system

Abstract

We provide the system. [Solution] A means of analyzing input data using natural language processing technology and extracting important information, A method for automatically generating a proposal talk script based on extracted key information, A means for predicting customer questions based on documents and historical data, and generating a question-and-answer collection, By collecting user feedback and updating the AI ​​model, we can improve the generated results. A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the proposal activity, the non-uniformity and quality variation of proposal documents and talk scripts for customer correspondence are problems. Furthermore, preparing question-and-answer responses related to the proposal requires time and effort, and it is particularly difficult to respond to unexpected questions from customers. In addition, each time a proposal activity is carried out, feedback is not efficiently collected and improved for each site, and there is a problem that it is difficult to improve the quality of proposal materials.

Means for Solving the Problems

[0005] This invention provides a system that analyzes input materials using natural language processing technology and extracts important information. Furthermore, it solves these problems by automatically generating a suggested talk script based on the extracted information and generating a question-and-answer guide by predicting customer questions based on the materials and past data. In addition, it collects user feedback and updates the AI ​​model to improve the generation results. By also using optical character recognition technology, text can be extracted from scanned images, so the system can be used regardless of the format of the materials.

[0006] "Submitted documents" refers to document data such as proposals and supplementary information that users provide to the system.

[0007] "Natural language processing technology" refers to methods that use artificial intelligence technology to analyze the grammatical structure and meaning of text data and extract information from it.

[0008] "Important information" refers to keywords related to points or themes that should be particularly emphasized in the proposal activity.

[0009] "Extraction" refers to the process of selecting and identifying specific information from a document.

[0010] A "proposal talk script" refers to a standardized, automatically generated draft of utterances for use in proposal activities.

[0011] A "question and answer guide" refers to a list of anticipated answers to questions from customers.

[0012] "User feedback" refers to the evaluations and suggestions for improvement that users who have made suggestions provide to the system.

[0013] An "AI model" refers to an artificial intelligence algorithm trained to perform a specific task, based on machine learning or deep learning.

[0014] "Optical character recognition technology" refers to the technology that electronically extracts text from scanned images or physical documents. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The system of this invention utilizes AI technology on a server to efficiently generate talk scripts and question-and-answer sets necessary for proposal activities. First, the user uploads proposal materials and supplementary materials to the system via a terminal. These materials are sent to the server in various formats, such as PDF and Word documents.

[0037] Next, the server receives these materials and performs text analysis using natural language processing techniques. Here, it grasps the grammatical structure and extracts important keywords and phrases from the materials. Based on this information, the server automatically generates suggested talk scripts and also creates FAQs. For the FAQs, the server also refers to similar past data to prepare for questions that are likely to be asked by customers.

[0038] Users can view the generated talk scripts and FAQs on their devices and utilize the information provided in their proposals. After a proposal is submitted, users input evaluation feedback from their devices and send it to the server, which trains the AI ​​model. This continuous feedback loop improves the generated content with each proposal activity, resulting in higher accuracy and effectiveness.

[0039] As a concrete example, in a document proposing cloud computing services, the server generates a script that identifies key points such as "the benefits of the cloud" and "security considerations," and provides a consistent explanation during the proposal. It also creates pre-answers to anticipated questions, such as "Are there any legal risks in adopting the cloud?", and incorporates them into an FAQ.

[0040] This system significantly improves the efficiency and quality of proposal activities by having the server automatically handle each stage of processing, including document analysis, talk script generation, question and answer compilation, and feedback collection.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users upload proposal documents and supplementary materials to the server using their devices. These documents include the proposal itself and related information.

[0044] Step 2:

[0045] The server converts the received documents into an analyzable format. If necessary, it utilizes OCR technology to extract text from scanned image data.

[0046] Step 3:

[0047] The server uses natural language processing techniques to analyze the grammatical structure within the document and extract important topics and keywords. Specifically, it uses TF-IDF and Word Embedding technologies to evaluate and identify the importance of the information.

[0048] Step 4:

[0049] Based on the extracted information, the server automatically generates a consistent proposal talk script using a template. A grammatical check is also performed to ensure that the generated script is grammatically correct.

[0050] Step 5:

[0051] The server references past data and documents to build answers to anticipated customer questions. This automatically generates a Q&A database, enabling users to interact with customers smoothly.

[0052] Step 6:

[0053] The server sends the generated proposal talk script and question-and-answer set to the terminal and provides it to the user. The user then uses these to conduct their proposal activities.

[0054] Step 7:

[0055] After submitting a proposal, users send the results and feedback to the server via their device. This allows the system to reflect the improvements and evaluations that users have identified.

[0056] Step 8:

[0057] The server uses the received feedback to retrain the AI ​​model. This improves the accuracy of subsequent document generation, making proposal activities even more effective.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In proposal activities using AI technology, there is a need to quickly and accurately generate talk scripts and question-and-answer sets. However, conventional methods require a great deal of time to generate these, and it is difficult to consistently provide highly accurate content. This invention aims to solve these problems and realize more efficient and accurate content generation.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for analyzing input digital materials using natural language processing technology and extracting important information units; means for automatically generating explanatory text of the proposed content based on the extracted information units; and means for predicting inquiries from users based on the information units and past information records and generating a collection of inquiry responses. This makes it possible to efficiently and accurately generate talk scripts and question-and-answer collections necessary for proposal activities.

[0063] "Submitted digital materials" refers to electronic document files that users upload to the server in connection with their proposal activities.

[0064] "Natural language processing technology" refers to a series of techniques and methods that enable computers to understand and analyze human language.

[0065] "Key information units" refer to keywords or phrases that deserve particular attention within the proposal document.

[0066] "Explanatory text of the proposal" refers to a series of automatically generated sentences used for explanations and presentations when making a proposal.

[0067] A "collection of inquiry responses" refers to a set of questions and answers that have been generated in advance to address anticipated questions from users during proposal activities.

[0068] "Optical character recognition technology" refers to technology that recognizes characters from image data and extracts them as text data.

[0069] A "generated AI model" refers to a mathematical and algorithmic system that uses artificial intelligence technology to learn and generate new data.

[0070] To implement this invention, a server, a terminal, and a user each play their respective roles. First, the user prepares the digital materials for the proposal via the terminal and uploads them to the server. These materials are saved in a standard electronic format, such as PDF or Word document.

[0071] Upon receiving the input data, the server begins analysis using natural language processing (NLTK) technology. The server has analysis tools such as Python's NLTK library and spaCy installed, which allow it to grasp the grammatical structure of the document and extract important information units. Specifically, this includes morphological analysis and keyword extraction.

[0072] Based on the extracted information, the server utilizes a generative AI model to automatically generate explanatory text for the proposed content. By using existing AI models such as GPT, natural-sounding text that is easily understandable to the user is provided. Furthermore, the server refers to past information records to prepare answers to anticipated user inquiries and creates a collection of inquiry responses.

[0073] Users review the explanatory texts and inquiry response lists generated on their devices and use them in their proposal activities. To ensure accuracy and consistency of the information, review functions may be provided within the system. After the proposal activity is completed, users provide evaluation feedback using their devices, and the server uses this feedback to improve the AI ​​model.

[0074] As a concrete example, if a cloud service is being proposed, and the user enters a prompt such as "Please create a description including examples of cloud service implementation," the server will extract relevant information and generate an appropriate description and FAQ.

[0075] This system will enable users to conduct proposal activities more efficiently and with higher quality.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] Users prepare digital materials for their proposals on their devices and upload them to the server. These materials are in PDF or Word document format and contain the information necessary for the proposal activity. The input is the digital materials created by the user, and the output is the uploading and delivery of these materials to the server.

[0079] Step 2:

[0080] The server receives the uploaded materials and stores them in secure storage. The server verifies the format of the materials and records metadata such as file names and date / time in a database. The input is the digital materials received in step 1, and the output is the storage of the materials and their metadata in the server's storage system.

[0081] Step 3:

[0082] The server begins text analysis of the document using natural language processing technology. Specifically, it analyzes the grammatical structure using Python's NLTK library and spaCy, and extracts keywords and phrases. The input is the digital document stored in step 2, and the output is the important information units extracted from the document.

[0083] Step 4:

[0084] The server utilizes a generative AI model to automatically generate explanatory text for the proposed content based on the extracted information units. Here, the generative AI model uses the input keywords to generate natural-sounding sentences. The input is the information units extracted in step 3, and the output is the generated explanatory text for the proposed content.

[0085] Step 5:

[0086] The server references past information records and generates a query response list containing answers to anticipated user inquiries. The generated answers are created based on a list of anticipated questions. The input is the important information from step 3 and past information records, and the output is the query response list.

[0087] Step 6:

[0088] The user reviews the generated explanatory text and inquiry response guide on their device and prepares them as proposal materials. The user verifies the accuracy of the information and makes corrections as necessary. The input is the digital content generated in steps 4 and 5, and the output is the proposal materials that the user can use.

[0089] Step 7:

[0090] After the proposal activity is completed, users input evaluation feedback via their terminal and send it to the server. The server updates the AI ​​model based on this feedback to improve generation accuracy. The input is the feedback provided by the user, and the output is the updated AI model.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In traditional sales activities, providing product information and responding to customer inquiries is time-consuming and labor-intensive. This results in inconsistent quality of proposals, hindering smooth purchasing decisions. Furthermore, a lack of continuous improvement through feedback leads to recurring problems.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information, means for automatically generating a proposal talk script based on the extracted important information, and means for predicting customer questions based on materials and past data and generating a question and answer collection. This enables more efficient information provision in proposal activities, improved quality of customer service, and continuous improvement of proposal accuracy through feedback.

[0096] "A means of analyzing input data using natural language processing technology and extracting important information" refers to a process in which a computer analyzes information provided by a user using natural language processing technology, and identifies and extracts information necessary for a specific purpose.

[0097] "A method for automatically generating proposal talk scripts based on extracted key information" refers to a technology that can automatically create standard explanations and sales talks used in proposals based on key information identified through analysis.

[0098] "A means of predicting customer questions based on materials and past data and generating a Q&A document" refers to a process of predicting in advance the questions that customers might ask when they receive a proposal, by referring to past data, and systematically preparing answers to those questions.

[0099] "Methods for improving generated results by collecting user feedback and updating the AI ​​model" refers to technologies that adjust the AI's learning model based on opinions and results obtained from users, thereby improving the quality of future suggestions and responses.

[0100] "A means of seamlessly integrating product-related suggestion scripts and Q&A guides while browsing product information" refers to a technology that improves the user experience by integrating and displaying relevant suggestions and answers to questions in real time when viewing products online.

[0101] This invention enables efficient proposal activities by utilizing input data, extracting important information through analysis using natural language processing technology, and automatically generating proposal talk scripts and question-and-answer sets. An embodiment of this system is described below.

[0102] System Overview

[0103] The server receives materials uploaded by users and analyzes them using natural language processing (NLP) technology. Specifically, it uses generative AI models to understand the text and extract keywords and important phrases. Examples of NLP technologies used include spaCy and BERT.

[0104] Based on the extracted information, the server generates a suggested talk script. Furthermore, it predicts potential customer questions by referring to past data and creates a suitable question-and-answer set.

[0105] The generated suggestion talk scripts and question-and-answer sets are sent to the user's device and integrated into the product information being viewed in real time. To help users more effectively utilize the product page, prompts generated using an AI model are employed.

[0106] User behavior and feedback information are collected from the device to the server, which uses this information to update the AI ​​model and improve the generated results. This feedback loop gradually improves the accuracy and usefulness of suggested content.

[0107] Specific example

[0108] As a concrete example, imagine a user browsing a new electronic device on an e-commerce website. The server prepares real-time answers to anticipated questions such as, "What are the main features of this device?", enriching the user experience.

[0109] Example of a prompt

[0110] Product Name: Latest Electronic Device. Features: High-performance processor, extended battery life, clear display. Please generate frequently asked questions and their answers for users.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server receives materials uploaded by users via their terminals. The input is in formats such as PDF and Word documents, and these are stored on the server. The server then prepares to analyze these materials using natural language processing techniques.

[0114] Step 2:

[0115] The server analyzes the received data using natural language processing tools (e.g., spaCy, BERT). This analysis involves understanding the grammatical structure of the data and extracting keywords and important phrases. The extracted results are stored on the server as foundational information for generating proposed scripts.

[0116] Step 3:

[0117] The server automatically generates a suggested talk script using a generative AI model (e.g., the GPT series) based on the extracted information. The AI ​​model generates a script based on the input prompt text and saves the script as output to the server.

[0118] Step 4:

[0119] The server references materials and similar past data to predict potential customer questions. Once a list of questions is generated by the AI ​​model, the answers are also generated by the AI ​​model, completing the question-and-answer set.

[0120] Step 5:

[0121] The generated proposal talk script and question-and-answer set are sent to the user's device. The device seamlessly integrates and displays this information to the user while they are browsing product information. This allows the user to see the proposal and responses in real time while browsing.

[0122] Step 6:

[0123] Users make purchases, inquiries, and provide feedback through their devices. This behavioral information and feedback are then sent back to the server. The server processes this feedback data to train an AI model, improving the accuracy of future suggestions.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] In this invention's system, the server analyzes the proposal materials using natural language processing technology and extracts important information. Subsequently, the server automatically generates a proposal talk script using AI based on the extracted information. The server also utilizes the materials and past data to predict potential questions from customers and generates an appropriate question-and-answer set.

[0126] This system also incorporates an emotion engine that recognizes the user's emotions. As the user reviews materials through their terminal, the system recognizes their emotional state in real time. Based on this, the server dynamically adjusts the content of the proposal talk script and question-and-answer set. Specifically, if the user feels anxious or confused about the proposal, the server provides a talk script with more detailed explanations.

[0127] Users utilize talk scripts and question-and-answer sets generated on their devices to conduct proposal activities. Users provide feedback during and at the end of the proposal process, and the server uses this feedback to update the AI ​​model and improve accuracy for the next time. This feedback also includes emotional data experienced by the user, contributing to improvements in the content adjustment function based on emotions.

[0128] As a concrete example, consider a scenario where a user proposes a new software solution. The server incorporates key points such as "implementation hurdles" and "support system" into its talk script, and if it senses user concerns, it provides additional specific examples regarding the support system. It also anticipates potential questions such as "How does this function work?" and prepares answers in advance.

[0129] In this way, this system provides various functions to support proposal activities, enabling efficient and effective proposals. Real-time adjustments powered by the emotion engine result in more personalized proposals.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] Users upload proposal documents and supplementary materials using their devices. These documents are sent to the server and are handled in various formats (PDF, Word, etc.).

[0133] Step 2:

[0134] The server converts the received documents into a parseable text format. This process involves using OCR (Optical Character Recognition) on PDF and image files to extract text data.

[0135] Step 3:

[0136] The server uses natural language processing technology to analyze the data and evaluate the importance of the information. AI algorithms analyze the grammatical structure and extract important keywords and phrases.

[0137] Step 4:

[0138] Based on the extracted information, the server automatically generates a proposal talk script using a template. Grammar checks are performed during script generation to ensure consistent content.

[0139] Step 5:

[0140] The server references accumulated historical data and predicts customer questions based on documents and similar past cases. Based on this predictive information, it generates a Q&A guide.

[0141] Step 6:

[0142] The generated talk script and question-and-answer set are sent to the user's terminal by the server. The user then uses these to carry out their proposal activities.

[0143] Step 7:

[0144] As the user makes a suggestion, the emotion engine built into the device analyzes the user's emotional state in real time. Emotions are evaluated based on factors such as facial expressions, voice, and input speed during data entry.

[0145] Step 8:

[0146] Based on the data obtained by the emotion engine, the server dynamically adjusts the suggested talk scripts and question-and-answer sets. For example, if the user is feeling stressed, the server will supplement the script content.

[0147] Step 9:

[0148] After the proposal activity, user feedback is sent to the server via the device. This feedback includes sentiment data and is used to retrain the AI ​​model.

[0149] Step 10:

[0150] The server analyzes the feedback and updates the AI ​​model to improve the generation process. This ensures that subsequent proposal activities provide more accurate results.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] In proposal activities, there is a problem in that it takes a great deal of time and effort to prepare and implement proposals because it is difficult to quickly extract appropriate information from a large amount of documents and proposals to customers are not effectively and individually optimized. In addition, there is a challenge in maximizing the effectiveness of proposals because it is difficult to grasp customer reactions in real time and dynamically adjust the content of the proposals.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes means for analyzing input documents using language processing technology and extracting important information; means for automatically generating proposal drafts using a generative model based on the extracted important information; means for predicting user inquiries based on documents and past information and generating a collection of inquiry responses; means for recognizing the user's emotional state in real time and dynamically adjusting the content of the proposal drafts and inquiry response collections; and means for improving the generation results by collecting user feedback and updating the artificial intelligence model. This improves the efficiency of proposal activities and enables more effective and personalized proposals to customers.

[0156] "Submitted documents" refer to text-based information provided by users or other systems, and their content includes various data related to the proposal.

[0157] "Language processing technology" refers to techniques for analyzing text data, understanding its content, and extracting important elements, with the aim of understanding and processing natural language.

[0158] "Important information" refers to data elements deemed necessary and useful for creating and presenting a proposal, and its extraction enables effective communication.

[0159] A "generative model" refers to an algorithm or system that automatically creates documents or text based on data, and typically utilizes artificial intelligence technology.

[0160] A "proposal draft" refers to a collection of text prepared in advance to explain the content of a proposal, and is used to effectively convey the main points and details of the proposal.

[0161] A "collection of answers to inquiries" refers to a collection of pre-prepared responses to anticipated inquiries, intended to quickly address customer questions and concerns during the proposal process.

[0162] "User" refers to an individual or organization that operates the system and receives its services, and is the entity that carries out the proposal activities.

[0163] "Emotional state" refers to an indicator that shows the user's psychological response, and recognizing it is used to improve the effectiveness of suggestions and the quality of interactions.

[0164] An "artificial intelligence model" refers to a computational model that uses data to self-learn and perform various inferences and generation tasks, with the aim of improving the accuracy of system proposals.

[0165] The embodiments for carrying out this invention are shown below.

[0166] In this invention's system, the server plays a central role, implementing various functions to effectively support proposal activities. The server receives documents provided by users and first performs analysis using language processing technology. Specifically, it utilizes natural language processing software (for example, a general cloud-based API service) to extract important information from the document. This process includes summarizing the information and extracting keywords.

[0167] Based on the extracted information, the server automatically generates a proposal draft using a generative AI model. At this time, the generative AI model (for example, a general-purpose natural language generation algorithm) is used to construct the content of the proposal. During generation, prompts such as "Please list three core points of this proposal and explain each of them" are used to efficiently obtain accurate content.

[0168] Furthermore, the server analyzes documents and historical information to predict queries based on similar past cases and prepares a query response database. This prediction uses machine learning models, and a concrete example of its use is that it can pre-prepare detailed answers to questions such as, "How does this feature work?"

[0169] Furthermore, the system integrates an emotion recognition engine that detects the user's emotional state in real time while they are reviewing proposal materials through their terminal. Emotion recognition uses techniques such as image analysis. Depending on the user's emotions, the server can dynamically adjust the content of the proposal draft and inquiry response collection, and add more detailed information as needed.

[0170] Ultimately, users conduct their proposal activities using the generated proposal draft and question-and-answer collection. After submitting their proposal, they can send feedback to the server, which collects this feedback and uses it to update and improve the AI ​​model. This makes it possible to improve the accuracy of future proposals.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server receives documents provided by users. The input includes text-based documents. Based on this input, the server analyzes the document using natural language processing techniques. Specifically, it uses a natural language processing API to analyze the sentence structure and extract important keywords and phrases. This process yields important information as output.

[0174] Step 2:

[0175] The server receives the key information extracted in Step 1 as input and automatically generates a proposal draft using a generative AI model. The prompt includes the instruction, "List three core points of your proposal and explain each of them." By passing this information to the generative AI model, a logically structured proposal draft is output.

[0176] Step 3:

[0177] The server takes proposed drafts and past query data as input and uses a machine learning model to predict future queries based on this data. This includes questions in the format of, for example, "How does this feature work?". The prediction results are output as a collection of query answers.

[0178] Step 4:

[0179] When a user reviews proposal materials on their device, an emotion recognition engine inputs the user's emotional state as information and determines it in real time. Specifically, it analyzes facial expression data obtained through a webcam and uses an API service. Based on this data, the server dynamically adjusts the proposal draft and the inquiry response collection. The output is an adjusted document that corresponds to the user's emotions.

[0180] Step 5:

[0181] After the user completes their proposal, they send feedback to the server. This feedback includes data on the validity of the proposal and the appropriateness of the query response. Based on this input, the server updates the AI ​​model to improve the accuracy of the generated results. The output is an updated version of the improved AI model.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In conventional proposal activities, information provision to customers is one-way, making it difficult to respond flexibly to customer emotions. Furthermore, the inability to respond to customer questions in real time made it difficult to improve customer satisfaction. This invention aims to improve customer satisfaction by accurately understanding customer emotions during the proposal process and dynamically adjusting the proposal content to facilitate smoother dialogue with customers.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information; means for automatically generating a proposal talk script based on the extracted important information; means for predicting customer questions based on materials and past data and generating a question-and-answer set; means for recognizing the customer's emotional state via a terminal device and dynamically adjusting the content of the proposal talk script and question-and-answer set based on this; and means for collecting user feedback and updating the AI ​​model to improve the generated results. This makes it possible to provide customers with more personalized proposals in real time.

[0187] "Natural language processing technology" is the technology that enables computers to understand, interpret, and generate human language.

[0188] A "talk script" is a document containing spoken content, generated for a specific purpose and used in a dialogue.

[0189] A "question and answer guide" is a document that compiles a series of pre-prepared answers to anticipated questions.

[0190] A "terminal device" is an electronic device used by a user to access or manipulate information.

[0191] "Emotional state" refers to the state of a customer's psychological or emotional response.

[0192] "To adjust dynamically" means to flexibly change the content according to the situation and conditions.

[0193] "Feedback" refers to opinions and information about the output collected from users.

[0194] An "AI model" is a computational model trained to automatically perform specific tasks using artificial intelligence technology.

[0195] A system for implementing this invention consists of a server, a user terminal, and AI technology.

[0196] The server analyzes the input data using natural language processing technology and extracts important information. This process utilizes natural language processing libraries (e.g., spaCy, NLTK). Based on the extracted information, the server uses AI models (e.g., OpenAI® GPT-3®) to generate a suggested talk script. It also analyzes anticipated customer questions by referring to past data and generates a question-and-answer script. In this process, it retrieves customer-related history from a database and prepares answers based on that.

[0197] Smart glasses or tablets are used as user terminals, allowing users to view suggested talk scripts and question-and-answer sets sent from the server in real time. The application on the terminal can recognize the user's emotional state from their facial expressions and speech. Sentiment analysis is performed using sentiment analysis libraries such as IBM Watson® Natural Language Understanding. The server receives this sentiment data and dynamically adjusts the suggested content.

[0198] A concrete example is a customer service scenario in a clothing store. A salesperson wearing smart glasses displays a script saying, "This item is currently 30% off," when introducing a new product to a customer. The script is adjusted in real time if the customer shows increased interest or expresses concerns about the price.

[0199] Examples of prompt statements to input into a generative AI model include the following:

[0200] "Based on the sentiment analysis results, it appears the customer is interested in [XX]. Please suggest what information we should provide to promote sales."

[0201] Thus, this system enables personalized suggestions for each customer, greatly improving the efficiency and effectiveness of sales activities.

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server receives data entered by the user and analyzes it using a natural language processing library. The input is the data itself, and the output is extracted important information. This analysis involves identifying keywords and context within the data and extracting valuable information.

[0205] Step 2:

[0206] The server automatically generates a suggested talk script using a generative AI model based on the extracted key information. The input is the key information, and the output is the suggested talk script. The generative AI model expands on the information using prompt sentences and puts into writing what the user should convey to the customer.

[0207] Step 3:

[0208] The server analyzes anticipated customer questions using documents and historically accumulated data to create a Q&A database. The input is document data and past question history, and the output is the Q&A database. By referencing the database, it extracts questions and answers from similar situations to prepare the Q&A database.

[0209] Step 4:

[0210] The device displays a proposal talk script and a Q&A list to the user via smart glasses. The input is the proposal talk script and Q&A list sent from the server, and the output is an information display as visual content. The user provides information to the customer while reviewing this on the device.

[0211] Step 5:

[0212] The device senses the customer's facial expressions and speech, and analyzes their emotional state through an emotion analysis library. The input is customer facial expression data and voice data, and the output is a quantified result of the customer's emotional state. This allows for an analysis of how the customer feels about a proposal, enabling appropriate responses.

[0213] Step 6:

[0214] The server receives the results of the sentiment analysis and dynamically adjusts the content of the suggested talk script and question-and-answer set. The input is the result of the sentiment analysis, and the output is the adjusted suggested talk script and question-and-answer set. Specifically, additional information and explanations are manually added to the talk script to alleviate customer interest and anxiety.

[0215] Step 7:

[0216] The user interacts with the customer based on information received via the device. Input consists of a pre-arranged talk script and a question-and-answer set, while output is verbal explanations and responses to the customer. Through this interaction, the user aims to improve customer understanding and satisfaction.

[0217] Step 8:

[0218] After serving a customer, the user provides feedback via a terminal, and the server updates the AI ​​model based on this feedback. The input is the user's feedback data, and the output is the updated AI model. The AI ​​learns from the information obtained from the feedback and improves the accuracy of its suggestions for the next time.

[0219] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0235] The system of this invention utilizes AI technology on a server to efficiently generate talk scripts and question-and-answer sets necessary for proposal activities. First, the user uploads proposal materials and supplementary materials to the system via a terminal. These materials are sent to the server in various formats, such as PDF and Word documents.

[0236] Next, the server receives these materials and performs text analysis using natural language processing techniques. Here, it grasps the grammatical structure and extracts important keywords and phrases from the materials. Based on this information, the server automatically generates suggested talk scripts and also creates FAQs. For the FAQs, the server also refers to similar past data to prepare for questions that are likely to be asked by customers.

[0237] Users can view the generated talk scripts and FAQs on their devices and utilize the information provided in their proposals. After a proposal is submitted, users input evaluation feedback from their devices and send it to the server, which trains the AI ​​model. This continuous feedback loop improves the generated content with each proposal activity, resulting in higher accuracy and effectiveness.

[0238] As a concrete example, in a document proposing cloud computing services, the server generates a script that identifies key points such as "the benefits of the cloud" and "security considerations," and provides a consistent explanation during the proposal. It also creates pre-answers to anticipated questions, such as "Are there any legal risks in adopting the cloud?", and incorporates them into an FAQ.

[0239] This system significantly improves the efficiency and quality of proposal activities by having the server automatically handle each stage of processing, including document analysis, talk script generation, question and answer compilation, and feedback collection.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] Users upload proposal documents and supplementary materials to the server using their devices. These documents include the proposal itself and related information.

[0243] Step 2:

[0244] The server converts the received documents into an analyzable format. If necessary, it utilizes OCR technology to extract text from scanned image data.

[0245] Step 3:

[0246] The server uses natural language processing techniques to analyze the grammatical structure within the document and extract important topics and keywords. Specifically, it uses TF-IDF and Word Embedding technologies to evaluate and identify the importance of the information.

[0247] Step 4:

[0248] Based on the extracted information, the server automatically generates a consistent proposal talk script using a template. A grammatical check is also performed to ensure that the generated script is grammatically correct.

[0249] Step 5:

[0250] The server references past data and documents to build answers to anticipated customer questions. This automatically generates a Q&A database, enabling users to interact with customers smoothly.

[0251] Step 6:

[0252] The server sends the generated proposal talk script and question-and-answer set to the terminal and provides it to the user. The user then uses these to conduct their proposal activities.

[0253] Step 7:

[0254] After submitting a proposal, users send the results and feedback to the server via their device. This allows the system to reflect the improvements and evaluations that users have identified.

[0255] Step 8:

[0256] The server uses the received feedback to retrain the AI ​​model. This improves the accuracy of subsequent document generation, making proposal activities even more effective.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0259] In proposal activities using AI technology, there is a need to quickly and accurately generate talk scripts and question-and-answer sets. However, conventional methods require a great deal of time to generate these, and it is difficult to consistently provide highly accurate content. This invention aims to solve these problems and realize more efficient and accurate content generation.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for analyzing input digital materials using natural language processing technology and extracting important information units; means for automatically generating explanatory text of the proposed content based on the extracted information units; and means for predicting inquiries from users based on the information units and past information records and generating a collection of inquiry responses. This makes it possible to efficiently and accurately generate talk scripts and question-and-answer collections necessary for proposal activities.

[0262] "Submitted digital materials" refers to electronic document files that users upload to the server in connection with their proposal activities.

[0263] "Natural language processing technology" refers to a series of techniques and methods that enable computers to understand and analyze human language.

[0264] "Key information units" refer to keywords or phrases that deserve particular attention within the proposal document.

[0265] "Explanatory text of the proposal" refers to a series of automatically generated sentences used for explanations and presentations when making a proposal.

[0266] A "collection of inquiry responses" refers to a set of questions and answers that have been generated in advance to address anticipated questions from users during proposal activities.

[0267] "Optical character recognition technology" refers to technology that recognizes characters from image data and extracts them as text data.

[0268] A "generated AI model" refers to a mathematical and algorithmic system that uses artificial intelligence technology to learn and generate new data.

[0269] To implement this invention, a server, a terminal, and a user each play their respective roles. First, the user prepares the digital materials for the proposal via the terminal and uploads them to the server. These materials are saved in a standard electronic format, such as PDF or Word document.

[0270] Upon receiving the input data, the server begins analysis using natural language processing (NLTK) technology. The server has analysis tools such as Python's NLTK library and spaCy installed, which allow it to grasp the grammatical structure of the document and extract important information units. Specifically, this includes morphological analysis and keyword extraction.

[0271] Based on the extracted information, the server utilizes a generative AI model to automatically generate explanatory text for the proposed content. By using existing AI models such as GPT, natural-sounding text that is easily understandable to the user is provided. Furthermore, the server refers to past information records to prepare answers to anticipated user inquiries and creates a collection of inquiry responses.

[0272] Users review the explanatory texts and inquiry response lists generated on their devices and use them in their proposal activities. To ensure accuracy and consistency of the information, review functions may be provided within the system. After the proposal activity is completed, users provide evaluation feedback using their devices, and the server uses this feedback to improve the AI ​​model.

[0273] As a concrete example, if a cloud service is being proposed, and the user enters a prompt such as "Please create a description including examples of cloud service implementation," the server will extract relevant information and generate an appropriate description and FAQ.

[0274] This system will enable users to conduct proposal activities more efficiently and with higher quality.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] Users prepare digital materials for their proposals on their devices and upload them to the server. These materials are in PDF or Word document format and contain the information necessary for the proposal activity. The input is the digital materials created by the user, and the output is the uploading and delivery of these materials to the server.

[0278] Step 2:

[0279] The server receives the uploaded materials and stores them in secure storage. The server verifies the format of the materials and records metadata such as file names and date / time in a database. The input is the digital materials received in step 1, and the output is the storage of the materials and their metadata in the server's storage system.

[0280] Step 3:

[0281] The server starts text analysis of the materials using natural language processing technology. Specifically, it analyzes the grammatical structure using libraries such as NLTK in Python or spaCy, and extracts keywords and phrases. The input is the digital materials stored in Step 2, and the output is the important information units extracted from the materials.

[0282] Step 4:

[0283] The server utilizes a generative AI model to automatically generate an explanatory text for the proposed content based on the extracted information units. Here, the generative AI model uses the input keywords to generate natural sentences. The input is the information units extracted in Step 3, and the output is the explanatory text of the generated proposed content.

[0284] Step 5:

[0285] The server refers to past information records and generates responses to inquiries predicted from the user as an inquiry response collection. The generated responses are created based on a list of predicted questions. The input is the important information in Step 3 and the past information records, and the output is the inquiry response collection.

[0286] Step 6:

[0287] The user checks the explanatory text and inquiry response collection generated on the terminal and prepares them as proposed materials. The user checks the accuracy of the information and makes corrections if necessary. The input is the digital content generated in Steps 4 and 5, and the output is the proposed materials that the user can use.

[0288] Step 7:

[0289] After the proposal activity ends, the user inputs evaluation feedback through the terminal and sends it to the server. The server updates the AI model based on this feedback to improve the generation accuracy. The input is the feedback provided by the user, and the output is the updated AI model.

[0290] (Application Example 1)

[0291] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0292] In traditional sales activities, providing product information and responding to customer inquiries is time-consuming and labor-intensive. This results in inconsistent quality of proposals, hindering smooth purchasing decisions. Furthermore, a lack of continuous improvement through feedback leads to recurring problems.

[0293] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0294] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information, means for automatically generating a proposal talk script based on the extracted important information, and means for predicting customer questions based on materials and past data and generating a question and answer collection. This enables more efficient information provision in proposal activities, improved quality of customer service, and continuous improvement of proposal accuracy through feedback.

[0295] "A means of analyzing input data using natural language processing technology and extracting important information" refers to a process in which a computer analyzes information provided by a user using natural language processing technology, and identifies and extracts information necessary for a specific purpose.

[0296] "A method for automatically generating proposal talk scripts based on extracted key information" refers to a technology that can automatically create standard explanations and sales talks used in proposals based on key information identified through analysis.

[0297] "A means of predicting customer questions based on materials and past data and generating a Q&A document" refers to a process of predicting in advance the questions that customers might ask when they receive a proposal, by referring to past data, and systematically preparing answers to those questions.

[0298] "Methods for improving generated results by collecting user feedback and updating the AI ​​model" refers to technologies that adjust the AI's learning model based on opinions and results obtained from users, thereby improving the quality of future suggestions and responses.

[0299] "A means of seamlessly integrating product-related suggestion scripts and Q&A guides while browsing product information" refers to a technology that improves the user experience by integrating and displaying relevant suggestions and answers to questions in real time when viewing products online.

[0300] This invention enables efficient proposal activities by utilizing input data, extracting important information through analysis using natural language processing technology, and automatically generating proposal talk scripts and question-and-answer sets. An embodiment of this system is described below.

[0301] System Overview

[0302] The server receives materials uploaded by users and analyzes them using natural language processing (NLP) technology. Specifically, it uses generative AI models to understand the text and extract keywords and important phrases. Examples of NLP technologies used include spaCy and BERT.

[0303] Based on the extracted information, the server generates a suggested talk script. Furthermore, it predicts potential customer questions by referring to past data and creates a suitable question-and-answer set.

[0304] The generated proposed talk script and Q&A collection are sent to the user's terminal and integrated and displayed in real time with the product information being viewed. At this time, in order to enable the user to utilize the product page more effectively, a prompt sentence using the generation AI model is used.

[0305] The user's actions and feedback information are collected from the terminal to the server, and the server uses this to update the AI model to improve the generation results. Through this feedback loop, the accuracy and usefulness of the proposed content are gradually improved.

[0306] Specific Example

[0307] As a specific example, assume that the user is viewing a new electronic device on an e-commerce site. The server prepares a real-time answer to the predicted question "What are the main features of this device?" to enrich the user experience.

[0308] Example of Prompt Sentence

[0309] "Product Name: Latest Electronic Device. Features: High-performance processor, extended battery life, clear display. Please generate common questions from users and their answers."

[0310] The flow of a specific process in Application Example 1 will be described using FIG. 12.

[0311] Step 1:

[0312] The server receives the materials uploaded by the user through the terminal. The input is in the form of PDF, Word documents, etc., and these are saved on the server. The server then prepares to analyze these materials using natural language processing technology.

[0313] Step 2:

[0314] The server analyzes the received data using natural language processing tools (e.g., spaCy, BERT). This analysis involves understanding the grammatical structure of the data and extracting keywords and important phrases. The extracted results are stored on the server as foundational information for generating proposed scripts.

[0315] Step 3:

[0316] The server automatically generates a suggested talk script using a generative AI model (e.g., the GPT series) based on the extracted information. The AI ​​model generates a script based on the input prompt text and saves the script as output to the server.

[0317] Step 4:

[0318] The server references materials and similar past data to predict potential customer questions. Once a list of questions is generated by the AI ​​model, the answers are also generated by the AI ​​model, completing the question-and-answer set.

[0319] Step 5:

[0320] The generated proposal talk script and question-and-answer set are sent to the user's device. The device seamlessly integrates and displays this information to the user while they are browsing product information. This allows the user to see the proposal and responses in real time while browsing.

[0321] Step 6:

[0322] Users make purchases, inquiries, and provide feedback through their devices. This behavioral information and feedback are then sent back to the server. The server processes this feedback data to train an AI model, improving the accuracy of future suggestions.

[0323] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0324] In this invention's system, the server analyzes the proposal materials using natural language processing technology and extracts important information. Subsequently, the server automatically generates a proposal talk script using AI based on the extracted information. The server also utilizes the materials and past data to predict potential questions from customers and generates an appropriate question-and-answer set.

[0325] This system also incorporates an emotion engine that recognizes the user's emotions. As the user reviews materials through their terminal, the system recognizes their emotional state in real time. Based on this, the server dynamically adjusts the content of the proposal talk script and question-and-answer set. Specifically, if the user feels anxious or confused about the proposal, the server provides a talk script with more detailed explanations.

[0326] Users utilize talk scripts and question-and-answer sets generated on their devices to conduct proposal activities. Users provide feedback during and at the end of the proposal process, and the server uses this feedback to update the AI ​​model and improve accuracy for the next time. This feedback also includes emotional data experienced by the user, contributing to improvements in the content adjustment function based on emotions.

[0327] As a concrete example, consider a scenario where a user proposes a new software solution. The server incorporates key points such as "implementation hurdles" and "support system" into its talk script, and if it senses user concerns, it provides additional specific examples regarding the support system. It also anticipates potential questions such as "How does this function work?" and prepares answers in advance.

[0328] In this way, this system provides various functions to support proposal activities, enabling efficient and effective proposals. Real-time adjustments powered by the emotion engine result in more personalized proposals.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] Users upload proposal documents and supplementary materials using their devices. These documents are sent to the server and are handled in various formats (PDF, Word, etc.).

[0332] Step 2:

[0333] The server converts the received documents into a parseable text format. This process involves using OCR (Optical Character Recognition) on PDF and image files to extract text data.

[0334] Step 3:

[0335] The server uses natural language processing technology to analyze the data and evaluate the importance of the information. AI algorithms analyze the grammatical structure and extract important keywords and phrases.

[0336] Step 4:

[0337] Based on the extracted information, the server automatically generates a proposal talk script using a template. Grammar checks are performed during script generation to ensure consistent content.

[0338] Step 5:

[0339] The server references accumulated historical data and predicts customer questions based on documents and similar past cases. Based on this predictive information, it generates a Q&A guide.

[0340] Step 6:

[0341] The generated talk script and question-and-answer set are sent to the user's terminal by the server. The user then uses these to carry out their proposal activities.

[0342] Step 7:

[0343] As the user makes a suggestion, the emotion engine built into the device analyzes the user's emotional state in real time. Emotions are evaluated based on factors such as facial expressions, voice, and input speed during data entry.

[0344] Step 8:

[0345] Based on the data obtained by the emotion engine, the server dynamically adjusts the suggested talk scripts and question-and-answer sets. For example, if the user is feeling stressed, the server will supplement the script content.

[0346] Step 9:

[0347] After the proposal activity, user feedback is sent to the server via the device. This feedback includes sentiment data and is used to retrain the AI ​​model.

[0348] Step 10:

[0349] The server analyzes the feedback and updates the AI ​​model to improve the generation process. This ensures that subsequent proposal activities provide more accurate results.

[0350] (Example 2)

[0351] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0352] In proposal activities, there is a problem in that it takes a great deal of time and effort to prepare and implement proposals because it is difficult to quickly extract appropriate information from a large amount of documents and proposals to customers are not effectively and individually optimized. In addition, there is a challenge in maximizing the effectiveness of proposals because it is difficult to grasp customer reactions in real time and dynamically adjust the content of the proposals.

[0353] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0354] In this invention, the server includes means for analyzing input documents using language processing technology and extracting important information; means for automatically generating proposal drafts using a generative model based on the extracted important information; means for predicting user inquiries based on documents and past information and generating a collection of inquiry responses; means for recognizing the user's emotional state in real time and dynamically adjusting the content of the proposal drafts and inquiry response collections; and means for improving the generation results by collecting user feedback and updating the artificial intelligence model. This improves the efficiency of proposal activities and enables more effective and personalized proposals to customers.

[0355] "Submitted documents" refer to text-based information provided by users or other systems, and their content includes various data related to the proposal.

[0356] "Language processing technology" refers to techniques for analyzing text data, understanding its content, and extracting important elements, with the aim of understanding and processing natural language.

[0357] "Important information" refers to data elements deemed necessary and useful for creating and presenting a proposal, and its extraction enables effective communication.

[0358] A "generative model" refers to an algorithm or system that automatically creates documents or text based on data, and typically utilizes artificial intelligence technology.

[0359] A "proposal draft" refers to a collection of text prepared in advance to explain the content of a proposal, and is used to effectively convey the main points and details of the proposal.

[0360] A "collection of answers to inquiries" refers to a collection of pre-prepared responses to anticipated inquiries, intended to quickly address customer questions and concerns during the proposal process.

[0361] "User" refers to an individual or organization that operates the system and receives its services, and is the entity that carries out the proposal activities.

[0362] "Emotional state" refers to an indicator that shows the user's psychological response, and recognizing it is used to improve the effectiveness of suggestions and the quality of interactions.

[0363] An "artificial intelligence model" refers to a computational model that uses data to self-learn and perform various inferences and generation tasks, with the aim of improving the accuracy of system proposals.

[0364] The embodiments for carrying out this invention are shown below.

[0365] In this invention's system, the server plays a central role, implementing various functions to effectively support proposal activities. The server receives documents provided by users and first performs analysis using language processing technology. Specifically, it utilizes natural language processing software (for example, a general cloud-based API service) to extract important information from the document. This process includes summarizing the information and extracting keywords.

[0366] Based on the extracted information, the server automatically generates a proposal draft using a generative AI model. At this time, the generative AI model (for example, a general-purpose natural language generation algorithm) is used to construct the content of the proposal. During generation, prompts such as "Please list three core points of this proposal and explain each of them" are used to efficiently obtain accurate content.

[0367] Furthermore, the server analyzes documents and historical information to predict queries based on similar past cases and prepares a query response database. This prediction uses machine learning models, and a concrete example of its use is that it can pre-prepare detailed answers to questions such as, "How does this feature work?"

[0368] Furthermore, the system integrates an emotion recognition engine that detects the user's emotional state in real time while they are reviewing proposal materials through their terminal. Emotion recognition uses techniques such as image analysis. Depending on the user's emotions, the server can dynamically adjust the content of the proposal draft and inquiry response collection, and add more detailed information as needed.

[0369] Ultimately, users conduct their proposal activities using the generated proposal draft and question-and-answer collection. After submitting their proposal, they can send feedback to the server, which collects this feedback and uses it to update and improve the AI ​​model. This makes it possible to improve the accuracy of future proposals.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The server receives documents provided by users. The input includes text-based documents. Based on this input, the server analyzes the document using natural language processing techniques. Specifically, it uses a natural language processing API to analyze the sentence structure and extract important keywords and phrases. This process yields important information as output.

[0373] Step 2:

[0374] The server receives the key information extracted in Step 1 as input and automatically generates a proposal draft using a generative AI model. The prompt includes the instruction, "List three core points of your proposal and explain each of them." By passing this information to the generative AI model, a logically structured proposal draft is output.

[0375] Step 3:

[0376] The server takes proposed drafts and past query data as input and uses a machine learning model to predict future queries based on this data. This includes questions in the format of, for example, "How does this feature work?". The prediction results are output as a collection of query answers.

[0377] Step 4:

[0378] When a user reviews proposal materials on their device, an emotion recognition engine inputs the user's emotional state as information and determines it in real time. Specifically, it analyzes facial expression data obtained through a webcam and uses an API service. Based on this data, the server dynamically adjusts the proposal draft and the inquiry response collection. The output is an adjusted document that corresponds to the user's emotions.

[0379] Step 5:

[0380] After the user completes their proposal, they send feedback to the server. This feedback includes data on the validity of the proposal and the appropriateness of the query response. Based on this input, the server updates the AI ​​model to improve the accuracy of the generated results. The output is an updated version of the improved AI model.

[0381] (Application Example 2)

[0382] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0383] In conventional proposal activities, information provision to customers is one-way, making it difficult to respond flexibly to customer emotions. Furthermore, the inability to respond to customer questions in real time made it difficult to improve customer satisfaction. This invention aims to improve customer satisfaction by accurately understanding customer emotions during the proposal process and dynamically adjusting the proposal content to facilitate smoother dialogue with customers.

[0384] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0385] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information; means for automatically generating a proposal talk script based on the extracted important information; means for predicting customer questions based on materials and past data and generating a question-and-answer set; means for recognizing the customer's emotional state via a terminal device and dynamically adjusting the content of the proposal talk script and question-and-answer set based on this; and means for collecting user feedback and updating the AI ​​model to improve the generated results. This makes it possible to provide customers with more personalized proposals in real time.

[0386] "Natural language processing technology" is the technology that enables computers to understand, interpret, and generate human language.

[0387] A "talk script" is a document containing spoken content, generated for a specific purpose and used in a dialogue.

[0388] A "question and answer guide" is a document that compiles a series of pre-prepared answers to anticipated questions.

[0389] A "terminal device" is an electronic device used by a user to access or manipulate information.

[0390] "Emotional state" refers to the state of a customer's psychological or emotional response.

[0391] "To adjust dynamically" means to flexibly change the content according to the situation and conditions.

[0392] "Feedback" refers to opinions and information about the output collected from users.

[0393] An "AI model" is a computational model trained to automatically perform specific tasks using artificial intelligence technology.

[0394] A system for implementing this invention consists of a server, a user terminal, and AI technology.

[0395] The server analyzes the input materials using natural language processing technology and extracts important information. This process utilizes natural language processing libraries (e.g., spaCy, NLTK). Based on the extracted information, the server uses AI models (e.g., OpenAI GPT-3) to generate a suggested talk script. It also analyzes anticipated customer questions by referring to past data and generates a question-and-answer script. In this process, it retrieves customer-related history from a database and prepares answers based on that.

[0396] Smart glasses or tablets are used as user terminals, allowing users to view suggested talk scripts and question-and-answer sets sent from the server in real time. Applications on the terminals can recognize the user's emotional state from their facial expressions and speech. Sentiment analysis libraries such as IBM Watson Natural Language Understanding are used for sentiment analysis. The server receives this sentiment data and dynamically adjusts the suggested content.

[0397] A concrete example is a customer service scenario in a clothing store. A salesperson wearing smart glasses displays a script saying, "This item is currently 30% off," when introducing a new product to a customer. The script is adjusted in real time if the customer shows increased interest or expresses concerns about the price.

[0398] Examples of prompt statements to input into a generative AI model include the following:

[0399] "Based on the sentiment analysis results, it appears the customer is interested in [XX]. Please suggest what information we should provide to promote sales."

[0400] Thus, this system enables personalized suggestions for each customer, greatly improving the efficiency and effectiveness of sales activities.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server receives data entered by the user and analyzes it using a natural language processing library. The input is the data itself, and the output is extracted important information. This analysis involves identifying keywords and context within the data and extracting valuable information.

[0404] Step 2:

[0405] The server automatically generates a suggested talk script using a generative AI model based on the extracted key information. The input is the key information, and the output is the suggested talk script. The generative AI model expands on the information using prompt sentences and puts into writing what the user should convey to the customer.

[0406] Step 3:

[0407] The server analyzes anticipated customer questions using documents and historically accumulated data to create a Q&A database. The input is document data and past question history, and the output is the Q&A database. By referencing the database, it extracts questions and answers from similar situations to prepare the Q&A database.

[0408] Step 4:

[0409] The device displays a proposal talk script and a Q&A list to the user via smart glasses. The input is the proposal talk script and Q&A list sent from the server, and the output is an information display as visual content. The user provides information to the customer while reviewing this on the device.

[0410] Step 5:

[0411] The device senses the customer's facial expressions and speech, and analyzes their emotional state through an emotion analysis library. The input is customer facial expression data and voice data, and the output is a quantified result of the customer's emotional state. This allows for an analysis of how the customer feels about a proposal, enabling appropriate responses.

[0412] Step 6:

[0413] The server receives the results of the sentiment analysis and dynamically adjusts the content of the suggested talk script and question-and-answer set. The input is the result of the sentiment analysis, and the output is the adjusted suggested talk script and question-and-answer set. Specifically, additional information and explanations are manually added to the talk script to alleviate customer interest and anxiety.

[0414] Step 7:

[0415] The user interacts with the customer based on information received via the device. Input consists of a pre-arranged talk script and a question-and-answer set, while output is verbal explanations and responses to the customer. Through this interaction, the user aims to improve customer understanding and satisfaction.

[0416] Step 8:

[0417] After serving a customer, the user provides feedback via a terminal, and the server updates the AI ​​model based on this feedback. The input is the user's feedback data, and the output is the updated AI model. The AI ​​learns from the information obtained from the feedback and improves the accuracy of its suggestions for the next time.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] The system of this invention utilizes AI technology on a server to efficiently generate talk scripts and question-and-answer sets necessary for proposal activities. First, the user uploads proposal materials and supplementary materials to the system via a terminal. These materials are sent to the server in various formats, such as PDF and Word documents.

[0435] Next, the server receives these materials and performs text analysis using natural language processing techniques. Here, it grasps the grammatical structure and extracts important keywords and phrases from the materials. Based on this information, the server automatically generates suggested talk scripts and also creates FAQs. For the FAQs, the server also refers to similar past data to prepare for questions that are likely to be asked by customers.

[0436] Users can view the generated talk scripts and FAQs on their devices and utilize the information provided in their proposals. After a proposal is submitted, users input evaluation feedback from their devices and send it to the server, which trains the AI ​​model. This continuous feedback loop improves the generated content with each proposal activity, resulting in higher accuracy and effectiveness.

[0437] As a concrete example, in a document proposing cloud computing services, the server generates a script that identifies key points such as "the benefits of the cloud" and "security considerations," and provides a consistent explanation during the proposal. It also creates pre-answers to anticipated questions, such as "Are there any legal risks in adopting the cloud?", and incorporates them into an FAQ.

[0438] This system significantly improves the efficiency and quality of proposal activities by having the server automatically handle each stage of processing, including document analysis, talk script generation, question and answer compilation, and feedback collection.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] Users upload proposal documents and supplementary materials to the server using their devices. These documents include the proposal itself and related information.

[0442] Step 2:

[0443] The server converts the received documents into an analyzable format. If necessary, it utilizes OCR technology to extract text from scanned image data.

[0444] Step 3:

[0445] The server uses natural language processing techniques to analyze the grammatical structure within the document and extract important topics and keywords. Specifically, it uses TF-IDF and Word Embedding technologies to evaluate and identify the importance of the information.

[0446] Step 4:

[0447] Based on the extracted information, the server automatically generates a consistent proposal talk script using a template. A grammatical check is also performed to ensure that the generated script is grammatically correct.

[0448] Step 5:

[0449] The server references past data and documents to build answers to anticipated customer questions. This automatically generates a Q&A database, enabling users to interact with customers smoothly.

[0450] Step 6:

[0451] The server sends the generated proposal talk script and question-and-answer set to the terminal and provides it to the user. The user then uses these to conduct their proposal activities.

[0452] Step 7:

[0453] After submitting a proposal, users send the results and feedback to the server via their device. This allows the system to reflect the improvements and evaluations that users have identified.

[0454] Step 8:

[0455] The server uses the received feedback to retrain the AI ​​model. This improves the accuracy of subsequent document generation, making proposal activities even more effective.

[0456] (Example 1)

[0457] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] In proposal activities using AI technology, there is a need to quickly and accurately generate talk scripts and question-and-answer sets. However, conventional methods require a great deal of time to generate these, and it is difficult to consistently provide highly accurate content. This invention aims to solve these problems and realize more efficient and accurate content generation.

[0459] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0460] In this invention, the server includes means for analyzing input digital materials using natural language processing technology and extracting important information units; means for automatically generating explanatory text of the proposed content based on the extracted information units; and means for predicting inquiries from users based on the information units and past information records and generating a collection of inquiry responses. This makes it possible to efficiently and accurately generate talk scripts and question-and-answer collections necessary for proposal activities.

[0461] "Submitted digital materials" refers to electronic document files that users upload to the server in connection with their proposal activities.

[0462] "Natural language processing technology" refers to a series of techniques and methods that enable computers to understand and analyze human language.

[0463] "Key information units" refer to keywords or phrases that deserve particular attention within the proposal document.

[0464] "Explanatory text of the proposal" refers to a series of automatically generated sentences used for explanations and presentations when making a proposal.

[0465] A "collection of inquiry responses" refers to a set of questions and answers that have been generated in advance to address anticipated questions from users during proposal activities.

[0466] "Optical character recognition technology" refers to technology that recognizes characters from image data and extracts them as text data.

[0467] A "generated AI model" refers to a mathematical and algorithmic system that uses artificial intelligence technology to learn and generate new data.

[0468] To implement this invention, a server, a terminal, and a user each play their respective roles. First, the user prepares the digital materials for the proposal via the terminal and uploads them to the server. These materials are saved in a standard electronic format, such as PDF or Word document.

[0469] Upon receiving the input data, the server begins analysis using natural language processing (NLTK) technology. The server has analysis tools such as Python's NLTK library and spaCy installed, which allow it to grasp the grammatical structure of the document and extract important information units. Specifically, this includes morphological analysis and keyword extraction.

[0470] Based on the extracted information, the server utilizes a generative AI model to automatically generate explanatory text for the proposed content. By using existing AI models such as GPT, natural-sounding text that is easily understandable to the user is provided. Furthermore, the server refers to past information records to prepare answers to anticipated user inquiries and creates a collection of inquiry responses.

[0471] Users review the explanatory texts and inquiry response lists generated on their devices and use them in their proposal activities. To ensure accuracy and consistency of the information, review functions may be provided within the system. After the proposal activity is completed, users provide evaluation feedback using their devices, and the server uses this feedback to improve the AI ​​model.

[0472] As a concrete example, if a cloud service is being proposed, and the user enters a prompt such as "Please create a description including examples of cloud service implementation," the server will extract relevant information and generate an appropriate description and FAQ.

[0473] This system will enable users to conduct proposal activities more efficiently and with higher quality.

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] Users prepare digital materials for their proposals on their devices and upload them to the server. These materials are in PDF or Word document format and contain the information necessary for the proposal activity. The input is the digital materials created by the user, and the output is the uploading and delivery of these materials to the server.

[0477] Step 2:

[0478] The server receives the uploaded materials and stores them in secure storage. The server verifies the format of the materials and records metadata such as file names and date / time in a database. The input is the digital materials received in step 1, and the output is the storage of the materials and their metadata in the server's storage system.

[0479] Step 3:

[0480] The server begins text analysis of the document using natural language processing technology. Specifically, it analyzes the grammatical structure using Python's NLTK library and spaCy, and extracts keywords and phrases. The input is the digital document stored in step 2, and the output is the important information units extracted from the document.

[0481] Step 4:

[0482] The server utilizes a generative AI model to automatically generate explanatory text for the proposed content based on the extracted information units. Here, the generative AI model uses the input keywords to generate natural-sounding sentences. The input is the information units extracted in step 3, and the output is the generated explanatory text for the proposed content.

[0483] Step 5:

[0484] The server references past information records and generates a query response list containing answers to anticipated user inquiries. The generated answers are created based on a list of anticipated questions. The input is the important information from step 3 and past information records, and the output is the query response list.

[0485] Step 6:

[0486] The user reviews the generated explanatory text and inquiry response guide on their device and prepares them as proposal materials. The user verifies the accuracy of the information and makes corrections as necessary. The input is the digital content generated in steps 4 and 5, and the output is the proposal materials that the user can use.

[0487] Step 7:

[0488] After the proposal activity is completed, users input evaluation feedback via their terminal and send it to the server. The server updates the AI ​​model based on this feedback to improve generation accuracy. The input is the feedback provided by the user, and the output is the updated AI model.

[0489] (Application Example 1)

[0490] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0491] In traditional sales activities, providing product information and responding to customer inquiries is time-consuming and labor-intensive. This results in inconsistent quality of proposals, hindering smooth purchasing decisions. Furthermore, a lack of continuous improvement through feedback leads to recurring problems.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0493] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information, means for automatically generating a proposal talk script based on the extracted important information, and means for predicting customer questions based on materials and past data and generating a question and answer collection. This enables more efficient information provision in proposal activities, improved quality of customer service, and continuous improvement of proposal accuracy through feedback.

[0494] "A means of analyzing input data using natural language processing technology and extracting important information" refers to a process in which a computer analyzes information provided by a user using natural language processing technology, and identifies and extracts information necessary for a specific purpose.

[0495] "A method for automatically generating proposal talk scripts based on extracted key information" refers to a technology that can automatically create standard explanations and sales talks used in proposals based on key information identified through analysis.

[0496] "A means of predicting customer questions based on materials and past data and generating a Q&A document" refers to a process of predicting in advance the questions that customers might ask when they receive a proposal, by referring to past data, and systematically preparing answers to those questions.

[0497] "Methods for improving generated results by collecting user feedback and updating the AI ​​model" refers to technologies that adjust the AI's learning model based on opinions and results obtained from users, thereby improving the quality of future suggestions and responses.

[0498] "A means of seamlessly integrating product-related suggestion scripts and Q&A guides while browsing product information" refers to a technology that improves the user experience by integrating and displaying relevant suggestions and answers to questions in real time when viewing products online.

[0499] This invention enables efficient proposal activities by utilizing input data, extracting important information through analysis using natural language processing technology, and automatically generating proposal talk scripts and question-and-answer sets. An embodiment of this system is described below.

[0500] System Overview

[0501] The server receives materials uploaded by users and analyzes them using natural language processing (NLP) technology. Specifically, it uses generative AI models to understand the text and extract keywords and important phrases. Examples of NLP technologies used include spaCy and BERT.

[0502] Based on the extracted information, the server generates a suggested talk script. Furthermore, it predicts potential customer questions by referring to past data and creates a suitable question-and-answer set.

[0503] The generated suggestion talk scripts and question-and-answer sets are sent to the user's device and integrated into the product information being viewed in real time. To help users more effectively utilize the product page, prompts generated using an AI model are employed.

[0504] User behavior and feedback information are collected from the device to the server, which uses this information to update the AI ​​model and improve the generated results. This feedback loop gradually improves the accuracy and usefulness of suggested content.

[0505] Specific example

[0506] As a concrete example, imagine a user browsing a new electronic device on an e-commerce website. The server prepares real-time answers to anticipated questions such as, "What are the main features of this device?", enriching the user experience.

[0507] Example of a prompt

[0508] Product Name: Latest Electronic Device. Features: High-performance processor, extended battery life, clear display. Please generate frequently asked questions and their answers for users.

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The server receives materials uploaded by users via their terminals. The input is in formats such as PDF and Word documents, and these are stored on the server. The server then prepares to analyze these materials using natural language processing techniques.

[0512] Step 2:

[0513] The server analyzes the received data using natural language processing tools (e.g., spaCy, BERT). This analysis involves understanding the grammatical structure of the data and extracting keywords and important phrases. The extracted results are stored on the server as foundational information for generating proposed scripts.

[0514] Step 3:

[0515] The server automatically generates a suggested talk script using a generative AI model (e.g., the GPT series) based on the extracted information. The AI ​​model generates a script based on the input prompt text and saves the script as output to the server.

[0516] Step 4:

[0517] The server references materials and similar past data to predict potential customer questions. Once a list of questions is generated by the AI ​​model, the answers are also generated by the AI ​​model, completing the question-and-answer set.

[0518] Step 5:

[0519] The generated proposal talk script and question-and-answer set are sent to the user's device. The device seamlessly integrates and displays this information to the user while they are browsing product information. This allows the user to see the proposal and responses in real time while browsing.

[0520] Step 6:

[0521] Users make purchases, inquiries, and provide feedback through their devices. This behavioral information and feedback are then sent back to the server. The server processes this feedback data to train an AI model, improving the accuracy of future suggestions.

[0522] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0523] In this invention's system, the server analyzes the proposal materials using natural language processing technology and extracts important information. Subsequently, the server automatically generates a proposal talk script using AI based on the extracted information. The server also utilizes the materials and past data to predict potential questions from customers and generates an appropriate question-and-answer set.

[0524] This system also incorporates an emotion engine that recognizes the user's emotions. As the user reviews materials through their terminal, the system recognizes their emotional state in real time. Based on this, the server dynamically adjusts the content of the proposal talk script and question-and-answer set. Specifically, if the user feels anxious or confused about the proposal, the server provides a talk script with more detailed explanations.

[0525] Users utilize talk scripts and question-and-answer sets generated on their devices to conduct proposal activities. Users provide feedback during and at the end of the proposal process, and the server uses this feedback to update the AI ​​model and improve accuracy for the next time. This feedback also includes emotional data experienced by the user, contributing to improvements in the content adjustment function based on emotions.

[0526] As a concrete example, consider a scenario where a user proposes a new software solution. The server incorporates key points such as "implementation hurdles" and "support system" into its talk script, and if it senses user concerns, it provides additional specific examples regarding the support system. It also anticipates potential questions such as "How does this function work?" and prepares answers in advance.

[0527] In this way, this system provides various functions to support proposal activities, enabling efficient and effective proposals. Real-time adjustments powered by the emotion engine result in more personalized proposals.

[0528] The following describes the processing flow.

[0529] Step 1:

[0530] Users upload proposal documents and supplementary materials using their devices. These documents are sent to the server and are handled in various formats (PDF, Word, etc.).

[0531] Step 2:

[0532] The server converts the received documents into a parseable text format. This process involves using OCR (Optical Character Recognition) on PDF and image files to extract text data.

[0533] Step 3:

[0534] The server uses natural language processing technology to analyze the data and evaluate the importance of the information. AI algorithms analyze the grammatical structure and extract important keywords and phrases.

[0535] Step 4:

[0536] Based on the extracted information, the server automatically generates a proposal talk script using a template. Grammar checks are performed during script generation to ensure consistent content.

[0537] Step 5:

[0538] The server references accumulated historical data and predicts customer questions based on documents and similar past cases. Based on this predictive information, it generates a Q&A guide.

[0539] Step 6:

[0540] The generated talk script and question-and-answer set are sent to the user's terminal by the server. The user then uses these to carry out their proposal activities.

[0541] Step 7:

[0542] As the user makes a suggestion, the emotion engine built into the device analyzes the user's emotional state in real time. Emotions are evaluated based on factors such as facial expressions, voice, and input speed during data entry.

[0543] Step 8:

[0544] Based on the data obtained by the emotion engine, the server dynamically adjusts the suggested talk scripts and question-and-answer sets. For example, if the user is feeling stressed, the server will supplement the script content.

[0545] Step 9:

[0546] After the proposal activity, user feedback is sent to the server via the device. This feedback includes sentiment data and is used to retrain the AI ​​model.

[0547] Step 10:

[0548] The server analyzes the feedback and updates the AI ​​model to improve the generation process. This ensures that subsequent proposal activities provide more accurate results.

[0549] (Example 2)

[0550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] In proposal activities, there is a problem in that it takes a great deal of time and effort to prepare and implement proposals because it is difficult to quickly extract appropriate information from a large amount of documents and proposals to customers are not effectively and individually optimized. In addition, there is a challenge in maximizing the effectiveness of proposals because it is difficult to grasp customer reactions in real time and dynamically adjust the content of the proposals.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0553] In this invention, the server includes means for analyzing input documents using language processing technology and extracting important information; means for automatically generating proposal drafts using a generative model based on the extracted important information; means for predicting user inquiries based on documents and past information and generating a collection of inquiry responses; means for recognizing the user's emotional state in real time and dynamically adjusting the content of the proposal drafts and inquiry response collections; and means for improving the generation results by collecting user feedback and updating the artificial intelligence model. This improves the efficiency of proposal activities and enables more effective and personalized proposals to customers.

[0554] "Submitted documents" refer to text-based information provided by users or other systems, and their content includes various data related to the proposal.

[0555] "Language processing technology" refers to techniques for analyzing text data, understanding its content, and extracting important elements, with the aim of understanding and processing natural language.

[0556] "Important information" refers to data elements deemed necessary and useful for creating and presenting a proposal, and its extraction enables effective communication.

[0557] A "generative model" refers to an algorithm or system that automatically creates documents or text based on data, and typically utilizes artificial intelligence technology.

[0558] A "proposal draft" refers to a collection of text prepared in advance to explain the content of a proposal, and is used to effectively convey the main points and details of the proposal.

[0559] A "collection of answers to inquiries" refers to a collection of pre-prepared responses to anticipated inquiries, intended to quickly address customer questions and concerns during the proposal process.

[0560] "User" refers to an individual or organization that operates the system and receives its services, and is the entity that carries out the proposal activities.

[0561] "Emotional state" refers to an indicator that shows the user's psychological response, and recognizing it is used to improve the effectiveness of suggestions and the quality of interactions.

[0562] An "artificial intelligence model" refers to a computational model that uses data to self-learn and perform various inferences and generation tasks, with the aim of improving the accuracy of system proposals.

[0563] The embodiments for carrying out this invention are shown below.

[0564] In this invention's system, the server plays a central role, implementing various functions to effectively support proposal activities. The server receives documents provided by users and first performs analysis using language processing technology. Specifically, it utilizes natural language processing software (for example, a general cloud-based API service) to extract important information from the document. This process includes summarizing the information and extracting keywords.

[0565] Based on the extracted information, the server automatically generates a proposal draft using a generative AI model. At this time, the generative AI model (for example, a general-purpose natural language generation algorithm) is used to construct the content of the proposal. During generation, prompts such as "Please list three core points of this proposal and explain each of them" are used to efficiently obtain accurate content.

[0566] Furthermore, the server analyzes documents and historical information to predict queries based on similar past cases and prepares a query response database. This prediction uses machine learning models, and a concrete example of its use is that it can pre-prepare detailed answers to questions such as, "How does this feature work?"

[0567] Furthermore, the system integrates an emotion recognition engine that detects the user's emotional state in real time while they are reviewing proposal materials through their terminal. Emotion recognition uses techniques such as image analysis. Depending on the user's emotions, the server can dynamically adjust the content of the proposal draft and inquiry response collection, and add more detailed information as needed.

[0568] Ultimately, users conduct their proposal activities using the generated proposal draft and question-and-answer collection. After submitting their proposal, they can send feedback to the server, which collects this feedback and uses it to update and improve the AI ​​model. This makes it possible to improve the accuracy of future proposals.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server receives documents provided by users. The input includes text-based documents. Based on this input, the server analyzes the document using natural language processing techniques. Specifically, it uses a natural language processing API to analyze the sentence structure and extract important keywords and phrases. This process yields important information as output.

[0572] Step 2:

[0573] The server receives the key information extracted in Step 1 as input and automatically generates a proposal draft using a generative AI model. The prompt includes the instruction, "List three core points of your proposal and explain each of them." By passing this information to the generative AI model, a logically structured proposal draft is output.

[0574] Step 3:

[0575] The server takes proposed drafts and past query data as input and uses a machine learning model to predict future queries based on this data. This includes questions in the format of, for example, "How does this feature work?". The prediction results are output as a collection of query answers.

[0576] Step 4:

[0577] When a user reviews proposal materials on their device, an emotion recognition engine inputs the user's emotional state as information and determines it in real time. Specifically, it analyzes facial expression data obtained through a webcam and uses an API service. Based on this data, the server dynamically adjusts the proposal draft and the inquiry response collection. The output is an adjusted document that corresponds to the user's emotions.

[0578] Step 5:

[0579] After the user completes their proposal, they send feedback to the server. This feedback includes data on the validity of the proposal and the appropriateness of the query response. Based on this input, the server updates the AI ​​model to improve the accuracy of the generated results. The output is an updated version of the improved AI model.

[0580] (Application Example 2)

[0581] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0582] In conventional proposal activities, information provision to customers is one-way, making it difficult to respond flexibly to customer emotions. Furthermore, the inability to respond to customer questions in real time made it difficult to improve customer satisfaction. This invention aims to improve customer satisfaction by accurately understanding customer emotions during the proposal process and dynamically adjusting the proposal content to facilitate smoother dialogue with customers.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0584] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information; means for automatically generating a proposal talk script based on the extracted important information; means for predicting customer questions based on materials and past data and generating a question-and-answer set; means for recognizing the customer's emotional state via a terminal device and dynamically adjusting the content of the proposal talk script and question-and-answer set based on this; and means for collecting user feedback and updating the AI ​​model to improve the generated results. This makes it possible to provide customers with more personalized proposals in real time.

[0585] "Natural language processing technology" is the technology that enables computers to understand, interpret, and generate human language.

[0586] A "talk script" is a document containing spoken content, generated for a specific purpose and used in a dialogue.

[0587] A "question and answer guide" is a document that compiles a series of pre-prepared answers to anticipated questions.

[0588] A "terminal device" is an electronic device used by a user to access or manipulate information.

[0589] "Emotional state" refers to the state of a customer's psychological or emotional response.

[0590] "To adjust dynamically" means to flexibly change the content according to the situation and conditions.

[0591] "Feedback" refers to opinions and information about the output collected from users.

[0592] An "AI model" is a computational model trained to automatically perform specific tasks using artificial intelligence technology.

[0593] A system for implementing this invention consists of a server, a user terminal, and AI technology.

[0594] The server analyzes the input materials using natural language processing technology and extracts important information. This process utilizes natural language processing libraries (e.g., spaCy, NLTK). Based on the extracted information, the server uses AI models (e.g., OpenAI GPT-3) to generate a suggested talk script. It also analyzes anticipated customer questions by referring to past data and generates a question-and-answer script. In this process, it retrieves customer-related history from a database and prepares answers based on that.

[0595] Smart glasses or tablets are used as user terminals, allowing users to view suggested talk scripts and question-and-answer sets sent from the server in real time. Applications on the terminals can recognize the user's emotional state from their facial expressions and speech. Sentiment analysis libraries such as IBM Watson Natural Language Understanding are used for sentiment analysis. The server receives this sentiment data and dynamically adjusts the suggested content.

[0596] A concrete example is a customer service scenario in a clothing store. A salesperson wearing smart glasses displays a script saying, "This item is currently 30% off," when introducing a new product to a customer. The script is adjusted in real time if the customer shows increased interest or expresses concerns about the price.

[0597] Examples of prompt statements to input into a generative AI model include the following:

[0598] "Based on the sentiment analysis results, it appears the customer is interested in [XX]. Please suggest what information we should provide to promote sales."

[0599] Thus, this system enables personalized suggestions for each customer, greatly improving the efficiency and effectiveness of sales activities.

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The server receives data entered by the user and analyzes it using a natural language processing library. The input is the data itself, and the output is extracted important information. This analysis involves identifying keywords and context within the data and extracting valuable information.

[0603] Step 2:

[0604] The server automatically generates a suggested talk script using a generative AI model based on the extracted key information. The input is the key information, and the output is the suggested talk script. The generative AI model expands on the information using prompt sentences and puts into writing what the user should convey to the customer.

[0605] Step 3:

[0606] The server analyzes anticipated customer questions using documents and historically accumulated data to create a Q&A database. The input is document data and past question history, and the output is the Q&A database. By referencing the database, it extracts questions and answers from similar situations to prepare the Q&A database.

[0607] Step 4:

[0608] The device displays a proposal talk script and a Q&A list to the user via smart glasses. The input is the proposal talk script and Q&A list sent from the server, and the output is an information display as visual content. The user provides information to the customer while reviewing this on the device.

[0609] Step 5:

[0610] The device senses the customer's facial expressions and speech, and analyzes their emotional state through an emotion analysis library. The input is customer facial expression data and voice data, and the output is a quantified result of the customer's emotional state. This allows for an analysis of how the customer feels about a proposal, enabling appropriate responses.

[0611] Step 6:

[0612] The server receives the results of the sentiment analysis and dynamically adjusts the content of the suggested talk script and question-and-answer set. The input is the result of the sentiment analysis, and the output is the adjusted suggested talk script and question-and-answer set. Specifically, additional information and explanations are manually added to the talk script to alleviate customer interest and anxiety.

[0613] Step 7:

[0614] The user interacts with the customer based on information received via the device. Input consists of a pre-arranged talk script and a question-and-answer set, while output is verbal explanations and responses to the customer. Through this interaction, the user aims to improve customer understanding and satisfaction.

[0615] Step 8:

[0616] After serving a customer, the user provides feedback via a terminal, and the server updates the AI ​​model based on this feedback. The input is the user's feedback data, and the output is the updated AI model. The AI ​​learns from the information obtained from the feedback and improves the accuracy of its suggestions for the next time.

[0617] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0623] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0625] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0627] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0628] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0629] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0630] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0631] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0632] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0633] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] The system of this invention utilizes AI technology on a server to efficiently generate talk scripts and question-and-answer sets necessary for proposal activities. First, the user uploads proposal materials and supplementary materials to the system via a terminal. These materials are sent to the server in various formats, such as PDF and Word documents.

[0635] Next, the server receives these materials and performs text analysis using natural language processing techniques. Here, it grasps the grammatical structure and extracts important keywords and phrases from the materials. Based on this information, the server automatically generates suggested talk scripts and also creates FAQs. For the FAQs, the server also refers to similar past data to prepare for questions that are likely to be asked by customers.

[0636] Users can view the generated talk scripts and FAQs on their devices and utilize the information provided in their proposals. After a proposal is submitted, users input evaluation feedback from their devices and send it to the server, which trains the AI ​​model. This continuous feedback loop improves the generated content with each proposal activity, resulting in higher accuracy and effectiveness.

[0637] As a concrete example, in a document proposing cloud computing services, the server generates a script that identifies key points such as "the benefits of the cloud" and "security considerations," and provides a consistent explanation during the proposal. It also creates pre-answers to anticipated questions, such as "Are there any legal risks in adopting the cloud?", and incorporates them into an FAQ.

[0638] This system significantly improves the efficiency and quality of proposal activities by having the server automatically handle each stage of processing, including document analysis, talk script generation, question and answer compilation, and feedback collection.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] Users upload proposal documents and supplementary materials to the server using their devices. These documents include the proposal itself and related information.

[0642] Step 2:

[0643] The server converts the received documents into an analyzable format. If necessary, it utilizes OCR technology to extract text from scanned image data.

[0644] Step 3:

[0645] The server uses natural language processing techniques to analyze the grammatical structure within the document and extract important topics and keywords. Specifically, it uses TF-IDF and Word Embedding technologies to evaluate and identify the importance of the information.

[0646] Step 4:

[0647] Based on the extracted information, the server automatically generates a consistent proposal talk script using a template. A grammatical check is also performed to ensure that the generated script is grammatically correct.

[0648] Step 5:

[0649] The server references past data and documents to build answers to anticipated customer questions. This automatically generates a Q&A database, enabling users to interact with customers smoothly.

[0650] Step 6:

[0651] The server sends the generated proposal talk script and question-and-answer set to the terminal and provides it to the user. The user then uses these to conduct their proposal activities.

[0652] Step 7:

[0653] After submitting a proposal, users send the results and feedback to the server via their device. This allows the system to reflect the improvements and evaluations that users have identified.

[0654] Step 8:

[0655] The server uses the received feedback to retrain the AI ​​model. This improves the accuracy of subsequent document generation, making proposal activities even more effective.

[0656] (Example 1)

[0657] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] In proposal activities using AI technology, there is a need to quickly and accurately generate talk scripts and question-and-answer sets. However, conventional methods require a great deal of time to generate these, and it is difficult to consistently provide highly accurate content. This invention aims to solve these problems and realize more efficient and accurate content generation.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0660] In this invention, the server includes means for analyzing input digital materials using natural language processing technology and extracting important information units; means for automatically generating explanatory text of the proposed content based on the extracted information units; and means for predicting inquiries from users based on the information units and past information records and generating a collection of inquiry responses. This makes it possible to efficiently and accurately generate talk scripts and question-and-answer collections necessary for proposal activities.

[0661] "Submitted digital materials" refers to electronic document files that users upload to the server in connection with their proposal activities.

[0662] "Natural language processing technology" refers to a series of techniques and methods that enable computers to understand and analyze human language.

[0663] "Key information units" refer to keywords or phrases that deserve particular attention within the proposal document.

[0664] "Explanatory text of the proposal" refers to a series of automatically generated sentences used for explanations and presentations when making a proposal.

[0665] A "collection of inquiry responses" refers to a set of questions and answers that have been generated in advance to address anticipated questions from users during proposal activities.

[0666] "Optical character recognition technology" refers to technology that recognizes characters from image data and extracts them as text data.

[0667] A "generated AI model" refers to a mathematical and algorithmic system that uses artificial intelligence technology to learn and generate new data.

[0668] To implement this invention, a server, a terminal, and a user each play their respective roles. First, the user prepares the digital materials for the proposal via the terminal and uploads them to the server. These materials are saved in a standard electronic format, such as PDF or Word document.

[0669] Upon receiving the input data, the server begins analysis using natural language processing (NLTK) technology. The server has analysis tools such as Python's NLTK library and spaCy installed, which allow it to grasp the grammatical structure of the document and extract important information units. Specifically, this includes morphological analysis and keyword extraction.

[0670] Based on the extracted information, the server utilizes a generative AI model to automatically generate explanatory text for the proposed content. By using existing AI models such as GPT, natural-sounding text that is easily understandable to the user is provided. Furthermore, the server refers to past information records to prepare answers to anticipated user inquiries and creates a collection of inquiry responses.

[0671] Users review the explanatory texts and inquiry response lists generated on their devices and use them in their proposal activities. To ensure accuracy and consistency of the information, review functions may be provided within the system. After the proposal activity is completed, users provide evaluation feedback using their devices, and the server uses this feedback to improve the AI ​​model.

[0672] As a concrete example, if a cloud service is being proposed, and the user enters a prompt such as "Please create a description including examples of cloud service implementation," the server will extract relevant information and generate an appropriate description and FAQ.

[0673] This system will enable users to conduct proposal activities more efficiently and with higher quality.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] Users prepare digital materials for their proposals on their devices and upload them to the server. These materials are in PDF or Word document format and contain the information necessary for the proposal activity. The input is the digital materials created by the user, and the output is the uploading and delivery of these materials to the server.

[0677] Step 2:

[0678] The server receives the uploaded materials and stores them in secure storage. The server verifies the format of the materials and records metadata such as file names and date / time in a database. The input is the digital materials received in step 1, and the output is the storage of the materials and their metadata in the server's storage system.

[0679] Step 3:

[0680] The server begins text analysis of the document using natural language processing technology. Specifically, it analyzes the grammatical structure using Python's NLTK library and spaCy, and extracts keywords and phrases. The input is the digital document stored in step 2, and the output is the important information units extracted from the document.

[0681] Step 4:

[0682] The server utilizes a generative AI model to automatically generate explanatory text for the proposed content based on the extracted information units. Here, the generative AI model uses the input keywords to generate natural-sounding sentences. The input is the information units extracted in step 3, and the output is the generated explanatory text for the proposed content.

[0683] Step 5:

[0684] The server references past information records and generates a query response list containing answers to anticipated user inquiries. The generated answers are created based on a list of anticipated questions. The input is the important information from step 3 and past information records, and the output is the query response list.

[0685] Step 6:

[0686] The user reviews the generated explanatory text and inquiry response guide on their device and prepares them as proposal materials. The user verifies the accuracy of the information and makes corrections as necessary. The input is the digital content generated in steps 4 and 5, and the output is the proposal materials that the user can use.

[0687] Step 7:

[0688] After the proposal activity is completed, users input evaluation feedback via their terminal and send it to the server. The server updates the AI ​​model based on this feedback to improve generation accuracy. The input is the feedback provided by the user, and the output is the updated AI model.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] In traditional sales activities, providing product information and responding to customer inquiries is time-consuming and labor-intensive. This results in inconsistent quality of proposals, hindering smooth purchasing decisions. Furthermore, a lack of continuous improvement through feedback leads to recurring problems.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information, means for automatically generating a proposal talk script based on the extracted important information, and means for predicting customer questions based on materials and past data and generating a question and answer collection. This enables more efficient information provision in proposal activities, improved quality of customer service, and continuous improvement of proposal accuracy through feedback.

[0694] "A means of analyzing input data using natural language processing technology and extracting important information" refers to a process in which a computer analyzes information provided by a user using natural language processing technology, and identifies and extracts information necessary for a specific purpose.

[0695] "A method for automatically generating proposal talk scripts based on extracted key information" refers to a technology that can automatically create standard explanations and sales talks used in proposals based on key information identified through analysis.

[0696] "A means of predicting customer questions based on materials and past data and generating a Q&A document" refers to a process of predicting in advance the questions that customers might ask when they receive a proposal, by referring to past data, and systematically preparing answers to those questions.

[0697] "Methods for improving generated results by collecting user feedback and updating the AI ​​model" refers to technologies that adjust the AI's learning model based on opinions and results obtained from users, thereby improving the quality of future suggestions and responses.

[0698] "A means of seamlessly integrating product-related suggestion scripts and Q&A guides while browsing product information" refers to a technology that improves the user experience by integrating and displaying relevant suggestions and answers to questions in real time when viewing products online.

[0699] This invention enables efficient proposal activities by utilizing input data, extracting important information through analysis using natural language processing technology, and automatically generating proposal talk scripts and question-and-answer sets. An embodiment of this system is described below.

[0700] System Overview

[0701] The server receives materials uploaded by users and analyzes them using natural language processing (NLP) technology. Specifically, it uses generative AI models to understand the text and extract keywords and important phrases. Examples of NLP technologies used include spaCy and BERT.

[0702] Based on the extracted information, the server generates a suggested talk script. Furthermore, it predicts potential customer questions by referring to past data and creates a suitable question-and-answer set.

[0703] The generated suggestion talk scripts and question-and-answer sets are sent to the user's device and integrated into the product information being viewed in real time. To help users more effectively utilize the product page, prompts generated using an AI model are employed.

[0704] User behavior and feedback information are collected from the device to the server, which uses this information to update the AI ​​model and improve the generated results. This feedback loop gradually improves the accuracy and usefulness of suggested content.

[0705] Specific example

[0706] As a concrete example, imagine a user browsing a new electronic device on an e-commerce website. The server prepares real-time answers to anticipated questions such as, "What are the main features of this device?", enriching the user experience.

[0707] Example of a prompt

[0708] Product Name: Latest Electronic Device. Features: High-performance processor, extended battery life, clear display. Please generate frequently asked questions and their answers for users.

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The server receives materials uploaded by users via their terminals. The input is in formats such as PDF and Word documents, and these are stored on the server. The server then prepares to analyze these materials using natural language processing techniques.

[0712] Step 2:

[0713] The server analyzes the received data using natural language processing tools (e.g., spaCy, BERT). This analysis involves understanding the grammatical structure of the data and extracting keywords and important phrases. The extracted results are stored on the server as foundational information for generating proposed scripts.

[0714] Step 3:

[0715] The server automatically generates a suggested talk script using a generative AI model (e.g., the GPT series) based on the extracted information. The AI ​​model generates a script based on the input prompt text and saves the script as output to the server.

[0716] Step 4:

[0717] The server references materials and similar past data to predict potential customer questions. Once a list of questions is generated by the AI ​​model, the answers are also generated by the AI ​​model, completing the question-and-answer set.

[0718] Step 5:

[0719] The generated proposal talk script and question-and-answer set are sent to the user's device. The device seamlessly integrates and displays this information to the user while they are browsing product information. This allows the user to see the proposal and responses in real time while browsing.

[0720] Step 6:

[0721] Users make purchases, inquiries, and provide feedback through their devices. This behavioral information and feedback are then sent back to the server. The server processes this feedback data to train an AI model, improving the accuracy of future suggestions.

[0722] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0723] In this invention's system, the server analyzes the proposal materials using natural language processing technology and extracts important information. Subsequently, the server automatically generates a proposal talk script using AI based on the extracted information. The server also utilizes the materials and past data to predict potential questions from customers and generates an appropriate question-and-answer set.

[0724] This system also incorporates an emotion engine that recognizes the user's emotions. As the user reviews materials through their terminal, the system recognizes their emotional state in real time. Based on this, the server dynamically adjusts the content of the proposal talk script and question-and-answer set. Specifically, if the user feels anxious or confused about the proposal, the server provides a talk script with more detailed explanations.

[0725] Users utilize talk scripts and question-and-answer sets generated on their devices to conduct proposal activities. Users provide feedback during and at the end of the proposal process, and the server uses this feedback to update the AI ​​model and improve accuracy for the next time. This feedback also includes emotional data experienced by the user, contributing to improvements in the content adjustment function based on emotions.

[0726] As a concrete example, consider a scenario where a user proposes a new software solution. The server incorporates key points such as "implementation hurdles" and "support system" into its talk script, and if it senses user concerns, it provides additional specific examples regarding the support system. It also anticipates potential questions such as "How does this function work?" and prepares answers in advance.

[0727] In this way, this system provides various functions to support proposal activities, enabling efficient and effective proposals. Real-time adjustments powered by the emotion engine result in more personalized proposals.

[0728] The following describes the processing flow.

[0729] Step 1:

[0730] Users upload proposal documents and supplementary materials using their devices. These documents are sent to the server and are handled in various formats (PDF, Word, etc.).

[0731] Step 2:

[0732] The server converts the received documents into a parseable text format. This process involves using OCR (Optical Character Recognition) on PDF and image files to extract text data.

[0733] Step 3:

[0734] The server uses natural language processing technology to analyze the data and evaluate the importance of the information. AI algorithms analyze the grammatical structure and extract important keywords and phrases.

[0735] Step 4:

[0736] Based on the extracted information, the server automatically generates a proposal talk script using a template. Grammar checks are performed during script generation to ensure consistent content.

[0737] Step 5:

[0738] The server references accumulated historical data and predicts customer questions based on documents and similar past cases. Based on this predictive information, it generates a Q&A guide.

[0739] Step 6:

[0740] The generated talk script and question-and-answer set are sent to the user's terminal by the server. The user then uses these to carry out their proposal activities.

[0741] Step 7:

[0742] As the user makes a suggestion, the emotion engine built into the device analyzes the user's emotional state in real time. Emotions are evaluated based on factors such as facial expressions, voice, and input speed during data entry.

[0743] Step 8:

[0744] Based on the data obtained by the emotion engine, the server dynamically adjusts the suggested talk scripts and question-and-answer sets. For example, if the user is feeling stressed, the server will supplement the script content.

[0745] Step 9:

[0746] After the proposal activity, user feedback is sent to the server via the device. This feedback includes sentiment data and is used to retrain the AI ​​model.

[0747] Step 10:

[0748] The server analyzes the feedback and updates the AI ​​model to improve the generation process. This ensures that subsequent proposal activities provide more accurate results.

[0749] (Example 2)

[0750] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0751] In proposal activities, there is a problem in that it takes a great deal of time and effort to prepare and implement proposals because it is difficult to quickly extract appropriate information from a large amount of documents and proposals to customers are not effectively and individually optimized. In addition, there is a challenge in maximizing the effectiveness of proposals because it is difficult to grasp customer reactions in real time and dynamically adjust the content of the proposals.

[0752] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0753] In this invention, the server includes means for analyzing input documents using language processing technology and extracting important information; means for automatically generating proposal drafts using a generative model based on the extracted important information; means for predicting user inquiries based on documents and past information and generating a collection of inquiry responses; means for recognizing the user's emotional state in real time and dynamically adjusting the content of the proposal drafts and inquiry response collections; and means for improving the generation results by collecting user feedback and updating the artificial intelligence model. This improves the efficiency of proposal activities and enables more effective and personalized proposals to customers.

[0754] "Submitted documents" refer to text-based information provided by users or other systems, and their content includes various data related to the proposal.

[0755] "Language processing technology" refers to techniques for analyzing text data, understanding its content, and extracting important elements, with the aim of understanding and processing natural language.

[0756] "Important information" refers to data elements deemed necessary and useful for creating and presenting a proposal, and its extraction enables effective communication.

[0757] A "generative model" refers to an algorithm or system that automatically creates documents or text based on data, and typically utilizes artificial intelligence technology.

[0758] A "proposal draft" refers to a collection of text prepared in advance to explain the content of a proposal, and is used to effectively convey the main points and details of the proposal.

[0759] A "collection of answers to inquiries" refers to a collection of pre-prepared responses to anticipated inquiries, intended to quickly address customer questions and concerns during the proposal process.

[0760] "User" refers to an individual or organization that operates the system and receives its services, and is the entity that carries out the proposal activities.

[0761] "Emotional state" refers to an indicator that shows the user's psychological response, and recognizing it is used to improve the effectiveness of suggestions and the quality of interactions.

[0762] An "artificial intelligence model" refers to a computational model that uses data to self-learn and perform various inferences and generation tasks, with the aim of improving the accuracy of system proposals.

[0763] The embodiments for carrying out this invention are shown below.

[0764] In this invention's system, the server plays a central role, implementing various functions to effectively support proposal activities. The server receives documents provided by users and first performs analysis using language processing technology. Specifically, it utilizes natural language processing software (for example, a general cloud-based API service) to extract important information from the document. This process includes summarizing the information and extracting keywords.

[0765] Based on the extracted information, the server automatically generates a proposal draft using a generative AI model. At this time, the generative AI model (for example, a general-purpose natural language generation algorithm) is used to construct the content of the proposal. During generation, prompts such as "Please list three core points of this proposal and explain each of them" are used to efficiently obtain accurate content.

[0766] Furthermore, the server analyzes documents and historical information to predict queries based on similar past cases and prepares a query response database. This prediction uses machine learning models, and a concrete example of its use is that it can pre-prepare detailed answers to questions such as, "How does this feature work?"

[0767] Furthermore, the system integrates an emotion recognition engine that detects the user's emotional state in real time while they are reviewing proposal materials through their terminal. Emotion recognition uses techniques such as image analysis. Depending on the user's emotions, the server can dynamically adjust the content of the proposal draft and inquiry response collection, and add more detailed information as needed.

[0768] Ultimately, users conduct their proposal activities using the generated proposal draft and question-and-answer collection. After submitting their proposal, they can send feedback to the server, which collects this feedback and uses it to update and improve the AI ​​model. This makes it possible to improve the accuracy of future proposals.

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] The server receives documents provided by users. The input includes text-based documents. Based on this input, the server analyzes the document using natural language processing techniques. Specifically, it uses a natural language processing API to analyze the sentence structure and extract important keywords and phrases. This process yields important information as output.

[0772] Step 2:

[0773] The server receives the key information extracted in Step 1 as input and automatically generates a proposal draft using a generative AI model. The prompt includes the instruction, "List three core points of your proposal and explain each of them." By passing this information to the generative AI model, a logically structured proposal draft is output.

[0774] Step 3:

[0775] The server takes proposed drafts and past query data as input and uses a machine learning model to predict future queries based on this data. This includes questions in the format of, for example, "How does this feature work?". The prediction results are output as a collection of query answers.

[0776] Step 4:

[0777] When a user reviews proposal materials on their device, an emotion recognition engine inputs the user's emotional state as information and determines it in real time. Specifically, it analyzes facial expression data obtained through a webcam and uses an API service. Based on this data, the server dynamically adjusts the proposal draft and the inquiry response collection. The output is an adjusted document that corresponds to the user's emotions.

[0778] Step 5:

[0779] After the user completes their proposal, they send feedback to the server. This feedback includes data on the validity of the proposal and the appropriateness of the query response. Based on this input, the server updates the AI ​​model to improve the accuracy of the generated results. The output is an updated version of the improved AI model.

[0780] (Application Example 2)

[0781] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0782] In conventional proposal activities, information provision to customers is one-way, making it difficult to respond flexibly to customer emotions. Furthermore, the inability to respond to customer questions in real time made it difficult to improve customer satisfaction. This invention aims to improve customer satisfaction by accurately understanding customer emotions during the proposal process and dynamically adjusting the proposal content to facilitate smoother dialogue with customers.

[0783] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0784] In this invention, the server includes means for analyzing input materials using natural language processing technology and extracting important information; means for automatically generating a proposal talk script based on the extracted important information; means for predicting customer questions based on materials and past data and generating a question-and-answer set; means for recognizing the customer's emotional state via a terminal device and dynamically adjusting the content of the proposal talk script and question-and-answer set based on this; and means for collecting user feedback and updating the AI ​​model to improve the generated results. This makes it possible to provide customers with more personalized proposals in real time.

[0785] "Natural language processing technology" is the technology that enables computers to understand, interpret, and generate human language.

[0786] A "talk script" is a document containing spoken content, generated for a specific purpose and used in a dialogue.

[0787] A "question and answer guide" is a document that compiles a series of pre-prepared answers to anticipated questions.

[0788] A "terminal device" is an electronic device used by a user to access or manipulate information.

[0789] "Emotional state" refers to the state of a customer's psychological or emotional response.

[0790] "To adjust dynamically" means to flexibly change the content according to the situation and conditions.

[0791] "Feedback" refers to opinions and information about the output collected from users.

[0792] An "AI model" is a computational model trained to automatically perform specific tasks using artificial intelligence technology.

[0793] A system for implementing this invention consists of a server, a user terminal, and AI technology.

[0794] The server analyzes the input materials using natural language processing technology and extracts important information. This process utilizes natural language processing libraries (e.g., spaCy, NLTK). Based on the extracted information, the server uses AI models (e.g., OpenAI GPT-3) to generate a suggested talk script. It also analyzes anticipated customer questions by referring to past data and generates a question-and-answer script. In this process, it retrieves customer-related history from a database and prepares answers based on that.

[0795] Smart glasses or tablets are used as user terminals, allowing users to view suggested talk scripts and question-and-answer sets sent from the server in real time. Applications on the terminals can recognize the user's emotional state from their facial expressions and speech. Sentiment analysis libraries such as IBM Watson Natural Language Understanding are used for sentiment analysis. The server receives this sentiment data and dynamically adjusts the suggested content.

[0796] A concrete example is a customer service scenario in a clothing store. A salesperson wearing smart glasses displays a script saying, "This item is currently 30% off," when introducing a new product to a customer. The script is adjusted in real time if the customer shows increased interest or expresses concerns about the price.

[0797] Examples of prompt statements to input into a generative AI model include the following:

[0798] "Based on the sentiment analysis results, it appears the customer is interested in [XX]. Please suggest what information we should provide to promote sales."

[0799] Thus, this system enables personalized suggestions for each customer, greatly improving the efficiency and effectiveness of sales activities.

[0800] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0801] Step 1:

[0802] The server receives data entered by the user and analyzes it using a natural language processing library. The input is the data itself, and the output is extracted important information. This analysis involves identifying keywords and context within the data and extracting valuable information.

[0803] Step 2:

[0804] The server automatically generates a suggested talk script using a generative AI model based on the extracted key information. The input is the key information, and the output is the suggested talk script. The generative AI model expands on the information using prompt sentences and puts into writing what the user should convey to the customer.

[0805] Step 3:

[0806] The server analyzes anticipated customer questions using documents and historically accumulated data to create a Q&A database. The input is document data and past question history, and the output is the Q&A database. By referencing the database, it extracts questions and answers from similar situations to prepare the Q&A database.

[0807] Step 4:

[0808] The device displays a proposal talk script and a Q&A list to the user via smart glasses. The input is the proposal talk script and Q&A list sent from the server, and the output is an information display as visual content. The user provides information to the customer while reviewing this on the device.

[0809] Step 5:

[0810] The device senses the customer's facial expressions and speech, and analyzes their emotional state through an emotion analysis library. The input is customer facial expression data and voice data, and the output is a quantified result of the customer's emotional state. This allows for an analysis of how the customer feels about a proposal, enabling appropriate responses.

[0811] Step 6:

[0812] The server receives the results of the sentiment analysis and dynamically adjusts the content of the suggested talk script and question-and-answer set. The input is the result of the sentiment analysis, and the output is the adjusted suggested talk script and question-and-answer set. Specifically, additional information and explanations are manually added to the talk script to alleviate customer interest and anxiety.

[0813] Step 7:

[0814] The user interacts with the customer based on information received via the device. Input consists of a pre-arranged talk script and a question-and-answer set, while output is verbal explanations and responses to the customer. Through this interaction, the user aims to improve customer understanding and satisfaction.

[0815] Step 8:

[0816] After serving a customer, the user provides feedback via a terminal, and the server updates the AI ​​model based on this feedback. The input is the user's feedback data, and the output is the updated AI model. The AI ​​learns from the information obtained from the feedback and improves the accuracy of its suggestions for the next time.

[0817] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0818] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0819] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0820] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0821] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0822] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0823] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0824] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0825] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0826] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0827] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0828] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0829] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0830] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0831] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0832] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0833] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0834] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0835] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0836] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0837] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] A means of analyzing input data using natural language processing technology and extracting important information,

[0841] A method for automatically generating a proposal talk script based on extracted key information,

[0842] A means for predicting customer questions based on documents and historical data, and generating a question-and-answer collection,

[0843] By collecting user feedback and updating the AI ​​model, we can improve the generated results.

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising means for transmitting and providing a proposed talk script and a question-and-answer set to a user terminal.

[0847] (Claim 3)

[0848] The system according to claim 1, comprising means for extracting text from a scanned image using optical character recognition technology.

[0849] "Example 1"

[0850] (Claim 1)

[0851] A means of analyzing input digital materials using natural language processing technology and extracting important information units,

[0852] A means for automatically generating an explanatory text of the proposed content based on the extracted information units,

[0853] A means for predicting user inquiries based on information units and past information records, and generating a collection of inquiry responses,

[0854] By collecting user feedback and updating the generated AI model, a means of improving the generated content is provided.

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, comprising means for transmitting and providing a description of the proposed content and a collection of responses to inquiries to the user's terminal.

[0858] (Claim 3)

[0859] The system according to claim 1, comprising means for extracting character data from a scanned image using optical character recognition technology.

[0860] "Application Example 1"

[0861] (Claim 1)

[0862] A means of analyzing input data using natural language processing technology and extracting important information,

[0863] A method for automatically generating a proposal talk script based on extracted key information,

[0864] A means for predicting customer questions based on documents and historical data, and generating a question-and-answer collection,

[0865] By collecting user feedback and updating the AI ​​model, we can improve the generated results.

[0866] A means to seamlessly integrate product-related suggestion scripts and Q&A sets while viewing product information,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, comprising means for transmitting and providing a proposed talk script and a question-and-answer set to a user terminal.

[0870] (Claim 3)

[0871] The system according to claim 1, comprising means for extracting text from a scanned image using optical character recognition technology.

[0872] "Example 2 of combining an emotion engine"

[0873] (Claim 1)

[0874] A means of analyzing input documents using language processing technology and extracting important information,

[0875] A method for automatically generating a proposed draft using a generative model based on extracted key information,

[0876] A means for predicting user inquiries based on documents and historical information, and generating a collection of inquiry responses,

[0877] A means for recognizing the user's emotional state in real time and dynamically adjusting the content of the proposal draft and inquiry response collection,

[0878] By collecting feedback from users and updating the artificial intelligence model, a means of improving the generated results is provided.

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, comprising means for transmitting and providing a proposal draft and a collection of inquiry responses to a user's terminal.

[0882] (Claim 3)

[0883] The system according to claim 1, comprising means for extracting a string of characters from a scanned image using optical character recognition technology.

[0884] "Application example 2 when combining with an emotional engine"

[0885] (Claim 1)

[0886] A means of analyzing input data using natural language processing technology and extracting important information,

[0887] A method for automatically generating a proposal talk script based on extracted key information,

[0888] A means for predicting customer questions based on documents and historical data, and generating a question-and-answer collection,

[0889] A means for recognizing the customer's emotional state via a terminal device and dynamically adjusting the content of the proposed talk script and question-and-answer set based on this,

[0890] By collecting user feedback and updating the AI ​​model, we can improve the generated results.

[0891] A system that includes this.

[0892] (Claim 2)

[0893] A means of providing a proposed talk script and a collection of questions and answers to the user's terminal,

[0894] The system according to claim 1, further comprising means for continuously monitoring the customer's emotional state using a terminal device and adjusting the proposed content.

[0895] (Claim 3)

[0896] A means for extracting text from scanned images using optical character recognition technology,

[0897] The system according to claim 1, further comprising means for using a terminal device to grasp emotional changes during interaction and appropriately modifying the proposed talk script. [Explanation of Symbols]

[0898] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing input data using natural language processing technology and extracting important information, A method for automatically generating a proposal talk script based on extracted key information, A means for predicting customer questions based on documents and historical data, and generating a question-and-answer collection, By collecting user feedback and updating the AI ​​model, we can improve the generated results. A system that includes this.

2. The system according to claim 1, further comprising means for transmitting and providing a proposed talk script and a question-and-answer set to a user terminal.

3. The system according to claim 1, comprising means for extracting text from a scanned image using optical character recognition technology.

Images