Information processing device, information processing method, and program

Abstract

A multi-layered persona is generated by learning the user's thoughts that determine the final indicators. [Solution] The information processing device is configured to perform the following: querying a case data DB based on initial dialogue information received from a user terminal to read case data associated with the initial dialogue information, generating a first group of personas based on the case data; obtaining user ratings from the user terminal for each combination of elements and element values ​​of each persona in the first persona group; determining, based on the user ratings, whether the user ratings are positive or negative for each combination of elements and element values ​​of each persona in the first persona group; updating the read case data based on the user ratings; and generating a second group of personas based on the updated case data that is in line with the user's individual circumstances.

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 learns the thoughts of a user who determines a final indicator and generates a multiplexed persona. [Background technology]

[0002] A technology that generates "personas" by imitating humans is known (Patent Document 1). Personas may also be called conversational AI (artificial intelligence), and are a technology that enables computers to perform human-like intellectual activities such as recognition, inference, judgment, prediction, and proposals based on rule trees (decision trees). This technology can also treat personas generated for all aspects that make up a person (work, family, region, individual, hobbies, etc.) as a collection, and each persona can include one or more rule trees. The system in Patent Document 1 generates a persona of a human to be imitated, called a donor, and general users can access the system using their own devices and converse with the persona.

[0003] The system in Patent Document 1 expresses cases based on input data as pairs of elements (condition attributes) and target elements (conclusion attributes), and generates a rule tree by learning rules for estimating target element values ​​(conclusion attribute values) from element values ​​(condition attribute values) observed based on the cases. The system in Patent Document 1 outputs target element values ​​by automatically tracing the rule tree based on the response methods (element values) to preset question items (elements). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7216449 Summary of the Invention [Problem to be solved by the invention]

[0005] In the system described in Patent Document 1, the personaization system generates personas of experts in various fields and provides them to general users as conversation partners, allowing the general user to receive consulting services. However, the various problems in modern society are complex. While the problems people face may at first glance appear to be categorized into specific themes, in reality, the problems may arise from a mixture of various factors and the overlapping of various causes. When people converse with each other about a certain theme or problem, the topic may change to another theme or problem if a specific keyword comes up. In such cases, consulting cannot be provided by experts in a specific field alone; cooperation from experts in other fields is required.

[0006] It is possible to generate a digital chimera by combining the personas of multiple experts to address various problems. However, simply combining the personas of multiple experts will not adequately address the problems faced by general users. For example, in the medical field, even when prescribing the same medication, different doctors may have different criteria for prescription instructions, and nurses may have different rules for administering prescription medication. Furthermore, even when prescribing and administering the same medication for the same illness, different medical institutions may have different rules.

[0007] For this reason, simply combining the personas of multiple experts will result in a huge rule tree. 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) Considering the possibility of branching out into various themes and issues, the amount of information (elements) required for one case becomes 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. For this reason, simply combining the personas of multiple specialists is likely to pose major operational challenges. In the example of the medical field mentioned above, the selection of prescription drugs and the method of administration may differ depending on the individual circumstances of the patient (the general user), such as their health condition and their relationship with those around them, such as their family.

[0008] For this reason, there is a demand for combining the personas of multiple experts based on the individual circumstances of ordinary users to generate tailor-made digital chimeras (a collection of multiple personas).

[0009] The present invention has been made to solve such problems, and aims to provide an information processing device, information processing method, and program that learns the thoughts of users who determine final indicators and generates a multiplexed persona that is personified. [Means for solving the problem]

[0010] In order to solve the above problems, the information processing device according to the present invention comprises: An information processing device including a control unit and a storage unit, The storage unit includes a case data DB that stores elements associated with experts and case information that serve as a basis for generating personas, The control unit querying the case data DB based on initial dialogue information received from the user terminal to read out case data associated with the initial dialogue information; generating a first expert persona based on the retrieved case data; generating a first set of personas including the first expert persona; acquiring, from the user terminal, a user evaluation for each combination of an element and an element value of each persona in the first persona group; determining whether a user evaluation is positive or negative for each combination of an element and an element value of each persona in the first group of personas based on the user evaluation; updating the read case data based on the determination; generating a first modified expert persona based on the updated case data; generating a user persona based on combinations of elements and element values ​​that result in positive user ratings and combinations of elements and element values ​​that result in negative user ratings; generating a second set of personas including the first modified expert persona and the user persona; is configured to execute [Effects of the Invention]

[0011] According to the present invention, it is possible to adjust each persona included in a persona group associated with the service content desired by the user to suit the individual circumstances of the user. Furthermore, when conducting a dialogue with a user, it is possible to estimate the likelihood of obtaining a positive or negative evaluation if the dialogue proceeds as planned. Furthermore, when generating a persona group to be used in a dialogue with a user so that the dialogue with the user does not result in a negative evaluation, it is possible to generate a desired persona by selecting and discarding case data. [Brief explanation of the drawings]

[0012] 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] 1 is a diagram illustrating the configuration of an entire system including an information processing device 10, a user terminal 11, and an expert terminal 12 according to the present invention. [Figure 2] 1 is a system configuration diagram of an information processing device 10 according to the present invention. [Figure 3]10 is a diagram showing an example of elements and case information of each expert stored in case data information 106, and an example of a rule tree of personas of each expert generated from them. FIG. [Figure 4] FIG. 10 is a diagram illustrating a rule tree. [Figure 5] This is a flow diagram explaining the process in which a first multiplexed persona is generated through an initial dialogue between the user terminal 11 and the information processing device 10, and then a second multiplexed persona tailored to the user's individual circumstances is generated through expert dialogue. [Figure 6] FIG. 10 illustrates an example of merged case data and an example of an expert persona generated from the merged case data. [Figure 7] A figure showing an example of a first multiplexing persona group and a second multiplexing persona group. [Figure 8] FIG. 10 is a diagram illustrating the process of adjusting the combination of elements and element values ​​of each persona included in the second persona group. [Figure 9] FIG. 10 is a diagram illustrating whether each combination of target elements and target element values ​​is a positive evaluation or a negative evaluation. [Figure 10] FIG. 1 illustrates an example of a first modification expert persona and a second modification expert persona. DETAILED DESCRIPTION OF THE INVENTION

[0013] 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.

[0014] In this specification, examples of services provided by experts include medical services, legal services, accounting and tax services, etc. Medical services can be provided by a team of experts such as doctors, dentists, dental hygienists, nurses, public health nurses, physical therapists, occupational therapists, radiologists, and pharmacists. Legal services can be provided by a team of experts such as lawyers, judicial scriveners, patent attorneys, and administrative scriveners. Accounting and tax services can be provided by a team of experts such as certified public accountants, tax accountants, social insurance and labor consultants, and small and medium-sized business management consultants. Although this specification will be described using medical services as an example, the present invention can be applied to various professional services.

[0015] (Overall structure and functions of each component) Fig. 1 is a diagram illustrating the configuration of an entire system including an information processing device 10, a user terminal 11, and an expert terminal 12 according to the present invention. The information processing device 10 is connected to the user terminal 11 and the expert terminal 12 via any network so as to be able to communicate with each other. Although Fig. 1 shows only one user terminal 11 and one expert terminal 12, there may be multiple of these.

[0016] The information processing device 10 provides the user terminal 11 with an interactive application for conducting an interaction between the user and the information processing device 10. The information processing device 10 can communicate text information, audio information, and / or image information with the user terminal 11 via the interactive application. In response to access from the user terminal 11, the information processing device 10 provides the user terminal 11 with an initial interactive screen (first screen) of the interactive application. The initial interactive screen provides an interface that allows the user to input or select what they would like to consult about. For example, in the case of medical services, this interface allows the user to input or select information such as the reason for visiting the hospital, symptoms (chief complaint), the seriousness of the reason for visiting the hospital, the specific location of the symptoms, the progression of the symptoms, medical history, and the desired medical department. The input or selected information is called initial interactive information.

[0017] When the information processing device 10 receives initial dialogue information from the user terminal 11 via the initial dialogue screen, it analyzes the initial dialogue information. Based on the analysis result of the initial dialogue information, the information processing device 10 reads out case data associated with the initial dialogue information and generates a first expert persona based on each of the case data. The information processing device 10 can merge the read out case data and generate a second expert persona based on the merged case data. The first expert persona plays the role of an individual expert, and the second expert persona plays the role of an expert team. The information processing device 10 can combine the first expert persona and / or the second expert persona into a first multiplexed persona group.

[0018] The information processing device 10 receives and stores case data associated with each expert from the expert terminal 12. The information processing device 10 can generate a first expert persona, which is a persona of each expert, based on the stored case data, and stores data of the first expert persona (rule tree). The information processing device 10 can merge the stored case data based on predetermined conditions, and generate a second expert persona as a team of experts based on the merged case data.

[0019] The information processing device 10 can allow a user to interact with a first multiplexed persona group via an expert dialogue screen (second screen) of a dialogue application. The information processing device 10 displays a query about each combination of elements and element values ​​included in each of the first multiplexed persona group on the user terminal 11 and acquires a response from the user. The user's response may be a positive user evaluation (e.g., "OK") or a negative user evaluation (e.g., "NG"). In detail, during a conversation via the expert dialogue screen, the information processing device 10 can repeatedly trace the elements and element values ​​of the rule trees of the first expert persona and the second expert persona based on the above queries and responses, and determine which combinations of elements and element values ​​will result in a positive user evaluation or a negative user evaluation. The information processing device 10 can generate a user persona based on the positive and negative user evaluations for each combination of elements and element values.

[0020] The information processing device 10 updates the case data based on combinations of elements and element values ​​that result in positive user evaluations and combinations of elements and element values ​​that result in negative user evaluations. The information processing device 10 generates a first correction expert persona based on the updated case data. The information processing device 10 merges the updated case data and generates a second correction expert persona based on the merged updated case data. The information processing device 10 can combine the first correction expert persona, the second correction expert persona, and / or the user persona into a second multiplexed persona group.

[0021] The user terminal 11 may be any type of device (e.g., a smartphone, a PC, a tablet terminal, etc.) that can operate in a wired or wireless environment, and is not limited to a specific apparatus or device. The user terminal 11 can cause the information processing device 10 to generate case data and a rule tree that are tailored to the user's individual circumstances by interacting with the information processing device 10 via an initial dialogue screen and an expert dialogue screen.

[0022] The expert terminal 12 can transmit case data of services provided by experts, such as medical services, legal services, accounting and tax services, to the information processing device 10. This case data is stored in the case data information 106.

[0023] (System Configuration) 2 is a system configuration diagram of an information processing device 10 according to the present invention. Similar to 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, rule tree information 107, and user-specific persona information 108 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] 2 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 of experts, which are the basis for generating personas (rule trees). FIG. 3 shows an example of elements and case information of each expert stored in the case data information 106, and an example of a rule tree for each expert's persona generated from them. The case data includes elements of each expert and case information corresponding to the elements. For example, FIG. 3 shows an example of case data of expert A, which shows elements and case information. The information processing device 10 can generate case data including elements and case information based on the recognition result of the natural language recognition unit for input data received from the expert terminal 12 and add it to the case data information 106, or can add case data input via a case data input screen (not shown) to the case data information 106.

[0028] The rule tree information 107 stores information about personas (rule trees) generated based on case data. The example of Fig. 3 shows an example in which the information processing device 10 generates personas (rule trees) based on each piece of case data for an expert. The elements illustrated in Fig. 3 become elements in the persona, and the case information becomes element values ​​in the persona.

[0029] Here, a rule tree will be described with reference to FIG. 4. A rule tree has a combination of multiple elements 111 and element values ​​112. Any element (condition attribute) and element value (condition attribute value) in a rule tree may be a target element (conclusion attribute) and target element value (conclusion attribute value). For example, the element value 112 at the bottom of the tree may be a target element value (i.e., a persona conclusion). The branch structure and the number of target elements in a rule tree may be determined according to the content of the elements. In this specification, the elements 111 and element values ​​112 may be collectively referred to as "elements" (or "nodes"). An element value may be set to call another element in the same rule tree or an element in another rule tree, and may also be set to execute any program (executable file, API).

[0030] When generating (constructing) a rule tree, the information processing device 10 can set the name of the case that generated the rule for each element (node), the element name, the element value, the information entropy value, and an alias. The node can 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 case that generated the rule indicates the case or personaized subject (e.g., an expert) that was the source of generating the rule tree. The element type is a flag that indicates whether the type of element is a condition or a conclusion. The element name is a name that indicates 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] 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 may be executed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media.

[0032] (Process to generate multiple personas according to the individual circumstances of the user) The process of generating a different multiplexed persona for each user through two types of dialogue will be described with reference to Fig. 5. Fig. 5 is a flow diagram illustrating the process of generating a first multiplexed persona through an initial dialogue between the user terminal 11 and the information processing device 10, and then generating a second multiplexed persona tailored to the user's individual circumstances through an expert dialogue.

[0033] In S501, the information processing device 10 responds to access from the user terminal 11 by providing the user terminal 11 with an initial dialogue screen (first screen) of the dialogue application. The initial dialogue screen provides an interface that allows the user to input or select information about the user himself or herself and the content of the service the user wishes to receive. Note that the content that can be input or selected in this interface differs depending on the field of the service provided. The content that is input or selected on the initial dialogue screen is called initial dialogue information, and is used when generating a first multiplexed persona. The user terminal 11 transmits the initial dialogue information to the information processing device 10.

[0034] In S502, when the information processing device 10 receives initial dialogue information from the user terminal 11 via the initial dialogue screen, it analyzes the initial dialogue information. This analysis process may be performed based on whether the initial dialogue information contains a predetermined phrase. If the initial dialogue information is voice, voice recognition technology may be used to convert the voice data into text, or meaning, emotion, keywords, etc. may be grasped from the voice data. The information processing device 10 queries the case data information 106 based on the analysis result of the initial dialogue information, reads out case data associated with the initial dialogue information, and generates a first expert persona based on each of the case data, as exemplified in FIG. 3. The first expert persona is a persona (rule tree) that is generated commonly for all users if a specific keyword is included in the initial dialogue information.

[0035] The information processing device 10 can merge case data read from the case data information 106 to generate merged case data as exemplified in FIG. 6(a). The merged case data may be case data of experts of the same profession (e.g., case data of multiple nurses) merged together, or case data of experts of different professions (e.g., case data of a doctor, case data of a pharmacist, and case data of a nurse) merged together. The information processing device 10 can generate a second expert persona as exemplified in FIG. 6(b) based on the merged case data.

[0036] The first expert persona plays the role of an individual expert, and the second expert persona plays the role of an expert team. The information processing device 10 can configure a first multiplexed persona group by combining the first expert persona and (optionally) the second expert persona. That is, the first multiplexed persona group may be composed of only the first expert persona, or may be composed of the first expert persona and the second expert persona. FIG. 7(a) shows an example of a first multiplexed persona group, in which three first expert personas and one second expert persona are shown. In another example, the first multiplexed persona group may include only a plurality of first expert personas.

[0037] In S503, in response to the generation of the first multiplexed persona group, the information processing device 10 provides an expert dialogue screen (second screen) to the user terminal 11. The expert dialogue screen is an interface for obtaining an evaluation from a final evaluator (e.g., a user) for each combination of elements and element values ​​of each persona in the first multiplexed persona group. The information processing device 10 displays a query about each combination of elements and element values ​​of each persona in the first multiplexed persona group to the user terminal 11 via the expert dialogue screen and acquires a user response from the user terminal 11. The query may be something like "Would you use △△ when XX occurs?", where 〇〇 corresponds to the content of the element and △△ corresponds to the content of the element value. The user response may be a positive user evaluation (e.g., "Use" or "OK") or a negative user evaluation (e.g., "Do not use" or "NG").

[0038] At S504, the information processing device 10 determines which combinations of elements and element values ​​result in positive or negative user evaluations by tracing the elements and element values ​​of the rule trees of the first expert persona and the second expert persona in the first multiplexed persona group based on the inquiry and the user response. This process enables the information processing device 10 to determine whether identical and similar combinations of elements and element values ​​in each persona in the first multiplexed persona group result in positive or negative user evaluations. The information processing device 10 can use aliases to determine whether elements and element values ​​are identical or similar, but the determination may also be based on parameters other than aliases. The element and element value combinations may be target elements and target element values. The information processing device 10 updates the case data used to generate the first expert persona and the second expert persona in the first multiplexed persona group based on the element and element value combinations that result in positive user evaluations and the element and element value combinations that result in negative user evaluations. The information processing device 10 generates a first modified expert persona based on the updated case data. The information processing device 10 can merge the updated case data and generate a second modified expert persona based on the merged updated case data.

[0039] The information processing device 10 generates a user persona based on a combination of elements and element values ​​that result in a positive user evaluation and a combination of elements and element values ​​that result in a negative user evaluation. The information processing device 10 can associate the updated case data, the updated merged case data, the user persona, the first modified expert persona, and the second modified expert persona with the user information and store them in the user-specific persona information 108. This allows the information processing device 10 to have case data and expert personas tailored to the individual circumstances of the user.

[0040] In S505, the information processing device 10 can configure a second multiplexed persona group by combining the first correction expert persona, the second correction expert persona, and the user persona. FIG. 7(b) shows an example of the second multiplexed persona group, which includes three first correction expert personas, one second correction expert persona, and a user persona. In another example, the second multiplexed persona group may include only a plurality of first correction expert personas. In this specification, since the example is a medical setting, the user persona is referred to as a "patient persona."

[0041] As described below, the second multiplexed persona group includes updated personas and user personas, with case data updated based on the content of user responses, resulting in a different persona group for each user.

[0042] (The process of adjusting the element values ​​of a persona based on the individual circumstances of the user) 8 is a diagram illustrating a process for adjusting the combination of elements and element values ​​of each persona included in the second persona group. This process can be executed after the user persona is generated in S504.

[0043] In S801, the information processing device 10 determines which combinations of elements and element values ​​result in positive or negative user evaluations, and adds values ​​indicating the respective evaluations to the target element values ​​of the user persona. The user persona includes combinations of elements and element values ​​that result in positive user evaluations and combinations of elements and element values ​​that result in negative user evaluations. The information processing device 10 can add a first value to the target element values ​​of target elements and target element values ​​that can be traced back from the combinations of elements and element values ​​that result in positive user evaluations. The information processing device 10 can also add a second value to the target element values ​​of target elements and target element values ​​that can be traced back from the combinations of elements and element values ​​that result in negative user evaluations. In FIG. 9, when (element, element value) = (c, c1), (a, a1) is traced back by the information processing device 10, it is shown whether each combination of target elements and target element values ​​results in a positive evaluation or a negative evaluation (the tree portion indicated by "*1" in FIG. 9). As in this example, the information processing device 10 can determine which combination of target element and target element value is a positive evaluation or a negative evaluation, and add a positive or negative evaluation to the target element value.

[0044] In S802, the information processing device 10 updates the case data read out in S502 based on the combinations of elements and element values ​​that result in positive user evaluations and the combinations of elements and element values ​​that result in negative user evaluations. In this update process, case data associated with combinations of elements and element values ​​that result in negative user evaluations may be deleted, that is, updated so as not to be included, or the value of information entropy assigned to element values ​​when a persona is generated may be controlled so that the combination is less likely to be selected in a conversation.

[0045] The information processing device 10 generates a first correction expert persona based on the updated case data. The information processing device 10 merges the updated case data and generates a second correction expert persona based on the merged updated case data. FIG. 10 is a diagram showing an example of the first correction expert persona and the second correction expert persona. In FIG. 10, combinations where (element, element value) = (b, b2), (e, e1) are highlighted. The information processing device 10 controls the entropy value of the highlighted combination of element and element value to make it less likely to be selected. In another embodiment of the present invention, a rule tree may be generated so that the highlighted combination of element and element value is not included.

[0046] Here, the entropy value of a persona will be described. 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, with a higher entropy value indicating a larger amount of information. For example, a node with a high entropy value, i.e., a node containing a large amount of information, can be designated as a "high-priority element." For this reason, in an 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 information on the combination of elements and element values.

[0047] In S803, the information processing device 10 generates a second multiplexed persona group by combining the first correction expert persona, the second correction expert persona, and the user persona as one, as described in S505.

[0048] 8, the information processing device 10 can identify which combinations of target elements and target element values ​​will result in a negative evaluation, making it possible to easily update case data. Furthermore, by avoiding using combinations that lead to a negative evaluation when generating personas, the information processing device 10 can ensure that the first and second correction expert personas that are ultimately generated are in line with the individual circumstances of the user.

[0049] 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]

[0050] 10. Information processing equipment 11 User terminal 12 Expert Terminal 101 Control section 102 Main memory 103 Auxiliary storage 104 IF Section 105 Output section 106 Case Data Information 107 Rule Tree Information 108 User-specific persona information 111 Elements 112 Element Value

Claims

1. An information processing device including a control unit and a storage unit, the storage unit includes a case data DB that stores elements associated with experts and case information that serve as a basis for generating personas; The control unit querying the case data DB based on initial dialogue information received from the user terminal and reading out case data associated with the initial dialogue information; generating a first expert persona based on the retrieved case data; generating a first set of personas including the first expert persona; acquiring, from the user terminal, a user evaluation for each combination of an element and an element value of each persona in the first persona group; determining whether a user evaluation is positive or negative for each combination of an element and an element value of each persona in the first persona group based on the user evaluation; updating the read case data based on the determination; generating a first modified expert persona based on the updated case data; generating a user persona based on combinations of elements and element values ​​that result in positive user ratings and combinations of elements and element values ​​that result in negative user ratings; generating a second set of personas including the first modified expert persona and the user persona; An information processing device configured to execute the above.

2. The information processing apparatus according to claim 1 , wherein the first expert persona is a persona common to all users that is generated based on specific keywords included in the initial dialogue information.

3. 2. The information processing apparatus according to claim 1, wherein the initial dialogue information includes information about a user and information about a content of a service that the user desires to receive.

4. generating a second expert persona based on merged case data obtained by merging the retrieved case data; generating the first group of personas including the first expert persona and the second expert persona; generating a second modified expert persona based on merged case data generated based on the updated case data; generating the second set of personas including the first modified expert persona, the second modified expert persona, and the user persona; The information processing device of claim 1 further configured to perform the following:

5. 5. The information processing device of claim 4, wherein the determining step includes determining, based on the user evaluation, which combinations of elements and element values ​​result in a positive or negative user evaluation by tracing identical and similar elements and element values ​​in the rule trees of the first expert persona and the second expert persona of the first persona group.

6. The information processing apparatus of claim 5 , wherein the tracing of identical and similar elements and element values ​​is performed based on aliases.

7. Generating a user persona based on combinations of elements and element values ​​that result in positive user ratings and combinations of elements and element values ​​that result in negative user ratings, adding a first value to the target element value of the target element and the target element value that can be traced back to the combination of the element and the element value that results in a positive user evaluation; adding a second value to the target element value of the target element and target element value that can be traced back to the combination of element and element value that results in a negative user rating; The information processing device of claim 1 , further comprising:

8. The information processing device of claim 1 , wherein updating the read case data based on the determination is performed by deleting the case data associated with a combination of an element and an element value that results in a negative user evaluation.

9. An information processing method executed by an information processing device including a control unit and a storage unit, the storage unit includes a case data DB that stores elements associated with experts and case information that serve as a basis for generating personas; the control unit queries the case data DB based on initial dialogue information received from the user terminal and reads out case data associated with the initial dialogue information; The control unit generates a first expert persona based on the read case data; The control unit generates a first persona group including the first expert persona; the control unit acquires from the user terminal a user evaluation for each combination of an element and an element value of each persona in the first persona group; the control unit determines, based on the user evaluation, whether the user evaluation is positive or negative for each combination of an element and an element value of each persona in the first persona group; the control unit updates the read case data based on the determination; generating a first modified expert persona based on the updated case data; The control unit generates a user persona based on a combination of elements and element values ​​that result in a positive user evaluation and a combination of elements and element values ​​that result in a negative user evaluation; the control unit generating a second set of personas including the first modified expert persona and the user persona; A method for providing the above.

10. A program that causes a computer to execute the method according to claim 9.

Images