Information processing device and information processing method

Abstract

This information processing device comprises: an acquisition unit that acquires meeting information relating to a meeting and statement information indicating statement content to be stated by a user in the meeting; a determination unit that, on the basis of the meeting information, determines evaluation information including an evaluation item for the statement content; and a generation unit that, on the basis of the statement information and the evaluation information, generates a prompt for instructing a generation AI model to generate advice information including advice for correcting the statement content.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] Patent Document 1 describes a presentation support system that supports the creation of presentation materials to be used in presentations. This presentation support system evaluates presentation materials based on evaluation rules set in accordance with data related to the presentation execution situation, such as the size of the venue, time, and audience, and outputs necessary advice based on the evaluation results.

[0003] Japanese Patent Application Publication No. 2-64871

[0004] The appropriate presentation content may vary depending on the conference. In the presentation support system described above, the evaluation parameters of the pre-prepared evaluation rules are changed according to data on the presentation execution status, but the evaluation rules themselves are not changed. Therefore, there is a risk that advice appropriate for the conference may not be obtained.

[0005] The present disclosure describes an information processing device and an information processing method that enable advice suited to a meeting body to be obtained.

[0006] An information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires conference body information related to a conference body and presentation information indicating the content of the presentation to be made by a user at the conference body, a determination unit that determines evaluation information including evaluation items for the presentation content based on the conference body information, and a generation unit that generates a prompt to instruct a generation AI model to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information.

[0007] An information processing method according to another aspect of the present disclosure includes steps of acquiring conference body information related to a conference body and presentation information indicating the content of the presentation to be made by a user at the conference body, determining evaluation information including evaluation items for the presentation content based on the conference body information, and generating a prompt to instruct a generation AI model to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information.

[0008] According to the present disclosure, advice appropriate for the meeting body can be obtained.

[0009] Fig. 1 is a block diagram showing the overall configuration of a support system including an information processing device according to an embodiment. Fig. 2 is a diagram showing an example of an evaluation item table stored in a database shown in Fig. 1. Fig. 3 is a diagram showing an example of an evaluation criteria table stored in the database shown in Fig. 1. Fig. 4 is a flowchart showing an information processing method performed by the information processing device shown in Fig. 1. Fig. 5 is a diagram showing an example of a prompt. Fig. 6 is a diagram showing an example of a prompt. Fig. 7 is a diagram showing an example of advice information. Fig. 8 is a diagram showing the hardware configuration of the information processing device shown in Fig. 1.

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicated descriptions will be omitted.

[0011] An assistance system including an information processing device according to one embodiment will be described with reference to Figures 1 to 3. Figure 1 is a block diagram showing the overall configuration of the assistance system including an information processing device according to one embodiment. Figure 2 is a diagram showing an example of an evaluation item table stored in the database shown in Figure 1. Figure 3 is a diagram showing an example of an evaluation criteria table stored in the database shown in Figure 1.

[0012] The support system 1 shown in Fig. 1 is a computer system that supports the creation of presentation content (e.g., a script) suitable for a conference. Examples of conferences include exhibitions, lectures, and academic conferences. The support system 1 includes an information processing device 10, a user terminal 20, a database 30, and a generation AI server 40. The information processing device 10 is configured to be able to communicate with each of the user terminal 20, the database 30, and the generation AI server 40 via any communication network.

[0013] The information processing device 10 is a device that presents advice (counsel) to a user of a user terminal 20 regarding the content of a presentation that the user is making at a conference. The information processing device 10 functions as a Retrieval-Augmented Generation (RAG) system. The functional configuration of the information processing device 10 will be described later.

[0014] The user terminal 20 is a device used by a user who receives advice from the information processing device 10. The user terminal 20 is, for example, a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, or a game console. Although only one user terminal 20 is illustrated in FIG. 1 , the information processing device 10 may provide the above-described advice to each of multiple users. In this case, the assistance system 1 may include multiple user terminals 20 used by each of the multiple users. For example, if the information processing device 10 has a display device (output device) such as a display for presenting advice, the user may directly operate the information processing device 10. In this case, the assistance system 1 may not include a user terminal 20.

[0015] The database 30 is a knowledge database that stores various types of information. As shown in FIG. 1, the database 30 may be located outside the information processing device 10 or may be located within the information processing device 10. As shown in FIG. 2, the database 30 stores an evaluation item table. The evaluation item table indicates evaluation items that are applied to listener types. The evaluation items are items for evaluating the content of the presentation. The evaluation item table includes data records provided for each evaluation item. Each data record includes an evaluation item ID (identifier), the content of the evaluation item, and the listener type.

[0016] The evaluation item ID is an identifier that can uniquely identify an evaluation item. Hereinafter, an evaluation item with an evaluation item ID of "X" will be referred to as "evaluation item X." The audience type is the type of audience that will participate in the meeting and listen to the presentation. Examples of audience types include company executives, company general employees, users of products or services, and employees of partner companies.

[0017] Here, the content of evaluation item E1 is "Does the content allow the customer to specifically understand what kind of product or service it is?" The content of evaluation item E2 is "Does the content allow the listener to understand the technology in detail?" The content of evaluation item E3 is "Is the explanation from a management perspective, rather than a detailed technical explanation?" Evaluation item E4 is an evaluation item common to all listeners, and its content is "Are there any redundant expressions or grammatically incorrect expressions?"

[0018] Other evaluation items common to all listeners may include, "Has consideration been given to avoid hurting or offending some people?", "Are there expressions that promote discrimination?", "Are there expressions that are insulting to people with disabilities?", "Are there expressions that insult or glorify specific values ​​such as ideology, creed, or religion?", "Are there expressions that involve antisocial or dangerous behavior?", "Are there expressions that would be considered dangerous or inappropriate for listeners to engage in similar behavior?", and "Are there expressions that denigrate or defame competitors, specific individuals, or organizations?"

[0019] As shown in FIG. 3, the database 30 stores an evaluation criteria table including a plurality of data records. The evaluation criteria table indicates the evaluation criteria for each evaluation item. Each data record includes an evaluation item ID, an evaluation criterion, a score, and a case study. The evaluation criterion indicates the evaluation criteria indicated by the evaluation item. The score is a number of points awarded when the presentation content meets the evaluation criterion associated with the score. The case study is a sample of the presentation content that meets the evaluation criterion associated with the case study. At least one evaluation criterion is set for each evaluation item. The score and case study are set corresponding to the evaluation criterion.

[0020] 3, evaluation criteria are set for evaluation item E1, such as "Too little information, making it impossible to make a judgment," "All the information is there, but I can't understand specifically what kind of product / service it is as a whole," "I can understand what kind of product / service it is as a whole, but there are many parts I don't understand," "I can roughly understand what kind of product / service it is as a whole, but there are some parts I don't understand," and "It's very easy to understand what kind of product / service it is specifically." Scores of 0, 20, 40, 60, and 100 are set for these evaluation criteria, respectively.

[0021] For these evaluation criteria, examples are set such as "Improve the purchase rate," "Improve the purchase rate by using rule-based recommendations," "Improve the purchase rate by using rule-based recommendations on EC site XX," "Recommend popular products on EC site XX," and "Recommend products that are popular with the customer's generation when the customer logs in on EC site XX." Note that multiple examples may be set for one evaluation criterion (score).

[0022] The generation AI server 40 is a device that includes a generation AI model 41 and generates and provides content using the generation AI model 41. The generation AI model 41 is a model that, in response to a prompt input from the information processing device 10 (in this embodiment, the generation unit 13), generates content (in this embodiment, advice information) according to any one or a combination of the instructions, context, question, and output format indicated by the prompt, and returns the content as response information.

[0023] A prompt is information indicating an instruction or question input to the generative AI model 41 in an interactive system such as a dialogue with the generative AI model 41 or a command line interface (CLI). The prompt can include various types of input information. In this case, the generative AI model 41 generates response information targeted at the various types of input information. The type and format of the input information are not particularly limited, and the input information may include, for example, data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0024] The generative AI model 41 may be configured to include, for example, a large language model (LLM) and a user interface (UI) for interacting with a user. The generative AI model 41 may be an interactive AI model capable of chatting with a user via text or voice. Examples of such a generative AI model 41 include ChatGPT, GPT-3.5, GPT-4V, and PaLM2. The generative AI model 41 may be an AI model other than the large language model described above. The generative AI model 41 may be configured by combining multiple different AI models.

[0025] 1, the generating AI model 41 may be placed in a generating AI server 40 separate from the information processing device 10, or may be placed in the information processing device 10. The generating AI model 41 may also be placed in the user terminal 20. In this case, each function of the information processing device 10 may also be placed in the user terminal 20. That is, the user terminal 20 itself may function as the information processing device 10 of this embodiment.

[0026] In this embodiment, the generative AI model 41 is described as being capable of understanding the content of prompts composed of Japanese sentences, but a generative AI model 41 that supports a language other than Japanese or a predetermined grammar may be used. In this case, the content of the prompts in Japanese sentences, which will be described later, may be changed as appropriate depending on the language or grammar supported by the generative AI model 41.

[0027] Next, a description will be given of the functional configuration of the information processing device 10. As shown in Fig. 1, the information processing device 10 includes an acquisition unit 11, a determination unit 12, a generation unit 13, and a presentation unit 14 as functional elements.

[0028] The acquisition unit 11 acquires the conference entity information and the presentation information from, for example, the user terminal 20.

[0029] The conference body information is information about the conference body. The conference body information includes, for example, audience information and goal information. The audience information is information about the audience participating in the conference body (information indicating the audience). The audience information may include information indicating the type of audience and information indicating the audience attributes. Examples of audience attributes include experts in the field of the topic (presentation content) to be discussed at the conference body and amateurs in that field. The goal information is information indicating the goals of the conference body. The goal information indicates, for example, actions expected as a result of holding the conference body. Examples of such actions include purchasing a product, forming a business partnership, and acquiring knowledge. The conference body information may further include the type of conference (exhibition, academic conference, lecture, workshop, web conference, etc.), the date and time of the conference, the location (physical or virtual), a list of participants, the positions and areas of expertise of the participants, the format of the conference (interactive session, question and answer session, etc.), technical settings (projector and microphone, etc.), and the demographics of the conference body (age group and gender composition, etc.).

[0030] Presentation information is information that indicates the content of a presentation a user will make at a conference. Presentation information may be a text file, a document file, or a presentation file. Presentation information may be a script itself or a summary of the script. Presentation information may be presentation materials or information that describes the key points of the presentation materials. Presentation information may also include visual aids (diagrams, graphs, and images), audio data (recorded speeches), video data (recorded presentations), live demonstration scripts, interactive content (slide shows and virtual reality simulations), and digital media (web pages and social media posts).

[0031] The determination unit 12 determines evaluation information based on the meeting body information. The evaluation information is information for evaluating the presentation content. The evaluation information includes evaluation items for the presentation content and evaluation criteria for the evaluation items. The evaluation information may further include examples according to the evaluation criteria (see FIG. 3). Details of the method for determining the evaluation information will be described later.

[0032] The generation unit 13 generates a prompt to instruct the generative AI model to generate advice information based on the presentation information and the evaluation information. The advice information is content for suggesting to the user advice on correcting the presentation content. The advice information includes advice on correcting the presentation content. The presentation unit 14 presents the advice information to the user terminal 20. The advice information may be content including at least one of specific wording suggestions, readjustment of the presentation structure, addition or correction of visual support, improvement of vocal tone and intonation, advice on time management, suggestions for improvement based on audience reactions, suggestions for practice methods, technical advice (microphone usage, lighting settings, and slide design), changes in media format (video clips and infographics), and cultural and linguistic adjustments.

[0033] Next, an information processing method performed by the information processing device 10 will be described with reference to Figures 4 to 7. Figure 4 is a flowchart showing the information processing method performed by the information processing device shown in Figure 1. Figures 5 and 6 are diagrams showing examples of prompts. Figure 7 is a diagram showing an example of advice information. The series of processes shown in Figure 4 is started, for example, by the execution of an application for evaluating the content of a presentation on the user terminal 20.

[0034] First, the acquisition unit 11 acquires conference body information (step S1). In step S1, for example, a user may directly input the types of listeners, attributes of the listeners, and a goal of the conference body to the user terminal 20, and the acquisition unit 11 may acquire, as conference body information, listener information including information indicating the types of the input listeners and information indicating the attributes of the input listeners, and goal information indicating the goal of the input conference body.

[0035] Candidates for the type of listener, the attribute of listener, and the goal of the conference body may be stored in advance in the database 30. In this case, the acquisition unit 11 may acquire the candidates for the type of listener, the attribute of listener, and the goal of the conference body from the database 30 and display these candidates on the user terminal 20. When the user selects the type of listener, the attribute of listener, and the goal of the conference body from the displayed candidates, the acquisition unit 11 may acquire conference body information including the selected candidates from the user terminal 20. Then, the acquisition unit 11 outputs the conference body information to the determination unit 12 and the generation unit 13.

[0036] Next, the acquiring unit 11 acquires the presentation information (step S2). In step S2, for example, the user may directly input the presentation content into the user terminal 20, and the acquiring unit 11 may acquire the presentation information indicating the input presentation content from the user terminal 20.

[0037] A template of the presentation content may be stored in advance in the database 30. In this case, the acquisition unit 11 may transmit the template to the user terminal 20 and display it on the user terminal 20. When the user inputs the presentation content using the template displayed on the user terminal 20, the acquisition unit 11 may acquire presentation information indicating the input presentation content from the user terminal 20. For example, a template such as "I will now explain the exhibit in {{}}" is prepared. The user terminal 20 may prompt the user to input a title by displaying this template along with a message such as "Please enter the title of the exhibit content in {{}}."

[0038] A plurality of script files may be stored in advance in the database 30. In this case, the acquisition unit 11 may acquire a plurality of script files from the database 30 and display these script files on the user terminal 20. When the user selects a desired script file from the displayed script files, the acquisition unit 11 may acquire the selected script file as presentation information from the user terminal 20. Then, the acquisition unit 11 outputs the presentation information to the generation unit 13.

[0039] Next, the determiner 12 determines evaluation information based on the conference entity information (step S3). In step S3, the determiner 12 determines evaluation items based on the listener information included in the conference entity information. For example, the determiner 12 refers to an evaluation item table stored in the database 30 and extracts evaluation items (evaluation item IDs and evaluation item contents) associated with the listener types indicated by the listener information. Then, the determiner 12 determines the extracted evaluation items as evaluation items to be used for evaluating the presentation content.

[0040] In step S3, the determination unit 12 may refer to the evaluation criteria table stored in the database 30 and extract a data record including the evaluation item ID of the extracted evaluation item. In this case, the determination unit 12 determines a combination of the evaluation item and the evaluation criteria, score, and case example included in the extracted data record as evaluation information to be used for evaluating the presentation content. Then, the determination unit 12 outputs the evaluation information to the generation unit 13.

[0041] Next, the generation unit 13 generates a prompt for instructing the generation AI model 41 to generate advice information based on the presentation information and the evaluation information (step S4). In step S4, the generation unit 13 generates a prompt including the presentation content indicated by the presentation information and the evaluation items and evaluation criteria for the evaluation items included in the evaluation information. The generation unit 13 may include, in the prompt, a score included in the evaluation information and associated with the evaluation criteria. The generation unit 13 may include, in the prompt, a case included in the evaluation information and associated with the evaluation criteria (score).

[0042] The generation unit 13 may generate a prompt further based on the conference entity information. For example, the generation unit 13 may set at least one of the type and attribute of the listener indicated by the listener information included in the conference entity information in the prompt as the listener of the presentation content. The generation unit 13 may set the goal indicated by the goal information included in the conference entity information in the prompt as the goal of the conference entity. The generation unit 13 may generate a prompt using a template prepared in advance.

[0043] An example of a method for generating a prompt will be specifically described using the prompt P shown in Figures 5 and 6. The prompt P includes areas R1 to R6. Area R1 is an area where a command statement is written. The command statement is a sentence that indicates an execution instruction for the generative AI model 41. The command statement may include a statement specifying the role of the generative AI model 41. In this example, the command statement is "You are an excellent editor. Please perform the task according to the following # situation.", and the role of the generative AI model 41 is specified as "an excellent editor." Area R1 may contain a standard command statement.

[0044] The generation unit 13 may specify a role for the generated AI model 41 based on the meeting body information. For example, if the type of listener indicated by the listener information is a user of a product or service, "user of the product or service" may be specified as the role for the generated AI model 41. For example, a table in which roles are associated with each goal of the meeting body is stored in the database 30, and the generation unit 13 may refer to the table and specify a role associated with the goal indicated by the goal information as the role for the generated AI model 41.

[0045] The generation unit 13 may specify a role for the generative AI model 41 based on the evaluation item determined in step S3. For example, a table in which roles are associated with each evaluation item is stored in the database 30, and the generation unit 13 may refer to the table and specify the role associated with the evaluation item determined in step S3 as the role of the generative AI model 41. For example, if the evaluation item "Whether the expression is problematic from a legal perspective" is determined in step S3, "lawyer" may be specified as the role of the generative AI model 41.

[0046] The generation unit 13 may specify a different role for each evaluation item determined in step S3 as the role of the generative AI model 41. For example, the area R1 may include a statement such as "Evaluate evaluation items <1> and <2> with role A, and evaluate evaluation items <3> and <4> with role B."

[0047] Area R2 is an area where the situation is written. The situation is a sentence that specifically expresses the content of the imperative sentence. The situation includes, for example, the organizer of the meeting body, the type of meeting body, and specific instructions. In this example, the situation is written as follows: "Please review the #presentation content in the explanatory video for the following exhibit, which will be posted on the special website for the exhibition event hosted by NTT Docomo's R&D department, and check that there are no problems with the #presentation content according to the #evaluation items below." Area R2 may also contain standard phrases.

[0048] The generation unit 13 may set the text to be written in region R2 based on the conference body information. For example, when the conference body information includes information such as the organizer of the conference body and the type of the conference body, the generation unit 13 may generate the text to be written in region R2 from the information such as the organizer of the conference body and the type of the conference body included in the conference body information and set the generated text in region R2.

[0049] Area R3 is an area where the listeners are written. The generation unit 13 sets at least one of the type and attribute of the listener indicated by the listener information included in the meeting entity information in area R3. In this example, a "user of the product or service" is set as the listener. Area R4 is an area where the presentation content is written. The generation unit 13 sets the presentation content indicated by the presentation information in area R4. In this example, a script is set as the presentation content.

[0050] Region R5 is an area where evaluation items (evaluation information) are written. The generation unit 13 sets the evaluation information determined in step S3 in region R5. For example, the generation unit 13 sets a sentence describing evaluation criteria, scores, and examples (graded examples) for each evaluation item in region R5. Note that in FIG. 6, evaluation criteria, scores, and examples are written only for evaluation item <1>, but evaluation criteria, scores, and examples are also written for each of evaluation items <2> to <9>.

[0051] Area R6 is an area where the output format is written. A fixed phrase may be written in area R6. In this example, the output format is written as follows: "#Evaluate the presentation content according to the above #evaluation items, and output each of the #evaluation items in table format. -Areas that need to be corrected -Reasons for the corrections -Proposed revisions."

[0052] If a template is used to generate the prompt P, the template may include the boilerplate text described above.

[0053] Next, the generation unit 13 acquires advice information using the generation AI model 41 (step S5). Specifically, the generation unit 13 inputs the prompt generated in step S4 to the generation AI model 41 and acquires the content generated by the generation AI model 41 as advice information. Then, the generation unit 13 outputs the advice information to the presentation unit 14.

[0054] Next, the presentation unit 14 presents the advice information to the user terminal 20 (step S6). For example, the advice information shown in FIG. 7 is presented. In the example shown in FIG. 7, for evaluation item <1>, "If you have smart glasses, you need to launch various content and use them appropriately depending on the situation." is extracted as a part that needs revision, and "With smart glasses, you can quickly obtain data during a meeting or instantly display a shopping list in your daily life, and obtain a lot of information with one device. This will greatly improve work efficiency." is presented as a proposed revision. The reason for the need for revision is given as "There is an explanation of the technology itself, but there are no specific examples of how it will change your life or work processes."

[0055] This completes the series of steps in the information processing method. Note that step S2 may be performed before step S1 or in parallel with step S1.

[0056] In the information processing device 10 and the information processing method performed by the information processing device 10 described above, evaluation information including evaluation items for the presentation content is determined based on conference body information related to the conference body, and a prompt is generated to instruct the generation AI model 41 to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information. Therefore, rather than using all evaluation items, the prompt is generated using evaluation items determined according to the conference body. By inputting the prompt generated in this manner into the generation AI model 41, the presentation content is evaluated using evaluation items according to the conference body, and correction advice according to the evaluation results is obtained. From the above, the information processing device 10 and the information processing method make it possible to obtain correction advice appropriate for the conference body. Furthermore, by using the generation AI model 41, the time required to evaluate the presentation content can be reduced and the evaluation can be made more uniform.

[0057] The content that listeners want to hear may vary. For example, in a presentation about a "Non-Player Character (NPC) avatar value engine," regular employees within the company may be interested in detailed technical information, such as the AI ​​model used to implement the NPC avatar's values. On the other hand, senior employees within the company, such as management, may be interested in what kind of services can be provided to customers, whether the NPC avatars have inappropriate values, and so on. In the information processing device 10 and information processing method, evaluation items are determined based on listener information. Therefore, the evaluation items can be flexibly changed to suit the listener, making it possible to obtain correction advice that is appropriate for the listener.

[0058] The evaluation information includes evaluation criteria for the evaluation items in addition to the evaluation items. That is, prompts are generated using evaluation items and evaluation criteria determined according to the meeting body. For example, the evaluation items and evaluation criteria can be flexibly changed according to factors related to the meeting body, such as the audience, making it possible to obtain correction advice that is more appropriate for the meeting body.

[0059] The evaluation information further includes examples according to the evaluation criteria. That is, prompts are generated using examples according to the evaluation criteria in addition to the evaluation items and evaluation criteria determined according to the meeting body. By inputting these prompts into the generation AI model 41, evaluation (scoring) is performed taking into account the examples, enabling detailed evaluation as if done by a human. Therefore, more appropriate correction advice can be obtained.

[0060] Multiple examples may be set for one evaluation criterion. The more examples there are, the more accurately the degree of the evaluation criterion can be conveyed to the generative AI model 41. Therefore, more appropriate correction advice can be obtained.

[0061] The generator 13 may include, in the prompt, information specifying the role of the generated AI model 41 based on the meeting body information. For example, a role according to the audience or goals of the meeting body is assigned to the generated AI model 41, making it possible to obtain more appropriate correction advice.

[0062] The generation unit 13 may include information specifying the role of the generative AI model 41 in the prompt based on the evaluation item. For example, when the evaluation item "Is the expression problematic from a legal perspective?" is used, "lawyer" may be specified as the role of the generative AI model 41. In this way, a role appropriate for the evaluation item is assigned to the generative AI model 41, making it possible to obtain more appropriate correction advice.

[0063] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above embodiments.

[0064] The evaluation item table shown in Figure 2 indicates the listener types to which the evaluation items are applied, but it may also indicate meeting entity information to which the evaluation items are applied. In this case, each data record in the evaluation item table includes an evaluation item ID, the content of the evaluation item, and meeting entity information. The meeting entity information may include at least one listener type, at least one goal of the meeting entity, or a combination of listener types and goals of the meeting entity.

[0065] 3 shows the evaluation criteria for each evaluation item, but it may also show evaluation criteria for each combination of evaluation item and listener type. In this case, each data record in the evaluation criteria table may include an evaluation item ID, a listener type, an evaluation criterion, a score, and an example.

[0066] The database 30 may further include a table in which example sentences of correction advice (correction proposals) are associated with each evaluation item. For each evaluation item, meeting body information and example sentences of correction advice may be associated. For example, for evaluation item E1, "user of the product or service" is associated as the listener type, and "You can set a reminder before commuting to prevent forgetting something!" is associated as an example sentence of correction advice. In this case, the determination unit 12 may further determine example sentences of correction advice corresponding to the evaluation item by referring to the table. The generation unit 13 may include the example sentences determined by the determination unit 12 in the prompt. According to the above configuration, by providing example sentences to the generation AI model 41, more appropriate correction advice can be obtained.

[0067] The database 30 may further include a table in which example sentences of correction advice (correction proposals) are associated with the scores of each evaluation item. For example, a score of 0 for evaluation item E1 may be associated with an example sentence of correction advice such as, "There is insufficient information, so please be more specific about the product or service and its impact on the customer's life." A score of 20 for evaluation item E1 may be associated with an example sentence of correction advice such as, "Please be more specific about the benefits to the customer's life, such as 'You can set a reminder before commuting and prevent forgetting things!'"

[0068] In this case, the determination unit 12 may cause a scoring AI model to score the presentation content for each evaluation item and obtain the scoring results. An AI model using a normal scoring method or the generative AI model 41 may be used as the scoring AI model. The determination unit 12 may then determine example sentences for each score of the evaluation item by referencing the table. According to the above configuration, by providing the generative AI model 41 with example sentences according to the scores, more appropriate revision advice can be obtained. Note that the generation unit 13 may input a prompt set to output a score for each evaluation item as an output format to the generative AI model 41, and after obtaining the content generated by the generative AI model 41, the determination unit 12 may determine example sentences using the scores included in the content.

[0069] The configurations of the evaluation item table, evaluation criteria table, etc. are not limited to those in the above embodiment. The configuration of each table can be changed using known techniques. For example, each table may be configured using a relational database.

[0070] The determination unit 12 only needs to determine evaluation items as evaluation information, but does not need to determine evaluation criteria or case studies. In other words, the generation unit 13 only needs to generate prompts using the evaluation items determined by the determination unit 12, but does not need to use evaluation criteria or case studies.

[0071] The information processing device and information processing method of the present disclosure have the following configuration.

[0072] [1] An information processing device comprising: an acquisition unit that acquires conference body information related to a conference body and presentation information indicating the content of a presentation to be made by a user at the conference body; a determination unit that determines evaluation information including evaluation items for the presentation content based on the conference body information; and a generation unit that generates a prompt to instruct a generation AI model to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information.

[0073] [2] The information processing device according to [1], wherein the evaluation information further includes evaluation criteria for the evaluation items.

[0074] [3] The information processing device according to [2], wherein the evaluation information further includes examples according to the evaluation criteria.

[0075] [4] The information processing device according to any one of [1] to [3], wherein the conference body information includes listener information regarding listeners of the conference body, and the determination unit determines the evaluation items based on the listener information.

[0076] [5] The information processing device according to any one of [1] to [4], wherein the determination unit further determines an example sentence of the correction advice according to the evaluation item, and the generation unit includes the example sentence in the prompt.

[0077] [6] The information processing device according to [5], wherein the determination unit determines the example sentence for each score of the evaluation item.

[0078] [7] The information processing device according to any one of [1] to [6], wherein the generation unit includes information specifying a role of the generated AI model in the prompt based on the meeting body information.

[0079] [8] The information processing device according to any one of [1] to [6], wherein the generation unit includes information specifying a role of the generated AI model in the prompt based on the evaluation item.

[0080] [9] An information processing method including the steps of: acquiring conference body information related to a conference body and presentation information indicating the content of the presentation to be made by a user at the conference body; determining evaluation information including evaluation items for the presentation content based on the conference body information; and generating a prompt to instruct a generation AI model to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information.

[0081] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. The method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., using wires, wirelessly, etc.) and these multiple devices. The functional block may be realized by combining software with the single device or the multiple devices.

[0082] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs a transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how the functions are implemented.

[0083] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs processing of the information processing method according to the present disclosure. Fig. 8 is a diagram illustrating an example of a hardware configuration of a device according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0084] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may include one or more of the devices shown in the drawings, or may not include some of the devices.

[0085] Each function in the information processing device 10 is realized by loading a specified software (program) onto hardware such as the processor 1001 or memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0086] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, and a register. For example, at least one of the functional units of the information processing device 10 described above may be realized by the processor 1001.

[0087] The processor 1001 reads programs (program code), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used may be programs that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, at least one of the functional units of the information processing device 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional units may be implemented in a similar manner. While the above-described various processes have been described as being executed by a single processor 1001, the above-described various processes may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0088] The memory 1002 is a computer-readable recording medium and may be configured by at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be referred to as a register, a cache, or a main memory (primary storage device). The memory 1002 can store executable programs (program codes), software modules, and the like for implementing an information processing method according to an embodiment of the present disclosure.

[0089] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, and a magnetic strip. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0090] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include, for example, a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, at least one of the functional units of the information processing device 10 described above may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmitter and a receiver physically or logically separated from each other.

[0091] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (e.g., a touch panel).

[0092] The processor 1001, memory 1002, and other devices are connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses for each device.

[0093] The information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0094] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. The RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0095] In the processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure, the order of processing may be changed unless there is a contradiction. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the specific order presented.

[0096] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0097] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0098] The aspects / embodiments described in the present disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be performed implicitly (e.g., by not notifying the predetermined information).

[0099] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is for illustrative purposes only and does not have any limiting meaning on the present disclosure.

[0100] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, and the like, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0101] Software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), these wired and / or wireless technologies are included within the definition of transmission media.

[0102] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0103] Note that terms described in the present disclosure and terms necessary for understanding the present disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). A signal may be a message. A component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, or the like.

[0104] The information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0105] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the formulas using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0106] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0107] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0108] The terms "determining" and "determining" as used in this disclosure may encompass a wide variety of actions. "Determining" and "determining" may be considered, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., looking up in a table, database, or another data structure), ascertaining, etc. "Determining" and "determining" may also be considered, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), etc. "Determining" and "determining" may also be considered, for example, resolving, selecting, choosing, establishing, comparing, etc. That is, "determining" and "determining" may include considering any action related to "determining." The word "judgment (decision)" may be read as "assuming," "expecting," or "considering," etc.

[0109] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and there may be one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." When "connected" or "coupled" is used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of an electrical wire, cable, and printed electrical connection, or may be considered to be "connected" or "coupled" to each other using electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0110] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0111] Any reference to an element using designations such as "first" and "second" used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, reference to a first and a second element does not imply either that only two elements may be employed or that the first element must in some way precede the second element.

[0112] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0113] In this disclosure, where articles are added by translation, such as "a," "an," and "the" in English, the disclosure may include that the nouns following these articles are plural.

[0114] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0115] 1...Support system, 10...Information processing device, 11...Acquisition unit, 12...Decision unit, 13...Generation unit, 41...Generative AI model

Claims

1. An information processing device comprising: an acquisition unit that acquires conference body information related to a conference body and presentation information indicating the content of the presentation to be made by a user at the conference body; a determination unit that determines evaluation information including evaluation items for the presentation content based on the conference body information; and a generation unit that generates a prompt to instruct a generation AI model to generate advice information including advice for correcting the presentation content based on the presentation information and the evaluation information.

2. The information processing device according to claim 1, wherein the evaluation information further includes evaluation criteria for the evaluation items.

3. The information processing device according to claim 2, wherein the evaluation information further includes examples according to the evaluation criteria.

4. The information processing device according to claim 1, wherein the conference body information includes listener information regarding listeners of the conference body, and the determination unit determines the evaluation items based on the listener information.

5. The information processing device according to claim 1, wherein the determination unit further determines an example sentence of the correction advice according to the evaluation item, and the generation unit includes the example sentence in the prompt.

6. The information processing device according to claim 5, wherein the determination unit determines the example sentence for each score of the evaluation item.

7. The information processing device according to claim 1, wherein the generation unit includes information specifying the role of the generated AI model in the prompt based on the meeting body information.

8. The information processing device according to claim 1, wherein the generation unit includes information in the prompt that specifies the role of the generated AI model based on the evaluation items.

9. An information processing method comprising the steps of: acquiring conference body information relating to a conference body and presentation information indicating the content of the presentation to be made by a user at the conference body; determining evaluation information including evaluation items for the presentation content based on the conference body information; and generating a prompt to instruct a generation AI model to generate advice information including advice for modifying the presentation content based on the presentation information and the evaluation information.

Images