information processing device, information processing method, and program

Abstract

To generate more natural language representation from the content of a target element value of a plurality of role trees, when the target element value is obtained from the result of user interaction.SOLUTION: An information processor includes: generating an RTC content table associated with a persona selected by a user, acquiring all the elements and element values of a persona group including the selected persona; analyzing user inputs input to the RTC content cable on the basis of the acquired elements and element values and thereby specifying relevant element and element value; subjecting the target elements and the target element values, and all the user inputs input to the RTC content table to conversion processing, under the condition that the specified element and element value are a target element and a target element value; and outputting the conversion result for user presentation to the RTC content cable.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. More specifically, the present invention relates to an information processing device, an information processing method, and a program that associates multiple thoughts with multiple personas (rule trees), controls them so that they can be handled in multiple ways, and provides output results in more natural language through conversion functions such as generative AI. The present invention also relates to an information processing device, an information processing method, and a program that adds combinations of elements and element values ​​derived from new input data to case data, brushes up personas, and generates personas based on input data that can be associated with end users. [Background technology]

[0002] An expert system in the field of artificial intelligence (Patent Document 1) generates a decision tree by registering elements (condition attributes) and element values ​​(condition attribute values) for a specific theme, and then registering target elements (conclusion attributes) and target element values ​​(conclusion attribute values).The expert system can use the decision tree to provide consulting to users on a specific theme.

[0003] A personaization system (Patent Document 2) is also known as a technology for generating decision trees. The personaization system is equipped with a case-based learning and machine learning tool. This tool represents cases based on input data as pairs of elements (condition attributes) and target elements (conclusion attributes), and generates a decision tree (hereinafter referred to as a "rule tree") by learning rules that estimate target element values ​​(conclusion attribute values) from element values ​​(condition attribute values) observed based on the cases. This tool outputs target values ​​by automatically tracing the rule tree based on the response methods (element values) to pre-set questions (elements) (auto-consulting). Patent Document 2 discloses a technology for navigating multiple rule trees, which is achieved by setting the address of the rule tree to be called as key information for any element.

[0004] In recent years, a technology called generative AI has emerged in the field of artificial intelligence. Although generative AI is still in its infancy, it has the ability to generate and output new text, images, music, etc. based on input information and previously learned information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 5572615 [Patent Document 2] Patent No. 7216449 Summary of the Invention [Problem to be solved by the invention]

[0006] The problems of modern society are complex. At first glance, the problems people face may appear to be categorized into specific themes, but in reality, they are often caused by a mixture of various factors and a combination of various causes. When people converse with each other about a certain theme or problem, the topic may change to another theme or problem when a specific keyword comes up. In such cases, consulting cannot be carried out solely by experts in a specific field, and cooperation from experts in other fields is required.

[0007] In conventional technology, a rule tree is generated in advance to provide consulting to a user on a specific theme or problem. Even if a rule tree generated in this way is used, it is difficult to provide appropriate consulting on complex themes or problems. In order to handle multiple themes and problems, it is necessary to generate a rule tree that can handle multiple thoughts. However, in order to provide consulting to a user on various problems, it is necessary to generate a huge rule tree that combines multiple thoughts into one.

[0008] Figure 1 is a diagram explaining the process of generating one huge rule tree in the prior art. The huge rule tree is generated based on various elements and examples so that consulting can be performed on various problems. Although a huge rule tree has the advantage of being able to handle multiple thoughts, (1) It takes a huge amount of time to complete the process because it requires a large number of examples to generate. (2) When considering the possibility of branching out into various themes and issues, the amount of information (elements) required for one case becomes too large, and (3) If it is discovered after the fact that a necessary element is missing or has been added, it will be necessary to add the element to all cases. There are disadvantages such as:

[0009] When a topic shifts from a specific theme or problem to another theme or problem, it is necessary to set the address of the rule tree to be called as key information in an arbitrary element, as disclosed in Patent Document 2. FIG. 2 is a diagram illustrating the concept of setting the address of the rule tree to be called as key information in an arbitrary element. In FIG. 2, the shaded elements have the address of the rule tree to be called set. With such conventional technology, it is difficult to determine which address to set in which element, and in some cases, there is a risk that the rule tree may become rigid.

[0010] In conventional consulting using rule trees, the target element value of the tree traversed as a result of user interaction is output as is, which can result in unnatural linguistic expressions being output.

[0011] Previously, it was possible to generate a rule tree from case studies, but the case studies themselves had to be prepared by the rule tree generator. It was a heavy burden for the generator to prepare appropriate case data, including elements and values, and it was difficult for the generator to determine how to set elements and how to ensure consistency with existing personas.

[0012] For this reason, there is a need for information processing that can easily construct multiple thoughts using multiple rule trees and automatically select a rule tree for a desired theme or problem. There is also a need for information processing that can convert the target element values ​​of one or more rule trees obtained as a result of user dialogue into more natural language expressions. There is also a need for information processing that can easily generate case data that is consistent with the elements and element values ​​of existing personas based on new input data.

[0013] The present invention has been made to solve such problems, and aims to provide an information processing device, information processing method, and program that associates multiple thoughts with multiple personas (rule trees) and controls them so that they can be handled in multiple ways.

[0014] The present invention aims to provide an information processing device and an information processing method that, when target element values ​​of multiple rule trees are obtained as a result of user interaction, converts the content into a more natural language expression, or generates a new natural language expression based on the content.

[0015] The present invention aims to provide an information processing device and an information processing method that add, as new case data, combinations of elements and their values ​​that can be derived from new input data prepared by the user in a form that is consistent with the combinations of elements and element values ​​of existing personas. [Means for solving the problem]

[0016] In order to solve the above problems, the information processing device according to the present invention comprises: generating an RTC content table associated with the persona selected by the user; Obtaining all elements and element values ​​of a group of personas including the selected persona; Identifying relevant elements and element values ​​by analyzing the user input entered into the RTC content table based on the acquired elements and element values; On the condition that the identified element and element value are the target element and target element value, performing a conversion process on the target element and the target element value, and all user inputs entered in the RTC content table; outputting the conversion results to the RTC content table for presentation to the user; is configured to execute [Effects of the Invention]

[0017] According to the present invention, multiple thoughts can be associated with multiple personas (rule trees) and controlled so that they can be handled in multiple ways, enabling general-purpose consulting for a variety of themes and problems. The present invention has fewer elements for each persona than the prior art, so fewer case studies are required, and the amount of information per case is smaller. Even when adding necessary elements after the fact, the present invention only requires updating the associated persona, thereby reducing the scope of control. Furthermore, the present invention makes each persona relatively smaller than the prior art, making it easier to check and maintain rules.

[0018] According to the present invention, the target element values ​​of multiple rule trees obtained as a result of user interaction can be converted into more natural language expressions, or new more natural language expressions can be generated and output, allowing the user to interact with the persona using more natural language expressions.

[0019] According to the present invention, even during the service using a persona (rule tree), new case data can be added and the rule tree can be updated based on the added case data, allowing the persona to grow and the service to be localized to suit the region in which it is used.Furthermore, by providing case data for each end user, each rule tree can grow into a tailor-made rule tree tailored to the end user. [Brief explanation of the drawings]

[0020] A more detailed understanding of the embodiments disclosed herein can be had from the following description, taken in conjunction with the accompanying drawings, in which: [Figure 1] FIG. 1 is a diagram illustrating a process for generating a large rule tree in the prior art. [Figure 2]FIG. 10 is a diagram illustrating the concept of setting the address of a rule tree to be called as key information in an arbitrary element. [Figure 3] 1 is a diagram illustrating the configuration of an entire system including an information processing device 10, a user terminal 11, and a designer terminal 12 according to the present invention. [Figure 4] 10 is a diagram showing an example of elements and case information stored in case data information 106. FIG. [Figure 5] FIG. 2 is a diagram showing an example of a persona (rule tree) generated by the information processing device 10 based on case data. [Figure 6] 1 is a diagram illustrating the concept of a persona (rule tree) generated by the information processing device 10. FIG. [Figure 7] FIG. 10 is a flow diagram illustrating a process for making recommendations for a specific topic for a user using multiple personas. [Figure 8] This is a diagram explaining an example of "interaction between persona and user" and information processing performed on a group of personas. [Figure 9] FIG. 10 is a flow diagram illustrating the process of adding a new persona and modifying only the relevant personas. [Figure 10] This is a diagram illustrating the process of configuring existing personas into new personas. [Figure 11] FIG. 10 is a diagram illustrating a processing flow for converting the results of a user dialogue using multiple personas into natural Japanese and outputting the results. [Figure 12] This is a diagram explaining the concept of multiple personas generated based on case data and elements that were not included in those personas. [Figure 13] 10 is a diagram illustrating the concept of processing in which the information processing device 10 adds a recognition result as case data based on the original data of a new case and combinations of all elements and element values ​​acquired by a discovery acquisition request (ALL). FIG. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The same reference numerals in the drawings represent the same elements, and duplicated explanations will be omitted. The examples given in this specification are merely examples, and are not intended to be limiting in any way.

[0022] (System Configuration) 3 is a diagram illustrating the overall configuration of a system including an information processing device 10, a user terminal 11, and a designer terminal 12 according to the present invention. The information processing device 10, the user terminal 11, and the designer terminal 12 are connected to each other so as to be able to communicate with each other via a network 13. Although only one user terminal 11 and one designer terminal 12 are shown in FIG. 3, there may be multiple user terminals 11 and multiple designer terminals 12.

[0023] 3, like a general computer, the information processing device 10 includes a control unit 101, a main memory unit 102, an auxiliary memory unit 103, an IF unit 104, and an output unit 105, which are interconnected by a bus 120 or the like. The information processing device 10 also includes case data information 106 and rule tree information 107 in the form of a file / database or the like.

[0024] The control unit 101, also called a central processing unit (CPU), controls each component of the information processing device 10 and performs data calculations, and also reads various programs stored in the auxiliary storage unit 103 into the main storage unit 102 and executes them. The main storage unit 102, also called a main memory, stores various received data, computer-executable instructions, and data after calculation processing based on those instructions. The auxiliary storage unit 103 is a storage device typified by a hard disk drive (HDD) and stores data and programs for the long term.

[0025] 3 illustrates an embodiment in which the control unit 101, main memory unit 102, and auxiliary memory unit 103 are provided inside the same computer, but in another embodiment, the information processing device 10 can be configured to realize parallel distributed processing by a plurality of computers by using a plurality of control units 101, main memory units 102, and auxiliary memory units 103. In another embodiment, it is also possible to provide an embodiment in which a plurality of servers are installed for the information processing device 10, and the plurality of servers share a single auxiliary memory unit 103.

[0026] The IF unit 104 plays the role of an interface (IF) when sending and receiving data with other systems and devices, and provides an interface for accepting various commands and input data (various masters, tables, etc.) from a system operator. The output unit 105 provides a display screen for displaying processed data and printing means for printing the data.

[0027] The case data information 106 stores elements and case information that are the basis for generating a persona (rule tree). FIG. 4 shows an example of elements and case information stored in the case data information 106. As shown in FIG. 4, the case data includes an appropriate number of elements and case information corresponding to the elements, which are fewer than those in the prior art, and can be configured so that the number of cases for generating each persona (rule tree) is fewer than those in the prior art. The information processing device 10 generates case data including elements and case information based on the recognition results of the natural language recognition unit for new input data, or obtains case data from the designer terminal 12 and adds it to the case data information 106.

[0028] The rule tree information 107 stores information about personas (rule trees). Fig. 5 shows an example of a persona (rule tree) generated by the information processing device 10 based on case data. As shown in Fig. 5, the rule tree of a persona is relatively smaller than that of the conventional technology, making it easier to check and maintain the content.

[0029] FIG. 6 is a diagram illustrating the concept of a persona (rule tree) generated by the information processing device 10. The rule tree has a combination of multiple elements 111 and element values ​​112. Any element and element value in the rule tree may be a target element and target element value; for example, the element value 112 at the bottom of the tree may be a target element value (i.e., the conclusion of the persona). The number of target elements in a rule tree may vary depending on the content of the element. In this specification, the elements 111 and element values ​​112 may be collectively referred to as elements 100.

[0030] The element 100 may include at least the name of the event that generated the rule, the element type, the element name, the element value, the information entropy value, and an alias. The name of the event that generated the rule indicates the case (e.g., "health," "body makeup," "cost," "food selection," "physical condition," etc., described below) or the personified subject that served as the basis for generating the rule tree. The element type is a flag indicating whether the element type is a condition or a conclusion. The element name is a name indicating the content of the condition or conclusion. The element value indicates the attribute value of the condition or conclusion. The information entropy value indicates the entropy value of the element calculated by the information processing device 10 when the rule tree was generated. The entropy value can indicate how much information the element contains (also called "information value"). A high entropy value indicates that the element contains relatively more information, i.e., has relatively high information value, while a low entropy value indicates that the element contains relatively less information, i.e., has relatively low information value. An alias can indicate a value associated with the same meaning when a related element with the same meaning exists in the same or another persona, i.e., a synonym. An alias can have multiple synonyms.

[0031] 6, the information processing device 10 can set the name of the event that generated the rule for each element (also called a "node"), the element name, the element value, the information entropy value, and an alias. The information processing device 10 can store this set information in rule tree information 107.

[0032] The user terminal 11 can access the information processing device 10 to call one or more personas and use the rule trees to interact with the personas, that is, receive consulting.

[0033] The designer terminal 12 can register, in the information processing device 10, elements that are the basis for generating a persona and case information (case data information) via an input screen or the like provided by the information processing device 10.

[0034] An embodiment of the present invention can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform a particular job or implement a particular abstract data type. An embodiment of the present invention can also be implemented in a distributed computing environment where jobs are executed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media.

[0035] (Processing to make recommendations using multiple personas) FIG. 7 is a flow diagram illustrating an example of a process for making recommendations on a specific topic for a user using multiple personas. In explaining this processing flow, an example of making dietary recommendations using multiple personas will be used as an example to explain the process using the entropy value of a node. The rule tree information 107 stores personas for "health," "body makeup," "cost," and "diet selection," and each persona includes at least the following elements, but is not limited to these: "Health" persona: calories, various nutrients, etc. "Body Make" Persona: Calories, various nutrients, muscle mass, target weight, etc. "Cost" persona: food prices, contents of the refrigerator, etc. "Food Selection" persona: What you ate recently, other persona targets, etc.

[0036] In S701, the information processing device 10 reads a persona associated with a topic (e.g., a "health" persona) from the rule tree information 107 and acquires the entropy value of each node in the rule tree. The topic may be received from the user terminal 11, or may be a topic that has been selected as a candidate by the processing of S709, which will be described later. The information processing device 10 identifies the node having the highest entropy value among the acquired entropy values ​​as a "high-priority element" and executes a program associated with the identified element. For example, if the node having the highest entropy value is the top node in the rule tree, the information processing device 10 executes the program associated with the top node.

[0037] Figure 8 is a diagram illustrating an example of "interaction between persona and user" executed in this processing flow and the information processing performed on the persona group. In the example of Figure 8, the top node of the "health" persona is identified and marked by the processing of S701.

[0038] Here, the entropy value of a persona will be explained. Each node of a persona (rule tree) is associated with an entropy value calculated by the information processing device 10. The entropy value indicates the amount of information (information value) contained in the node, and the higher the entropy value, the greater the amount of information. In this embodiment, a node with a high entropy value, i.e., a node containing a lot of information, is considered to be a "high priority element."

[0039] In one embodiment of the present invention, the information processing device 10 can be configured to control the element selection method by changing the entropy value of each node using parameters and weighting based on instructions from the designer terminal 12. In the present invention, the information processing device 10 can set information that controls the element selection method via a setting command from the designer terminal 12. In other words, the information processing device 10 can also be configured to select elements based on information associated with elements other than the above-mentioned "entropy value."

[0040] In S702, when the information processing device 10 executes a program associated with the identified element, it displays a comment associated with the element on the user terminal 11 (arrow "A" in FIG. 8). As shown in "A" in FIG. 8, the information processing device 10 can display a comment such as "How many calories do you consume per day?" on the display of the user terminal 11.

[0041] In S703, the information processing device 10 acquires the value of the user's answer from the user terminal 11 (arrow "B" in FIG. 8), and performs processing to mark the combination of the identified element and the acquired value as having acquired a value on the node of the persona. By this processing, the top node of the "health" persona and the value associated therewith may be marked as having acquired a value. Note that, as long as it is clear that a value has been acquired, any value other than marking may be set in the element or element value to indicate that it has been acquired, and the method for doing so is not particularly limited.

[0042] In S704, the information processing device 10 queries the rule tree information 107 to determine whether a node having the combination of the identified element and the acquired value exists in another persona. More specifically, the information processing device 10 reads the alias set for the element of this combination and identifies elements to which aliases having the same replacement value as the read alias and replacement values ​​that are acceptable (i.e., similar) as the same replacement value according to predetermined criteria are set. The identified element may exist in the rule tree of the same persona, or in the rule tree of another persona. Note that in the present invention, the information processing device 10 can also determine whether the same or similar combination exists by using the element-value combination itself without using an alias.

[0043] If it is determined as a result of the inquiry that the same or similar combination exists, in S705 the information processing device 10 marks one or more combinations of elements and element values ​​of the determined one or more personas as having acquired values. For example, in "C" in Fig. 8, the combination of a specific element and element value of the "body make" persona is determined to be the same combination, and is marked by the information processing device 10.

[0044] In S706, the information processing device 10 determines whether all elements and element values ​​existing between the top node and the target element of each persona marked in the processes of S703 and S705 (i.e., whose values ​​have been acquired) have been acquired. In the example of Fig. 8, all elements and values ​​existing between the top node and the target element of the "Body Makeup" persona have been acquired.

[0045] If it is determined that all of the values ​​have been acquired, in S707, the information processing device 10 determines that the value of the target element (i.e., the conclusion of the persona) has been acquired, and displays a comment (value value) of the target element value on the display of the user terminal 11. In "D" in Fig. 8, the information processing device 10 displays a comment such as "From the perspective of body building, I would like you to eat a little more now" on the display of the user terminal 11.

[0046] In S708, the information processing device 10 queries the rule tree information 107 to determine whether elements identical to or similar to the acquired target element value exist in other personas. More specifically, the information processing device 10 reads the alias set for the target element and determines whether there are elements for which aliases are set that have the same replacement value as the read alias and that are acceptable replacement values ​​according to predetermined criteria. If the determination results in the existence of elements, the information processing device 10 marks those elements as having values ​​already acquired. After this process, the process returns to S706.

[0047] If the result of the query processing in S704 is that it is determined that no identical or similar combinations exist, and if the result of the judgment processing in S706 is that it is determined that all elements and element values ​​existing between the top node of each persona and the target element have not been acquired, in S709, the information processing device 10 selects the next topic.

[0048] In S709, the information processing device 10 compares the entropy values ​​of unmarked nodes among the elements in the rule tree of the persona in which the element identified in S704 exists, and selects an "element with high priority." The selected element becomes the next topic, and processing returns to S701, where the information processing device 10 executes a program associated with the element selected as the "element with high priority." Processing then proceeds to S702.

[0049] Alternatively, in S709, the information processing device 10 compares the entropy values ​​of unmarked nodes among the elements of the rule trees of each persona determined in S706, and selects an "element with high priority." The selected element becomes the next topic, and processing returns to S701, where the information processing device 10 executes a program associated with the element selected as the "element with high priority." Thereafter, processing proceeds to S702.

[0050] In S709, two processes were explained, but the difference is that the former compares entropy values ​​within the same persona, while the latter compares entropy values ​​within the same and other personas. In other words, in the latter case, there is a possibility that a topic will be selected from another persona.

[0051] In the example of the above embodiment, the next topic element is determined based on the entropy value, but this is just one example. In the present invention, the information processing device 10 can select an element identified based on predetermined requirements as the next topic element.

[0052] The predetermined requirements for identifying an element can be roughly divided into two categories. One is that the information processing device 10 identifies an element based on one or more of text information, audio information, and image information that can be acquired via any sensor or device. The other is that the information processing device 10 identifies an element based on information obtained from a rule tree.

[0053] More specifically, the information processing device 10 can select the next topic element based on one or more of the following information acquired via any sensor or device: -Compare the user's facial expression obtained from an arbitrary facial recognition system with the facial expressions of various people that have been learned in advance to determine whether the user's emotion is positive or negative, and decide whether to continue the conversation using the rule tree for the current topic, or to have a conversation that can transition to a rule tree for another topic (e.g., "By the way, regarding XX...", etc.). - Determine whether the user is likely to continue the conversation based on whether the string entered by the user contains predetermined words. If it is determined that the user is likely to continue the conversation, select an element in the currently selected rule tree that has not yet been given a value as the next topic. On the other hand, if it is determined that the user does not want to continue the conversation because, for example, the same conversation has continued more than a predetermined number of times, words suggesting boredom have appeared, or the length of the conversation sentence has decreased by more than a predetermined percentage compared to the previous input, suggesting waning interest, change to a different rule tree.

[0054] More specifically, the information processing device 10 can select the next topical element based on information associated with the element other than the "entropy value." For each route from the top node of each of the multiple rule trees currently being discussed to the target element, the ratio of the number of elements marked with an element value (the value is known) to the total number of elements is calculated, and the rule tree with the root having the highest calculated ratio is selected as the rule tree for the next topic. Then, any element from the elements at the root of the selected rule tree is presented to the user as the next topic. This allows the information processing device 10 to prioritize the selection of rule trees that are likely to lead to a conclusion.

[0055] The above processing flow enables the information processing device 10 to make recommendations for a specific topic for a user using multiple personas. For this reason, in conventional technology, a rule tree had to be prepared in advance to provide consulting to a user on a specific theme or problem, but according to the present invention, elements of different rule trees can be connected by using information associated with elements, such as entropy values ​​and aliases associated with elements, and information acquired via any sensor or device, thereby enabling consulting for complex problems.

[0056] (Process to add persona) 9 and 10, we will explain the information processing for adding a new persona based on a viewpoint that is missing from an existing persona group and modifying only related personas. Fig. 9 is a flow diagram explaining the processing for adding a new persona and modifying only related personas. Fig. 10 is a diagram explaining the processing for configuring an existing persona group into a new persona group.

[0057] In this processing flow, we will look at a case where, after generating an existing group of personas, the "food selection" persona's food recommendations were missing the element of physical condition, and the persona needed to determine whether the persona was good or bad. For example, elements of the "physical condition" persona include, but are not limited to, chronic illness, stomach upset, calories, and nutrients.

[0058] In S901, the information processing device 10 acquires case data of the "Physical Condition" persona to be added from the designer terminal 12 and stores it in the case data information 106. Taking into consideration the elements of the existing personas, the designer prepares case data of the "Physical Condition" persona to be newly added and case data of the existing persona to be changed. As shown in Figure 10, the elements included in the case data of the "Physical Condition" persona are a mixture of common elements that are also included in the existing personas and newly added elements.

[0059] In S902, the information processing device 10 generates a rule tree for the “physical condition” persona based on the added case data, and stores it in the rule tree information 107.

[0060] In S903, the information processing device 10 acquires the case data of the “meal selection” persona to be corrected from the designer terminal 12, and updates the data stored in the case data information 106.

[0061] In S904, the information processing device 10 regenerates the rule tree for the "meal selection" persona based on the updated case data.

[0062] As described above, in this processing flow, only personas related to the added element need to be newly generated or modified (replaced), and unrelated personas remain unchanged. This reduces the scope of control, making it much easier to maintain and check the content of each persona. In other words, the new persona group shown in Figure 10 can be reconfigured with minimal addition and modification. Note that the order of the above flow may be changed; for example, the order of S902 and S903 may be changed.

[0063] (Process of converting output results into natural language) FIG. 11 illustrates a process flow for converting the results of a user dialogue using multiple personas into natural Japanese and outputting the results. If the elements of a rule tree generated from a case study and the values ​​of the target element are output without editing, the linguistic expression may not be natural. For this reason, the information processing device 10 can convert the output content presented to the user into natural linguistic expression according to the method shown in FIG. 11.

[0064] In the example described below, it is assumed that the user selects a general theme of the conversation, i.e., a persona that can be a target, when starting a conversation with a persona. For example, the user can select a general theme of the conversation, such as health, learning, shopping, or hobbies, which allows the information processing device 10 to select a target persona (rule tree).

[0065] In S1101, when a dialogue between a user and a persona starts, the information processing device 10 generates a real-time communication content table (referred to herein as an "RTC content table") associated with the user dialogue, inputs the utterance at the start of the dialogue set in the top node of the selected persona (for example, "Hello. What shall we talk about?") into the RTC content table, and provides it to the user terminal 11. As a result, the utterance at the start of the dialogue is displayed on the display of the user terminal 11.

[0066] In S1102, the user inputs information into the RTC content table via the user terminal 11 in response to a statement made at the start of the dialogue or in response to dialogue content received from the persona, and the information processing device 10 receives the user input into the RTC content table.

[0067] In step S1103, the natural language recognition unit of the information processing device 10 acquires all elements and element values ​​of a persona group, including the selected persona, through a discovery and acquisition request (GROUP) and analyzes the content of the user input in the RTC content table based on the acquired information. The user input sentence may not match the information on elements, target elements, and their values ​​in the rule tree. Therefore, the natural language recognition unit segments the user input sentence according to predetermined rules, determines whether each segmented word matches or is similar to the acquired combination of elements and element values, and identifies the elements and element values ​​associated with each segmented word. In the present invention, the information processing device 10 can determine whether each segmented word is similar to the acquired combination of elements and element values ​​based on similar expressions listed in the similarity criteria table. Similar expressions listed in the similarity criteria table indicate expressions that may be considered similar, even if they are not identical. For example, similar expressions can indicate that the expression "A" is similar to the expressions "A1" and "A2."

[0068] In S1104, the information processing device 10 determines whether the element identified in S1103 is a target element. An element type (target flag) can be set for elements in the rule tree, and each element can be set to be a target element (conclusion) or an element (condition). If the result of the determination is that it is a target element, the process proceeds to S1106, and if it is not a target element, the process proceeds to S1105.

[0069] In S1105, the information processing device 10 performs natural language generation processing by the generation request function using the information of the identified element and element value, inputs a first natural language expression associated with the identified element and element value into the RTC content table, and provides it to the user terminal 11. The natural language generation processing by the generation request function of the information processing device 10 means converting information of one element and element value into a natural expression.

[0070] In S1106, the information processing device 10 causes the conversion unit of the information processing device 10 to perform a conversion process using the identified target element and target element value, and the content that has been input to the RTC content table up to that point. The conversion unit cooperates with the generative AI and uses functions provided in the generative AI to generate a second natural language expression based on the target element, target element value, and the input content of the RTC content table. The "second natural language expression" refers to a natural language expression generated using functions provided in the generative AI.

[0071] The "first natural language expression" is a natural language expression obtained by converting the values ​​of elements and element values ​​into a natural language expression, and therefore can be processed by the generation request function of the information processing device 10. On the other hand, the "second natural language expression" is generated from the target elements and target element values ​​of one or more personas, as well as the input contents of the RTC content table, and therefore there is a large amount of information to be processed, and the natural language expression is generated using the functions provided in the generative AI.

[0072] When generating natural language expressions such as those described above, the information processing device 10 can separate words and intentions when generating such expressions. Specifically, the information processing device 10 cooperates with a generative AI and utilizes the functions of the generative AI to generate words that are in line with the current trend and local context for the conclusions (target elements, values) reached by a persona. Furthermore, the information processing device 10 can generate appropriate words by combining the conclusions (target elements, values) reached by multiple personas. For example, when a first persona reaches the conclusion "encourage" and a second persona reaches the conclusion "admonish," the words generated will be different from the words generated when the first persona reaches the conclusion "encourage" and the second persona reaches the conclusion "empathize with the other person's position." While appropriate words differ depending on each conclusion, the information processing device 10 can use the functions of the generative AI to appropriately express the conclusions reached by multiple personas and output them to the RTC content table. Therefore, according to the present invention, it is not necessary to prepare different words for each combination of conclusions reached by multiple personas.

[0073] In S1107, the information processing device 10 inputs the conversion result, i.e., the second natural language expression, into the RTC content table and provides it to the user terminal 11. This enables the information processing device 10 to provide the user with a dialogue result in more natural language expression for a user dialogue using multiple personas.

[0074] (Processing of adding the recognition result of the natural language recognition unit of the information processing device 10 to the case) The information processing device 10 can store the recognition result of the natural language recognition unit as a new case in the case data information 106. The information processing device 10 has been described above with reference to FIGS. 4 and 5 as generating a persona (rule tree) from case data. However, when generating a persona, not all elements included in the case data are used, and some elements with low information value are pruned. FIG. 12 is a diagram illustrating the concept of multiple personas generated based on case data and elements not included in those personas. As shown in FIG. 12, the information processing device 10 generates a first persona, a second persona, etc. from the case data and stores them in the rule tree information 107, and stores information on the pruned elements in the auxiliary storage unit 103.

[0075] The discovery acquisition request described above is a function for acquiring a combination of elements and element values, and when using the discovery acquisition request, the information processing device 10 can control the range of information to be acquired by specifying the following four parameters. Note that in S1103, the discovery acquisition request (GROUP) is used, so all elements and element values ​​of the persona group including the persona selected in that dialogue are acquired.

[0076] [Table 1]

[0077] 13 explains the concept of the process in which the information processing device 10 adds a recognition result as case data based on the original data of a new case and all combinations of elements and element values ​​acquired by a discovery acquisition request (ALL). The information processing device 10 determines which element and element value acquired corresponds to the input data from the original data of the case, and stores the combination of elements and case as the determination result (recognition result) in the case data information 106. This process accumulates case data and refines the persona group.

[0078] Although the principles of the present invention have been described above with reference to exemplary embodiments, various embodiments that change in configuration and details can be realized without departing from the spirit of the present invention. That is, the present invention can be embodied as, for example, a system, an apparatus, a method, a program, or a storage medium. [Explanation of symbols]

[0079] 10. Information processing equipment 11 User terminal 12 Designer Terminals 101 Control section 102 Main memory 103 Auxiliary storage 104 IF Section 105 Output section 106 Case Data Information 107 Rule Tree Information 111 Elements 112 Element Value

Claims

1. generating an RTC content table associated with the persona selected by the user; Obtaining all elements and element values ​​of a group of personas including the selected persona; Identifying relevant elements and element values ​​by analyzing user input entered into the RTC content table based on the obtained elements and element values; On the condition that the identified element and element value are a target element and a target element value, performing a conversion process on the target element and the target element value and all user inputs entered in the RTC content table; outputting the conversion results to the RTC content table for presentation to the user; An information processing device configured to execute the above.

2. 2. The information processing device of claim 1, further configured to perform a natural language generation process based on the identified element and element value, on the condition that the identified element and element value are not a target element and target element value, and input the generated natural language expression into the RTC content table for presentation to the user.

3. Obtaining all elements and element values ​​associated with each persona of the personas as a first element and a first element value; When generating the persona, an element and an element value that were not selected as an element of the persona are acquired as a second element and a second element value; determining whether input data from the original data of the case corresponds to the acquired first element and first element value or the acquired second element and second element value, and storing a combination of the element and the case as a determination result; An information processing device configured to execute the above.

4. A method performed by an information processing device, comprising: generating an RTC content table associated with the persona selected by the user; Obtaining all elements and element values ​​of a group of personas including the selected persona; Identifying relevant elements and element values ​​by analyzing user input entered into the RTC content table based on the obtained elements and element values; On the condition that the identified element and element value are a target element and a target element value, performing a conversion process on the target element and the target element value and all user inputs entered in the RTC content table; outputting the conversion results to the RTC content table for presentation to the user; A method for providing the above.

5. 5. The method of claim 4, further comprising: performing a natural language generation process based on the identified element and element value, provided that the identified element and element value are not a target element and target element value, and inputting the generated natural language expression into the RTC content table for presentation to the user.

6. A method executed by an information processing device, comprising: Obtaining all elements and element values ​​associated with each persona of the personas as a first element and a first element value; When generating the persona, an element and an element value that were not selected as an element of the persona are acquired as a second element and a second element value; determining whether input data from the original data of the case corresponds to the acquired first element and first element value or the acquired second element and second element value, and storing a combination of the element and the case as a determination result; A method for providing the above.

7. A program that causes a computer to execute the method according to any one of claims 4 to 6.

Images