Information processing systems, information processing methods, and programs

Abstract

To efficiently support the improvement of sales skills. [Solution] An information processing system that supports sales role-playing using a generating AI, comprising: a skill storage unit that stores skills to be measured in association with each of multiple phases of a sales negotiation; an educational content storage unit that stores educational content for skill improvement for each skill; a scenario storage unit that stores a role-playing scenario for each phase; an evaluation unit that evaluates the role-playing performed between the user and the generating AI based on the scenario corresponding to the sales negotiation phase specified by the user and calculates a score; and a recommendation unit that, when the score is below a predetermined threshold, refers to the skill storage unit and the educational content storage unit to identify educational content corresponding to the skills associated with the sales negotiation phase and presents the identified educational content to the user.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] There is known a technique of estimating a user's emotion from an electroencephalogram signal and playing music from a playlist according to the emotion (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to generate a playlist for each emotion as in the prior art, it is necessary to have the user make annotations, which has caused the user to perform complicated processing. In addition, the playlist contains only content of one genre, for example, only music, and there has been a case where the desired emotion control cannot be achieved when the user becomes accustomed to the content.

[0005] The present invention has been made in view of such a background, and an object thereof is to provide a technique that can efficiently support the improvement of sales skills.

Means for Solving the Problems

[0006] The main invention of the present invention for solving the above problems is an information processing system that supports sales role-playing using a generating AI, comprising: a skill storage unit that stores skills to be measured in association with each of multiple phases of a business negotiation; an educational content storage unit that stores educational content for skill improvement for each of the skills; a scenario storage unit that stores a role-playing scenario for each of the phases; an evaluation unit that evaluates the role-playing performed between the user and the generating AI based on the scenario corresponding to the business negotiation phase specified by the user and calculates a score; and a recommendation unit that, when the score is below a predetermined threshold, refers to the skill storage unit and the educational content storage unit to identify the educational content corresponding to the skills associated with the business negotiation phase and presents the identified educational content to the user.

[0007] Further issues and solutions disclosed in this application will be made clear in the section on embodiments of the invention and in the drawings. [Effects of the Invention]

[0008] According to this invention, it is possible to efficiently support the improvement of sales skills. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of an information processing system. [Figure 2] This figure shows an example of the hardware configuration of management server 2. [Figure 3] This figure shows an example of the software configuration for management server 2. [Figure 4] This diagram illustrates the processing flow of the scenario generation phase in an information processing system. [Figure 5] This diagram illustrates the processing flow of the role-playing execution phase in an information processing system. [Modes for carrying out the invention]

[0010] <System Overview> The following describes an information processing system according to one embodiment of the present invention. This information processing system utilizes artificial intelligence (AI) to support role-playing training for sales representatives. The system manages skill evaluation items corresponding to each phase of a sales negotiation, and the AI ​​generates an avatar of the sales partner based on the sales negotiation phase to be role-played. The generated avatar interacts with the user according to a realistic sales negotiation scenario, practically training the user's sales skills. The system analyzes the user's speech content and response patterns in detail during role-playing and calculates a score for each skill item. If the score falls below a certain threshold, the system automatically recommends educational content to improve the corresponding skill, supporting efficient skill development.

[0011] Figure 1 shows an example of the overall configuration of an information processing system. The information processing system in this embodiment includes a management server 2. The management server 2 is connected to the user terminal 1 via a communication network. The communication network is, for example, the internet and is constructed using public telephone networks, mobile phone networks, wireless communication channels, Ethernet (registered trademark), etc.

[0012] User terminal 1 is a computer operated by the user. User terminal 1 can be, for example, a smartphone, a tablet computer, or a personal computer.

[0013] The management server 2 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] <Management Server> Figure 2 shows an example of the hardware configuration of the management server 2. Note that the illustrated configuration is just one example, and other configurations are also possible. The management server 2 includes a CPU 201, memory 202, storage device 203, communication interface 204, input device 205, and output device 206. The storage device 203 stores various data and programs, such as a hard disk drive, solid-state drive, or flash memory. The communication interface 204 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The input device 205 is for inputting data, such as a keyboard, mouse, touch panel, button, or microphone. The output device 206 is for outputting data, such as a display, printer, or speaker. Furthermore, each functional unit of the management server 2, as described later, is realized by the CPU 201 reading programs stored in the storage device 203 into memory 202 and executing them, and each storage unit of the management server 2 is realized as part of the storage area provided by memory 202 and storage device 203. <Step 1: Explanation of Software Configuration>

[0015] Figure 3 shows an example of the software configuration of the management server 2. The management server 2 comprises a scenario generation unit 211, an evaluation unit 212, a recommendation unit 213, a learning control unit 214, a customization unit 215, an effectiveness analysis unit 216, a real-time analysis unit 217, a guidance unit 218, a skill memory unit 231, an educational content memory unit 232, a scenario memory unit 233, a history memory unit 234, an industry information memory unit 235, and a test result memory unit 236. <Step 2: Explanation of Functional Parts>

[0016] <Management Server 2> The following describes the functional components of the management server 2.

[0017] The skill memory unit 231 stores, in association with each of a plurality of phases of a business negotiation, skills to be measured. The skill memory unit 231 stores, as business negotiation phases, for example, five phases of "approach", "hearing", "proposal", "closing", and "follow-up". For each business negotiation phase, the skill memory unit 231 hierarchically stores a plurality of skill categories including hearing skills, proposal skills, and closing skills. For example, in the "hearing" phase, "questioning skills", "listening skills", and "problem discovery skills" are associated, and in the "proposal" phase, "logical composition skills", "persuasion skills", and "material utilization skills" are associated.

[0018] The education content memory unit 232 stores education content for skill improvement for each skill. The education content memory unit 232 can store step-by-step education content at a basic level, an application level, and an advanced level for each skill. The education content includes video teaching materials, text teaching materials, audio teaching materials, and interactive teaching materials. For example, at the basic level of "questioning skills", a video teaching material about "types of effective questions" is stored, at the application level, a text teaching material about "questioning techniques for eliciting customers' true intentions" is stored, and at the advanced level, a case study teaching material about "strategic questions in complex business negotiations" is stored.

[0019] The scenario memory unit 233 stores role-play scenarios for each phase. The scenario memory unit 233 stores a plurality of scenario patterns corresponding to each business negotiation phase of "approach", "hearing", "proposal", "closing", and "follow-up". Parameters such as the customer's industry, company size, purchase stage, budget scale, and decision-making process are set for each scenario, and the scenarios generated by the scenario generation unit 211 are also accumulated. The scenario memory unit 233 also stores scenario patterns with a high success rate and scenario templates specialized for specific industries and products.

[0020] The history memory unit 234 stores the past role-playing history and score transitions of the user. The history memory unit 234 stores history data including the implementation date and time, negotiation phase, scenario content, speech content, evaluation score, required time, and improvement points for each user. The history memory unit 234 stores, as score transition data, the time-series score changes of each skill item, the measurement results of learning effects, and the identification results of weak skills.

[0021] The industry information memory unit 235 stores the industry information and handled product information to which the user belongs. The industry information memory unit 235 stores negotiation characteristics for each industry, industry-specific technical terms, general negotiation processes, and customer decision-making patterns. As handled product information, it stores product categories, price ranges, sales cycles, competitive product information, and customer segment information.

[0022] The test result memory unit 236 stores the results of the confirmation tests conducted after learning educational content. The test result memory unit 236 stores, for each user, the test implementation date and time, target skills, question content, answer content, correct answer rate, required time, and understanding level.

[0023] The scenario generation unit 211 generates a role-playing scenario using a generating AI for each negotiation phase. The scenario generation unit 211 can generate a role-playing scenario using a generating AI based on the negotiation phase to be role-played. The negotiation phase to be role-played can be specified by the user or set in advance by the operator. The scenario generation unit 211 generates a scenario that defines the actions of the avatar of the sales partner. The scenario includes the avatar's personality settings, industry background, purchase intent level, budget constraints, decision-making authority, past transaction history, and comparison status with competitors. The scenario generation unit 211 dynamically generates the avatar's response patterns, questions, objections, and purchase signals according to the specified negotiation phase. For example, in the "hearing" phase, the avatar is set to gradually disclose issues and requests, and in the "proposal" phase, it is set to express specific questions and concerns about the proposal. The scenario generation unit 211 may generate scenarios in advance or generate them when role-playing is performed.

[0024] The evaluation unit 212 evaluates the role-playing performed between the user and the generating AI and calculates a score. The evaluation unit 212 can retrieve the relevant scenario from the scenario memory unit 233 and perform an evaluation according to the evaluation criteria set for that scenario. The evaluation unit 212 analyzes the user's utterances in the role-playing using speech recognition and calculates a score based on pre-set evaluation items. Evaluation items include the logicality of the utterances, the appropriateness of the questions, the degree to which customer needs are understood, the persuasiveness of the proposal, and the timing of the closing. The evaluation unit 212 performs semantic analysis of the utterances using natural language processing technology and calculates a score from 0 to 100 for each evaluation item. For example, in the evaluation of logicality, it determines whether the logical development of "conclusion → evidence → specific example" is appropriately performed by analyzing the structure of the utterance, and in the evaluation of the appropriateness of the questions, it evaluates the use of open and closed questions and the timing of the questions. In addition to or instead of the user's utterances, the evaluation unit 212 may also calculate a score based on non-verbal features such as the user's facial expressions and actions.

[0025] The recommendation unit 213 presents educational content for skill improvement to the user if the score is below a predetermined threshold. If the score is below the predetermined threshold, the recommendation unit 213 refers to the skill memory unit 231 and the educational content memory unit 232 to identify educational content corresponding to the skills associated with the current sales phase and presents the identified educational content to the user. For specific skills with low scores, the recommendation unit 213 selects and presents content from educational content categorized into basic, applied, and advanced levels, according to the user's skill level. The recommendation unit 213 analyzes the user's past learning history and current skill level and recommends educational content in the optimal learning order. For example, if the questioning skill score is below 60 points, it recommends starting with the basic level "Types of Effective Questions" and then recommending applied level content after the user achieves a score of 80 points or higher on the comprehension test. The recommendation unit may also present recommendations if they exist, even if the score is above the threshold.

[0026] The learning control unit 214 identifies the user's weak skill areas based on their history and controls the scenario generation unit 211 to prioritize the generation of role-playing scenarios that focus on training those areas. The learning control unit 214 analyzes the role-playing history over the past three months and identifies skill areas where the user consistently scores low (e.g., below 70 points) as weak areas. The learning control unit 214 then generates intensive training scenarios for the identified weak areas, adjusting the difficulty level in stages. For example, for a user who struggles with closing skills, the training program is designed to gradually increase the difficulty of the scenario, starting with customers with high purchase intent and progressing to customers with low purchase intent.

[0027] The customization unit 215 generates industry-specific sales scenarios based on industry information and controls the generation AI to execute role-playing that reflects product characteristics based on product information. Depending on the user's industry, the customization unit 215 generates scenarios that reflect industry-specific sales processes, terminology, and customer decision-making patterns. For example, a scenario for the manufacturing industry would set up a long-term sales process that takes into account the approval process for capital investment and the involvement of multiple departments, while a scenario for the IT industry would generate a scenario that emphasizes technical details and quantitative explanations of implementation effects.

[0028] The effectiveness analysis unit 216 analyzes the correlation between the results of confirmation tests and improvements in role-playing scores to identify effective educational content. For each educational content, the effectiveness analysis unit 216 measures the change in role-playing scores before and after learning to identify content with high learning effectiveness. The effectiveness analysis unit 216 uses statistical analysis methods to analyze the correlation between the type of educational content, learning time, the results of comprehension tests, and skill improvement. Based on the analysis results, it makes suggestions for improving low-effective content and prioritizes recommending high-effective content.

[0029] The real-time analysis unit 217 analyzes the user's response time, speech fluency, and logical structure in real time during role-playing. The real-time analysis unit 217 combines speech recognition technology and natural language processing technology to detect pauses, hesitations, and logical leaps in speech. For response time, it measures the time from question to answer and distinguishes between appropriate thinking time and excessive silence. For speech fluency, it analyzes speech speed, frequency of pauses, and frequency of filler use ("um," "uh," etc.). For logical structure, it evaluates the relationship between conclusions and evidence, and the consistency of speech through structural analysis of the utterance content.

[0030] The guidance unit 218 provides the user with appropriate hints or feedback during the role-playing session based on the results of real-time analysis. If the guidance unit 218 detects a problem with the user's speech, it immediately displays suggestions for improvement. For example, if the response time is excessively long, it may suggest "Try to answer more concisely," and if there is a problem with the logical structure, it may suggest "Try stating the conclusion first." The guidance unit 218 adjusts the timing and method of displaying hints so as not to interrupt the user's concentration. High-priority improvements are given via voice guidance, while minor improvements are given via text hints.

[0031] Figure 4 is a diagram illustrating the processing flow in an information processing system.

[0032] As shown in Figure 4, in the scenario generation phase, the management server 2 first receives a specification of the negotiation phase from the user terminal 1 (S401). Next, it retrieves relevant skills from the skill storage unit 231 based on the specified negotiation phase (S402), and retrieves the user's industry information and product information from the industry information storage unit 235 (S403). Note that the industry information and product information may be uploaded by the user. The scenario generation unit 211 generates a role-playing scenario using the generation AI based on the negotiation phase, relevant skills, and industry information (S404). The generated scenario includes parameters such as the personality settings of the sales partner's avatar, industry background, purchase intent level, budget constraints, and decision-making authority (S405). Finally, the generated scenario is stored in the scenario storage unit 233 in association with the negotiation phase (S406).

[0033] Figure 5 shows the processing flow of the role-playing execution phase in an information processing system.

[0034] As shown in Figure 5, in the role-playing execution phase, the management server 2 first obtains a scenario corresponding to the specified negotiation phase from the scenario storage unit 233 (S501). Based on the obtained scenario, the generation AI generates an avatar of the sales partner (S502), and the role-playing begins between the generated avatar and the user (S503). During the role-playing execution, the real-time analysis unit 217 analyzes the user's utterances, response times, and speech fluency in real time (S504), and the guidance unit 218 provides hints and feedback as needed based on the analysis results (S505).

[0035] After the role-playing is complete, the evaluation unit 212 analyzes the evaluation criteria set in the scenario and the user's utterances using speech recognition to calculate a score (S506). The calculated score and detailed evaluation results are recorded as role-playing results in the history storage unit 234 (S507). The recommendation unit 213 determines whether the score is below a predetermined threshold (S508). If it is below the threshold, it refers to the skill storage unit 231 and the educational content storage unit 232 to identify educational content corresponding to the skills associated with the relevant negotiation phase (S509). The identified educational content is transmitted to the user terminal 1 to support the user's skill improvement (S510). Furthermore, the learning control unit 214 periodically analyzes the history data stored in the history storage unit 234 to identify the user's weak areas and set them as areas that should be prioritized for training when the next scenario is generated (S511).

[0036] As described above, the information processing system of this embodiment can efficiently support the skill improvement of sales representatives through sales role-playing training utilizing generation AI. In the scenario generation phase, the optimal scenario according to the user's industry and negotiation phase is generated and stored in advance, reducing the waiting time at the start of role-playing. Furthermore, by reusing scenarios stored in the scenario storage unit 233, similar training can be efficiently conducted. In the role-playing execution phase, role-playing can be started immediately based on the stored scenario, and effective learning can be promoted through real-time analysis and guidance. Systematized skill evaluation for each negotiation phase allows for an objective understanding of the user's strengths and weaknesses, and an effective learning program can be provided by automatically recommending step-by-step educational content according to the individual's proficiency level. In addition, customized scenarios according to industry characteristics and products handled enable training in an environment closer to the actual sales site, promoting the acquisition of practical skills. Furthermore, real-time analysis and guidance functions maximize learning effects through immediate feedback during role-playing, and continuous historical analysis identifies areas of weakness, enabling focused training and steady improvement of sales skills.

[0037] Although these embodiments have been described above, they are intended to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and equivalents thereof are also included.

[0038] For example, the processing performed by each functional unit of the management server 2 described above may be executed by any of the functional units. Furthermore, different functional units may be added to perform some of the processing performed by each of the functional units described above. Also, the functional units of the management server 2 may be distributed across multiple computers.

[0039] Furthermore, the information stored in each memory unit of the management server 2 may be stored in any of the memory units. That is, the information stored in the multiple memory units mentioned above may be stored in a single memory unit, or a portion of the information stored in one memory unit may be stored in another memory unit.

[0040] <Example 1> In the embodiment described above, an example was shown in which the generating AI generates an avatar of a sales partner and performs role-playing. However, it is also possible to generate multiple avatars simultaneously to realize complex sales scenarios. For example, the scenario generation unit 211 generates three avatars: a decision-maker, a technical staff member, and a budget manager, each set to have different interests and responsibilities. The user can perform a sales role-playing scenario in the form of a meeting with multiple stakeholders, and learn appropriate approaches while understanding the position of each stakeholder. The evaluation unit 212 individually analyzes the interaction with each avatar and evaluates the response skills of each stakeholder. In this case, the skill memory unit 231 adds and stores skill items specifically for dealing with multiple stakeholders, such as "stakeholder management skills" and "consensus building skills."

[0041] <Modification 2> In the embodiment described above, an example was shown in which speech content is analyzed by speech recognition and a score is calculated. However, the user's facial expressions and gestures may also be analyzed using image recognition technology and included in the evaluation. The real-time analysis unit 217 analyzes video data acquired from the camera of the user terminal 1 and detects changes in facial expressions, eye movements, hand movements, and posture changes. In addition to the content of speech, the evaluation unit 212 calculates a score by including the frequency of smiles, maintenance of eye contact, and use of appropriate gestures as evaluation items. For example, in the proposal phase, hand movements when explaining important points and eye movements when checking customer reactions are analyzed and evaluated as "nonverbal communication skills." The guidance unit 218 provides nonverbal improvement suggestions such as "Try to smile a little more" or "Look the other person in the eye when you speak."

[0042] <Variation 3> The above-described embodiment shows an example of supporting individual role-playing training, but it may also be used to support role-playing for team sales involving multiple users. The scenario generation unit 211 generates scenarios according to the division of roles within the sales team (lead salesperson, technical support, manager) and evaluates the collaboration of each member. The evaluation unit 212 adds "team collaboration skills," "role division skills," and "information sharing skills" as evaluation items in addition to individual skills and analyzes the overall team performance. For example, it evaluates the actions of the lead salesperson in appropriately referring technical questions to technical support members, and the actions of the manager in joining a sales negotiation at the appropriate time. The history storage unit 233 stores collaboration patterns and success stories among team members, and the learning control unit 214 identifies weaknesses in the overall team and proposes improvement programs.

[0043] <Modification 4> In the embodiments described above, an example was shown in which a score is calculated based on pre-set evaluation items, but the evaluation criteria may be dynamically adjusted using machine learning technology. The effectiveness analysis unit 216 uses past success and failure cases as learning data to identify speech patterns and behavioral patterns that are highly correlated with sales results. The evaluation unit 212 dynamically adjusts the evaluation weighting based on the identified patterns to achieve a more practical evaluation. For example, if "speed of response to price-related questions" shows a high correlation with the closing rate in a particular industry, the evaluation weight of that item is set higher for users in that industry. Furthermore, by gradually increasing the difficulty of the evaluation criteria as the user's proficiency improves, continuous growth is promoted. The machine learning model is retrained each time new role-playing data is accumulated to improve evaluation accuracy.

[0044] <Modification 5> The above embodiment shows an example of presenting educational content to the user, but the method of providing educational content may be optimized according to the user's learning style and time constraints. The recommendation unit 213 analyzes the user's past learning history to identify learning styles such as "visual learning type," "auditory learning type," and "experiential learning type." For visual learning type users, it prioritizes recommending content that makes extensive use of charts and infographics, and for auditory learning type users, it prioritizes recommending content centered on audio explanations. In addition, it uses different learning content of short duration (within 5 minutes), medium duration (within 15 minutes), and long duration (30 minutes or more) depending on the user's available time. The educational content memory unit 232 stores content in multiple presentation formats for the same skill and dynamically selects the content best suited to the user's situation. Furthermore, it provides microlearning-style subdivided content to support efficient learning during spare time.

[0045] <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] An information processing system that uses generative AI to support sales role-playing, For each of the multiple phases of a business negotiation, a skill memory unit stores the skills to be measured in association with each other, An educational content storage unit that stores educational content for skill improvement for each of the aforementioned skills, Each of the aforementioned phases includes a scenario memory unit that stores the role-playing scenario, An evaluation unit evaluates the role-playing performed between the user and the generating AI based on the scenario corresponding to the negotiation phase specified by the user and calculates a score, A recommendation unit that refers to the skill storage unit and the educational content storage unit to identify the educational content corresponding to the skill associated with the negotiation phase, and presents the identified educational content to the user, An information processing system equipped with the following features. [Item 2] The information processing system according to item 1, characterized in that the evaluation unit analyzes the user's speech content in the role-playing using speech recognition and calculates the score based on pre-set evaluation items. [Item 3] The information processing system according to item 1, characterized in that the skill memory unit hierarchically stores multiple skill categories, including listening skills, proposal skills, and closing skills, for each negotiation phase. [Item 4] A scenario generation unit that generates a role-playing scenario using the aforementioned AI, A history storage unit that stores the user's past role-playing history and score progression, A learning control unit controls the scenario generation unit to identify the user's weak skill areas based on the history and to prioritize the generation of role-playing scenarios that focus on training those areas. The information processing system described in item 1, further characterized by comprising the following features. [Item 5] An industry information storage unit that stores information about the industry to which the user belongs and information about the products handled, A customization unit controls the generation AI to generate industry-specific business negotiation scenarios based on the aforementioned industry information and to perform role-playing that reflects product characteristics based on the aforementioned product information. The information processing system described in item 1, further characterized by comprising the following features. [Item 6] A test result storage unit that stores the results of a confirmation test administered after learning the aforementioned educational content, An effectiveness analysis unit analyzes the correlation between the results of the aforementioned confirmation test and the improvement in the score of the aforementioned role-playing, and identifies effective educational content. The information processing system described in item 1, further characterized by comprising the following features. [Item 7] A real-time analysis unit analyzes the user's response time, speech fluency, and logical structure in real time during the execution of the role-playing, A guidance unit provides the user with appropriate hints or feedback during the role-playing session based on the results of the real-time analysis. The information processing system described in item 1, further characterized by comprising the following features. [Item 8] An information processing method that uses generative AI to support sales role-playing, For each of the multiple phases of a sales negotiation, there is a step to associate and remember the skills to be measured, The steps include memorizing educational content for skill improvement for each of the aforementioned skills, Each of the aforementioned phases includes a step of memorizing the role-playing scenario, A step of evaluating the role-playing performed between the user and the generating AI based on the scenario corresponding to the negotiation phase specified by the user and calculating a score, A step of presenting the user with the educational content corresponding to the skills associated with the negotiation phase, A method of information processing performed by a computer. [Item 9] A program that uses generative AI to support sales role-playing, For each of the multiple phases of a sales negotiation, there is a step to associate and remember the skills to be measured, The steps include memorizing educational content for skill improvement for each of the aforementioned skills, A step of evaluating the role-playing performed between the user and the generating AI based on the scenario corresponding to the negotiation phase specified by the user and calculating a score, Each of the aforementioned phases includes a step of memorizing the role-playing scenario, A step of presenting the user with the educational content corresponding to the skills associated with the negotiation phase, A program that causes a computer to execute something. [Explanation of Symbols]

[0046] 1 User terminal 2 Management Server

Claims

1. An information processing system that uses generational AI to support sales role-playing, For each of the multiple phases of a business negotiation, a skill memory unit stores the skills to be measured in association with each other, An educational content storage unit that stores educational content for skill improvement for each of the aforementioned skills, Each of the aforementioned phases includes a scenario memory unit that stores the role-playing scenario, An evaluation unit evaluates the role-playing performed between the user and the generated AI based on the scenario corresponding to the negotiation phase specified by the user and calculates a score. A recommendation unit that refers to the skill storage unit and the educational content storage unit to identify the educational content corresponding to the skill associated with the negotiation phase, and presents the identified educational content to the user, An information processing system equipped with the following features.

2. The information processing system according to claim 1, characterized in that the evaluation unit analyzes the user's speech content in the role-playing using speech recognition and calculates the score based on pre-set evaluation items.

3. The information processing system according to claim 1, characterized in that the skill memory unit hierarchically stores multiple skill categories, including listening skills, proposal skills, and closing skills, for each negotiation phase.

4. A scenario generation unit generates a role-playing scenario using the aforementioned AI based on the negotiation phase specified by the user, A history storage unit that stores the user's past role-playing history and score progression, A learning control unit controls the scenario generation unit to identify the user's weak skill areas based on the history and to prioritize the generation of role-playing scenarios that focus on training those areas. The information processing system according to claim 1, further comprising the features described above.

5. An industry information storage unit that stores information about the industry to which the user belongs and information about the products handled, A customization unit controls the generating AI to generate industry-specific business negotiation scenarios based on the aforementioned industry information and to perform role-playing that reflects product characteristics based on the aforementioned product information. The information processing system according to claim 1, further comprising the features described above.

6. A test result storage unit that stores the results of a confirmation test administered after learning the aforementioned educational content, An effectiveness analysis unit analyzes the correlation between the results of the aforementioned confirmation test and the improvement in the score of the aforementioned role-playing, and identifies effective educational content. The information processing system according to claim 1, further comprising the features described above.

7. A real-time analysis unit analyzes the user's response time, speech fluency, and logical structure in real time during the execution of the role-playing, A guidance unit provides the user with appropriate hints or feedback during the role-playing session based on the results of the analysis performed by the real-time analysis unit. The information processing system according to claim 1, further comprising the features described above.

8. An information processing method that uses generative AI to support sales role-playing, For each of the multiple phases of a sales negotiation, there is a step to associate and remember the skills to be measured, The steps include memorizing educational content for skill improvement for each of the aforementioned skills, Each of the aforementioned phases includes a step of memorizing the role-playing scenario, A step of evaluating the role-playing performed between the user and the generating AI based on the scenario corresponding to the negotiation phase specified by the user and calculating a score, A step of presenting the user with the educational content corresponding to the skills associated with the negotiation phase, A method of information processing performed by a computer.

9. A program that uses generative AI to support sales role-playing, For each of the multiple phases of a sales negotiation, there is a step to associate and remember the skills to be measured, The steps include memorizing educational content for skill improvement for each of the aforementioned skills, Each of the aforementioned phases includes a step of memorizing the role-playing scenario, A step of evaluating the role-playing performed between the user and the generating AI based on the scenario corresponding to the negotiation phase specified by the user and calculating a score, A step of presenting the user with the educational content corresponding to the skills associated with the negotiation phase, A program that causes a computer to execute something.

Images