Information processing apparatus, assistance method, and computer-readable recording medium

Abstract

To improve a technique for presenting a portfolio of asset management corresponding to an object person.SOLUTION: An information processing device includes a question selection unit that selects a question to be presented next from unpresented questions included in a group of questions based on an answer to a question selected from the group of questions for determining a portfolio of asset management and presented to a subject, and a presentation control unit that presents a portfolio according to the answer to the selected and presented question to the subject. In addition, according to the information processing apparatus, it is possible to support decision-making of a subject who manages assets.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In asset management, it is considered best to first decide on a portfolio and then consider specific investment options, such as selecting financial products in line with that portfolio. However, creating a portfolio is not easy for many people, as the optimal portfolio varies depending on the manager's life stage, investment philosophy, and investment funds.

[0003] Consulting with a specialist such as a banker or financial planner is one way to create an optimal portfolio. A more convenient solution is to use a service that automatically suggests a portfolio based on the answers to a number of pre-prepared questions about asset management. Prior art related to such a service includes, for example, a recommendation service system described in Patent Document 1 below. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-341784 Summary of the Invention [Problem to be solved by the invention]

[0005] When presenting pre-prepared asset management questions to service recipients, if the number of questions is too few, it is difficult to determine a portfolio that is adequately suited to that individual. Conversely, presenting too many questions increases the likelihood of determining a portfolio that is appropriate for the individual, but it also increases the burden on the individual who has to answer them. Furthermore, since the matters that need to be confirmed vary depending on the individual, presenting the same questions to all recipients will inevitably result in mismatches. For example, asking questions about retirement benefits to recipients in their 20s or questions about long-term asset management to recipients in their 80s is unlikely to yield useful answers for determining a portfolio that is appropriate for each individual.

[0006] The present disclosure has been made in consideration of such problems, and one exemplary purpose thereof is to improve the technology for presenting an asset management portfolio tailored to a subject based on the subject's answers to questions. [Means for solving the problem]

[0007] An information processing device according to an exemplary aspect of the present disclosure includes a question selection means that selects a question to be next presented to a subject from among questions included in a group of questions that have not yet been presented to the subject, based on the subject's answer to a question selected from the group of questions for determining an asset management portfolio and presented to the subject, and a presentation control means that presents to the subject a portfolio that corresponds to the subject's answer to each of the selected and presented questions.

[0008] An assistance method according to an exemplary aspect of the present disclosure includes a question selection process in which at least one processor selects a question to be next presented to a subject from among questions included in a group of questions for determining an asset management portfolio that have not yet been presented to the subject, based on the subject's answer to the question, and a presentation control process in which a portfolio is presented to the subject according to the subject's answer to each of the selected and presented questions.

[0009] An assistance program according to an exemplary aspect of the present disclosure causes a computer to function as a question selection means that selects the next question to be presented to a subject from among questions included in a group of questions for determining an asset management portfolio that have not yet been presented to the subject, based on the subject's answer to the question selected from the group of questions and presented to the subject, and a presentation control means that presents to the subject a portfolio that corresponds to the subject's answer to each of the selected and presented questions. [Effects of the Invention]

[0010] According to one exemplary aspect of the present disclosure, an exemplary effect is achieved in that it becomes possible to improve a technique for presenting an asset management portfolio tailored to a subject based on the subject's answers to questions. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 2] FIG. 1 is a flow chart showing the flow of a support method according to the present disclosure. [Figure 3] FIG. 10 is a block diagram showing a configuration of another information processing device according to the present disclosure. [Figure 4] FIG. 10 is a diagram showing an example of a display screen presenting a portfolio. [Figure 5] 4 is a flowchart showing the flow of processing executed by the information processing device shown in FIG. 3. [Figure 6]FIG. 10 is a flowchart showing a series of processes related to prediction of questions. [Figure 7] FIG. 10 is a flowchart showing a series of processes related to investment decision support. [Figure 8] FIG. 1 is a block diagram illustrating a configuration of a computer that functions as an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0013] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0014] (Configuration of information processing device 1) The configuration of an information processing device 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. As shown in Fig. 1, the information processing device 1 includes a question selection unit 101 and a presentation control unit 102.

[0015] The question selection unit 101 selects a question to be presented to the subject next from among the questions included in the question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject. Note that the above-mentioned "subject" is a person for whom an asset management portfolio is to be determined.

[0016] Here, "asset management portfolio" refers to the asset allocation in asset management. For example, suppose 10 million yen in assets is invested equally in domestic stocks, domestic bonds, foreign stocks, and foreign bonds. In this case, the portfolio will allocate 25% of assets each to domestic stocks, domestic bonds, foreign stocks, and foreign bonds. The allocation destinations are arbitrary, and can include, for example, financial assets such as deposits and insurance, as well as physical assets such as real estate and precious metals.

[0017] The presentation control unit 102 presents to the subject a portfolio corresponding to the subject's answers to each of the questions selected by the question selection unit 101 and presented to the subject. The presentation method and manner are arbitrary. For example, the presentation control unit 102 may present the portfolio by outputting the portfolio to an arbitrary output device. The output manner may be, for example, display output, audio output, or print output. Furthermore, this output device may be one included in the information processing device 1, or may be a device external to the information processing device 1. Furthermore, when presenting the portfolio by displaying or printing it out, the presentation control unit 102 may present the portfolio using an image such as a pie chart.

[0018] As described above, the information processing device 1 includes a question selection unit 101 that selects a question to be presented to the subject next from among questions included in the question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject, and a presentation control unit 102 that presents to the subject a portfolio that corresponds to the subject's answer to each of the selected and presented questions.

[0019] According to the above configuration, the next question to be presented is selected based on the subject's answer to the previous question, so that the information necessary to determine a portfolio suitable for the subject can be collected by asking a minimum number of questions appropriate for the subject, and a portfolio suitable for the subject can be presented. In this way, the information processing device 1 has the effect of improving the technology for presenting an asset management portfolio suitable for the subject based on the subject's answers to questions. Furthermore, the information processing device 1 can support the subject's decision-making regarding asset management by presenting a portfolio suitable for the subject.

[0020] (Support Program) The functions of the information processing device 1 described above can also be realized by a program. The assistance program according to this exemplary embodiment is a program used to assist in asset management, and causes a computer to function as: a question selection unit that selects a question to be presented to a subject next from among questions included in a group of questions for determining an asset management portfolio and that have not yet been presented to the subject, based on the subject's answers to the questions; and a presentation control unit that presents the subject with a portfolio based on the subject's answers to each of the selected and presented questions. This assistance program has the effect of improving the technology for presenting an asset management portfolio tailored to the subject based on the subject's answers to the questions.

[0021] (Flow of support methods) The flow of the support method according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the support method. Note that the execution entity of each step in this support method may be a processor provided in the information processing device 1, or a processor provided in another device, or each step may be executed by a processor provided in a different device.

[0022] In S1, at least one processor selects a question from a set of questions for determining an asset management portfolio. Note that the number of questions selected in S1 may be one or more.

[0023] In S2, at least one processor presents the question selected in S1 to the subject. In S3, at least one processor acquires the subject's answer to the question presented in S2. If multiple questions are selected in S1, each of the selected questions is presented in S2 and S3, and the answer to each presented question is acquired. The multiple questions may be presented at once, or may be presented sequentially in multiple batches.

[0024] In S4 (question selection process), at least one processor selects a question to be presented to the subject next from among the questions included in the question set that have not yet been presented to the subject, based on the answer obtained in S3. Here, the answer obtained in S3 is the subject's answer to the question generated in S1 and presented in S2. Note that, similar to S1, the question selected in S4 may be one or more.

[0025] In S5, at least one processor presents the question selected in S4 to the subject. In S6, at least one processor obtains the subject's answer to the question presented in S5. Note that the processes of S5 and S6 when multiple questions are selected in S4 are similar to the processes of S2 and S3 when multiple questions are selected in S1.

[0026] In S7 (presentation process), at least one processor presents to the subject a portfolio corresponding to the subject's answers to each of the questions selected and presented by processes S1, S2, S4, and S5, i.e., the answers obtained in S3 and S6.

[0027] As described above, the support method according to this exemplary embodiment is a support method for supporting asset management, and includes a question selection process in which at least one processor selects a question to be next presented to the subject from among questions included in a question set for determining an asset management portfolio that have not yet been presented to the subject, based on the subject's answers to questions selected from the question set and presented to the subject, and a presentation control process in which a portfolio is presented to the subject according to the subject's answers to each of the selected and presented questions. Therefore, the support method according to this embodiment has the advantage of enabling an improvement in the technology for presenting an asset management portfolio tailored to the subject based on the subject's answers to questions.

[0028] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0029] (Configuration of information processing device 1A) The configuration of an information processing device 1A according to this exemplary embodiment will be described with reference to FIG. 3. FIG. 3 is a block diagram showing the configuration of the information processing device 1A. The information processing device 1A is a device having a function of supporting asset management. Note that the information processing device 1A may be a device whose main function is to support asset management, or may be a general-purpose device having other functions as well. Furthermore, the information processing device 1A may be a stationary device or a portable device.

[0030] 3, information processing device 1A includes a control unit 10A that controls each unit of information processing device 1A and a storage unit 11A that stores various data used by information processing device 1A. Information processing device 1A also includes a communication unit 12A that enables information processing device 1A to communicate with other devices, an input unit 13A that accepts input to information processing device 1A, and an output unit 14A that enables information processing device 1A to output data. Control unit 10A includes a question selection unit 101A, a presentation control unit 102A, a related information acquisition unit 103A, an answer acquisition unit 104A, a classification unit 105A, a determination unit 106A, a basis information generation unit 107A, a prediction unit 108A, and a generation control unit 109A. Details of prediction unit 108A and generation control unit 109A will be described later.

[0031] Similar to the question selection unit 101 described in exemplary embodiment 1, the question selection unit 101A selects the next question to be presented to the subject from among the questions included in the question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject.

[0032] The presentation control unit 102A presents various types of information to the subject. For example, similar to the presentation control unit 102A described in the exemplary embodiment 1, the presentation control unit 102A presents to the subject a portfolio corresponding to the subject's answers to each of the questions selected by the question selection unit 101A and presented to the subject. In addition, the presentation control unit 102A also presents, for example, the questions selected by the question selection unit 101A, evidence information indicating the evidence for recommending a portfolio, and the like. Note that the presentation method and manner are arbitrary, similar to the presentation control unit 102 in the exemplary embodiment 1.

[0033] In this way, the information processing device 1A includes a question selection unit 101A that selects a question to be next presented to the subject from among questions included in a question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject, and a presentation control unit 102A that presents the subject with a portfolio corresponding to the subject's answers to each of the selected and presented questions. Thus, similar to the information processing device 1 of exemplary embodiment 1, an effect can be obtained in which it is possible to improve the technology for presenting an asset management portfolio tailored to the subject based on the subject's answers to questions.

[0034] The related information acquisition unit 103A acquires related information, which is information used by the question selection unit 101A to select a question. The related information may be any information that can be used to select a question. For example, the related information acquisition unit 103A may acquire related information that indicates the attributes of a subject for whom a portfolio is to be determined. Examples of the subject's attributes include personal characteristics (age, gender, occupation, assets held, past asset management history, etc.) that the subject has registered in advance.

[0035] The answer acquisition unit 104A acquires the subject's answer to the question selected by the question selection unit 101A and presented by the presentation control unit 102A. The subject's answer may be input as text or as voice. When the subject's answer is input as voice, the answer acquisition unit 104A converts the input voice into text using a voice recognition device (not shown), and acquires the text obtained by the conversion as the subject's answer. The subject's answer may be input via the input unit 13A or via the communication unit 12A. The above voice recognition device may be included in the information processing device 1A, or a voice recognition device external to the information processing device 1A may be used.

[0036] The classification unit 105A classifies the subject based on the subject's answers to the multiple questions selected by the question selection unit 101A and presented by the presentation control unit 102A. Once the classification unit 105A has classified the subject, the question selection unit 101A selects a question according to the subject's classification as the question to be presented next to the multiple questions. This provides the effect of being able to select and present an appropriate question according to the subject's classification, in addition to the effect provided by the information processing device 1.

[0037] The classification method applied by the classification unit 105A is not particularly limited. For example, the classification unit 105A may evaluate the subject based on a plurality of predetermined evaluation axes, including at least one of investment knowledge, investment experience, investment confidence, calmness, and behavioral tendency, and classify the subject based on the results of the evaluation. All of the above evaluation axes relate to factors important in determining the subject's portfolio. Therefore, with the above configuration, in addition to the effects achieved by the information processing device 1, it is possible to obtain an effect of selecting and presenting appropriate questions based on the evaluation results of factors important in determining the subject's portfolio. Note that "behavioral tendency" refers to a tendency in a behavioral characteristic. For example, being able to calmly deal with unexpected situations is an example of a behavioral tendency.

[0038] The evaluation method for each evaluation axis may also be arbitrary. For example, when presenting a question requiring the subject to select an answer from multiple options, an evaluation value for each evaluation axis may be assigned to each answer option for each question. This allows the classification unit 105A to sum up, for each evaluation axis, the evaluation values ​​assigned to each option selected by the subject for the multiple questions presented to the subject, and obtain the subject's evaluation result for each evaluation axis. The classification unit 105A then plots the subject's evaluation result in a feature space consisting of multiple evaluation axes, and classifies the subject based on which of multiple pre-set areas the plot falls within.

[0039] Furthermore, for example, the classification unit 105A may classify the subject using a language model. In this case, the classification unit 105A may input, to the language model, the subject's answer along with a prompt that instructs the language model to classify the subject based on the answer. This causes information indicating the subject's classification to be output from the language model. In this case, by using a prompt that includes categories that are candidates for classification and instructs the user to select a category that suits the subject from among the categories, it is also possible to output information indicating which category the subject falls into.

[0040] A language model is a model that uses machine learning to learn the arrangement of components (such as words) in a sentence or the arrangement of sentences in a document. For example, a Generative Pre-Trained Transformer (GPT) can be used as a language model for classifying subjects. The GPT predicts a character string that is likely to follow an input character string, thereby outputting a sentence containing the input character string. In addition to the GPT, a Text-to-Text Transfer Transformer (T5), a Bidirectional Encoder Representations from Transformers (BERT), a Robustly optimized BERT approach (RoBERTa), an Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA), and the like can also be used for classifying subjects.

[0041] Furthermore, for example, the classification unit 105A may classify a subject based on the evaluation results obtained by evaluating the subject relative to other subjects. This, in addition to the effects of the information processing device 1, can also provide the effect of making it possible to propose diverse portfolios in a balanced manner to a group of subjects who are the subject of relative evaluation. For example, if multiple subjects are each evaluated absolutely, there is a possibility that the classification of the subjects will be biased, and the portfolios presented to those subjects will be similar. In this regard, if classification is performed based on the evaluation results obtained by relative evaluation, there is less chance of bias in the classification results, making it possible to propose diverse portfolios in a balanced manner.

[0042] The "other person" may be any person related to the subject, and may be, for example, another user of the asset management support service provided by the information processing device 1A. The relative evaluation method may also be arbitrary. For example, as described above, an evaluation value on each evaluation axis may be assigned to each answer option for each question. In this case, the classification unit 105A may calculate the sum of the evaluation values ​​on each evaluation axis for each subject in the relative evaluation, and use the calculated sum to calculate the relative evaluation value of each subject. For example, the classification unit 105A may use the standard deviation of the calculated sum as the relative evaluation value of each subject, and classify each subject using the standard deviation.

[0043] The determination unit 106A determines a portfolio to be presented to the subject based on the subject's answers to each of the presented questions. The method for determining the portfolio is not particularly limited. For example, multiple patterns of portfolios may be prepared in advance, and application conditions may be set for each portfolio. In this case, the determination unit 106A may determine which of the portfolios the subject's answers satisfy the application conditions, and determine the portfolio determined to satisfy the application conditions as the portfolio to be presented to the subject. The application conditions, in other words, the rules for determining a portfolio according to the subject's answers, may be set appropriately using a rule base or the like.

[0044] Furthermore, for example, the determination unit 106A may determine a portfolio using a language model. In this case, the determination unit 106A may input to the language model the subject's answer, a description of each candidate portfolio to be presented to the subject, and a prompt instructing the language model to output a portfolio corresponding to the answer. This causes the language model to output information indicating the portfolio to be presented to the subject. Note that in addition to the subject's answer, other information that serves as a reference for determining the optimal portfolio, such as the classification determined by the classification unit 105A or the subject's attribute information, may also be input to the language model. Furthermore, by using a prompt that includes multiple candidate portfolios to be presented and instructs the subject to select a portfolio that suits the subject from among the portfolios, it is possible to output information indicating the portfolio to be presented to the subject from among the candidates.

[0045] Here, the above-mentioned set of questions may include questions asking about an overview of a certain item and questions asking about the details of that item. In this case, it is preferable that the question selection unit 101A selects all of the questions asking about the overview before selecting questions asking about the details. Then, after the classification unit 105A classifies the subject based on the subject's answers to the questions asking about the overview, the question selection unit 101A may select some of the questions asking about the details in accordance with the classification results. In other words, the question selection unit 101A may determine whether to select additional questions that delve deeper into the previously presented questions based on the answers to those questions. This makes it possible to avoid asking unnecessarily intrusive questions that cause the subject to feel uncomfortable or burdened.

[0046] For example, the above-described set of questions may include a question inquiring about the subject's approximate asset amount and a question inquiring about the detailed asset amount. In this case, the question selection unit 101A selects the question inquiring about the approximate asset amount before a question inquiring about the detailed asset amount. Then, based on the subject's answers to multiple questions including the selected question, if the subject is classified into a category in which it is considered appropriate to confirm the detailed asset amount (for example, a category for people who lack knowledge and experience about investment but are confident in investing), the question selection unit 101A selects the question inquiring about the detailed asset amount. On the other hand, if the subject is classified into a category in which it is not necessary to confirm the detailed asset amount (a category for people who have extensive knowledge and experience about investment), the question selection unit 101A does not select the question inquiring about the detailed asset amount. This minimizes the opportunity to present a sensitive question such as the detailed asset amount.

[0047] The basis information generating unit 107A generates basis information indicating the basis for recommending a portfolio to a subject based on each piece of information used to determine the portfolio to be presented to the subject. Then, the presentation control unit 102A presents the generated basis information to the subject. In addition to the effects achieved by the information processing device 1, the information processing device 1A including the basis information generating unit 107A has the effect of being able to present to the subject basis information that is information useful to the subject checking the contents of the portfolio.

[0048] The method for generating the evidence information is not particularly limited. For example, the evidence information generating unit 107A may evaluate the subject's financial capacity, experience, and knowledge of asset management based on the subject's responses used to generate the portfolio, and generate evidence information that indicates the evaluation results as the basis for portfolio determination. Such evidence information can also be generated by inputting the evaluation results into a predetermined template. For example, a template such as "For those with {high / average / low} financial capacity and {rich / average / inexperienced} knowledge and experience in asset management, this portfolio, which emphasizes {high return / risk-return balance / risk aversion}, is recommended." may be used. In this case, the evidence information generating unit 107A can generate evidence information by selecting one of the words in parentheses based on the subject's responses and inputting the selected word into the template.

[0049] The basis information generating unit 107A can also generate the basis information using a language model or the like. When using a language model, the subject's evaluation results may be input to the language model, or the subject's answers used in the evaluation, an explanation of the presented portfolio, etc. may be input to the language model so that the language model also performs the evaluation. In the latter case, the basis information generating unit 107A may generate and use a prompt that instructs the user to explain the basis for proposing the portfolio based on the input portfolio and the subject's answers. The basis information may be in text format, image format (e.g., graph), or a combination of text and images.

[0050] (Portfolio presentation example) Fig. 4 is a diagram showing an example of a display screen presenting a portfolio. Displayed on the display screen 2 shown in Fig. 4 are a pie chart 21 showing the portfolio determined by the determination unit 106A, a radar chart 22 showing the results of evaluating the subject along multiple evaluation axes, and an explanatory statement 23 showing the basis for recommending the portfolio. The explanatory statement 23 is an example of basis information generated by the basis information generation unit 107A.

[0051] As in the example of FIG. 4, the presentation control unit 102A may present the portfolio determined by the determination unit 106A as a graph. In particular, it is preferable to present the portfolio as a pie chart as in the example of FIG. 4. The graph may be generated by the determination unit 106A or the presentation control unit 102A. Furthermore, as in the example of FIG. 4, the presentation control unit 102A may present the evaluation results of the subject as a graph. In addition, the presentation control unit 102A may present, for example, the classification results of the subject by the classification unit 105A.

[0052] (Processing flow) The flow of processing executed by the information processing device 1A will be described with reference to Fig. 5. Fig. 5 is a flow diagram showing an example of processing executed by the information processing device 1A. Fig. 5 includes each process of the support method according to this exemplary embodiment.

[0053] In S11, the related information acquisition unit 103A acquires related information, which is information used by the question selection unit 101A to select a question for the subject. The method of acquiring the related information is arbitrary. For example, the related information acquisition unit 103A may acquire the related information input by the subject via the communication unit 12A or the input unit 13A, or may acquire the related information from a predetermined source (for example, a database in which the subject's related information is recorded in advance).

[0054] In S12, the question selection unit 101A selects multiple questions to be initially presented to the subject from a group of questions for determining an asset management portfolio. At this time, the question selection unit 101A may select multiple questions according to the related information acquired in S11. For example, if the related information acquired in S11 indicates that the subject has extensive investment experience, the question selection unit 101A may select questions aimed at people with extensive investment experience. Then, the presentation control unit 102A presents the questions selected by the question selection unit 101A to the subject.

[0055] The multiple questions selected in S12 are questions for classifying the subjects. Therefore, if the related information acquired in S11 includes information that can be used to classify the subjects, that information may be used to classify the subjects. In this case, in S12, the question selection unit 101A may narrow down the number of questions to be selected. For example, if the related information acquired in S11 includes information indicating at least one of age, amount of assets held, and segment (related to asset management), the question selection unit 101A may avoid selecting questions about these in S12. In S12, the question selection unit 101A may select questions using a rule base that predefines such rules regarding question selection.

[0056] In S13, the answer acquisition unit 104A acquires the subject's answer to the question presented in S12. Note that multiple questions may be presented at once, or may be presented sequentially in multiple batches. When questions are presented in multiple batches, the answers are also acquired in multiple batches. This also applies to S15 and S16 described below.

[0057] In S14, the classification unit 105A classifies the subject based on the responses acquired in S13. For example, as described above, the classification unit 105A may classify the subject based on the results of evaluating the subject along multiple evaluation axes. In this classification, the classification unit 105A may use the related information acquired in S11. For example, suppose the related information acquired in S11 includes data reflecting the subject's personality, such as financial product purchase history, past investment performance, or documents created by the subject or emails sent by the subject. In this case, the classification unit 105A analyzes the data, and when an analysis result indicating that the subject is confident in investing is obtained, the analysis result may be reflected in the evaluation along the evaluation axis of the subject's confidence in investing.

[0058] In S15 (question selection process), the question selection unit 101A selects a question to be presented to the subject next from among the questions included in the above-mentioned question group that have not yet been presented to the subject, based on the subject's answer to the question presented to the subject. Specifically, the question selection unit 101A selects a question from the above-mentioned question group according to the classification result of S14. Then, the presentation control unit 102A presents the question selected by the question selection unit 101A to the subject.

[0059] For example, if one or more questions corresponding to each category are associated in advance with each category, then in S15 the question selection unit 101A can select a question according to the classification result in accordance with the association.

[0060] Furthermore, in S15, the question selection unit 101A may select a question according to the classification result using a language model. In this case, the question selection unit 101A may input, to the language model, each question included in the question group that has not yet been presented to the subject and the classification result of S15, as well as a prompt that instructs the language model to extract, from the input questions, questions that should be presented to the subject in the classification shown in the classification result. As a result, the questions to be presented to the subject are output from the language model.

[0061] In S16, the answer acquisition unit 104A acquires the subject's answer to the question presented in S15.

[0062] In S17, the question selection unit 101A determines whether to end the selection of questions. If the determination in S17 is NO, the process returns to S15, and a question to be presented to the subject next is selected from among the unpresented questions. On the other hand, if the determination in S17 is YES, the process proceeds to S18. In this way, the series of processes of selecting, presenting, and obtaining answers to questions is repeated until the determination in S17 is YES. The determination in S17 is YES means that the answers necessary to determine the portfolio to be presented to the subject have been gathered.

[0063] The termination condition for question selection in S17 may be determined in advance. For example, the termination condition for question selection may be that all questions to be presented to the subject according to the classification result in S14, among the questions included in the above-mentioned question group, have been presented and answers have been obtained. Alternatively, the termination condition for question selection may be that the determining unit 106A has obtained the answers necessary to determine a portfolio. In this case, the determining unit 106A may narrow down the portfolio each time an answer is obtained in S16, and the question selecting unit 101A may determine that the termination condition has been satisfied when the portfolio has been narrowed down to one.

[0064] In this way, the question selection unit 101A may repeatedly select questions from the set of questions until all the answers necessary to determine the portfolio to be presented to the subject are collected. This provides the effect of being able to collect the information necessary to determine the portfolio by presenting a minimum number of questions, in addition to the effect provided by the information processing device 1.

[0065] In S18, the determination unit 106A determines a portfolio to be presented to the subject based on the answers acquired in S16. Note that the determination of the portfolio may also use the related information acquired in S11, the answers acquired in S13, the classification results in S14, etc.

[0066] In S19, the basis information generating unit 107A generates basis information indicating the basis for recommending the portfolio to the subject based on the information used to determine the portfolio in S18.

[0067] In S20 (presentation control process), the presentation control unit 102A presents to the subject a portfolio corresponding to the subject's answers to each of the questions selected and presented by the above process. Specifically, the presentation control unit 102A presents to the subject the portfolio determined in S18 and the evidence information generated in S19. This ends the process of FIG. 5.

[0068] It should be noted that the portfolio and the basis information do not necessarily need to be presented at the same time. For example, the presentation control unit 102A may first present the portfolio, and then present the basis information when the subject inputs a request for the presentation of the basis information. Furthermore, for example, the presentation control unit 102A may also present various information related to the presented portfolio, such as the classification results of S14, to the subject.

[0069] (Example 1 of processing after portfolio presentation) After presenting the portfolio in the above manner, the information processing device 1A may provide a service of accepting questions from the subject and presenting answers to the questions. However, if the subject is unfamiliar with asset management, it may not know what questions to ask. The prediction unit 108A and generation control unit 109A included in the information processing device 1A are intended to address such problems.

[0070] The prediction unit 108A predicts questions about asset management from the subject using a language model that has been machine-learned from consultation cases about asset management. Then, the presentation control unit 102A presents the questions predicted by the prediction unit 108A to the subject. In addition to the effects of the information processing device 1, the information processing device 1A equipped with the prediction unit 108A has the effect of being able to appropriately support subjects who do not know what questions to ask. Note that the machine learning of consultation cases may be performed by fine-tuning the language model using training data in which text indicating the content of a client's utterance is associated with text indicating the advisor's response to that utterance as correct answer data, for example.

[0071] For example, the prediction unit 108A may input various information related to questions that the subject may want to ask, along with a prompt to the language model instructing the language model to output questions that the subject should ask. This causes the language model to output information indicating the questions that the subject should ask. Examples of the various information include attribute information of the subject, a portfolio presented to the subject, and the classification results of the subject by the classification unit 105A. Note that candidate questions may be prepared in advance. In this case, the prediction unit 108A may input these candidates to the language model and determine which candidate should be applied.

[0072] The generation control unit 109A causes a language model to generate an answer to a question. For example, suppose that the prediction unit 108A predicts a question and presents it to the subject, and the subject inputs an answer that the subject would like to ask about the question. In this case, the generation control unit 109A inputs the question into the language model to generate an answer to the question. The language model used to generate the answer is preferably the same as the language model used by the prediction unit 108A, that is, a model that has been machine-learned from consultation cases regarding asset management. However, the generation control unit 109A may also cause another language model, such as a general-purpose language model, to generate the answer. Furthermore, when candidate questions are prepared in advance, answers to each candidate can also be prepared in advance. In this case, it is not necessary for the generation control unit 109A to generate the answer.

[0073] (Processing flow) Fig. 6 is a flow diagram showing a series of processes related to prediction of questions. The process of Fig. 6 is performed, for example, after the portfolio is presented to the subject in the process of S20 of Fig. 5 and then questions from the subject are started to be accepted. In other words, the process of Fig. 6 may be performed following the series of processes of Fig. 5.

[0074] In S31, the generation control unit 109A determines whether or not a question has been received from the subject. If the determination in S31 is YES, the process proceeds to S36, and if the determination in S31 is NO, the process proceeds to S32. For example, the generation control unit 109A may determine that a question has not been received (NO in S31) if no question is input even after a predetermined time has elapsed since the generation control unit 109A started receiving questions.

[0075] In S32, the prediction unit 108A predicts questions about asset management from the subject using a language model that has been machine-learned from consultation cases about asset management. Note that before predicting the questions, a dialogue with the subject using the language model may be conducted. In this case, the prediction unit 108A may also input the content of the dialogue with the subject into the language model, and reflect the content of the dialogue in the prediction result.

[0076] In S33, the presentation control unit 102A presents the questions predicted in S32 to the subject. Subsequently, in S34, the answer acquisition unit 104A acquires the subject's answers to the presented questions. For example, the presentation control unit 102A may display, together with the questions predicted in S32, options that allow the subject to select whether or not the questions include content that the subject wants to hear. In this case, in S34, the subject's selection from the displayed options may be acquired as the subject's answer.

[0077] In S35, the answer acquisition unit 104A determines whether or not to terminate the prediction by the prediction unit 108A based on the answer acquired in S34. The condition for terminating the prediction may be determined in advance. For example, the termination condition may be that the subject has input an indication that they would like to hear the answer to the presented question. Furthermore, for example, the answer acquisition unit 104A may determine to terminate the prediction if, even after repeating the prediction and presentation of the question a predetermined number of times, the subject has not input an indication that they would like to hear the answer.

[0078] In S36, following S35, the generation control unit 109A generates an answer to the question presented in S33 (the answer to which the subject has input that he or she would like to hear). As described above, the generation control unit 109A can generate an answer to the question by inputting the question into a language model. The generated answer is presented to the subject by the presentation control unit 102A, and the processing in FIG. 6 is then terminated. Note that after S36, the subject may ask a question regarding the presented answer.

[0079] On the other hand, in S36, which is a transition from S31, the generation control unit 109A generates an answer to the question input by the subject. In this case, too, the generation control unit 109A can generate an answer to the question by inputting the question input by the subject into a language model. Then, the generated answer is presented to the subject by the presentation control unit 102A.

[0080] (Example 2 of processing after portfolio presentation) After presenting the portfolio, the information processing device 1A may also provide a service that supports investment decision making. Such a service can be realized by the generation control unit 109A included in the information processing device 1A.

[0081] As described above, the generation control unit 109A causes the language model to generate answers to questions. The generation control unit 109A can also cause the language model to generate questions for the subject. For example, the generation control unit 109A may input various pieces of information useful for generating appropriate questions, as well as a prompt to the language model instructing the language model to generate questions that elicit information necessary for deciding on an investment destination. As a result, questions that elicit information necessary for deciding on an investment destination are output from the language model. The various pieces of information described above include at least the subject's attribute information and the portfolio presented to the subject. The various pieces of information described above may also include, for example, the subject's classification results by the classification unit 105A, the subject's attribute information, and a history of interactions between the subject and the information processing device 1A.

[0082] In this way, the information processing device 1A includes a generation control unit 109A that causes a machine-learned language model to generate questions for eliciting from the subject information necessary for deciding on investment destinations that match the presented portfolio. Therefore, in addition to the effects achieved by the information processing device 1, the information processing device 1A has the effect of being able to elicit from the subject information necessary for deciding on investment destinations that match the portfolio without the intervention of an operator.

[0083] For example, in order to determine a portfolio, it is not necessarily necessary to know the specific amount of funds to be invested by the subject. On the other hand, when it comes to deciding on an investment destination, it is necessary to know the specific amount of funds to be invested. For this reason, the generation control unit 109A may cause the language model to generate questions to elicit the specific amount of funds to be invested. In this way, by predefining the information necessary to determine an investment destination, the generation control unit 109A can generate questions to elicit such information.

[0084] Furthermore, when candidate financial products for investment have been determined in advance, the generation control unit 109A may input each financial product and its description into a language model to generate questions that elicit information necessary for determining which financial product to select. In this case, by acquiring the subject's answers to each generated question, it becomes possible to identify one or more financial products that the subject should select.

[0085] Here, if the target person is a person from a country or region where the recommendation of financial products by computer is not restricted by laws and regulations, the offer control unit 102A may offer the identified financial product to the target person as a recommended financial product. On the other hand, if the target person is a person from a country or region where the recommendation of financial products by computer is restricted by laws and regulations, the offer control unit 102A may notify the identified financial product to an operator who is capable of recommending financial products. This allows the operator to support the target person in purchasing the financial product by referring to the identified financial product.

[0086] Furthermore, when generating questions, the generation control unit 109A can input attribute information of the subject and preference information indicating the subject's tastes into the language model, thereby generating questions that take such information into consideration. For example, it is possible to generate a question that directly asks about the amount for a subject who prefers direct expressions, and a question that indirectly asks about the amount for a subject who does not prefer direct expressions.

[0087] It is also effective to change the language model to be used depending on the target person's attribute information and preference information. In this case, a language model fine-tuned to suit a conversation with a target person of each category (which may be a classification by the classification unit 105A or a classification based on other criteria) can be used. This makes it possible to have a conversation with the target person using a tone, story development, or tone of voice that is appropriate for the target person's classification. It is also possible to generate optimal questions and answers from a behavioral economics perspective, in other words, questions and answers that are effective in encouraging the target person to take a predetermined action, depending on the target person's classification.

[0088] (Processing flow) Fig. 7 is a flow diagram showing a series of processes related to investment decision support. The processes in Fig. 7 are performed, for example, after a portfolio is presented to a target person. In other words, the processes in Fig. 7 may be performed following the series of processes in Fig. 5.

[0089] In S41, the generation control unit 109A causes the machine-learned language model to generate questions for eliciting from the subject information necessary for deciding on an investment destination that is in line with the portfolio presented to the subject.

[0090] In S42, the presentation control unit 102A presents the question generated in S41 to the subject. In addition, in S43, the answer acquisition unit 104A acquires the subject's answer to the question presented in S42.

[0091] In S44, the presentation control unit 102A determines whether or not to end the generation of the question. If the determination in S44 is YES, the processing in FIG. 7 ends. On the other hand, if the determination in S44 is NO, the processing returns to S41. In S41 to which the transition is made from S44, the generation control unit 109A may also input the history of the previous dialogue into the language model. This allows a new question to be generated taking into account the history of the previous dialogue.

[0092] The condition for ending the generation of questions in S44 may be determined in advance. For example, the condition for ending the dialogue may be when the subject makes an utterance indicating that the dialogue is to be ended or when the subject performs an operation to end the dialogue. Alternatively, the condition for ending the dialogue may be when all the information necessary for deciding on an investment destination has been collected. Whether all the information necessary for deciding on an investment destination has been collected can be determined, for example, by creating a list of the information necessary for deciding on an investment destination in advance and comparing the answer acquired in S43 with the list. A language model can also be used for this determination.

[0093] 6 and 7, additional information about the subject, such as the dialogue history with the subject, can be obtained. Therefore, once a portfolio has been determined, the determination unit 106A may change the proposed portfolio based on the content of the dialogue if a dialogue takes place with the subject. The presentation control unit 102A then presents the changed portfolio to the subject. This makes it possible to propose a portfolio that is more suited to the subject.

[0094] [Modification] The execution entity of each process described in the above exemplary embodiment is arbitrary and is not limited to the above example. For example, a system having the same functions as the information processing devices 1 and 1A can be constructed using multiple devices that can communicate with each other. Furthermore, the execution entity of each process shown in the flowcharts of Figures 5 to 7 may be one device (which can also be called a processor) or multiple devices (which can also be called processors).

[0095] [Software implementation example] Some or all of the functions of the information processing device 1, 1A may be realized by hardware such as an integrated circuit (IC chip), or may be realized by software.

[0096] In the latter case, the information processing devices 1 and 1A are realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Fig. 8. Fig. 8 is a block diagram showing the hardware configuration of the computer C that functions as the information processing device 1 or 1A.

[0097] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as the information processing device 1 or 1A. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the information processing device 1 or 1A.

[0098] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0099] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0100] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0101] Furthermore, each of the above functions of the information processing device 1 or 1A may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working together, or by multiple processors provided in each of multiple computers working together. Furthermore, the program for causing the information processing device 1, 1A to realize each of the above functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0102] [Additional Notes] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0103] (Appendix A1) An information processing device comprising: a question selection means for selecting a question to be next presented to a subject from among questions included in a group of questions that have not yet been presented to the subject, based on the subject's answer to a question selected from the group of questions for determining an asset management portfolio and presented to the subject; and a presentation control means for presenting to the subject a portfolio corresponding to the subject's answer to each of the selected and presented questions.

[0104] (Appendix A2) The information processing device described in Appendix A1, wherein the question selection means includes a classification means that selects a plurality of questions from the group of questions and classifies the subject based on answers to the plurality of questions, and the question selection means selects a question that corresponds to the classification of the subject as the question to be presented next to the plurality of questions.

[0105] (Appendix A3) The information processing device described in Appendix A2, wherein the classification means evaluates the subject based on a plurality of predetermined evaluation axes including at least one of knowledge about investment, experience about investment, confidence in investment, calmness, and behavioral tendencies, and classifies the subject based on the results of the evaluation.

[0106] (Appendix A4) The information processing device according to appendix A2 or A3, wherein the classification means classifies the subject based on an evaluation result of evaluating the subject relative to other people.

[0107] (Appendix A5) The information processing device according to any one of appendices A1 to A4, wherein the question selection means repeatedly selects questions from the set of questions until all the answers necessary to determine the portfolio to be presented to the subject are obtained.

[0108] (Appendix A6) An information processing device described in any of Appendices A1 to A5, comprising a basis information generation means for generating basis information indicating the basis for recommending the portfolio to the subject based on each piece of information used to determine the portfolio to be presented to the subject, and the presentation control means presents the basis information to the subject.

[0109] (Appendix A7) An information processing device according to any one of Appendices A1 to A6, comprising a prediction means for predicting questions regarding asset management of the subject using a language model that has been machine-learned from consultation cases regarding asset management, and the presentation control means for presenting the predicted questions to the subject.

[0110] (Appendix A8) An information processing device described in any of Appendices A1 to A7, comprising a generation control means for causing a machine-learned language model to generate questions to elicit from the subject information necessary to decide on investment destinations that are in line with the presented portfolio.

[0111] (Appendix B1) An assistance method including: a question selection process in which at least one processor selects a question to be next presented to a subject from among questions included in a group of questions for determining an asset management portfolio that have not yet been presented to the subject, based on the subject's answer to the question selected from the group of questions and presented to the subject; and a presentation control process in which a portfolio is presented to the subject according to the subject's answer to each of the selected and presented questions.

[0112] (Appendix B2) The support method described in Appendix B1, wherein the at least one processor selects a plurality of questions from the group of questions, and the at least one processor includes a classification process of classifying the subject based on answers to the plurality of questions, and in the question selection process, the at least one processor selects a question corresponding to the classification of the subject as a question to be presented next to the plurality of questions.

[0113] (Appendix B3) The support method described in Appendix B2, wherein in the classification process, the at least one processor evaluates the subject based on a plurality of predetermined evaluation axes including at least one of knowledge about investment, experience about investment, confidence in investment, calmness, and behavioral tendencies, and classifies the subject based on the results of the evaluation.

[0114] (Appendix B4) The support method according to appendix B2 or B3, wherein in the classification process, the at least one processor classifies the subject based on an evaluation result of evaluating the subject relative to other subjects.

[0115] (Appendix B5) An assistance method described in any of Appendices B1 to B4, wherein, in the question selection process, the at least one processor repeatedly selects questions from the set of questions until all the answers necessary to determine the portfolio to be presented to the subject are obtained.

[0116] (Appendix B6) A support method described in any of Appendices B1 to B5, including a basis information generation process in which the at least one processor generates basis information indicating the basis for recommending the portfolio to the subject based on each piece of information used by the at least one processor to determine the portfolio to be presented to the subject, and a process in which the at least one processor presents the basis information to the subject.

[0117] (Appendix B7) The support method described in any of Appendices B1 to B6, including a prediction process in which the at least one processor predicts questions regarding asset management from the subject using a language model that has been machine-learned from consultation cases regarding asset management, and a process in which the at least one processor presents the predicted questions to the subject.

[0118] (Appendix B8) An assistance method described in any of Appendices B1 to B7, including a generation control process in which the at least one processor causes a machine-learned language model to generate questions to elicit from the subject information necessary to decide on investment destinations that are in line with the presented portfolio.

[0119] (Appendix C1) An assistance program that causes a computer to function as a question selection means that selects the next question to be presented to a subject from among the questions included in a group of questions for determining an asset management portfolio that have not yet been presented to the subject, based on the subject's answer to the question selected from the group of questions and presented to the subject, and a presentation control means that presents to the subject a portfolio that corresponds to the subject's answer to each of the selected and presented questions.

[0120] (Appendix C2) The assistance program described in Appendix C1, wherein the question selection means selects a plurality of questions from the group of questions and causes the computer to function as a classification means that classifies the subject based on answers to the plurality of questions, and the question selection means selects a question that corresponds to the classification of the subject as the question to be presented next after the plurality of questions.

[0121] (Appendix C3) The support program described in Appendix C2, wherein the classification means evaluates the subject based on a plurality of predetermined evaluation criteria including at least one of knowledge about investment, experience about investment, confidence in investment, calmness, and behavioral tendencies, and classifies the subject based on the results of the evaluation.

[0122] (Appendix C4) The assistance program according to appendix C2 or C3, wherein the classification means classifies the subject based on an evaluation result obtained by evaluating the subject relative to other people.

[0123] (Appendix C5) An assistance program described in any of Appendices C1 to C4, wherein the question selection means repeatedly selects questions from the group of questions until all the answers necessary to determine the portfolio to be presented to the subject are obtained.

[0124] (Appendix C6) An assistance program described in any of Appendices C1 to C5, which causes the computer to function as evidence information generation means that generates evidence information indicating the basis for recommending the portfolio to the subject based on each piece of information used to determine the portfolio to be presented to the subject, and the presentation control means presents the evidence information to the subject.

[0125] (Appendix C7) The support program described in any of Appendices C1 to C6, wherein the computer functions as a prediction means that predicts questions regarding asset management from the subject using a language model that has been machine-learned from consultation cases regarding asset management, and the presentation control means presents the predicted questions to the subject.

[0126] (Appendix C8) The support program described in any of Appendices C1 to C7, which causes the computer to function as a generation control means that causes a machine-learned language model to generate questions to elicit from the subject the information necessary to decide on investment destinations that are in line with the presented portfolio.

[0127] (Appendix D1) An information processing device comprising at least one processor, which executes a question selection process for selecting a question to be next presented to a subject from among questions included in a group of questions for determining an asset management portfolio and that have not yet been presented to the subject, based on the subject's answer to the question, and a presentation control process for presenting to the subject a portfolio corresponding to the subject's answer to each of the selected and presented questions.

[0128] The information processing device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0129] (Appendix D2) The information processing device described in Appendix D1, wherein, in the question selection process, the at least one processor selects a plurality of questions from the group of questions, and the at least one processor performs a classification process to classify the subject based on answers to the plurality of questions, and in the question selection process, the at least one processor selects a question according to the classification of the subject as a question to be presented next to the plurality of questions.

[0130] (Appendix D3) The information processing device described in Appendix D2, wherein in the classification process, the at least one processor evaluates the subject based on a plurality of predetermined evaluation axes including at least one of knowledge about investment, experience about investment, confidence in investment, calmness, and behavioral tendencies, and classifies the subject based on the results of the evaluation.

[0131] (Appendix D4) The information processing device according to appendix D2 or D3, wherein in the classification process, the at least one processor classifies the subject based on an evaluation result of evaluating the subject relative to other subjects.

[0132] (Appendix D5) An information processing device described in any of Appendices D1 to D4, wherein in the question selection process, the at least one processor repeatedly selects questions from the set of questions until all the answers necessary to determine the portfolio to be presented to the subject are obtained.

[0133] (Appendix D6) An information processing device described in any of Appendices D1 to D5, wherein the at least one processor executes a process of generating evidence information indicating the basis for recommending the portfolio to the subject based on each piece of information used to determine the portfolio to be presented to the subject, and a process of presenting the evidence information to the subject.

[0134] (Appendix D7) The information processing device described in any of Appendices D1 to D6, wherein the at least one processor executes a prediction process for predicting questions regarding asset management of the subject using a language model that has been machine-learned from consultation cases regarding asset management, and a process for presenting the predicted questions to the subject.

[0135] (Appendix D8) An information processing device described in any of Appendices D1 to D7, wherein the at least one processor executes a generation control process that causes a machine-learned language model to generate questions to elicit from the subject information necessary to decide on investment destinations that are in line with the presented portfolio.

[0136] (Appendix E) A non-transient recording medium having recorded thereon an assistance program that causes a computer to execute a question selection process that selects the next question to be presented to a subject from among questions included in a group of questions that have not yet been presented to the subject, based on the subject's answer to a question selected from the group of questions for determining an asset management portfolio and presented to the subject, and a presentation control process that presents to the subject a portfolio that corresponds to the subject's answer to each of the selected and presented questions. [Explanation of symbols]

[0137] 1. Information processing equipment 101 Question selection unit (question selection means) 102 Presentation control unit (presentation control means) 1A Information processing equipment 101A Question selection unit (question selection means) 102A presentation control unit (presentation control means) 105A Classification section (classification means) 107A Basis information generation unit (basis information generation means) 108A prediction unit (prediction means) 109A Generation control unit (generation control means)

Claims

1. a question selection means for selecting a question to be presented to the subject next from among questions included in a question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject; and a presentation control means for presenting to the subject a portfolio according to the subject's answers to each of the selected and presented questions.

2. the question selection means selects a plurality of questions from the group of questions; a classification means for classifying the subjects based on their answers to the plurality of questions; The information processing apparatus according to claim 1 , wherein the question selection means selects a question according to the classification of the subject as a question to be presented next to the plurality of questions.

3. 3. The information processing device according to claim 2, wherein the classification means evaluates the subject based on a plurality of predetermined evaluation axes including at least one of knowledge about investment, experience about investment, confidence in investment, calmness, and behavioral tendencies, and classifies the subject based on the results of the evaluation.

4. The information processing device according to claim 2 , wherein the classification means classifies the subject based on an evaluation result obtained by evaluating the subject relative to other subjects.

5. The information processing device according to claim 1 , wherein the question selection means repeatedly selects questions from the set of questions until all the answers necessary to determine the portfolio to be presented to the subject are obtained.

6. An information processing device as described in any one of claims 1 to 3, comprising a basis information generation means for generating basis information indicating the basis for recommending the portfolio to the subject based on each piece of information used to determine the portfolio to be presented to the subject, and the presentation control means presents the basis information to the subject.

7. a prediction means for predicting questions about asset management of the subject by using a language model that has been machine-learned from consultation cases about asset management; The information processing device according to claim 1 , wherein the presentation control means presents the predicted questions to the subject.

8. 4. The information processing device according to claim 1, further comprising a generation control means for causing a machine-learned language model to generate questions to elicit from the subject information necessary to determine investment destinations in line with the presented portfolio.

9. At least one processor a question selection process for selecting a question to be presented to the subject next from among questions included in a question group that have not yet been presented to the subject, based on the subject's answer to a question selected from the question group for determining an asset management portfolio and presented to the subject; and a presentation control process for presenting to the subject a portfolio according to the subject's answers to each of the selected and presented questions.

10. Computer, a question selection means for selecting a question to be presented to the subject next from among questions included in a group of questions for determining an asset management portfolio and not yet presented to the subject, based on the subject's answer to the question; and and a support program that functions as a presentation control means for presenting to the subject a portfolio according to the subject's answers to each of the selected and presented questions.

Images