system

Abstract

We provide the system. [Solution] An information gathering method that conducts dialogue based on user input, An analytical method that uses natural language processing to analyze dialogue content and identify user needs, A generation means that automatically generates and outputs a proposal based on identified needs, An information processing 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] Conventionally, the creation of a proposal depends on the skills of salespersons, and the quality varies among individual salespersons, so it may not be able to provide sufficient satisfaction to customers. Such variations result in opportunity losses and the problem of being unable to quickly and accurately provide the information required by customers. Furthermore, if the proposal creation process is not efficient, it will cause waste of time and resources. It is necessary to address such situations and solve the problem of improving customer satisfaction.

Means for Solving the Problems

[0005] This invention includes an analysis means that uses information gathering means to engage in dialogue based on user input information and analyzes the collected information using natural language processing technology. Based on the analysis results, it includes a generation means that identifies the user's true needs and automatically generates a proposal based on those identified needs, thereby reducing variations in the quality of proposals. Furthermore, the generation means includes a verification means that scrutinizes the content of the generated proposal and automatically corrects errors as necessary, thereby improving the accuracy and reliability of the proposal. In addition, by including a learning means that obtains user feedback, stores that information, and reflects it in the AI's training data, it is possible to improve the efficiency of the process and the accuracy of the generation.

[0006] An "information gathering tool" is a system that has the function of engaging in dialogue based on information entered by the user and collecting necessary data.

[0007] Natural language processing is a set of techniques that enable computers to understand and analyze human language, and is used to identify user needs.

[0008] "Analysis method" refers to the system's function of analyzing collected dialogue data using natural language processing technology to extract user requests and interests.

[0009] A "generation method" is a system that has the function of automatically creating and outputting a proposal based on the needs identified by the analysis method.

[0010] "Verification means" refers to a system function that includes a process of reviewing the content of the generated proposal and correcting grammatical and substantive errors.

[0011] "Learning methods" refer to functions that collect user feedback, reflect the results in the system, and improve the accuracy of proposal generation. [Brief explanation of the drawing]

[0012] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled 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), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled 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.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention utilizes an information processing system to automatically generate proposals. The system mainly consists of a server, a terminal, and a user, and each element works in cooperation with the others. An embodiment of this system is described below.

[0034] First, the user accesses the proposal document request page from their device and enters the necessary information. At this stage, the information gathering mechanism is activated, and a chatbot dialogue with the user begins. The device receives and processes this information, extracting customer needs necessary for creating the proposal.

[0035] Next, the collected dialogue information is sent to a server and processed by an analysis tool using natural language processing. Here, the customer's true needs and concerns are extracted, and based on this, specific proposals are automatically designed by a generation tool.

[0036] After the proposal is generated, the server uses verification tools to scrutinize its contents. Grammar checks and data integrity checks are performed, and corrections are automatically made as needed. Through this process, high-quality and accurate proposals are generated.

[0037] The generated proposal is exported in PDF or Word format and provided to the user via their device. The user can download the proposal via a link.

[0038] As a concrete example, consider a case where a product vendor needs a proposal for a new product. The user inputs needs such as "it must include the latest technological features" and "I would like a quote within a specific budget." This information is collected and analyzed, and a proposal with the most suitable content is automatically generated. In this way, it becomes possible to quickly meet customer needs while maintaining the quality and accuracy of the proposal.

[0039] Furthermore, user feedback is acquired through the system's learning mechanisms, contributing to improvements in the accuracy of future proposal generation. This feedback process continuously enhances the personalization and refinement of proposals.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user accesses the proposal document request page from their device and enters the required information. This information is used as initial data for creating the proposal.

[0043] Step 2:

[0044] The device initiates a chatbot conversation based on the input information. Here, the information gathering tool asks standardized and adaptive questions to elicit the user's interests and needs.

[0045] Step 3:

[0046] Users respond to the chatbot's questions, providing detailed information about their needs and preferences. The device collects this information in real time.

[0047] Step 4:

[0048] On the server, the collected dialogue information is processed by analysis tools. Natural language processing is used to analyze the text data and identify the user's requests and objectives.

[0049] Step 5:

[0050] Based on the analysis results, the server automatically generates a proposal using a generation method. Here, information is organized according to a standardized format based on identified needs, and the optimal proposal content is constructed.

[0051] Step 6:

[0052] The server uses verification tools to scrutinize the content of the generated proposal. It checks for grammatical errors and data inconsistencies and makes corrections as needed.

[0053] Step 7:

[0054] The proposal exported from the server is provided to the user via the terminal. The user can download the proposal from the specified link.

[0055] Step 8:

[0056] The user provides feedback on the provided proposal. The device collects this feedback and sends it to the server.

[0057] Step 9:

[0058] The server analyzes feedback through learning mechanisms and uses it to generate future proposals. This allows the system to continuously improve its accuracy and enhance its ability to generate proposals that better meet customer needs.

[0059] (Example 1)

[0060] 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."

[0061] In traditional proposal creation processes, it was difficult to quickly generate proposals that accurately reflected the specific needs of the customer, and there was a need to work efficiently while maintaining the quality and accuracy of the documents. Furthermore, there was insufficient automation of proposal revisions and quality improvement through the use of user feedback.

[0062] 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.

[0063] In this invention, the server includes acquisition means, analysis means, generation means, and transmission means. This enables automation of all processes from information collection to proposal generation and delivery, making it possible to provide proposals that quickly and accurately meet customer needs. Furthermore, verification means and learning means enable improvement of proposal quality and system performance.

[0064] "Acquisition means" refers to a device or software that has the function of receiving information provided by the user and collecting information through dialogue as needed.

[0065] "Analysis means" refers to a device or program that applies natural language processing to acquired information and has the function of extracting and structuring the user's requests and needs.

[0066] "Generation means" refers to a device or algorithm that has the function of automatically generating a proposal document based on the requirements extracted through analysis.

[0067] "Transmission means" refers to a device or process that converts the generated proposal document into an electronic document format and provides it to the user using appropriate communication means.

[0068] A "verification tool" is a device or software that has the function of verifying the content of the generated proposal document, checking the quality and consistency of the document, and making corrections automatically as needed.

[0069] A "learning tool" is a device or function that acquires evaluation information and feedback from users and uses that information to accumulate and utilize data in order to improve the overall performance and accuracy of the system.

[0070] Embodiments of this invention are described below.

[0071] First, the user uses their device to access the proposal document request page and enters their needs and requirements. During this input stage, the collected information is temporarily stored on the device. At this point, the data collection system works to organize the necessary information.

[0072] Next, the terminal is responsible for sending the entered information to the server. The terminal converts the text data into a standardized format, making it easier for the server to process.

[0073] Subsequently, the server performs analysis based on the received information. Within the server, a generative AI model for natural language processing (e.g., GPT-3®) is used. This model is used to analyze the customer's true needs and requirements from the input text, and the extracted data is used to concretize the proposed content.

[0074] For example, if a product vendor wants to propose a new product to a customer, the user inputs needs such as "it must include the latest energy-saving technology" or "we want the best solution within our annual budget." This information is analyzed by a model, which then automatically generates appropriate proposals.

[0075] Through the generation process, this data is automatically assembled into a proposal format on the server. During this process, the server performs grammar checks and data integrity verification. Grammarly or similar grammar checking software may be used. After the proposal is completed, it is converted to PDF or Word format.

[0076] Subsequently, the server sends the proposal to the user via a transmission method. Specifically, a download link is generated and provided to the user through their device. The user can use this link to obtain and review the completed proposal.

[0077] Examples of prompt statements include "include the latest technical features" and "request an estimate within a specific budget."

[0078] This overall system flow allows users to receive fast and highly accurate services, and ensures that proposals are generated and delivered smoothly.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The user accesses the proposal document request page using their device. The user enters specific needs and requirements, which the device receives. The input is text data about the needs and requests, and the output is temporarily stored on the device as formatted information. The device collects the entered information and converts it into a specified format.

[0082] Step 2:

[0083] The terminal sends organized information to the server. The input is formatted data about the user's needs, and the output is data packets for the server to receive. In this process, the terminal performs specific actions to standardize the information and make it a format that is easy for the server to process.

[0084] Step 3:

[0085] The server begins analyzing the received information. The input is needs data sent from the terminal, and the output is extracted customer requests and concerns. The server applies a generative AI model (e.g., GPT-3) to analyze the text data, extract the necessary information, and structure it.

[0086] Step 4:

[0087] Based on the analysis, the server automatically generates specific proposal content using a proposal generation method. The input is the analyzed data, and the output is a draft-level proposal document. In this operation, the server performs calculations to assemble the proposal to meet the extracted needs.

[0088] Step 5:

[0089] The server validates the generated proposal document and automatically makes corrections as needed. The input is a draft-level proposal document, and the output is a completed proposal document. Here, the server performs specific actions such as grammar checks and data integrity verification, and makes corrections if necessary.

[0090] Step 6:

[0091] The server converts the completed proposal document into an appropriate file format (e.g., PDF, Word) and sends it to the terminal. The input is the completed proposal document, and the output is a downloadable file link sent to the user. The server converts the document and provides the proposal document in a format that is easily accessible to the user.

[0092] Step 7:

[0093] The user clicks a link provided through their device to download the completed proposal document. The input is the download link, and the output is the proposal document saved on the user's device. The user then reviews the proposal document on their device and performs specific actions to confirm that the content meets their final needs.

[0094] (Application Example 1)

[0095] 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."

[0096] In information processing systems, there is a need to build a system that can automatically generate high-quality advertising proposals that quickly respond to user needs, and that allows for rapid review and revision of proposal content. Furthermore, a challenge is to continuously improve the accuracy of proposals by utilizing feedback obtained from users.

[0097] 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.

[0098] In this invention, the server includes data acquisition means, data analysis means, and generation function means. This makes it possible to collect and analyze necessary data from interactions based on user input information and to quickly supply automatically generated, high-quality advertising proposals. Furthermore, the system can continuously improve its accuracy by scrutinizing the generated proposals, automatically making necessary corrections, and utilizing user feedback.

[0099] A "data acquisition method" is a means that has the function of collecting necessary data by engaging in dialogue based on information input from the user.

[0100] "Data analysis means" refers to a method that analyzes collected dialogue content using natural language processing and performs the function of identifying user needs.

[0101] A "generation function means" is a means equipped with the function of automatically generating and outputting advertising proposals based on specified needs.

[0102] The "proofreading function" is a feature that scrutinizes the content of the generated advertising proposal and automatically makes corrections as needed.

[0103] A "learning function" is a means of improving the accuracy of the system's generation functions by acquiring and accumulating feedback from users.

[0104] A "server" is a central device that performs information processing, including means for data acquisition, data analysis, and generation.

[0105] To implement this invention, a server, terminal, and user must cooperate to form an information processing system, with each element playing a specific role. First, the user uses the terminal to input details of an advertising campaign in a marketing activity. The input information is collected by a data acquisition means.

[0106] Next, the server uses data analysis tools to analyze the collected data, leveraging natural language processing. In this process, a generative AI model is used to identify user needs. Based on the analyzed needs, the generative function automatically generates an advertising proposal and outputs it to the terminal.

[0107] The generated advertising proposals are reviewed by the server's proofreading function and automatically corrected as needed. This ensures that users receive high-quality and accurate advertising proposals.

[0108] User feedback is collected by the server and stored in the system through a learning function. This feedback is used to improve the accuracy of the generation function, enabling more precise proposals in the creation of future advertising proposals.

[0109] As a concrete example, consider a case where you want to advertise a new smartphone case to women in their 20s. In this case, the user inputs the following prompt into the system: "I am planning an advertising campaign for a smartphone case targeting women in their 20s. I want to emphasize a stylish and practical design. The objective of the campaign is to increase brand awareness, and the budget is 300,000 yen. Based on this information, please create an appropriate advertising proposal." Based on this, the server generates an advertising proposal.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] Users input detailed information about advertising campaigns necessary for marketing activities via their devices. This input includes target audience, campaign objectives, and budget information. This data is collected by the system's data acquisition mechanisms.

[0113] Step 2:

[0114] The server processes the collected input data using data analysis tools. Specifically, it uses natural language processing to analyze and identify user needs within the input data. In this process, a generative AI model is utilized to extract and analyze data based on the input prompt sentences.

[0115] Step 3:

[0116] The server automatically generates advertising proposals using generation functions based on the needs identified by data analysis. In this generation process, the server constructs the optimal content for the advertising proposal based on the user's input data and analysis results, and outputs it to the terminal.

[0117] Step 4:

[0118] The generated advertising proposals are automatically reviewed by the server's proofreading function. This step includes grammatical checks and information consistency verification, with automatic corrections made as needed. This ensures the quality of the advertising proposals provided to users.

[0119] Step 5:

[0120] The user receives the generated advertising proposal and sends feedback back to the server. This feedback information is stored in the system through a learning function. This data is used to improve the accuracy of advertising proposals in subsequent generation processes. This continuously improves the system's response quality.

[0121] 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.

[0122] This invention combines an emotion engine with an information processing system, providing more personalized results by utilizing emotion recognition in the process of automatically generating proposals through interaction with the user. The system consists of three elements: a server, a terminal, and a user, each of which performs the following processes.

[0123] The user accesses the information request page using their device and begins entering information. The device activates information gathering mechanisms via a chatbot to collect necessary information from the user. In this interaction, the device transmits the text data entered by the user to an emotion engine based on voice and expressions.

[0124] On the server, this emotion engine analyzes the user's emotions. Combining natural language processing and emotion analysis techniques, it detects emotional characteristics such as positive, negative, and neutral from the dialogue. The identified emotions are then used to identify needs through analytical methods.

[0125] The server automatically generates proposals using generation methods based on these needs and emotional states. Emotional information is reflected in and optimized for the tone and content of the proposals. For example, if the user is feeling anxious, the proposal may include more information about guarantees.

[0126] After the proposal is generated, the server scrutinizes its contents using verification tools. It checks for errors and logical consistency. The terminal then provides the generated proposal to the user, who can download it via a link.

[0127] As a concrete example, consider a scenario where a user requires a proposal when introducing a new product. The user communicates their desired features, price range, and implementation timeline via chat, while an emotion engine detects emotions such as tension and anticipation. In this case, the server generates a proposal with recommended support plans, thereby reducing the user's anxiety and supporting their purchasing decision.

[0128] User feedback is sent to the server, processed through a learning mechanism, and incorporated into the AI ​​model. This feedback process allows for continuous improvement in the personalization and accuracy of future proposals.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user accesses the document request page from their device and enters the required information. This information includes specific requests and preferences related to the proposal.

[0132] Step 2:

[0133] The terminal initiates a conversation with the user using a chatbot. Questions are asked to more accurately elicit the user's needs and specific requirements through information gathering mechanisms.

[0134] Step 3:

[0135] The device sends the conversational text data to the emotion engine. The emotion engine analyzes the user's input and uses natural language processing to identify emotional characteristics. This identification includes emotional categories such as positive, negative, and neutral.

[0136] Step 4:

[0137] The server integrates the emotional data received from the interaction with the requests obtained through analysis to identify the user's specific needs. For example, if anxiety is indicated, the server prioritizes information that provides greater reassurance.

[0138] Step 5:

[0139] The server's generation method automatically generates proposals tailored to identified needs and emotional states. This process utilizes emotional information to adjust the content and tone of the proposals. For example, it might include guarantees and support information to provide reassurance.

[0140] Step 6:

[0141] The server uses verification tools to check the generated proposal for typographical errors, grammatical inconsistencies, and logical inconsistencies. If problems are found, necessary automatic corrections are performed.

[0142] Step 7:

[0143] The terminal provides the user with the generated proposal. The user can download the proposal from a designated link and review its contents.

[0144] Step 8:

[0145] Users evaluate proposals and provide feedback. The device collects this feedback and sends it to the server.

[0146] Step 9:

[0147] The server uses learning mechanisms to analyze feedback and incorporate it into the AI ​​model. This improves the proposal generation process and enhances personalization for future generations.

[0148] (Example 2)

[0149] 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".

[0150] In modern information processing systems, accurately understanding user needs and automatically generating effective proposals based on them is difficult. Furthermore, creating proposals that take user emotions into account requires accurately analyzing user emotions and providing personalized content that reflects them, but conventional systems do not adequately handle this process.

[0151] 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.

[0152] In this invention, the server includes means for conducting a dialogue based on input information from the user and detecting emotions from voice and expressions; means for analyzing the dialogue content using natural language processing and sentiment analysis to identify the user's emotions; and means for automatically generating a proposal based on the identified needs and emotions, and outputting it while reflecting the emotional information. This makes it possible to automatically generate highly personalized proposals that meet the user's needs and emotions.

[0153] "Input information" refers to data provided by the user, including the content necessary for generating the proposal.

[0154] "Dialogue" is the process of information exchange between the user and the system, and a means of eliciting the user's needs and emotions.

[0155] "Means of detecting emotions" refers to technologies and processes for identifying a user's psychological state from their voice and expressions.

[0156] "Natural language processing" refers to the technology that enables computers to interpret and analyze human language.

[0157] "Sentiment analysis" refers to a technology that analyzes a user's psychological state from their text and voice data.

[0158] A "proposal" refers to a document containing plans and recommendations that are generated based on the user's needs and feelings and provided to the user.

[0159] "Personalized content" refers to information tailored to the individual user's needs, emotions, and circumstances.

[0160] This invention begins when a user accesses a document request page using a terminal. The terminal collects information entered by the user, and this information, along with voice and expression data, is transmitted to an emotion engine. This emotion engine combines natural language processing and sentiment analysis techniques to identify emotional characteristics such as positive, negative, and neutral from the user's text data.

[0161] The server identifies the user's specific needs based on data analyzed by the emotion engine. This identification process utilizes a generative AI model, which generates the user's expected results based on prompt text. The server then automatically generates a proposal based on the needs and identified emotions. The proposal's content is adjusted based on emotional information, ensuring it is delivered in a tone appropriate to the user's psychological state.

[0162] Once the proposal is generated, the server analyzes it through verification mechanisms to check for errors and logical inconsistencies. After this thorough review, the proposal is presented to the user via their terminal. The user can then download the proposal via a link.

[0163] A concrete example is when a user needs a proposal when introducing a new product. The user begins inputting information on their device, and a chatbot provides details such as desired features, budget, and implementation timing. In this situation, an emotion engine may detect the user's anxiety. Based on this, the server generates a proposal that emphasizes guarantees, reducing anxiety and supporting the implementation decision.

[0164] An example of a prompt message is: "Please create a proposal outlining the support needed when introducing a new product. The user is interested in cost-effectiveness but seems concerned about the smoothness of the implementation." In this way, the present invention makes it possible to efficiently and accurately generate proposals that meet the user's needs.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The user accesses the information request page using their device and enters the required information. The device collects the data entered by the user and sends it to the server as input information. This input contains detailed information related to the user's request.

[0168] Step 2:

[0169] The device transmits user input text, its expression, and audio data to an emotion analysis module via an emotion engine. This process uses natural language processing techniques to analyze emotions and generate emotional characteristics such as positive, negative, and neutral as output.

[0170] Step 3:

[0171] The server uses emotional data obtained from the emotion engine and information collected about user needs to identify user needs using a generative AI model. From this input data, it generates prompt sentences and outputs the identified needs.

[0172] Step 4:

[0173] The server utilizes a generative AI model based on identified needs and sentiment data to automatically generate proposal content. This process involves tone and content adjustments that reflect sentiment information, resulting in a personalized proposal output.

[0174] Step 5:

[0175] The server sends the generated proposal to a verification system. Here, errors are detected and the logic of the proposal is checked. The verified proposal is then output and finally sent to the terminal.

[0176] Step 6:

[0177] The terminal receives the proposal sent from the server and provides it to the user. The proposal is provided as a download link, and the user can review this output and download and save it as needed.

[0178] Step 7:

[0179] The user reviews the proposal and provides feedback. The terminal sends this feedback as input to the server. The server uses learning mechanisms to store this feedback as data to improve the accuracy of future proposal generation processes.

[0180] (Application Example 2)

[0181] 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".

[0182] Conventional information processing systems provide proposals that are generated without considering the user's emotions, resulting in insufficient personalization based on the user's psychological state. As a result, proposals may not meet the user's expectations or needs. This problem can increase user anxiety and decrease purchasing intent, especially in fields where a sense of security is crucial, such as security services.

[0183] 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.

[0184] In this invention, the server includes means for collecting user input information as audio and visual data and analyzing emotional states in real time; means for analyzing dialogue content and emotional characteristics using natural language processing and identifying user needs; and means for automatically generating proposals based on the identified needs and emotions, and outputting them while reflecting emotional elements. This makes it possible to provide optimal proposals that are tailored to individual needs while being attentive to the user's emotions.

[0185] A "user" is an individual who receives a proposal using an information processing system, and whose emotional state is the subject of analysis.

[0186] "Input information" refers to data that users provide to the system, and includes various formats such as audio, visual data, and text.

[0187] "Audio and visual data" refers to audio information that records the user's speech, and visual information related to the user's facial expressions and other physical movements.

[0188] "Emotional state" refers to a user's psychological or emotional condition and is categorized as positive, negative, or neutral.

[0189] "Real-time analysis methods" refer to technologies that process data acquired instantaneously and analyze users' emotions on the spot.

[0190] "Natural language processing" is a technology that enables computers to understand and process human language, and is used for analyzing text data.

[0191] "Emotional characteristics" are attributes that indicate the type and intensity of a user's emotions, as identified through emotion analysis.

[0192] "Needs" refer to the requests and demands that users have, and they influence the content of the suggestions that the system should provide.

[0193] "Automatic generation" refers to the process by which a system generates proposals based on data without requiring human intervention.

[0194] "Emotional elements" refer to the psychologically impactful information and tone included in the proposal, which are adjusted according to the user's emotions.

[0195] In the system implementing this invention, a server efficiently processes the user's voice and visual data and generates a proposal. The main hardware includes smart glasses and smartphones, which are worn by the user. These devices are equipped with cameras and microphones to capture the user's voice and facial expressions in real time.

[0196] Data collected from smart glasses and smartphones is sent to a server. The server uses this data to run software for sentiment analysis. Typical software includes a sentiment analysis engine and a natural language processing unit. This software classifies the user's emotional state as positive, negative, or neutral, and based on the results, analyzes the user's needs in detail.

[0197] Furthermore, the server uses a generation mechanism to create personalized proposals based on the user's emotional state. The generation AI model is used to apply emotional elements to the proposal to address the user's emotional needs. For example, if a user feels anxious while considering security services, the proposal will include specific success stories and guarantee details to alleviate that anxiety.

[0198] An example of a prompt message could be: "If the user's current emotion is detected as 'anxiety,' generate a proposal that highlights successful safety measures and guarantee details." In this way, it is possible to provide more personalized proposals based on the user's emotions.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The device collects audio and visual data from the user in real time. Input consists of the user's speech and facial expressions, captured through the device's camera and microphone. Output is data transfer to the server.

[0202] Step 2:

[0203] The server inputs data received from the terminal into an emotion analysis engine to analyze the user's emotions. Here, data processing is performed based on audio and image data to identify the user's emotional state (positive, negative, neutral, etc.). The output is the analysis result regarding the user's emotional state.

[0204] Step 3:

[0205] The server uses a natural language processing unit to analyze the dialogue. The input is the user's utterances, and semantic analysis is performed to identify their needs. The output is the analyzed user needs information.

[0206] Step 4:

[0207] The server integrates emotional state and needs information and generates prompt sentences necessary for proposal generation. Prompt sentences are created for input into the generation AI model. These prompt sentences are then output.

[0208] Step 5:

[0209] The server uses a generative AI model to automatically generate personalized proposals based on prompt text. The input is the prompt text, and the output is a proposal with emotionally appropriate adjustments.

[0210] Step 6:

[0211] The terminal displays the generated proposal to the user. The output is the presented proposal, which the user reviews and provides feedback on.

[0212] Step 7:

[0213] Users send feedback on proposals to the server via their devices. The input is user feedback. The server uses this feedback to store it as training data and improve the accuracy of future proposal generation.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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".

[0230] This invention utilizes an information processing system to automatically generate proposals. The system mainly consists of a server, a terminal, and a user, and each element works in cooperation with the others. An embodiment of this system is described below.

[0231] First, the user accesses the proposal document request page from their device and enters the necessary information. At this stage, the information gathering mechanism is activated, and a chatbot dialogue with the user begins. The device receives and processes this information, extracting customer needs necessary for creating the proposal.

[0232] Next, the collected dialogue information is sent to a server and processed by an analysis tool using natural language processing. Here, the customer's true needs and concerns are extracted, and based on this, specific proposals are automatically designed by a generation tool.

[0233] After the proposal is generated, the server uses verification tools to scrutinize its contents. Grammar checks and data integrity checks are performed, and corrections are automatically made as needed. Through this process, high-quality and accurate proposals are generated.

[0234] The generated proposal is exported in PDF or Word format and provided to the user via their device. The user can download the proposal via a link.

[0235] As a concrete example, consider a case where a product vendor needs a proposal for a new product. The user inputs needs such as "it must include the latest technological features" and "I would like a quote within a specific budget." This information is collected and analyzed, and a proposal with the most suitable content is automatically generated. In this way, it becomes possible to quickly meet customer needs while maintaining the quality and accuracy of the proposal.

[0236] Furthermore, user feedback is acquired through the system's learning mechanisms, contributing to improvements in the accuracy of future proposal generation. This feedback process continuously enhances the personalization and refinement of proposals.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] The user accesses the proposal document request page from their device and enters the required information. This information is used as initial data for creating the proposal.

[0240] Step 2:

[0241] The device initiates a chatbot conversation based on the input information. Here, the information gathering tool asks standardized and adaptive questions to elicit the user's interests and needs.

[0242] Step 3:

[0243] Users respond to the chatbot's questions, providing detailed information about their needs and preferences. The device collects this information in real time.

[0244] Step 4:

[0245] On the server, the collected dialogue information is processed by analysis tools. Natural language processing is used to analyze the text data and identify the user's requests and objectives.

[0246] Step 5:

[0247] Based on the analysis results, the server automatically generates a proposal using a generation method. Here, information is organized according to a standardized format based on identified needs, and the optimal proposal content is constructed.

[0248] Step 6:

[0249] The server uses verification tools to scrutinize the content of the generated proposal. It checks for grammatical errors and data inconsistencies and makes corrections as needed.

[0250] Step 7:

[0251] The proposal exported from the server is provided to the user via the terminal. The user can download the proposal from the specified link.

[0252] Step 8:

[0253] The user provides feedback on the provided proposal. The device collects this feedback and sends it to the server.

[0254] Step 9:

[0255] The server analyzes feedback through learning mechanisms and uses it to generate future proposals. This allows the system to continuously improve its accuracy and enhance its ability to generate proposals that better meet customer needs.

[0256] (Example 1)

[0257] 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."

[0258] In traditional proposal creation processes, it was difficult to quickly generate proposals that accurately reflected the specific needs of the customer, and there was a need to work efficiently while maintaining the quality and accuracy of the documents. Furthermore, there was insufficient automation of proposal revisions and quality improvement through the use of user feedback.

[0259] 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.

[0260] In this invention, the server includes acquisition means, analysis means, generation means, and transmission means. This enables automation of all processes from information collection to proposal generation and delivery, making it possible to provide proposals that quickly and accurately meet customer needs. Furthermore, verification means and learning means enable improvement of proposal quality and system performance.

[0261] "Acquisition means" refers to a device or software that has the function of receiving information provided by the user and collecting information through dialogue as needed.

[0262] "Analysis means" refers to a device or program that applies natural language processing to acquired information and has the function of extracting and structuring the user's requests and needs.

[0263] "Generation means" refers to a device or algorithm that has the function of automatically generating a proposal document based on the requirements extracted through analysis.

[0264] "Transmission means" refers to a device or process that converts the generated proposal document into an electronic document format and provides it to the user using appropriate communication means.

[0265] A "verification tool" is a device or software that has the function of verifying the content of the generated proposal document, checking the quality and consistency of the document, and making corrections automatically as needed.

[0266] A "learning tool" is a device or function that acquires evaluation information and feedback from users and uses that information to accumulate and utilize data in order to improve the overall performance and accuracy of the system.

[0267] Embodiments of this invention are described below.

[0268] First, the user uses their device to access the proposal document request page and enters their needs and requirements. During this input stage, the collected information is temporarily stored on the device. At this point, the data collection system works to organize the necessary information.

[0269] Next, the terminal is responsible for sending the entered information to the server. The terminal converts the text data into a standardized format, making it easier for the server to process.

[0270] The server then performs analysis based on the received information. Within the server, a generative AI model for natural language processing (such as GPT-3) is used. This model is used to analyze the customer's true needs and requirements from the input text, and the extracted data is used to refine the proposed solutions.

[0271] For example, if a product vendor wants to propose a new product to a customer, the user inputs needs such as "it must include the latest energy-saving technology" or "we want the best solution within our annual budget." This information is analyzed by a model, which then automatically generates appropriate proposals.

[0272] Through the generation process, this data is automatically assembled into a proposal format on the server. During this process, the server performs grammar checks and data integrity verification. Grammarly or similar grammar checking software may be used. After the proposal is completed, it is converted to PDF or Word format.

[0273] Subsequently, the server sends the proposal to the user via a transmission method. Specifically, a download link is generated and provided to the user through their device. The user can use this link to obtain and review the completed proposal.

[0274] Examples of prompt statements include "include the latest technical features" and "request an estimate within a specific budget."

[0275] This overall system flow allows users to receive fast and highly accurate services, and ensures that proposals are generated and delivered smoothly.

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The user accesses the proposal document request page using their device. The user enters specific needs and requirements, which the device receives. The input is text data about the needs and requests, and the output is temporarily stored on the device as formatted information. The device collects the entered information and converts it into a specified format.

[0279] Step 2:

[0280] The terminal sends the organized information to the server. The input is formatted data regarding the user's needs, and the output is data packets for the server to receive. In this process, the terminal standardizes the information and performs specific operations to make it in a format that is easy for the server to process.

[0281] Step 3:

[0282] The server begins to analyze the received information. The input is the need data sent from the terminal, and the output is the extracted customer requirements and concerns. The server applies a generated AI model (e.g., GPT-3) to analyze the text data, extract the necessary information, and structure it.

[0283] Step 4:

[0284] Based on the analysis, the server automatically generates specific proposal content using the proposal generation means. The input is the analyzed data, and the output is a draft-level proposal document. In this operation, the server executes calculations to assemble a proposal document to meet the extracted needs.

[0285] Step 5:

[0286] The server verifies the generated proposal document and automatically makes corrections if necessary. The input is the draft-level proposal document, and the output is a completed proposal document. Here, the server performs specific operations to verify grammar checking and data consistency and execute corrections if necessary.

[0287] Step 6:

[0288] The server converts the completed proposal document into an appropriate file format (e.g., PDF, Word) and sends it to the terminal. The input is the completed proposal document, and the output is a downloadable file link sent to the user. The server performs document conversion and provides the proposal document in a form that is easy for the user to access.

[0289] Step 7:

[0290] The user clicks a link provided through their device to download the completed proposal document. The input is the download link, and the output is the proposal document saved on the user's device. The user then reviews the proposal document on their device and performs specific actions to confirm that the content meets their final needs.

[0291] (Application Example 1)

[0292] 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."

[0293] In information processing systems, there is a need to build a system that can automatically generate high-quality advertising proposals that quickly respond to user needs, and that allows for rapid review and revision of proposal content. Furthermore, a challenge is to continuously improve the accuracy of proposals by utilizing feedback obtained from users.

[0294] 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.

[0295] In this invention, the server includes data acquisition means, data analysis means, and generation function means. This makes it possible to collect and analyze necessary data from interactions based on user input information and to quickly supply automatically generated, high-quality advertising proposals. Furthermore, the system can continuously improve its accuracy by scrutinizing the generated proposals, automatically making necessary corrections, and utilizing user feedback.

[0296] A "data acquisition method" is a means that has the function of collecting necessary data by engaging in dialogue based on information input from the user.

[0297] "Data analysis means" refers to a method that analyzes collected dialogue content using natural language processing and performs the function of identifying user needs.

[0298] A "generation function means" is a means equipped with the function of automatically generating and outputting advertising proposals based on specified needs.

[0299] The "proofreading function" is a feature that scrutinizes the content of the generated advertising proposal and automatically makes corrections as needed.

[0300] A "learning function" is a means of improving the accuracy of the system's generation functions by acquiring and accumulating feedback from users.

[0301] A "server" is a central device that performs information processing, including means for data acquisition, data analysis, and generation.

[0302] To implement this invention, a server, terminal, and user must cooperate to form an information processing system, with each element playing a specific role. First, the user uses the terminal to input details of an advertising campaign in a marketing activity. The input information is collected by a data acquisition means.

[0303] Next, the server uses data analysis tools to analyze the collected data, leveraging natural language processing. In this process, a generative AI model is used to identify user needs. Based on the analyzed needs, the generative function automatically generates an advertising proposal and outputs it to the terminal.

[0304] The generated advertising proposals are reviewed by the server's proofreading function and automatically corrected as needed. This ensures that users receive high-quality and accurate advertising proposals.

[0305] Feedback from users is obtained by the server and accumulated in the system by the learning function. This feedback is utilized to improve the accuracy of the generation function means, enabling more refined proposals in the production of advertising planning documents from the next time onwards.

[0306] As a specific example, consider the case where you want to promote a new smartphone case for women in their 20s. In this case, the user inputs a prompt sentence to the system such as "I am planning an advertising campaign for a smartphone case targeting women in their 20s. I want to emphasize a fashionable and practical design. The purpose of the campaign is to improve brand awareness, and the budget is 300,000 yen. Based on this information, please create an appropriate advertising proposal." Based on this, the server generates an advertising planning document.

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The user inputs detailed information about the advertising campaign required for the marketing activity through the terminal. The input content here includes the target audience, the purpose of the campaign, budget information, etc. These data are collected by the data acquisition means in the system.

[0310] Step 2:

[0311] The server processes the collected input data by the data analysis means. Specifically, natural language processing is utilized to analyze and identify the user's needs from the input data. In this process, the generation AI model is utilized to extract and analyze data based on the input prompt sentence.

[0312] Step 3:

[0313] The server automatically generates advertising proposals using generation functions based on the needs identified by data analysis. In this generation process, the server constructs the optimal content for the advertising proposal based on the user's input data and analysis results, and outputs it to the terminal.

[0314] Step 4:

[0315] The generated advertising proposals are automatically reviewed by the server's proofreading function. This step includes grammatical checks and information consistency verification, with automatic corrections made as needed. This ensures the quality of the advertising proposals provided to users.

[0316] Step 5:

[0317] The user receives the generated advertising proposal and sends feedback back to the server. This feedback information is stored in the system through a learning function. This data is used to improve the accuracy of advertising proposals in subsequent generation processes. This continuously improves the system's response quality.

[0318] 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.

[0319] This invention combines an emotion engine with an information processing system, providing more personalized results by utilizing emotion recognition in the process of automatically generating proposals through interaction with the user. The system consists of three elements: a server, a terminal, and a user, each of which performs the following processes.

[0320] The user accesses the information request page using their device and begins entering information. The device activates information gathering mechanisms via a chatbot to collect necessary information from the user. In this interaction, the device transmits the text data entered by the user to an emotion engine based on voice and expressions.

[0321] On the server, this emotion engine analyzes the user's emotions. Combining natural language processing and emotion analysis techniques, it detects emotional characteristics such as positive, negative, and neutral from the dialogue. The identified emotions are then used to identify needs through analytical methods.

[0322] The server automatically generates proposals using generation methods based on these needs and emotional states. Emotional information is reflected in and optimized for the tone and content of the proposals. For example, if the user is feeling anxious, the proposal may include more information about guarantees.

[0323] After the proposal is generated, the server scrutinizes its contents using verification tools. It checks for errors and logical consistency. The terminal then provides the generated proposal to the user, who can download it via a link.

[0324] As a concrete example, consider a scenario where a user requires a proposal when introducing a new product. The user communicates their desired features, price range, and implementation timeline via chat, while an emotion engine detects emotions such as tension and anticipation. In this case, the server generates a proposal with recommended support plans, thereby reducing the user's anxiety and supporting their purchasing decision.

[0325] User feedback is sent to the server, processed through a learning mechanism, and incorporated into the AI ​​model. This feedback process allows for continuous improvement in the personalization and accuracy of future proposals.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The user accesses the document request page from their device and enters the required information. This information includes specific requests and preferences related to the proposal.

[0329] Step 2:

[0330] The terminal initiates a conversation with the user using a chatbot. Questions are asked to more accurately elicit the user's needs and specific requirements through information gathering mechanisms.

[0331] Step 3:

[0332] The device sends the text data of the conversation to the emotion engine. The emotion engine analyzes the user's input and uses natural language processing to identify emotional characteristics. This identification includes emotional categories such as positive, negative, and neutral.

[0333] Step 4:

[0334] The server integrates the emotional data received from the interaction with the requests obtained through analysis to identify the user's specific needs. For example, if anxiety is indicated, the server prioritizes information that provides greater reassurance.

[0335] Step 5:

[0336] The server's generation method automatically generates proposals tailored to identified needs and emotional states. This process utilizes emotional information to adjust the content and tone of the proposals. For example, it might include guarantees and support information to provide reassurance.

[0337] Step 6:

[0338] The server uses verification tools to check the generated proposal for typographical errors, grammatical mistakes, and logical inconsistencies. If problems are found, necessary automatic corrections are performed.

[0339] Step 7:

[0340] The terminal provides the user with the generated proposal. The user can download the proposal from a designated link and review its contents.

[0341] Step 8:

[0342] Users evaluate proposals and provide feedback. The device collects this feedback and sends it to the server.

[0343] Step 9:

[0344] The server uses learning mechanisms to analyze feedback and incorporate it into the AI ​​model. This improves the proposal generation process and enhances personalization for future generations.

[0345] (Example 2)

[0346] 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".

[0347] In modern information processing systems, accurately understanding user needs and automatically generating effective proposals based on them is difficult. Furthermore, creating proposals that take user emotions into account requires accurately analyzing user emotions and providing personalized content that reflects them, but conventional systems do not adequately handle this process.

[0348] 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.

[0349] In this invention, the server includes means for conducting a dialogue based on input information from the user and detecting emotions from voice and expressions; means for analyzing the dialogue content using natural language processing and sentiment analysis to identify the user's emotions; and means for automatically generating a proposal based on the identified needs and emotions, and outputting it while reflecting the emotional information. This makes it possible to automatically generate highly personalized proposals that meet the user's needs and emotions.

[0350] "Input information" refers to data provided by the user, including the content necessary for generating the proposal.

[0351] "Dialogue" is the process of information exchange between the user and the system, and a means of eliciting the user's needs and emotions.

[0352] "Means of detecting emotions" refers to technologies and processes for identifying a user's psychological state from their voice and expressions.

[0353] "Natural language processing" refers to the technology that enables computers to interpret and analyze human language.

[0354] "Sentiment analysis" refers to a technology that analyzes a user's psychological state from their text and voice data.

[0355] A "proposal" refers to a document containing plans and recommendations that are generated based on the user's needs and feelings and provided to the user.

[0356] "Personalized content" refers to information tailored to the individual user's needs, emotions, and circumstances.

[0357] This invention begins when a user accesses a document request page using a terminal. The terminal collects information entered by the user, and this information, along with voice and expression data, is transmitted to an emotion engine. This emotion engine combines natural language processing and sentiment analysis techniques to identify emotional characteristics such as positive, negative, and neutral from the user's text data.

[0358] The server identifies the user's specific needs based on data analyzed by the emotion engine. This identification process utilizes a generative AI model, which generates the user's expected results based on prompt text. The server then automatically generates a proposal based on the needs and identified emotions. The proposal's content is adjusted based on emotional information, ensuring it is delivered in a tone appropriate to the user's psychological state.

[0359] Once the proposal is generated, the server analyzes it through verification mechanisms to check for errors and logical inconsistencies. After this thorough review, the proposal is presented to the user via their terminal. The user can then download the proposal via a link.

[0360] A concrete example is when a user needs a proposal when introducing a new product. The user begins inputting information on their device, and a chatbot provides details such as desired features, budget, and implementation timing. In this situation, an emotion engine may detect the user's anxiety. Based on this, the server generates a proposal that emphasizes guarantees, reducing anxiety and supporting the implementation decision.

[0361] An example of a prompt message is: "Please create a proposal outlining the support needed when introducing a new product. The user is interested in cost-effectiveness but seems concerned about the smoothness of the implementation." In this way, the present invention makes it possible to efficiently and accurately generate proposals that meet the user's needs.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] The user accesses the information request page using their device and enters the required information. The device collects the data entered by the user and sends it to the server as input information. This input includes detailed information related to the user's request.

[0365] Step 2:

[0366] The device transmits user input text, its expression, and audio data to an emotion analysis module via an emotion engine. This process uses natural language processing techniques to analyze emotions and generate emotional characteristics such as positive, negative, and neutral as output.

[0367] Step 3:

[0368] The server uses emotional data obtained from the emotion engine and information collected about user needs to identify user needs using a generative AI model. From this input data, it generates prompt sentences and outputs the identified needs.

[0369] Step 4:

[0370] The server utilizes a generative AI model based on identified needs and sentiment data to automatically generate proposal content. This process involves tone and content adjustments that reflect sentiment information, resulting in a personalized proposal output.

[0371] Step 5:

[0372] The server sends the generated proposal to a verification system. Here, errors are detected and the logic of the proposal is checked. The verified proposal is then output and finally sent to the terminal.

[0373] Step 6:

[0374] The terminal receives the proposal sent from the server and provides it to the user. The proposal is provided as a download link, and the user can review this output and download and save it as needed.

[0375] Step 7:

[0376] The user reviews the proposal and provides feedback. The terminal sends this feedback as input to the server. The server uses learning mechanisms to store this feedback as data to improve the accuracy of future proposal generation processes.

[0377] (Application Example 2)

[0378] 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."

[0379] Conventional information processing systems provide proposals that are generated without considering the user's emotions, resulting in insufficient personalization based on the user's psychological state. As a result, proposals may not meet the user's expectations or needs. This problem can increase user anxiety and decrease purchasing intent, especially in fields where a sense of security is crucial, such as security services.

[0380] 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.

[0381] In this invention, the server includes means for collecting user input information as audio and visual data and analyzing emotional states in real time; means for analyzing dialogue content and emotional characteristics using natural language processing and identifying user needs; and means for automatically generating proposals based on the identified needs and emotions, and outputting them while reflecting emotional elements. This makes it possible to provide optimal proposals that are tailored to individual needs while being attentive to the user's emotions.

[0382] A "user" is an individual who receives a proposal using an information processing system, and whose emotional state is the subject of analysis.

[0383] "Input information" refers to data that users provide to the system, and includes various formats such as audio, visual data, and text.

[0384] "Audio and visual data" refers to audio information that records the user's speech, and visual information related to the user's facial expressions and other physical movements.

[0385] "Emotional state" refers to a user's psychological or emotional condition and is categorized as positive, negative, or neutral.

[0386] "Real-time analysis methods" refer to technologies that process data acquired instantaneously and analyze users' emotions on the spot.

[0387] "Natural language processing" is a technology that enables computers to understand and process human language, and is used for analyzing text data.

[0388] "Emotional characteristics" are attributes that indicate the type and intensity of a user's emotions, as identified through emotion analysis.

[0389] "Needs" refer to the requests and demands that users have, and they influence the content of the suggestions that the system should provide.

[0390] "Automatic generation" refers to the process by which a system generates proposals based on data without requiring human intervention.

[0391] "Emotional elements" refer to the psychologically impactful information and tone included in the proposal, which are adjusted according to the user's emotions.

[0392] In the system implementing this invention, a server efficiently processes the user's voice and visual data and generates a proposal. The main hardware includes smart glasses and smartphones, which are worn by the user. These devices are equipped with cameras and microphones to capture the user's voice and facial expressions in real time.

[0393] Data collected from smart glasses and smartphones is sent to a server. The server uses this data to run software for sentiment analysis. Typical software includes a sentiment analysis engine and a natural language processing unit. This software classifies the user's emotional state as positive, negative, or neutral, and based on the results, analyzes the user's needs in detail.

[0394] Furthermore, the server uses a generation mechanism to create personalized proposals based on the user's emotional state. The generation AI model is used to apply emotional elements to the proposal to address the user's emotional needs. For example, if a user feels anxious while considering security services, the proposal will include specific success stories and guarantee details to alleviate that anxiety.

[0395] An example of a prompt message could be: "If the user's current emotion is detected as 'anxiety,' generate a proposal that highlights successful safety measures and guarantee details." In this way, it is possible to provide more personalized proposals based on the user's emotions.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The device collects audio and visual data from the user in real time. Input consists of the user's speech and facial expressions, captured through the device's camera and microphone. Output is data transfer to the server.

[0399] Step 2:

[0400] The server inputs data received from the terminal into an emotion analysis engine to analyze the user's emotions. Here, data processing is performed based on audio and image data to identify the user's emotional state (positive, negative, neutral, etc.). The output is the analysis result regarding the user's emotional state.

[0401] Step 3:

[0402] The server uses a natural language processing unit to analyze the dialogue. The input is the user's utterances, and semantic analysis is performed to identify their needs. The output is the analyzed user needs information.

[0403] Step 4:

[0404] The server integrates emotional state and needs information and generates prompt sentences necessary for proposal generation. Prompt sentences are created for input into the generation AI model. These prompt sentences are then output.

[0405] Step 5:

[0406] The server uses a generative AI model to automatically generate personalized proposals based on prompt text. The input is the prompt text, and the output is a proposal with emotionally appropriate adjustments.

[0407] Step 6:

[0408] The terminal displays the generated proposal to the user. The output is the presented proposal, which the user reviews and provides feedback on.

[0409] Step 7:

[0410] Users send feedback on proposals to the server via their devices. The input is user feedback. The server uses this feedback to store it as training data and improve the accuracy of future proposal generation.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention utilizes an information processing system to automatically generate proposals. The system mainly consists of a server, a terminal, and a user, and each element works in cooperation with the others. An embodiment of this system is described below.

[0428] First, the user accesses the proposal document request page from their device and enters the necessary information. At this stage, the information gathering mechanism is activated, and a chatbot dialogue with the user begins. The device receives and processes this information, extracting customer needs necessary for creating the proposal.

[0429] Next, the collected dialogue information is sent to a server and processed by an analysis tool using natural language processing. Here, the customer's true needs and concerns are extracted, and based on this, specific proposals are automatically designed by a generation tool.

[0430] After the proposal is generated, the server uses verification tools to scrutinize its contents. Grammar checks and data integrity checks are performed, and corrections are automatically made as needed. Through this process, high-quality and accurate proposals are generated.

[0431] The generated proposal is exported in PDF or Word format and provided to the user via their device. The user can download the proposal via a link.

[0432] As a concrete example, consider a case where a product vendor needs a proposal for a new product. The user inputs needs such as "it must include the latest technological features" and "I would like a quote within a specific budget." This information is collected and analyzed, and a proposal with the most suitable content is automatically generated. In this way, it becomes possible to quickly meet customer needs while maintaining the quality and accuracy of the proposal.

[0433] Furthermore, user feedback is acquired through the system's learning mechanisms, contributing to improvements in the accuracy of future proposal generation. This feedback process continuously enhances the personalization and refinement of proposals.

[0434] The following describes the processing flow.

[0435] Step 1:

[0436] The user accesses the proposal document request page from their device and enters the required information. This information is used as initial data for creating the proposal.

[0437] Step 2:

[0438] The device initiates a chatbot conversation based on the input information. Here, the information gathering tool asks standardized and adaptive questions to elicit the user's interests and needs.

[0439] Step 3:

[0440] Users respond to the chatbot's questions, providing detailed information about their needs and preferences. The device collects this information in real time.

[0441] Step 4:

[0442] On the server, the collected dialogue information is processed by analysis tools. Natural language processing is used to analyze the text data and identify the user's requests and objectives.

[0443] Step 5:

[0444] Based on the analysis results, the server automatically generates a proposal using a generation method. Here, information is organized according to a standardized format based on identified needs, and the optimal proposal content is constructed.

[0445] Step 6:

[0446] The server uses verification tools to scrutinize the content of the generated proposal. It checks for grammatical errors and data inconsistencies and makes corrections as needed.

[0447] Step 7:

[0448] The proposal exported from the server is provided to the user via the terminal. The user can download the proposal from the specified link.

[0449] Step 8:

[0450] The user provides feedback on the provided proposal. The device collects this feedback and sends it to the server.

[0451] Step 9:

[0452] The server analyzes feedback through learning mechanisms and uses it to generate future proposals. This allows the system to continuously improve its accuracy and enhance its ability to generate proposals that better meet customer needs.

[0453] (Example 1)

[0454] 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."

[0455] In traditional proposal creation processes, it was difficult to quickly generate proposals that accurately reflected the specific needs of the customer, and there was a need to work efficiently while maintaining the quality and accuracy of the documents. Furthermore, there was insufficient automation of proposal revisions and quality improvement through the use of user feedback.

[0456] 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.

[0457] In this invention, the server includes acquisition means, analysis means, generation means, and transmission means. This enables automation of all processes from information collection to proposal generation and delivery, making it possible to provide proposals that quickly and accurately meet customer needs. Furthermore, verification means and learning means enable improvement of proposal quality and system performance.

[0458] "Acquisition means" refers to a device or software that has the function of receiving information provided by the user and collecting information through dialogue as needed.

[0459] "Analysis means" refers to a device or program that applies natural language processing to acquired information and has the function of extracting and structuring the user's requests and needs.

[0460] "Generation means" refers to a device or algorithm that has the function of automatically generating a proposal document based on the requirements extracted through analysis.

[0461] "Transmission means" refers to a device or process that converts the generated proposal document into an electronic document format and provides it to the user using appropriate communication means.

[0462] A "verification tool" is a device or software that has the function of verifying the content of the generated proposal document, checking the quality and consistency of the document, and making corrections automatically as needed.

[0463] A "learning tool" is a device or function that acquires evaluation information and feedback from users and uses that information to accumulate and utilize data in order to improve the overall performance and accuracy of the system.

[0464] Embodiments of this invention are described below.

[0465] First, the user uses their device to access the proposal document request page and enters their needs and requirements. During this input stage, the collected information is temporarily stored on the device. At this point, the data collection system works to organize the necessary information.

[0466] Next, the terminal is responsible for sending the entered information to the server. The terminal converts the text data into a standardized format, making it easier for the server to process.

[0467] The server then performs analysis based on the received information. Within the server, a generative AI model for natural language processing (such as GPT-3) is used. This model is used to analyze the customer's true needs and requirements from the input text, and the extracted data is used to refine the proposed solutions.

[0468] For example, if a product vendor wants to propose a new product to a customer, the user inputs needs such as "it must include the latest energy-saving technology" or "we want the best solution within our annual budget." This information is analyzed by a model, which then automatically generates appropriate proposals.

[0469] Through the generation process, this data is automatically assembled into a proposal format on the server. During this process, the server performs grammar checks and data integrity verification. Grammarly or similar grammar checking software may be used. After the proposal is completed, it is converted to PDF or Word format.

[0470] Subsequently, the server sends the proposal to the user via a transmission method. Specifically, a download link is generated and provided to the user through their device. The user can use this link to obtain and review the completed proposal.

[0471] Examples of prompt statements include "include the latest technical features" and "request an estimate within a specific budget."

[0472] This overall system flow allows users to receive fast and highly accurate services, and ensures that proposals are generated and delivered smoothly.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The user accesses the proposal document request page using their device. The user enters specific needs and requirements, which the device receives. The input is text data about the needs and requests, and the output is temporarily stored on the device as formatted information. The device collects the entered information and converts it into a specified format.

[0476] Step 2:

[0477] The terminal sends organized information to the server. The input is formatted data about the user's needs, and the output is data packets for the server to receive. In this process, the terminal performs specific actions to standardize the information and make it a format that is easy for the server to process.

[0478] Step 3:

[0479] The server begins analyzing the received information. The input is needs data sent from the terminal, and the output is extracted customer requests and concerns. The server applies a generative AI model (e.g., GPT-3) to analyze the text data, extract the necessary information, and structure it.

[0480] Step 4:

[0481] Based on the analysis, the server automatically generates specific proposal content using a proposal generation method. The input is the analyzed data, and the output is a draft-level proposal document. In this operation, the server performs calculations to assemble the proposal to meet the extracted needs.

[0482] Step 5:

[0483] The server validates the generated proposal document and automatically makes corrections as needed. The input is a draft-level proposal document, and the output is a completed proposal document. Here, the server performs specific actions such as grammar checks and data integrity verification, and makes corrections if necessary.

[0484] Step 6:

[0485] The server converts the completed proposal document into an appropriate file format (e.g., PDF, Word) and sends it to the terminal. The input is the completed proposal document, and the output is a downloadable file link sent to the user. The server converts the document and provides the proposal document in a format that is easily accessible to the user.

[0486] Step 7:

[0487] The user clicks a link provided through their device to download the completed proposal document. The input is the download link, and the output is the proposal document saved on the user's device. The user then reviews the proposal document on their device and performs specific actions to confirm that the content meets their final needs.

[0488] (Application Example 1)

[0489] 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."

[0490] In information processing systems, there is a need to build a system that can automatically generate high-quality advertising proposals that quickly respond to user needs, and that allows for rapid review and revision of proposal content. Furthermore, a challenge is to continuously improve the accuracy of proposals by utilizing feedback obtained from users.

[0491] 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.

[0492] In this invention, the server includes data acquisition means, data analysis means, and generation function means. This makes it possible to collect and analyze necessary data from interactions based on user input information and to quickly supply automatically generated, high-quality advertising proposals. Furthermore, the system can continuously improve its accuracy by scrutinizing the generated proposals, automatically making necessary corrections, and utilizing user feedback.

[0493] A "data acquisition method" is a means that has the function of collecting necessary data by engaging in dialogue based on information input from the user.

[0494] "Data analysis means" refers to a method that analyzes collected dialogue content using natural language processing and performs the function of identifying user needs.

[0495] A "generation function means" is a means equipped with the function of automatically generating and outputting advertising proposals based on specified needs.

[0496] The "proofreading function" is a feature that scrutinizes the content of the generated advertising proposal and automatically makes corrections as needed.

[0497] A "learning function" is a means of improving the accuracy of the system's generation functions by acquiring and accumulating feedback from users.

[0498] A "server" is a central device that performs information processing, including means for data acquisition, data analysis, and generation.

[0499] To implement this invention, a server, terminal, and user must cooperate to form an information processing system, with each element playing a specific role. First, the user uses the terminal to input details of an advertising campaign in a marketing activity. The input information is collected by a data acquisition means.

[0500] Next, the server uses data analysis tools to analyze the collected data, leveraging natural language processing. In this process, a generative AI model is used to identify user needs. Based on the analyzed needs, the generative function automatically generates an advertising proposal and outputs it to the terminal.

[0501] The generated advertising proposals are reviewed by the server's proofreading function and automatically corrected as needed. This ensures that users receive high-quality and accurate advertising proposals.

[0502] User feedback is collected by the server and stored in the system through a learning function. This feedback is used to improve the accuracy of the generation function, enabling more precise proposals in the creation of future advertising proposals.

[0503] As a concrete example, consider a case where you want to advertise a new smartphone case to women in their 20s. In this case, the user inputs the following prompt into the system: "I am planning an advertising campaign for a smartphone case targeting women in their 20s. I want to emphasize a stylish and practical design. The objective of the campaign is to increase brand awareness, and the budget is 300,000 yen. Based on this information, please create an appropriate advertising proposal." Based on this, the server generates an advertising proposal.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] Users input detailed information about advertising campaigns necessary for marketing activities via their devices. This input includes target audience, campaign objectives, and budget information. This data is collected by the system's data acquisition mechanisms.

[0507] Step 2:

[0508] The server processes the collected input data using data analysis tools. Specifically, it uses natural language processing to analyze and identify user needs within the input data. In this process, a generative AI model is utilized to extract and analyze data based on the input prompt sentences.

[0509] Step 3:

[0510] The server automatically generates advertising proposals using generation functions based on the needs identified by data analysis. In this generation process, the server constructs the optimal content for the advertising proposal based on the user's input data and analysis results, and outputs it to the terminal.

[0511] Step 4:

[0512] The generated advertising proposals are automatically reviewed by the server's proofreading function. This step includes grammatical checks and information consistency verification, with automatic corrections made as needed. This ensures the quality of the advertising proposals provided to users.

[0513] Step 5:

[0514] The user receives the generated advertising proposal and sends feedback back to the server. This feedback information is stored in the system through a learning function. This data is used to improve the accuracy of advertising proposals in subsequent generation processes. This continuously improves the system's response quality.

[0515] 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.

[0516] This invention combines an emotion engine with an information processing system, providing more personalized results by utilizing emotion recognition in the process of automatically generating proposals through interaction with the user. The system consists of three elements: a server, a terminal, and a user, each of which performs the following processes.

[0517] The user accesses the information request page using their device and begins entering information. The device activates information gathering mechanisms via a chatbot to collect necessary information from the user. In this interaction, the device transmits the text data entered by the user to an emotion engine based on voice and expressions.

[0518] On the server, this emotion engine analyzes the user's emotions. Combining natural language processing and emotion analysis techniques, it detects emotional characteristics such as positive, negative, and neutral from the dialogue. The identified emotions are then used to identify needs through analytical methods.

[0519] The server automatically generates proposals using generation methods based on these needs and emotional states. Emotional information is reflected in and optimized for the tone and content of the proposals. For example, if the user is feeling anxious, the proposal may include more information about guarantees.

[0520] After the proposal is generated, the server scrutinizes its contents using verification tools. It checks for errors and logical consistency. The terminal then provides the generated proposal to the user, who can download it via a link.

[0521] As a concrete example, consider a scenario where a user requires a proposal when introducing a new product. The user communicates their desired features, price range, and implementation timeline via chat, while an emotion engine detects emotions such as tension and anticipation. In this case, the server generates a proposal with recommended support plans, thereby reducing the user's anxiety and supporting their purchasing decision.

[0522] User feedback is sent to the server, processed through a learning mechanism, and incorporated into the AI ​​model. This feedback process allows for continuous improvement in the personalization and accuracy of future proposals.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The user accesses the document request page from their device and enters the required information. This information includes specific requests and preferences related to the proposal.

[0526] Step 2:

[0527] The terminal initiates a conversation with the user using a chatbot. Questions are asked to more accurately elicit the user's needs and specific requirements through information gathering mechanisms.

[0528] Step 3:

[0529] The device sends the text data of the conversation to the emotion engine. The emotion engine analyzes the user's input and uses natural language processing to identify emotional characteristics. This identification includes emotional categories such as positive, negative, and neutral.

[0530] Step 4:

[0531] The server integrates the emotional data received from the interaction with the requests obtained through analysis to identify the user's specific needs. For example, if anxiety is indicated, the server prioritizes information that provides greater reassurance.

[0532] Step 5:

[0533] The server's generation method automatically generates proposals tailored to identified needs and emotional states. This process utilizes emotional information to adjust the content and tone of the proposals. For example, it might include guarantees and support information to provide reassurance.

[0534] Step 6:

[0535] The server uses verification tools to check the generated proposal for typographical errors, grammatical mistakes, and logical inconsistencies. If problems are found, necessary automatic corrections are performed.

[0536] Step 7:

[0537] The terminal provides the user with the generated proposal. The user can download the proposal from a designated link and review its contents.

[0538] Step 8:

[0539] Users evaluate proposals and provide feedback. The device collects this feedback and sends it to the server.

[0540] Step 9:

[0541] The server uses learning mechanisms to analyze feedback and incorporate it into the AI ​​model. This improves the proposal generation process and enhances personalization for future generations.

[0542] (Example 2)

[0543] 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."

[0544] In modern information processing systems, accurately understanding user needs and automatically generating effective proposals based on them is difficult. Furthermore, creating proposals that take user emotions into account requires accurately analyzing user emotions and providing personalized content that reflects them, but conventional systems do not adequately handle this process.

[0545] 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.

[0546] In this invention, the server includes means for conducting a dialogue based on input information from the user and detecting emotions from voice and expressions; means for analyzing the dialogue content using natural language processing and sentiment analysis to identify the user's emotions; and means for automatically generating a proposal based on the identified needs and emotions, and outputting it while reflecting the emotional information. This makes it possible to automatically generate highly personalized proposals that meet the user's needs and emotions.

[0547] "Input information" refers to data provided by the user, including the content necessary for generating the proposal.

[0548] "Dialogue" is the process of information exchange between the user and the system, and a means of eliciting the user's needs and emotions.

[0549] "Means of detecting emotions" refers to technologies and processes for identifying a user's psychological state from their voice and expressions.

[0550] "Natural language processing" refers to the technology that enables computers to interpret and analyze human language.

[0551] "Sentiment analysis" refers to a technology that analyzes a user's psychological state from their text and voice data.

[0552] A "proposal" refers to a document containing plans and recommendations that are generated based on the user's needs and feelings and provided to the user.

[0553] "Personalized content" refers to information tailored to the individual user's needs, emotions, and circumstances.

[0554] This invention begins when a user accesses a document request page using a terminal. The terminal collects information entered by the user, and this information, along with voice and expression data, is transmitted to an emotion engine. This emotion engine combines natural language processing and sentiment analysis techniques to identify emotional characteristics such as positive, negative, and neutral from the user's text data.

[0555] The server identifies the user's specific needs based on data analyzed by the emotion engine. This identification process utilizes a generative AI model, which generates the user's expected results based on prompt text. The server then automatically generates a proposal based on the needs and identified emotions. The proposal's content is adjusted based on emotional information, ensuring it is delivered in a tone appropriate to the user's psychological state.

[0556] Once the proposal is generated, the server analyzes it through verification mechanisms to check for errors and logical inconsistencies. After this thorough review, the proposal is presented to the user via their terminal. The user can then download the proposal via a link.

[0557] A concrete example is when a user needs a proposal when introducing a new product. The user begins inputting information on their device, and a chatbot provides details such as desired features, budget, and implementation timing. In this situation, an emotion engine may detect the user's anxiety. Based on this, the server generates a proposal that emphasizes guarantees, reducing anxiety and supporting the implementation decision.

[0558] An example of a prompt message is: "Please create a proposal outlining the support needed when introducing a new product. The user is interested in cost-effectiveness but seems concerned about the smoothness of the implementation." In this way, the present invention makes it possible to efficiently and accurately generate proposals that meet the user's needs.

[0559] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0560] Step 1:

[0561] The user accesses the information request page using their device and enters the required information. The device collects the data entered by the user and sends it to the server as input information. This input includes detailed information related to the user's request.

[0562] Step 2:

[0563] The device transmits user input text, its expression, and audio data to an emotion analysis module via an emotion engine. This process uses natural language processing techniques to analyze emotions and generate emotional characteristics such as positive, negative, and neutral as output.

[0564] Step 3:

[0565] The server uses emotional data obtained from the emotion engine and information collected about user needs to identify user needs using a generative AI model. From this input data, it generates prompt sentences and outputs the identified needs.

[0566] Step 4:

[0567] The server utilizes a generative AI model based on identified needs and sentiment data to automatically generate proposal content. This process involves tone and content adjustments that reflect sentiment information, resulting in a personalized proposal output.

[0568] Step 5:

[0569] The server sends the generated proposal to a verification system. Here, errors are detected and the logic of the proposal is checked. The verified proposal is then output and finally sent to the terminal.

[0570] Step 6:

[0571] The terminal receives the proposal sent from the server and provides it to the user. The proposal is provided as a download link, and the user can review this output and download and save it as needed.

[0572] Step 7:

[0573] The user reviews the proposal and provides feedback. The terminal sends this feedback as input to the server. The server uses learning mechanisms to store this feedback as data to improve the accuracy of future proposal generation processes.

[0574] (Application Example 2)

[0575] 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."

[0576] Conventional information processing systems provide proposals that are generated without considering the user's emotions, resulting in insufficient personalization based on the user's psychological state. As a result, proposals may not meet the user's expectations or needs. This problem can increase user anxiety and decrease purchasing intent, especially in fields where a sense of security is crucial, such as security services.

[0577] 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.

[0578] In this invention, the server includes means for collecting user input information as audio and visual data and analyzing emotional states in real time; means for analyzing dialogue content and emotional characteristics using natural language processing and identifying user needs; and means for automatically generating proposals based on the identified needs and emotions, and outputting them while reflecting emotional elements. This makes it possible to provide optimal proposals that are tailored to individual needs while being attentive to the user's emotions.

[0579] A "user" is an individual who receives a proposal using an information processing system, and whose emotional state is the subject of analysis.

[0580] "Input information" refers to data that users provide to the system, and includes various formats such as audio, visual data, and text.

[0581] "Audio and visual data" refers to audio information that records the user's speech, and visual information related to the user's facial expressions and other physical movements.

[0582] "Emotional state" refers to a user's psychological or emotional condition and is categorized as positive, negative, or neutral.

[0583] "Real-time analysis methods" refer to technologies that process data acquired instantaneously and analyze users' emotions on the spot.

[0584] "Natural language processing" is a technology that enables computers to understand and process human language, and is used for analyzing text data.

[0585] "Emotional characteristics" are attributes that indicate the type and intensity of a user's emotions, as identified through emotion analysis.

[0586] "Needs" refer to the requests and demands that users have, and they influence the content of the suggestions that the system should provide.

[0587] "Automatic generation" refers to the process by which a system generates proposals based on data without requiring human intervention.

[0588] "Emotional elements" refer to the psychologically impactful information and tone included in the proposal, which are adjusted according to the user's emotions.

[0589] In the system implementing this invention, a server efficiently processes the user's voice and visual data and generates a proposal. The main hardware includes smart glasses and smartphones, which are worn by the user. These devices are equipped with cameras and microphones to capture the user's voice and facial expressions in real time.

[0590] Data collected from smart glasses and smartphones is sent to a server. The server uses this data to run software for sentiment analysis. Typical software includes a sentiment analysis engine and a natural language processing unit. This software classifies the user's emotional state as positive, negative, or neutral, and based on the results, analyzes the user's needs in detail.

[0591] Furthermore, the server uses a generation mechanism to create personalized proposals based on the user's emotional state. The generation AI model is used to apply emotional elements to the proposal to address the user's emotional needs. For example, if a user feels anxious while considering security services, the proposal will include specific success stories and guarantee details to alleviate that anxiety.

[0592] An example of a prompt message could be: "If the user's current emotion is detected as 'anxiety,' generate a proposal that highlights successful safety measures and guarantee details." In this way, it is possible to provide more personalized proposals based on the user's emotions.

[0593] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0594] Step 1:

[0595] The device collects audio and visual data from the user in real time. Input consists of the user's speech and facial expressions, captured through the device's camera and microphone. Output is data transfer to the server.

[0596] Step 2:

[0597] The server inputs data received from the terminal into an emotion analysis engine to analyze the user's emotions. Here, data processing is performed based on audio and image data to identify the user's emotional state (positive, negative, neutral, etc.). The output is the analysis result regarding the user's emotional state.

[0598] Step 3:

[0599] The server uses a natural language processing unit to analyze the dialogue. The input is the user's utterances, and semantic analysis is performed to identify their needs. The output is the analyzed user needs information.

[0600] Step 4:

[0601] The server integrates emotional state and needs information and generates prompt sentences necessary for proposal generation. Prompt sentences are created for input into the generation AI model. These prompt sentences are then output.

[0602] Step 5:

[0603] The server uses a generative AI model to automatically generate personalized proposals based on prompt text. The input is the prompt text, and the output is a proposal with emotionally appropriate adjustments.

[0604] Step 6:

[0605] The terminal displays the generated proposal to the user. The output is the presented proposal, which the user reviews and provides feedback on.

[0606] Step 7:

[0607] Users send feedback on proposals to the server via their devices. The input is user feedback. The server uses this feedback to store it as training data and improve the accuracy of future proposal generation.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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".

[0625] This invention utilizes an information processing system to automatically generate proposals. The system mainly consists of a server, a terminal, and a user, and each element works in cooperation with the others. An embodiment of this system is described below.

[0626] First, the user accesses the proposal document request page from their device and enters the necessary information. At this stage, the information gathering mechanism is activated, and a chatbot dialogue with the user begins. The device receives and processes this information, extracting customer needs necessary for creating the proposal.

[0627] Next, the collected dialogue information is sent to a server and processed by an analysis tool using natural language processing. Here, the customer's true needs and concerns are extracted, and based on this, specific proposals are automatically designed by a generation tool.

[0628] After the proposal is generated, the server uses verification tools to scrutinize its contents. Grammar checks and data integrity checks are performed, and corrections are automatically made as needed. Through this process, high-quality and accurate proposals are generated.

[0629] The generated proposal is exported in PDF or Word format and provided to the user via their device. The user can download the proposal via a link.

[0630] As a concrete example, consider a case where a product vendor needs a proposal for a new product. The user inputs needs such as "it must include the latest technological features" and "I would like a quote within a specific budget." This information is collected and analyzed, and a proposal with the most suitable content is automatically generated. In this way, it becomes possible to quickly meet customer needs while maintaining the quality and accuracy of the proposal.

[0631] Furthermore, user feedback is acquired through the system's learning mechanisms, contributing to improvements in the accuracy of future proposal generation. This feedback process continuously enhances the personalization and refinement of proposals.

[0632] The following describes the processing flow.

[0633] Step 1:

[0634] The user accesses the proposal document request page from their device and enters the required information. This information is used as initial data for creating the proposal.

[0635] Step 2:

[0636] The device initiates a chatbot conversation based on the input information. Here, the information gathering tool asks standardized and adaptive questions to elicit the user's interests and needs.

[0637] Step 3:

[0638] Users respond to the chatbot's questions, providing detailed information about their needs and preferences. The device collects this information in real time.

[0639] Step 4:

[0640] On the server, the collected dialogue information is processed by analysis tools. Natural language processing is used to analyze the text data and identify the user's requests and objectives.

[0641] Step 5:

[0642] Based on the analysis results, the server automatically generates a proposal using a generation method. Here, information is organized according to a standardized format based on identified needs, and the optimal proposal content is constructed.

[0643] Step 6:

[0644] The server uses verification tools to scrutinize the content of the generated proposal. It checks for grammatical errors and data inconsistencies and makes corrections as needed.

[0645] Step 7:

[0646] The proposal exported from the server is provided to the user via the terminal. The user can download the proposal from the specified link.

[0647] Step 8:

[0648] The user provides feedback on the provided proposal. The device collects this feedback and sends it to the server.

[0649] Step 9:

[0650] The server analyzes feedback through learning mechanisms and uses it to generate future proposals. This allows the system to continuously improve its accuracy and enhance its ability to generate proposals that better meet customer needs.

[0651] (Example 1)

[0652] 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".

[0653] In traditional proposal creation processes, it was difficult to quickly generate proposals that accurately reflected the specific needs of the customer, and there was a need to work efficiently while maintaining the quality and accuracy of the documents. Furthermore, there was insufficient automation of proposal revisions and quality improvement through the use of user feedback.

[0654] 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.

[0655] In this invention, the server includes acquisition means, analysis means, generation means, and transmission means. This enables automation of all processes from information collection to proposal generation and delivery, making it possible to provide proposals that quickly and accurately meet customer needs. Furthermore, verification means and learning means enable improvement of proposal quality and system performance.

[0656] "Acquisition means" refers to a device or software that has the function of receiving information provided by the user and collecting information through dialogue as needed.

[0657] "Analysis means" refers to a device or program that applies natural language processing to acquired information and has the function of extracting and structuring the user's requests and needs.

[0658] "Generation means" refers to a device or algorithm that has the function of automatically generating a proposal document based on the requirements extracted through analysis.

[0659] "Transmission means" refers to a device or process that converts the generated proposal document into an electronic document format and provides it to the user using appropriate communication means.

[0660] A "verification tool" is a device or software that has the function of verifying the content of the generated proposal document, checking the quality and consistency of the document, and making corrections automatically as needed.

[0661] A "learning tool" is a device or function that acquires evaluation information and feedback from users and uses that information to accumulate and utilize data in order to improve the overall performance and accuracy of the system.

[0662] Embodiments of this invention are described below.

[0663] First, the user uses their device to access the proposal document request page and enters their needs and requirements. During this input stage, the collected information is temporarily stored on the device. At this point, the data collection system works to organize the necessary information.

[0664] Next, the terminal is responsible for sending the entered information to the server. The terminal converts the text data into a standardized format, making it easier for the server to process.

[0665] The server then performs analysis based on the received information. Within the server, a generative AI model for natural language processing (such as GPT-3) is used. This model is used to analyze the customer's true needs and requirements from the input text, and the extracted data is used to refine the proposed solutions.

[0666] For example, if a product vendor wants to propose a new product to a customer, the user inputs needs such as "it must include the latest energy-saving technology" or "we want the best solution within our annual budget." This information is analyzed by a model, which then automatically generates appropriate proposals.

[0667] Through the generation process, this data is automatically assembled into a proposal format on the server. During this process, the server performs grammar checks and data integrity verification. Grammarly or similar grammar checking software may be used. After the proposal is completed, it is converted to PDF or Word format.

[0668] Subsequently, the server sends the proposal to the user via a transmission method. Specifically, a download link is generated and provided to the user through their device. The user can use this link to obtain and review the completed proposal.

[0669] Examples of prompt statements include "include the latest technical features" and "request an estimate within a specific budget."

[0670] This overall system flow allows users to receive fast and highly accurate services, and ensures that proposals are generated and delivered smoothly.

[0671] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0672] Step 1:

[0673] The user accesses the proposal document request page using their device. The user enters specific needs and requirements, which the device receives. The input is text data about the needs and requests, and the output is temporarily stored on the device as formatted information. The device collects the entered information and converts it into a specified format.

[0674] Step 2:

[0675] The terminal sends organized information to the server. The input is formatted data about the user's needs, and the output is data packets for the server to receive. In this process, the terminal performs specific actions to standardize the information and make it a format that is easy for the server to process.

[0676] Step 3:

[0677] The server begins analyzing the received information. The input is needs data sent from the terminal, and the output is extracted customer requests and concerns. The server applies a generative AI model (e.g., GPT-3) to analyze the text data, extract the necessary information, and structure it.

[0678] Step 4:

[0679] Based on the analysis, the server automatically generates specific proposal content using a proposal generation method. The input is the analyzed data, and the output is a draft-level proposal document. In this operation, the server performs calculations to assemble the proposal to meet the extracted needs.

[0680] Step 5:

[0681] The server validates the generated proposal document and automatically makes corrections as needed. The input is a draft-level proposal document, and the output is a completed proposal document. Here, the server performs specific actions such as grammar checks and data integrity verification, and makes corrections if necessary.

[0682] Step 6:

[0683] The server converts the completed proposal document into an appropriate file format (e.g., PDF, Word) and sends it to the terminal. The input is the completed proposal document, and the output is a downloadable file link sent to the user. The server converts the document and provides the proposal document in a format that is easily accessible to the user.

[0684] Step 7:

[0685] The user clicks a link provided through their device to download the completed proposal document. The input is the download link, and the output is the proposal document saved on the user's device. The user then reviews the proposal document on their device and performs specific actions to confirm that the content meets their final needs.

[0686] (Application Example 1)

[0687] 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".

[0688] In information processing systems, there is a need to build a system that can automatically generate high-quality advertising proposals that quickly respond to user needs, and that allows for rapid review and revision of proposal content. Furthermore, a challenge is to continuously improve the accuracy of proposals by utilizing feedback obtained from users.

[0689] 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.

[0690] In this invention, the server includes data acquisition means, data analysis means, and generation function means. This makes it possible to collect and analyze necessary data from interactions based on user input information and to quickly supply automatically generated, high-quality advertising proposals. Furthermore, the system can continuously improve its accuracy by scrutinizing the generated proposals, automatically making necessary corrections, and utilizing user feedback.

[0691] A "data acquisition method" is a means that has the function of collecting necessary data by engaging in dialogue based on information input from the user.

[0692] "Data analysis means" refers to a method that analyzes collected dialogue content using natural language processing and performs the function of identifying user needs.

[0693] A "generation function means" is a means equipped with the function of automatically generating and outputting advertising proposals based on specified needs.

[0694] The "proofreading function" is a feature that scrutinizes the content of the generated advertising proposal and automatically makes corrections as needed.

[0695] A "learning function" is a means of improving the accuracy of the system's generation functions by acquiring and accumulating feedback from users.

[0696] A "server" is a central device that performs information processing, including means for data acquisition, data analysis, and generation.

[0697] To implement this invention, a server, terminal, and user must cooperate to form an information processing system, with each element playing a specific role. First, the user uses the terminal to input details of an advertising campaign in a marketing activity. The input information is collected by a data acquisition means.

[0698] Next, the server uses data analysis tools to analyze the collected data, leveraging natural language processing. In this process, a generative AI model is used to identify user needs. Based on the analyzed needs, the generative function automatically generates an advertising proposal and outputs it to the terminal.

[0699] The generated advertising proposals are reviewed by the server's proofreading function and automatically corrected as needed. This ensures that users receive high-quality and accurate advertising proposals.

[0700] User feedback is collected by the server and stored in the system through a learning function. This feedback is used to improve the accuracy of the generation function, enabling more precise proposals in the creation of future advertising proposals.

[0701] As a concrete example, consider a case where you want to advertise a new smartphone case to women in their 20s. In this case, the user inputs the following prompt into the system: "I am planning an advertising campaign for a smartphone case targeting women in their 20s. I want to emphasize a stylish and practical design. The objective of the campaign is to increase brand awareness, and the budget is 300,000 yen. Based on this information, please create an appropriate advertising proposal." Based on this, the server generates an advertising proposal.

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] Users input detailed information about advertising campaigns necessary for marketing activities via their devices. This input includes target audience, campaign objectives, and budget information. This data is collected by the system's data acquisition mechanisms.

[0705] Step 2:

[0706] The server processes the collected input data using data analysis tools. Specifically, it uses natural language processing to analyze and identify user needs within the input data. In this process, a generative AI model is utilized to extract and analyze data based on the input prompt sentences.

[0707] Step 3:

[0708] The server automatically generates advertising proposals using generation functions based on the needs identified by data analysis. In this generation process, the server constructs the optimal content for the advertising proposal based on the user's input data and analysis results, and outputs it to the terminal.

[0709] Step 4:

[0710] The generated advertising proposals are automatically reviewed by the server's proofreading function. This step includes grammatical checks and information consistency verification, with automatic corrections made as needed. This ensures the quality of the advertising proposals provided to users.

[0711] Step 5:

[0712] The user receives the generated advertising proposal and sends feedback back to the server. This feedback information is stored in the system through a learning function. This data is used to improve the accuracy of advertising proposals in subsequent generation processes. This continuously improves the system's response quality.

[0713] 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.

[0714] This invention combines an emotion engine with an information processing system, providing more personalized results by utilizing emotion recognition in the process of automatically generating proposals through interaction with the user. The system consists of three elements: a server, a terminal, and a user, each of which performs the following processes.

[0715] The user accesses the information request page using their device and begins entering information. The device activates information gathering mechanisms via a chatbot to collect necessary information from the user. In this interaction, the device transmits the text data entered by the user to an emotion engine based on voice and expressions.

[0716] On the server, this emotion engine analyzes the user's emotions. Combining natural language processing and emotion analysis techniques, it detects emotional characteristics such as positive, negative, and neutral from the dialogue. The identified emotions are then used to identify needs through analytical methods.

[0717] The server automatically generates proposals using generation methods based on these needs and emotional states. Emotional information is reflected in and optimized for the tone and content of the proposals. For example, if the user is feeling anxious, the proposal may include more information about guarantees.

[0718] After the proposal is generated, the server scrutinizes its contents using verification tools. It checks for errors and logical consistency. The terminal then provides the generated proposal to the user, who can download it via a link.

[0719] As a concrete example, consider a scenario where a user requires a proposal when introducing a new product. The user communicates their desired features, price range, and implementation timeline via chat, while an emotion engine detects emotions such as tension and anticipation. In this case, the server generates a proposal with recommended support plans, thereby reducing the user's anxiety and supporting their purchasing decision.

[0720] User feedback is sent to the server, processed through a learning mechanism, and incorporated into the AI ​​model. This feedback process allows for continuous improvement in the personalization and accuracy of future proposals.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The user accesses the document request page from their device and enters the required information. This information includes specific requests and preferences related to the proposal.

[0724] Step 2:

[0725] The terminal initiates a conversation with the user using a chatbot. Questions are asked to more accurately elicit the user's needs and specific requirements through information gathering mechanisms.

[0726] Step 3:

[0727] The device sends the text data of the conversation to the emotion engine. The emotion engine analyzes the user's input and uses natural language processing to identify emotional characteristics. This identification includes emotional categories such as positive, negative, and neutral.

[0728] Step 4:

[0729] The server integrates the emotional data received from the interaction with the requests obtained through analysis to identify the user's specific needs. For example, if anxiety is indicated, the server prioritizes information that provides greater reassurance.

[0730] Step 5:

[0731] The server's generation method automatically generates proposals tailored to identified needs and emotional states. This process utilizes emotional information to adjust the content and tone of the proposals. For example, it might include guarantees and support information to provide reassurance.

[0732] Step 6:

[0733] The server uses verification tools to check the generated proposal for typographical errors, grammatical mistakes, and logical inconsistencies. If problems are found, necessary automatic corrections are performed.

[0734] Step 7:

[0735] The terminal provides the user with the generated proposal. The user can download the proposal from a designated link and review its contents.

[0736] Step 8:

[0737] Users evaluate proposals and provide feedback. The device collects this feedback and sends it to the server.

[0738] Step 9:

[0739] The server uses learning mechanisms to analyze feedback and incorporate it into the AI ​​model. This improves the proposal generation process and enhances personalization for future generations.

[0740] (Example 2)

[0741] 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".

[0742] In modern information processing systems, accurately understanding user needs and automatically generating effective proposals based on them is difficult. Furthermore, creating proposals that take user emotions into account requires accurately analyzing user emotions and providing personalized content that reflects them, but conventional systems do not adequately handle this process.

[0743] 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.

[0744] In this invention, the server includes means for conducting a dialogue based on input information from the user and detecting emotions from voice and expressions; means for analyzing the dialogue content using natural language processing and sentiment analysis to identify the user's emotions; and means for automatically generating a proposal based on the identified needs and emotions, and outputting it while reflecting the emotional information. This makes it possible to automatically generate highly personalized proposals that meet the user's needs and emotions.

[0745] "Input information" refers to data provided by the user, including the content necessary for generating the proposal.

[0746] "Dialogue" is the process of information exchange between the user and the system, and a means of eliciting the user's needs and emotions.

[0747] "Means of detecting emotions" refers to technologies and processes for identifying a user's psychological state from their voice and expressions.

[0748] "Natural language processing" refers to the technology that enables computers to interpret and analyze human language.

[0749] "Sentiment analysis" refers to a technology that analyzes a user's psychological state from their text and voice data.

[0750] A "proposal" refers to a document containing plans and recommendations that are generated based on the user's needs and feelings and provided to the user.

[0751] "Personalized content" refers to information tailored to the individual user's needs, emotions, and circumstances.

[0752] This invention begins when a user accesses a document request page using a terminal. The terminal collects information entered by the user, and this information, along with voice and expression data, is transmitted to an emotion engine. This emotion engine combines natural language processing and sentiment analysis techniques to identify emotional characteristics such as positive, negative, and neutral from the user's text data.

[0753] The server identifies the user's specific needs based on data analyzed by the emotion engine. This identification process utilizes a generative AI model, which generates the user's expected results based on prompt text. The server then automatically generates a proposal based on the needs and identified emotions. The proposal's content is adjusted based on emotional information, ensuring it is delivered in a tone appropriate to the user's psychological state.

[0754] Once the proposal is generated, the server analyzes it through verification mechanisms to check for errors and logical inconsistencies. After this thorough review, the proposal is presented to the user via their terminal. The user can then download the proposal via a link.

[0755] A concrete example is when a user needs a proposal when introducing a new product. The user begins inputting information on their device, and a chatbot provides details such as desired features, budget, and implementation timing. In this situation, an emotion engine may detect the user's anxiety. Based on this, the server generates a proposal that emphasizes guarantees, reducing anxiety and supporting the implementation decision.

[0756] An example of a prompt message is: "Please create a proposal outlining the support needed when introducing a new product. The user is interested in cost-effectiveness but seems concerned about the smoothness of the implementation." In this way, the present invention makes it possible to efficiently and accurately generate proposals that meet the user's needs.

[0757] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0758] Step 1:

[0759] The user accesses the information request page using their device and enters the required information. The device collects the data entered by the user and sends it to the server as input information. This input includes detailed information related to the user's request.

[0760] Step 2:

[0761] The device transmits user input text, its expression, and audio data to an emotion analysis module via an emotion engine. This process uses natural language processing techniques to analyze emotions and generate emotional characteristics such as positive, negative, and neutral as output.

[0762] Step 3:

[0763] The server uses emotional data obtained from the emotion engine and information collected about user needs to identify user needs using a generative AI model. From this input data, it generates prompt sentences and outputs the identified needs.

[0764] Step 4:

[0765] The server utilizes a generative AI model based on identified needs and sentiment data to automatically generate proposal content. This process involves tone and content adjustments that reflect sentiment information, resulting in a personalized proposal output.

[0766] Step 5:

[0767] The server sends the generated proposal to a verification system. Here, errors are detected and the logic of the proposal is checked. The verified proposal is then output and finally sent to the terminal.

[0768] Step 6:

[0769] The terminal receives the proposal sent from the server and provides it to the user. The proposal is provided as a download link, and the user can review this output and download and save it as needed.

[0770] Step 7:

[0771] The user reviews the proposal and provides feedback. The terminal sends this feedback as input to the server. The server uses learning mechanisms to store this feedback as data to improve the accuracy of future proposal generation processes.

[0772] (Application Example 2)

[0773] 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".

[0774] Conventional information processing systems provide proposals that are generated without considering the user's emotions, resulting in insufficient personalization based on the user's psychological state. As a result, proposals may not meet the user's expectations or needs. This problem can increase user anxiety and decrease purchasing intent, especially in fields where a sense of security is crucial, such as security services.

[0775] 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.

[0776] In this invention, the server includes means for collecting user input information as audio and visual data and analyzing emotional states in real time; means for analyzing dialogue content and emotional characteristics using natural language processing and identifying user needs; and means for automatically generating proposals based on the identified needs and emotions, and outputting them while reflecting emotional elements. This makes it possible to provide optimal proposals that are tailored to individual needs while being attentive to the user's emotions.

[0777] A "user" is an individual who receives a proposal using an information processing system, and whose emotional state is the subject of analysis.

[0778] "Input information" refers to data that users provide to the system, and includes various formats such as audio, visual data, and text.

[0779] "Audio and visual data" refers to audio information that records the user's speech, and visual information related to the user's facial expressions and other physical movements.

[0780] "Emotional state" refers to a user's psychological or emotional condition and is categorized as positive, negative, or neutral.

[0781] "Real-time analysis methods" refer to technologies that process data acquired instantaneously and analyze users' emotions on the spot.

[0782] "Natural language processing" is a technology that enables computers to understand and process human language, and is used for analyzing text data.

[0783] "Emotional characteristics" are attributes that indicate the type and intensity of a user's emotions, as identified through emotion analysis.

[0784] "Needs" refer to the requests and demands that users have, and they influence the content of the suggestions that the system should provide.

[0785] "Automatic generation" refers to the process by which a system generates proposals based on data without requiring human intervention.

[0786] "Emotional elements" refer to the psychologically impactful information and tone included in the proposal, which are adjusted according to the user's emotions.

[0787] In the system implementing this invention, a server efficiently processes the user's voice and visual data and generates a proposal. The main hardware includes smart glasses and smartphones, which are worn by the user. These devices are equipped with cameras and microphones to capture the user's voice and facial expressions in real time.

[0788] Data collected from smart glasses and smartphones is sent to a server. The server uses this data to run software for sentiment analysis. Typical software includes a sentiment analysis engine and a natural language processing unit. This software classifies the user's emotional state as positive, negative, or neutral, and based on the results, analyzes the user's needs in detail.

[0789] Furthermore, the server uses a generation mechanism to create personalized proposals based on the user's emotional state. The generation AI model is used to apply emotional elements to the proposal to address the user's emotional needs. For example, if a user feels anxious while considering security services, the proposal will include specific success stories and guarantee details to alleviate that anxiety.

[0790] An example of a prompt message could be: "If the user's current emotion is detected as 'anxiety,' generate a proposal that highlights successful safety measures and guarantee details." In this way, it is possible to provide more personalized proposals based on the user's emotions.

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The device collects audio and visual data from the user in real time. Input consists of the user's speech and facial expressions, captured through the device's camera and microphone. Output is data transfer to the server.

[0794] Step 2:

[0795] The server inputs data received from the terminal into an emotion analysis engine to analyze the user's emotions. Here, data processing is performed based on audio and image data to identify the user's emotional state (positive, negative, neutral, etc.). The output is the analysis result regarding the user's emotional state.

[0796] Step 3:

[0797] The server uses a natural language processing unit to analyze the dialogue. The input is the user's utterances, and semantic analysis is performed to identify their needs. The output is the analyzed user needs information.

[0798] Step 4:

[0799] The server integrates emotional state and needs information and generates prompt sentences necessary for proposal generation. Prompt sentences are created for input into the generation AI model. These prompt sentences are then output.

[0800] Step 5:

[0801] The server uses a generative AI model to automatically generate personalized proposals based on prompt text. The input is the prompt text, and the output is a proposal with emotionally appropriate adjustments.

[0802] Step 6:

[0803] The terminal displays the generated proposal to the user. The output is the presented proposal, which the user reviews and provides feedback on.

[0804] Step 7:

[0805] Users send feedback on proposals to the server via their devices. The input is user feedback. The server uses this feedback to store it as training data and improve the accuracy of future proposal generation.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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 to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] An information gathering method that conducts dialogue based on user input,

[0830] An analytical method that uses natural language processing to analyze dialogue content and identify user needs,

[0831] A generation means that automatically generates and outputs a proposal based on identified needs,

[0832] An information processing system that includes this.

[0833] (Claim 2)

[0834] The information processing system according to claim 1, further comprising verification means for scrutinizing the contents of the generated proposal and automatically correcting it as necessary.

[0835] (Claim 3)

[0836] The information processing system according to claim 1, further comprising a learning means for improving the accuracy of a generation means by obtaining user feedback and accumulating that information.

[0837] "Example 1"

[0838] (Claim 1)

[0839] A means of acquiring information that allows for dialogue based on information from users,

[0840] An analysis means that analyzes dialogue information using natural language processing and extracts user requests,

[0841] A generation means for automatically generating a proposal document based on extracted requirements,

[0842] A transmission means that converts the generated proposal document into an electronic document format and provides it,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, further comprising verification means for verifying the information in the generated proposal document and automatically making corrections as necessary.

[0846] (Claim 3)

[0847] The system according to claim 1, further comprising a learning means for improving the performance of a generation means by acquiring evaluation information from users and storing that data.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] A data acquisition method that conducts dialogue based on user input information,

[0851] A data analysis method that uses natural language processing to analyze dialogue content and identify the necessity of entities,

[0852] A generation function means that automatically generates a proposal based on identified needs and outputs it as an advertising plan,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, which includes a proofreading function that scrutinizes the content of the generated advertising proposal and automatically makes corrections upon request.

[0856] (Claim 3)

[0857] The system according to claim 1, which includes a learning function that improves the accuracy of the generation function by obtaining feedback from users and accumulating that information.

[0858] "Example 2 of combining an emotion engine"

[0859] (Claim 1)

[0860] A means of conducting a dialogue based on user input and detecting emotions from voice and expressions,

[0861] A means of analyzing dialogue content using natural language processing and sentiment analysis to identify the user's emotions,

[0862] A means for automatically generating proposals based on identified needs and emotions, and outputting them while reflecting emotional information,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, further comprising means for scrutinizing the contents of the generated proposal and making automatic corrections as necessary.

[0866] (Claim 3)

[0867] The system according to claim 1, further comprising means for improving the accuracy of proposal generation by obtaining user feedback and accumulating that information.

[0868] "Application example 2 when combining with an emotional engine"

[0869] (Claim 1)

[0870] A means of collecting user input information as audio and visual data and analyzing emotional states in real time,

[0871] A means of analyzing dialogue content and emotional characteristics using natural language processing to identify user needs,

[0872] A means of automatically generating proposals based on identified needs and emotions, and outputting them while reflecting emotional elements,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising a function to scrutinize the content of the generated proposal, optimize it according to the emotional state, and make automatic corrections as necessary.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising a learning function that improves the accuracy of emotion analysis and generation means by obtaining user feedback and accumulating that information. [Explanation of Symbols]

[0878] 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. An information gathering method that conducts dialogue based on user input, An analytical method that uses natural language processing to analyze dialogue content and identify user needs, A generation method that automatically generates and outputs a proposal based on identified needs, An information processing system that includes this.

2. The information processing system according to claim 1, further comprising verification means for scrutinizing the contents of the generated proposal and automatically correcting it as necessary.

3. The information processing system according to claim 1, further comprising a learning means for improving the accuracy of the generation means by obtaining user feedback and accumulating that information.

Images