system

Abstract

We provide the system. [Solution] A means of receiving voice or text input from a user and sending it to a server, A means of performing natural language analysis on user input received by the server to identify the user's intent, A server provides a means for acquiring and analyzing users' past transaction data and market information, A server provides means for generating an asset management plan or investment advice based on the analysis results, A means of sending the generated advice to the user's terminal and displaying it to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] Many users lacking financial literacy find it difficult to formulate appropriate asset management and investment plans. Also, conventional financial advisory services often require high-level expertise and it is difficult to obtain quick and personalized advice. As a result, users have financial anxiety and there is a problem that they cannot feel secure in asset management.

Means for Solving the Problems

[0005] This invention provides a system that receives user input and uses a generative AI to perform natural language processing to identify the user's asset management and investment needs. Subsequently, it acquires and analyzes the user's past transaction data and the latest market information to generate an individually optimized asset management plan or investment advice. This allows users to easily receive accurate advice, improve their financial knowledge, and reduce financial anxiety.

[0006] "User input" refers to instructions or requests that a user sends via a device in voice or text format.

[0007] A "server" refers to a computer system that receives user input and performs analysis and data processing using generating AI.

[0008] "Natural language processing" refers to the process of using generative AI to understand the user's intent and the information they are seeking from input text.

[0009] "Transaction data" refers to historical information about financial transactions that a user has made in the past.

[0010] "Market information" refers to data such as trends and price movements in the current financial markets.

[0011] "Generative AI" refers to artificial intelligence systems that use machine learning to perform inferences and predictions from data.

[0012] An "asset management plan" refers to a strategy or plan formulated to efficiently manage a user's assets.

[0013] "Investment advice" refers to suggestions and proposals provided based on the user's investment strategy.

[0014] A "user terminal" refers to an electronic device used by a user to input information or receive results. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Also, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices 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.

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention is a system that provides asset management and investment advice using a device that the user uses in their daily life. The user inputs their financial situation and questions into the device via voice or text. The device converts this into text data and sends it to the server.

[0037] The server receives this data and uses generative AI to perform natural language processing. After identifying the user's intent, it accesses trading and market databases to query and analyze the user's past trading history and the latest market information. This analysis automatically generates an asset management plan and investment advice that best suits the user's needs.

[0038] The generated plans and advice are sent to the user's device as text messages and displayed to them. Based on this information, the user can develop a concrete asset management plan. Furthermore, they can obtain more detailed information by asking further questions as needed.

[0039] For example, if a user enters "I want to know about future investment strategies," the server analyzes past investment trends and the latest market developments and generates advice such as "Conservative bond investments are safe in the current market." This allows users to obtain concrete action plans and improve their financial literacy.

[0040] This system allows users to easily deepen their understanding of asset management and conduct financial activities with peace of mind.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters questions or requests using voice or text via the device. In the case of voice input, the device uses speech recognition technology to convert it into text data and prepares it for transmission to the server.

[0044] Step 2:

[0045] The terminal sends text data from the user to the server. The server receives the data and prepares it for the next analysis.

[0046] Step 3:

[0047] The server uses generative AI to perform natural language analysis on text data received from users, identifying the intent behind the user's questions and the information they are seeking. It also determines whether additional information is needed to clarify any ambiguities.

[0048] Step 4:

[0049] The server searches the database to retrieve the user's past transaction data and related market information. During this process, it extracts the necessary data based on the identified user's needs.

[0050] Step 5:

[0051] The server analyzes the data acquired using generative AI and generates an asset management plan or investment advice best suited to the user's needs. Various statistical analyses and predictive algorithms are applied at this stage.

[0052] Step 6:

[0053] The server converts the generated advice into text format and sends it to the user's connected device.

[0054] Step 7:

[0055] The terminal displays advice received from the server to the user. The user can view the presented information and develop a concrete action plan. Furthermore, if they have further questions, they can ask them again.

[0056] (Example 1)

[0057] 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."

[0058] For users, efficiently obtaining information on asset management and investment, and receiving advice tailored to their individual needs, is not easy. In particular, many users feel anxious due to market changes and their own lack of financial knowledge. Therefore, it is necessary to provide a system that addresses these challenges and allows users to manage their assets with peace of mind.

[0059] 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.

[0060] In this invention, the server includes means for acquiring voice or text input from a user and transmitting it to a computer; means for the computer to perform natural language analysis on the received user input and clarify the user's purpose; and means for the computer to acquire and analyze the user's past transaction records and market information. This makes it possible to provide the user with an optimal asset management plan and investment advice tailored to their individual needs and current market conditions.

[0061] "Users" refers to individuals or organizations seeking information and advice regarding asset management and investment.

[0062] "Voice or text input" refers to voice or text data used by users to send questions or information related to asset management or investment to their devices.

[0063] A "computer" refers to a central processing system that receives input from users and performs data analysis, generates advice, and so on.

[0064] "Natural language processing" refers to the process of understanding the intent behind text data from users and converting it into a format that a computer can understand.

[0065] "Clarifying the objective" refers to the process by which a computer analyzes the information it receives from a user and identifies the specific information or advice the user is seeking.

[0066] "Transaction records" refer to historical data of financial transactions conducted by a user in the past.

[0067] "Market information" refers to data that shows the current situation and trends in financial markets.

[0068] "Analyzing" refers to the process of generating optimal asset management plans and investment advice based on acquired data.

[0069] An "asset management plan" refers to a specific strategy proposed by a computer to effectively manage a user's assets.

[0070] "Investment advice" refers to specific suggestions provided by a computer to help users effectively increase their assets.

[0071] "Terminal" refers to a communication device used by a user for voice or text input.

[0072] This invention is a system that provides users with advice on asset management and investment. Users can input their financial situation and questions through a device they use daily, either by voice or text. Specifically, devices such as smartphones and personal computers are used, and when voice input is performed, voice recognition software (e.g., a general voice recognition API) performs the function of converting it into text data.

[0073] The terminal has the function of sending the converted text data to the server, which processes the received data using advanced natural language processing. In this analysis, a generative AI model (e.g., a general natural language processing model) is used to identify the specific asset management information and investment advice that the user is seeking.

[0074] The server then accesses a database that stores the user's past transaction records and current market information. In this step, it comprehensively analyzes the acquired data using a database management system and data analysis tools (e.g., a general data analysis library). Based on the results of this analysis, the server generates an optimal operational plan and advice tailored to individual needs and market conditions.

[0075] The generated advice is sent to the user's device as a text message and presented to them. This allows the user to develop a concrete investment strategy and improve their financial literacy. Furthermore, if the user asks another question, they can enter "I want to know about future investment strategies" as a prompt, and the system will analyze past investment trends and the latest market trends to provide specific suggestions such as "Conservative bond investments are safe in the current market." In this way, users can receive support to conduct financial activities with confidence.

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

[0077] Step 1:

[0078] Users input questions about asset management and investment into the terminal in either voice or text format. The input data includes specific questions, such as "I want to know about future investment strategies." When voice input is received, the terminal uses speech recognition software to convert the voice into text. This conversion generates text data.

[0079] Step 2:

[0080] The terminal sends the generated text data to the server. This data is transmitted via HTTP request. The server receives the text data and saves its contents in preparation for the next processing step.

[0081] Step 3:

[0082] The server performs natural language processing using a generative AI model based on the received text data. Specifically, it uses generative AI models such as the GPT series or BERT to extract the user's intent from the text data. Through this process, the server can identify what information the user is looking for and stores the results internally.

[0083] Step 4:

[0084] Based on the analyzed intent, the server accesses a database containing the user's past transaction records and current market information. The server retrieves this information using SQL queries and other methods, preparing it for analysis. The retrieved data is collected in a way that aligns with the user's intent.

[0085] Step 5:

[0086] The server performs data analysis using the acquired data. It uses data analysis libraries such as Python's Pandas and NumPy to numerically analyze past trading trends and market movements. Based on the results, the server generates an optimal asset management plan or investment advice. For example, it might generate a specific suggestion such as, "In the current market, conservative bond investments are safe."

[0087] Step 6:

[0088] The server sends the generated advice as a text message to the terminal. The terminal displays the received text message and presents it to the user. The user can then use this advice to create their own investment plan. If the user requires further information, they can ask new questions to receive additional advice.

[0089] (Application Example 1)

[0090] 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."

[0091] In recent years, there has been a growing demand for accurate and timely advice regarding personal asset management and investment strategies. However, it is not easy for ordinary households to obtain this information appropriately without specialized knowledge. Therefore, there is a need for a method that uses voice input to provide optimal investment advice tailored to individual asset situations.

[0092] 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.

[0093] In this invention, the server includes means for recognizing voice input from a user and converting it into data, means for transmitting the converted data to an external processing unit, and means for the external processing unit to perform natural language analysis on the received user input and identify the user's intent. This enables an assistant device installed in the home to provide the user with timely and personalized asset management plans and investment advice.

[0094] A "user" is an individual who seeks information related to asset management and investment by inputting voice or data.

[0095] "Voice input" is a method of communicating with a system by having the user speak.

[0096] "Data conversion" is the process of analyzing voice input and converting it into a format that can be processed by a machine.

[0097] An "external processing device" is a device, including a server, that analyzes and processes voice input data.

[0098] "Natural language processing" is a technology that analyzes a user's voice input to understand their intentions and requests.

[0099] "Identifying intent" means identifying user requests and desires through natural language processing.

[0100] "Information analysis" is a method of generating appropriate advice based on the user's past trading data and market information.

[0101] An "asset management plan" is the process of developing a strategy for efficiently managing a user's assets.

[0102] "Investment advice" refers to providing information to guide users in finding the most appropriate investment strategy.

[0103] A "display device" is a device that visually presents generated advice and information to the user.

[0104] In implementing this invention, the user provides voice input regarding asset management and investment advice to a home-use support device. The support device is equipped with a voice recognition function, which is implemented using the Google® Cloud Speech-to-Text API. The voice information is converted into digital text and sent to the server.

[0105] The server receives text data and analyzes the user's intent through Azure's natural language processing service. This provides specific analytical information to address the user's questions. Based on the analysis results, the server uses data processing libraries such as NumPy and Pandas to analyze the user's past trading data and the latest market information. This generates asset management plans and investment advice tailored to the individual's situation.

[0106] The generated advice is sent to the display unit of the support device, allowing the user to review it visually. This is implemented using the LINE Messaging API. Users can use this information to plan their asset management. Furthermore, by asking repeated questions, they can obtain more detailed advice, allowing for flexible responses tailored to the user's needs.

[0107] For example, if a user asks the support device, "I want to know the right investment methods to prepare for my children's education expenses," the server can analyze the user's trading history and market conditions and provide specific advice from multiple perspectives, such as, "Consider investing in a safe, long-term index fund."

[0108] The AI ​​generation model uses prompts to respond accurately and quickly to user requests. An example of a prompt might be: "The user is seeking advice on saving for education expenses. Please provide appropriate investment advice considering the user's past trading history and market conditions." This prompt sets the context for the AI ​​to generate accurate advice.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The user voice-inputs questions into the assistive device, and the voice information is captured by the terminal. The terminal uses the Google Cloud Speech-to-Text API to convert the voice into digital text. The input is the user's voice information, and the output is data in text format.

[0112] Step 2:

[0113] The terminal sends the converted text data to the server. The server receives this text data and uses Azure's natural language processing service to analyze the text and identify the user's intent. The input is the text data, and the output is the analyzed user intent. In this step, the server performs syntactic and semantic analysis of the text.

[0114] Step 3:

[0115] Based on the analyzed intent, the server retrieves the user's past trading data and market information. Using this information, the server performs statistical and evaluative data analysis with NumPy and Pandas. The input is the user's trading history and market data, and the output is the analysis results and their interpretation. Here, the server performs data aggregation and pattern recognition.

[0116] Step 4:

[0117] The server generates appropriate asset management plans and investment advice through a generative AI model based on the analysis results. In this process, prompts are used to effectively guide the AI ​​model's responses. The input consists of the analysis results and appropriate prompts, while the output is the generated advice. Through this process, the server provides instructions to the model to generate the optimal solution.

[0118] Step 5:

[0119] The server sends the generated advice back to the device using the LINE Messaging API. The device then displays this information to the user. The input is the generated advice, and the output is the advice provided to the user visually or audibly. The device is responsible for displaying the received text in the most appropriate format.

[0120] 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.

[0121] This invention combines an emotion engine with a system that receives user voice or text input, analyzes its content, and provides asset management and investment advice. The user inputs financial questions or instructions using a terminal. The terminal then transmits the user input to the server.

[0122] The server performs natural language analysis on received user input to identify the user's intent. Furthermore, it uses an emotion engine to recognize the user's emotional state based on the user's tone of voice and text wording. For example, it can identify emotional states such as tension, anxiety, and relief.

[0123] Based on this information, the server retrieves and analyzes the user's past trading data and market information. Taking into account the user's emotional state, it generates an optimal asset management plan or investment advice. In this process, if the user is feeling anxious, the server can adjust the recommendations accordingly, such as recommending a lower-risk plan.

[0124] The generated advice is sent to the user's device in text format and displayed to the user. Users can utilize this information to manage their assets in a more emotionally conscious way. Furthermore, new emotional data can be collected as user feedback to improve the accuracy of the advice.

[0125] For example, if a user enters "I'm a little worried about future investments," the server uses an emotion engine to recognize this feeling of "anxiety" and suggests a conservative investment strategy that is appropriate for it. The user can then use the suggested advice to make investment decisions with greater confidence.

[0126] This system configuration enables flexible asset management and the provision of financial information that takes into account the user's emotions.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user enters questions or requests regarding asset management via voice or text through the device. In the case of voice input, the device converts it to text using a speech recognition device and prepares to send the data to the server.

[0130] Step 2:

[0131] The terminal sends user input data to the server. The server receives this data and prepares for the next analysis process.

[0132] Step 3:

[0133] The server uses a generative AI to perform natural language analysis on the received user input and identify the user's intent. Based on the analysis results, it estimates what information is needed.

[0134] Step 4:

[0135] The server uses an emotion engine to analyze the user's emotional state from their voice tone and text context. It identifies emotions such as tension, anxiety, and relief to understand the user's state.

[0136] Step 5:

[0137] The server retrieves the user's past transaction data and market information from the database. Based on the identified user's needs and emotional state, it extracts relevant data.

[0138] Step 6:

[0139] The server integrates emotional states and data analysis results to generate an optimal asset management plan or investment advice for the user. For example, if anxiety is detected, it will suggest low-risk options.

[0140] Step 7:

[0141] The server formats the generated advice into a text message and sends it to the user's terminal.

[0142] Step 8:

[0143] The device displays advice received from the server to the user. Based on the provided information, the user can develop a concrete action plan and make emotionally conscious decisions. Furthermore, the device can provide additional input, including further questions and feedback.

[0144] (Example 2)

[0145] 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".

[0146] In modern asset management, there is a lack of advice that takes into account the emotional state and subjective anxieties of clients. As a result, clients may feel anxious when making investment decisions and may make inappropriate decisions. Furthermore, efficient asset management is not being carried out because changing market conditions and past transaction history are not being fully utilized.

[0147] 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.

[0148] In this invention, the server includes means for receiving information input from a user and transmitting it to an information processing device, means for analyzing the emotional state based on the voice tone and expression of the information input, and means for adjusting the recommended content of the advice based on the emotional state. This makes it possible to provide flexible and personalized asset management advice while taking into consideration the user's emotions.

[0149] A "user" is an entity that utilizes the system to receive asset management or investment advice.

[0150] "Information input" refers to voice or text data that users provide to the system.

[0151] An "information processing device" refers to a device or program that analyzes user input data received and performs the necessary processing.

[0152] "Linguistic analysis" is a technology that converts text and voice input from users into a format that computers can understand and identifies their intent.

[0153] "Identifying intent" means that the computer understands the true purpose and request from the user's input.

[0154] "Transaction information" refers to the historical data of transactions that a user has made in the past.

[0155] "Market information" refers to external information, including fluctuations in financial markets and related data.

[0156] "Emotional state" refers to information that indicates the user's mental state, and is analyzed from voice tone and text expression.

[0157] "Advice" refers to the guidelines and suggestions provided to users regarding their asset management.

[0158] "Recommended content" refers to a specific asset management plan proposed based on analysis results and the user's sentiment.

[0159] "Response" refers to the evaluation or opinion that a user gives to the advice provided by the system.

[0160] "Financial understanding" refers to the level of a user's knowledge and judgment regarding finance.

[0161] The system in this invention receives user input, analyzes it, and provides emotion-based asset management advice. The embodiments for carrying out the invention are described in detail below.

[0162] First, the user uses a device to input questions and instructions regarding asset management in either voice or text format. In the case of voice input, speech recognition software is used to convert it into text data. Specifically, general speech recognition technology is implemented as the software.

[0163] The terminal sends user input data to the server. The server uses the received text data to perform natural language processing (NLP) techniques. Specifically, it utilizes technologies such as the Google Cloud Natural Language API to analyze the input content and identify the user's intent.

[0164] Furthermore, the server utilizes an emotion analysis engine to determine the user's emotional state from their input. In this process, software such as IBM Watson® Tone Analyzer is used to analyze whether the user's emotions are in a state of anxiety or reassurance.

[0165] The server collects users' past transaction information and the latest market information, and combines and analyzes this data. The technologies used for this analysis include data processing libraries such as Python's Pandas.

[0166] Based on the analysis results and sentiment analysis, the server uses a generative AI model to generate the optimal asset management plan or investment advice for the user. An example of a prompt to the generative AI model would be, "Generate the best investment advice based on the user's emotional state."

[0167] The generated advice is sent from the server to the terminal and displayed to the user. The user can manage their assets based on this information and send feedback on the provided advice back to the server via the terminal. Based on this feedback, the server can further improve the accuracy of future advice.

[0168] This will enable users to perform flexible asset management that takes their emotions into consideration, resulting in a system that allows them to engage in investment activities with greater peace of mind.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] Users input questions and instructions regarding asset management into the terminal in either voice or text format. If the input is voice, it is converted to text by speech recognition software. The input data includes the user's specific questions and instructions.

[0172] Step 2:

[0173] The terminal transmits user input data to the server as digital data. In this process, the input data is securely transferred using encryption technology.

[0174] Step 3:

[0175] After receiving text input, the server begins analyzing the data using natural language processing (NLP) tools. Specifically, it uses the Google Cloud Natural Language API to analyze the input data and identify the user's intent. In this process, the input data is analyzed, and the user's intent and requests are clarified.

[0176] Step 4:

[0177] The server utilizes an emotion analysis engine based on voice tone and text expression to reveal the user's emotional state. For example, it uses IBM Watson Tone Analyzer to identify emotions such as anxiety and reassurance. The input to this analysis is the characteristics of the received text and voice, and the output is the identification of the user's emotional state.

[0178] Step 5:

[0179] The server retrieves the user's historical trading data and the latest market information from internal databases and external data sources, and integrates and analyzes this data. The analysis uses libraries such as Python's Pandas library, and the data is processed statistically. The output provides the user's past performance and market trends as analysis results.

[0180] Step 6:

[0181] The server uses a generative AI model to generate optimal asset management plans and investment advice based on the analysis results and sentiment analysis results. The generative AI model is given a prompt such as, "Generate optimal investment advice based on the user's emotional state." The output is investment advice optimized for the user.

[0182] Step 7:

[0183] The server sends the generated advice to the terminal in text format, and the terminal displays it to the user. The user can then review the presented information and manage their assets based on it.

[0184] Step 8:

[0185] Users send feedback on the advice they receive back to the server via their device. The server stores this feedback as new sentiment data and uses it to improve the advice generation process for future sessions. The input for this feedback is the user's evaluation and impressions, and the output is data that contributes to system improvement.

[0186] (Application Example 2)

[0187] 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".

[0188] Traditional asset management systems have struggled to provide advice that takes users' emotions into account, often leading to emotional anxiety and tension. This resulted in a challenge in making optimal investment decisions.

[0189] 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.

[0190] In this invention, the server includes means for using an emotion engine to recognize the user's emotional state, means for generating an asset management plan or investment advice based on the analysis results and emotional state, and means for providing the user with financial knowledge, generating information to improve financial literacy, and making suggestions that take the emotional state into consideration. This makes it possible to provide flexible and accurate asset management and investment advice that takes the user's emotions into consideration.

[0191] "Voice or text input" refers to voice or text data used by a user to communicate their intentions to a system.

[0192] A "server" is a computer system that processes information received from a user, generates results, and sends them to the user's terminal.

[0193] "Natural language processing" is a technology that analyzes data in natural language form input by users and interprets its meaning and intent.

[0194] An "emotion engine" is a technology that identifies a user's emotional state from their voice or text and provides information to the system based on that state.

[0195] "Past transaction data" refers to information about financial transactions that a user has previously made, and serves as basic data for asset management and investment advice.

[0196] "Market information" refers to the latest data and trends related to financial markets, and is used for asset management and investment decisions.

[0197] An "asset management plan or investment advice" is a proposal outlining how to manage a user's assets or what investments they should make.

[0198] "Financial literacy" refers to the ability or aptitude to improve an individual's financial knowledge and understanding, and to make better financial decisions.

[0199] The system implementing this invention consists of a terminal that receives user voice or text input, a cloud-based server, an emotion engine, a natural language processing engine, and financial data analysis software. The terminal can be a smartphone or a computer, and it sends the voice or text input by the user to the server.

[0200] The server is located in the cloud and uses a natural language processing engine to identify the user's intent. This process can utilize software such as the Google Cloud Natural Language API. The server then uses an emotion engine to analyze the user's emotions from their tone of voice and word choice. Various emotion models and tools are used for emotion analysis to identify the user's approximate emotional state—for example, "anxiety" or "reassurance."

[0201] Along with this data, the server analyzes the user's past transaction data and the latest market information using financial data analysis software. As a result, it generates asset management plans and investment advice that take into account the user's emotions and current economic situation. This generated advice is sent to the terminal in text format and displayed to the user.

[0202] For example, if a user sends the input "I'm worried because of the market instability" to the server, the emotion engine recognizes "anxiety" from this statement. In this case, the financial data analysis software suggests low-risk investment options and asset management plans that prioritize stability. Along with displaying this information to the user, it also provides additional financial knowledge to improve financial literacy.

[0203] An example of a prompt might be, "Asset management assistant, I'd like some advice on my investment situation. I'm concerned about market trends." This allows the user to express their feelings while receiving appropriate advice.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The user provides voice or text input to the device. This input is captured through the device's interface. The input voice data is converted to text data and then sent to the server. As output of the input data, the voice is converted to text format.

[0207] Step 2:

[0208] The server analyzes the received text data using a natural language processing engine. This process utilizes software such as the Google Cloud Natural Language API to extract the user's intent. Text data is used as input, and user intent information is obtained as output. The analysis clarifies specific needs and questions.

[0209] Step 3:

[0210] The server uses an emotion engine to analyze the emotions in text data. The tone of voice in audio data is also considered to identify the user's emotions (e.g., "anxious," "relieved"). Input is emotional information in text or audio, and output is data related to the emotional state. The analysis evaluates the user's current psychological state.

[0211] Step 4:

[0212] The server retrieves the user's past trading data and market information, and performs financial data analysis based on this data. Past trading data and real-time market data are used as input data, and asset management plans or investment advice are generated as output. Financial data analysis software is utilized to calculate the optimal recommendations tailored to the user's situation.

[0213] Step 5:

[0214] The server sends an asset management plan or investment advice generated based on the emotional state and analysis results to the terminal. This data is displayed to the user in text format and presented in an easy-to-understand manner. The output data suggests what actions the user should take next.

[0215] Step 6:

[0216] Based on the information received, users can provide additional feedback or ask questions. This user feedback is then sent back to the server via the device. This allows the server to continuously improve the accuracy of its advice and helps the generative AI model generate more sophisticated responses through prompts.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is a system that provides asset management and investment advice using a device that the user uses in their daily life. The user inputs their financial situation and questions into the device via voice or text. The device converts this into text data and sends it to the server.

[0234] The server receives this data and uses generative AI to perform natural language processing. After identifying the user's intent, it accesses trading and market databases to query and analyze the user's past trading history and the latest market information. This analysis automatically generates an asset management plan and investment advice that best suits the user's needs.

[0235] The generated plans and advice are sent to the user's device as text messages and displayed to them. Based on this information, the user can develop a concrete asset management plan. Furthermore, they can obtain more detailed information by asking further questions as needed.

[0236] For example, if a user enters "I want to know about future investment strategies," the server analyzes past investment trends and the latest market developments and generates advice such as "Conservative bond investments are safe in the current market." This allows users to obtain concrete action plans and improve their financial literacy.

[0237] This system allows users to easily deepen their understanding of asset management and conduct financial activities with peace of mind.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user enters questions or requests using voice or text via the device. In the case of voice input, the device uses speech recognition technology to convert it into text data and prepares it for transmission to the server.

[0241] Step 2:

[0242] The terminal sends text data from the user to the server. The server receives the data and prepares it for the next analysis.

[0243] Step 3:

[0244] The server uses generative AI to perform natural language analysis on text data received from users, identifying the intent behind the user's questions and the information they are seeking. It also determines whether additional information is needed to clarify any ambiguities.

[0245] Step 4:

[0246] The server searches the database to retrieve the user's past transaction data and related market information. During this process, it extracts the necessary data based on the identified user's needs.

[0247] Step 5:

[0248] The server analyzes the data acquired using generative AI and generates an asset management plan or investment advice best suited to the user's needs. Various statistical analyses and predictive algorithms are applied at this stage.

[0249] Step 6:

[0250] The server converts the generated advice into text format and sends it to the user's connected device.

[0251] Step 7:

[0252] The terminal displays advice received from the server to the user. The user can view the presented information and develop a concrete action plan. Furthermore, if they have further questions, they can ask them again.

[0253] (Example 1)

[0254] 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."

[0255] For users, efficiently obtaining information on asset management and investment, and receiving advice tailored to their individual needs, is not easy. In particular, many users feel anxious due to market changes and their own lack of financial knowledge. Therefore, it is necessary to provide a system that addresses these challenges and allows users to manage their assets with peace of mind.

[0256] 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.

[0257] In this invention, the server includes means for acquiring voice or text input from a user and transmitting it to a computer; means for the computer to perform natural language analysis on the received user input and clarify the user's purpose; and means for the computer to acquire and analyze the user's past transaction records and market information. This makes it possible to provide the user with an optimal asset management plan and investment advice tailored to their individual needs and current market conditions.

[0258] "Users" refers to individuals or organizations seeking information and advice regarding asset management and investment.

[0259] "Voice or text input" refers to voice or text data used by users to send questions or information related to asset management or investment to their devices.

[0260] A "computer" refers to a central processing system that receives input from users and performs data analysis, generates advice, and so on.

[0261] "Natural language processing" refers to the process of understanding the intent behind text data from users and converting it into a format that a computer can understand.

[0262] "Clarifying the objective" refers to the process by which a computer analyzes the information it receives from a user and identifies the specific information or advice the user is seeking.

[0263] "Transaction records" refer to historical data of financial transactions conducted by a user in the past.

[0264] "Market information" refers to data that shows the current situation and trends in financial markets.

[0265] "Analyzing" refers to the process of generating optimal asset management plans and investment advice based on acquired data.

[0266] An "asset management plan" refers to a specific strategy proposed by a computer to effectively manage a user's assets.

[0267] "Investment advice" refers to specific suggestions provided by a computer to help users effectively increase their assets.

[0268] "Terminal" refers to a communication device used by a user for voice or text input.

[0269] This invention is a system that provides users with advice on asset management and investment. Users can input their financial situation and questions through a device they use daily, either by voice or text. Specifically, devices such as smartphones and personal computers are used, and when voice input is performed, voice recognition software (e.g., a general voice recognition API) performs the function of converting it into text data.

[0270] The terminal has the function of sending the converted text data to the server, which processes the received data using advanced natural language processing. In this analysis, a generative AI model (e.g., a general natural language processing model) is used to identify the specific asset management information and investment advice that the user is seeking.

[0271] The server then accesses a database that stores the user's past transaction records and current market information. In this step, it comprehensively analyzes the acquired data using a database management system and data analysis tools (e.g., a general data analysis library). Based on the results of this analysis, the server generates an optimal operational plan and advice tailored to individual needs and market conditions.

[0272] The generated advice is sent to the user's device as a text message and presented to them. This allows the user to develop a concrete investment strategy and improve their financial literacy. Furthermore, if the user asks another question, they can enter "I want to know about future investment strategies" as a prompt, and the system will analyze past investment trends and the latest market trends to provide specific suggestions such as "Conservative bond investments are safe in the current market." In this way, users can receive support to conduct financial activities with confidence.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] Users input questions about asset management and investment into the terminal in either voice or text format. The input data includes specific questions, such as "I want to know about future investment strategies." When voice input is received, the terminal uses speech recognition software to convert the voice into text. This conversion generates text data.

[0276] Step 2:

[0277] The terminal sends the generated text data to the server. This data is transmitted via HTTP request. The server receives the text data and saves its contents in preparation for the next processing step.

[0278] Step 3:

[0279] The server performs natural language processing using a generative AI model based on the received text data. Specifically, it uses generative AI models such as the GPT series or BERT to extract the user's intent from the text data. Through this process, the server can identify what information the user is looking for and stores the results internally.

[0280] Step 4:

[0281] Based on the analyzed intention, the server accesses a database containing the user's past transaction records and current market information. The server uses an SQL query or the like to obtain this information and prepares it for analysis. The acquired data is collected in a form that conforms to the user's intention.

[0282] Step 5:

[0283] The server performs data analysis using the acquired data. Using data analysis libraries such as Python's Pandas and NumPy, it numerically analyzes past transaction trends and market trends. Based on the results, the server generates an optimal asset management plan or investment advice. For example, a specific proposal such as "Conservative bond investment is safe in the current market" is generated.

[0284] Step 6:

[0285] The server sends the generated advice to the terminal as a text message. The terminal displays the received text message and presents it to the user. The user can formulate their own asset management plan based on this advice. If the user requires further information, they can ask new questions to obtain additional advice.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] In recent years, the demand for accurate and timely advice regarding personal asset management and investment strategies has been increasing. However, it is not easy for ordinary households to appropriately obtain this information without specialized knowledge. For this reason, a means of obtaining optimal investment advice based on voice input according to individual asset situations is being sought.

[0289] 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.

[0290] In this invention, the server includes means for recognizing voice input from a user and converting it into data, means for transmitting the converted data to an external processing unit, and means for the external processing unit to perform natural language analysis on the received user input and identify the user's intent. This enables an assistant device installed in the home to provide the user with timely and personalized asset management plans and investment advice.

[0291] A "user" is an individual who seeks information related to asset management and investment by inputting voice or data.

[0292] "Voice input" is a method of communicating with a system by having the user speak.

[0293] "Data conversion" is the process of analyzing voice input and converting it into a format that can be processed by a machine.

[0294] An "external processing device" is a device, including a server, that analyzes and processes voice input data.

[0295] "Natural language processing" is a technology that analyzes a user's voice input to understand their intentions and requests.

[0296] "Identifying intent" means identifying user requests and desires through natural language processing.

[0297] "Information analysis" is a method of generating appropriate advice based on the user's past trading data and market information.

[0298] An "asset management plan" is the process of developing a strategy for efficiently managing a user's assets.

[0299] "Investment advice" refers to providing information to guide users in finding the most appropriate investment strategy.

[0300] A "display device" is a device that visually presents generated advice and information to the user.

[0301] In implementing this invention, the user provides voice input regarding asset management and investment advice to a home-use support device. The support device is equipped with a voice recognition function, which is implemented using the Google Cloud Speech-to-Text API. The voice information is converted into digital text and sent to the server.

[0302] The server receives text data and analyzes the user's intent through Azure's natural language processing service. This provides specific analytical information to address the user's questions. Based on the analysis results, the server uses data processing libraries such as NumPy and Pandas to analyze the user's past trading data and the latest market information. This generates asset management plans and investment advice tailored to the individual's situation.

[0303] The generated advice is sent to the display unit of the support device, allowing the user to review it visually. This is implemented using the LINE Messaging API. Users can use this information to plan their asset management. Furthermore, by asking repeated questions, they can obtain more detailed advice, allowing for flexible responses tailored to the user's needs.

[0304] For example, if a user asks the support device, "I want to know the right investment methods to prepare for my children's education expenses," the server can analyze the user's trading history and market conditions and provide specific advice from multiple perspectives, such as, "Consider investing in a safe, long-term index fund."

[0305] To generate an AI model, a prompt sentence is used to respond accurately and quickly to user requests. As an example of a prompt sentence, it is used in the form of "A user is consulting about preparing for education expenses. Please provide appropriate investment advice considering the user's past transaction history and market conditions." This prompt sentence sets the context for the AI to generate accurate advice.

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The user inputs a question verbally towards the support device, and the voice information is captured by the terminal. The terminal uses the Google Cloud Speech-to-Text API to convert the voice into digital text. The input is the user's voice information, and the output is data in text format.

[0309] Step 2:

[0310] The terminal sends the converted text data to the server. The server receives this text data, analyzes the text using Azure's natural language processing service, and identifies the user's intention. The input is the text data, and the output is the analyzed user's intention. In this step, the server performs syntactic and semantic analysis of the text.

[0311] Step 3:

[0312] Based on the analyzed intention, the server retrieves the user's past transaction data and market information. The server uses NumPy and Pandas to perform statistical and evaluative data analysis with this information. The input is the user's transaction history and market data, and the output is the analysis results and their interpretations. Here, the server conducts data aggregation and pattern recognition.

[0313] Step 4:

[0314] The server generates appropriate asset management plans and investment advice through a generative AI model based on the analysis results. In this process, prompts are used to effectively guide the AI ​​model's responses. The input consists of the analysis results and appropriate prompts, while the output is the generated advice. Through this process, the server provides instructions to the model to generate the optimal solution.

[0315] Step 5:

[0316] The server sends the generated advice back to the device using the LINE Messaging API. The device then displays this information to the user. The input is the generated advice, and the output is the advice provided to the user visually or audibly. The device is responsible for displaying the received text in the most appropriate format.

[0317] 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.

[0318] This invention combines an emotion engine with a system that receives user voice or text input, analyzes its content, and provides asset management and investment advice. The user inputs financial questions or instructions using a terminal. The terminal then transmits the user input to the server.

[0319] The server performs natural language analysis on received user input to identify the user's intent. Furthermore, it uses an emotion engine to recognize the user's emotional state based on the user's tone of voice and text wording. For example, it can identify emotional states such as tension, anxiety, and relief.

[0320] Based on this information, the server retrieves and analyzes the user's past trading data and market information. Taking into account the user's emotional state, it generates an optimal asset management plan or investment advice. In this process, if the user is feeling anxious, the server can adjust the recommendations accordingly, such as recommending a lower-risk plan.

[0321] The generated advice is sent to the user's device in text format and displayed to the user. Users can utilize this information to manage their assets in a more emotionally conscious way. Furthermore, new emotional data can be collected as user feedback to improve the accuracy of the advice.

[0322] For example, if a user enters "I'm a little worried about future investments," the server uses an emotion engine to recognize this feeling of "anxiety" and suggests a conservative investment strategy that is appropriate for it. The user can then use the suggested advice to make investment decisions with greater confidence.

[0323] This system configuration enables flexible asset management and the provision of financial information that takes into account the user's emotions.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The user enters questions or requests regarding asset management via voice or text through the device. In the case of voice input, the device converts it to text using a speech recognition device and prepares to send the data to the server.

[0327] Step 2:

[0328] The terminal sends user input data to the server. The server receives this data and prepares for the next analysis process.

[0329] Step 3:

[0330] The server uses a generative AI to perform natural language analysis on the received user input and identify the user's intent. Based on the analysis results, it estimates what information is needed.

[0331] Step 4:

[0332] The server uses an emotion engine to analyze the user's emotional state from their voice tone and text context. It identifies emotions such as tension, anxiety, and relief to understand the user's state.

[0333] Step 5:

[0334] The server retrieves the user's past transaction data and market information from the database. Based on the identified user's needs and emotional state, it extracts relevant data.

[0335] Step 6:

[0336] The server integrates emotional states and data analysis results to generate an optimal asset management plan or investment advice for the user. For example, if anxiety is detected, it will suggest low-risk options.

[0337] Step 7:

[0338] The server formats the generated advice into a text message and sends it to the user's terminal.

[0339] Step 8:

[0340] The device displays advice received from the server to the user. Based on the provided information, the user can develop a concrete action plan and make emotionally conscious decisions. Furthermore, the device can provide additional input, including further questions and feedback.

[0341] (Example 2)

[0342] 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".

[0343] In modern asset management, there is a lack of advice that takes into account the emotional state and subjective anxieties of clients. As a result, clients may feel anxious when making investment decisions and may make inappropriate decisions. Furthermore, efficient asset management is not being carried out because changing market conditions and past transaction history are not being fully utilized.

[0344] 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.

[0345] In this invention, the server includes means for receiving information input from a user and transmitting it to an information processing device, means for analyzing the emotional state based on the voice tone and expression of the information input, and means for adjusting the recommended content of the advice based on the emotional state. This makes it possible to provide flexible and personalized asset management advice while taking into consideration the user's emotions.

[0346] A "user" is an entity that utilizes the system to receive asset management or investment advice.

[0347] "Information input" refers to voice or text data that users provide to the system.

[0348] An "information processing device" refers to a device or program that analyzes user input data received and performs the necessary processing.

[0349] "Linguistic analysis" is a technology that converts text and voice input from users into a format that computers can understand and identifies their intent.

[0350] "Identifying intent" means that the computer understands the true purpose and request from the user's input.

[0351] "Transaction information" refers to the historical data of transactions that a user has made in the past.

[0352] "Market information" refers to external information, including fluctuations in financial markets and related data.

[0353] "Emotional state" refers to information that indicates the user's mental state, and is analyzed from voice tone and text expression.

[0354] "Advice" refers to the guidelines and suggestions provided to users regarding their asset management.

[0355] "Recommended content" refers to a specific asset management plan proposed based on analysis results and the user's sentiment.

[0356] "Response" refers to the evaluation or opinion that a user gives to the advice provided by the system.

[0357] "Financial understanding" refers to the level of a user's knowledge and judgment regarding finance.

[0358] The system in this invention receives user input, analyzes it, and provides emotion-based asset management advice. The embodiments for carrying out the invention are described in detail below.

[0359] First, the user uses a device to input questions and instructions regarding asset management in either voice or text format. In the case of voice input, speech recognition software is used to convert it into text data. Specifically, general speech recognition technology is implemented as the software.

[0360] The terminal sends user input data to the server. The server uses the received text data to perform natural language processing (NLP) techniques. Specifically, it utilizes technologies such as the Google Cloud Natural Language API to analyze the input content and identify the user's intent.

[0361] Furthermore, the server utilizes an emotion analysis engine to determine the user's emotional state from their input. In this process, software such as IBM Watson Tone Analyzer is used to analyze whether the user's emotions are in a state of anxiety or reassurance.

[0362] The server collects users' past transaction information and the latest market information, and combines and analyzes this data. The technologies used for this analysis include data processing libraries such as Python's Pandas.

[0363] Based on the analysis results and sentiment analysis, the server uses a generative AI model to generate the optimal asset management plan or investment advice for the user. An example of a prompt to the generative AI model would be, "Generate the best investment advice based on the user's emotional state."

[0364] The generated advice is sent from the server to the terminal and displayed to the user. The user can manage their assets based on this information and send feedback on the provided advice back to the server via the terminal. Based on this feedback, the server can further improve the accuracy of future advice.

[0365] This will enable users to perform flexible asset management that takes their emotions into consideration, resulting in a system that allows them to engage in investment activities with greater peace of mind.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] Users input questions and instructions regarding asset management into the terminal in either voice or text format. If the input is voice, it is converted to text by speech recognition software. The input data includes the user's specific questions and instructions.

[0369] Step 2:

[0370] The terminal transmits user input data to the server as digital data. In this process, the input data is securely transferred using encryption technology.

[0371] Step 3:

[0372] After receiving text input, the server begins analyzing the data using natural language processing (NLP) tools. Specifically, it uses the Google Cloud Natural Language API to analyze the input data and identify the user's intent. In this process, the input data is analyzed, and the user's intent and requests are clarified.

[0373] Step 4:

[0374] The server utilizes an emotion analysis engine based on voice tone and text expression to reveal the user's emotional state. For example, it uses IBM Watson Tone Analyzer to identify emotions such as anxiety and reassurance. The input to this analysis is the characteristics of the received text and voice, and the output is the identification of the user's emotional state.

[0375] Step 5:

[0376] The server retrieves the user's historical trading data and the latest market information from internal databases and external data sources, and integrates and analyzes this data. The analysis uses libraries such as Python's Pandas library, and the data is processed statistically. The output provides the user's past performance and market trends as analysis results.

[0377] Step 6:

[0378] The server uses a generative AI model to generate optimal asset management plans and investment advice based on the analysis results and sentiment analysis results. The generative AI model is given a prompt such as, "Generate optimal investment advice based on the user's emotional state." The output is investment advice optimized for the user.

[0379] Step 7:

[0380] The server sends the generated advice to the terminal in text format, and the terminal displays it to the user. The user can then review the presented information and manage their assets based on it.

[0381] Step 8:

[0382] Users send feedback on the advice they receive back to the server via their device. The server stores this feedback as new sentiment data and uses it to improve the advice generation process for future sessions. The input for this feedback is the user's evaluation and impressions, and the output is data that contributes to system improvement.

[0383] (Application Example 2)

[0384] 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."

[0385] Traditional asset management systems have struggled to provide advice that takes users' emotions into account, often leading to emotional anxiety and tension. This resulted in a challenge in making optimal investment decisions.

[0386] 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.

[0387] In this invention, the server includes means for using an emotion engine to recognize the user's emotional state, means for generating an asset management plan or investment advice based on the analysis results and emotional state, and means for providing the user with financial knowledge, generating information to improve financial literacy, and making suggestions that take the emotional state into consideration. This makes it possible to provide flexible and accurate asset management and investment advice that takes the user's emotions into consideration.

[0388] "Voice or text input" refers to voice or text data used by a user to communicate their intentions to a system.

[0389] A "server" is a computer system that processes information received from a user, generates results, and sends them to the user's terminal.

[0390] "Natural language processing" is a technology that analyzes data in natural language form input by users and interprets its meaning and intent.

[0391] An "emotion engine" is a technology that identifies a user's emotional state from their voice or text and provides information to the system based on that state.

[0392] "Past transaction data" refers to information about financial transactions that a user has previously made, and serves as basic data for asset management and investment advice.

[0393] "Market information" refers to the latest data and trends related to financial markets, and is used for asset management and investment decisions.

[0394] An "asset management plan or investment advice" is a proposal outlining how to manage a user's assets or what investments they should make.

[0395] "Financial literacy" refers to the ability or aptitude to improve an individual's financial knowledge and understanding, and to make better financial decisions.

[0396] The system implementing this invention consists of a terminal that receives user voice or text input, a cloud-based server, an emotion engine, a natural language processing engine, and financial data analysis software. The terminal can be a smartphone or a computer, and it sends the voice or text input by the user to the server.

[0397] The server is located in the cloud and uses a natural language processing engine to identify the user's intent. This process can utilize software such as the Google Cloud Natural Language API. The server then uses an emotion engine to analyze the user's emotions from their tone of voice and word choice. Various emotion models and tools are used for emotion analysis to identify the user's approximate emotional state—for example, "anxiety" or "reassurance."

[0398] Along with this data, the server analyzes the user's past transaction data and the latest market information using financial data analysis software. As a result, it generates asset management plans and investment advice that take into account the user's emotions and current economic situation. This generated advice is sent to the terminal in text format and displayed to the user.

[0399] For example, if a user sends the input "I'm worried because of the market instability" to the server, the emotion engine recognizes "anxiety" from this statement. In this case, the financial data analysis software suggests low-risk investment options and asset management plans that prioritize stability. Along with displaying this information to the user, it also provides additional financial knowledge to improve financial literacy.

[0400] An example of a prompt might be, "Asset management assistant, I'd like some advice on my investment situation. I'm concerned about market trends." This allows the user to express their feelings while receiving appropriate advice.

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

[0402] Step 1:

[0403] The user provides voice or text input to the device. This input is captured through the device's interface. The input voice data is converted to text data and then sent to the server. As output of the input data, the voice is converted to text format.

[0404] Step 2:

[0405] The server analyzes the received text data using a natural language processing engine. This process utilizes software such as the Google Cloud Natural Language API to extract the user's intent. Text data is used as input, and user intent information is obtained as output. The analysis clarifies specific needs and questions.

[0406] Step 3:

[0407] The server uses an emotion engine to analyze the emotions in text data. The tone of voice in audio data is also considered to identify the user's emotions (e.g., "anxious," "relieved"). Input is emotional information in text or audio, and output is data related to the emotional state. The analysis evaluates the user's current psychological state.

[0408] Step 4:

[0409] The server retrieves the user's past trading data and market information, and performs financial data analysis based on this data. Past trading data and real-time market data are used as input data, and asset management plans or investment advice are generated as output. Financial data analysis software is utilized to calculate the optimal recommendations tailored to the user's situation.

[0410] Step 5:

[0411] The server sends an asset management plan or investment advice generated based on the emotional state and analysis results to the terminal. This data is displayed to the user in text format and presented in an easy-to-understand manner. The output data suggests what actions the user should take next.

[0412] Step 6:

[0413] Based on the information received, users can provide additional feedback or ask questions. This user feedback is then sent back to the server via the device. This allows the server to continuously improve the accuracy of its advice and helps the generative AI model generate more sophisticated responses through prompts.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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".

[0430] This invention is a system that provides asset management and investment advice using a device that the user uses in their daily life. The user inputs their financial situation and questions into the device via voice or text. The device converts this into text data and sends it to the server.

[0431] The server receives this data and uses generative AI to perform natural language processing. After identifying the user's intent, it accesses trading and market databases to query and analyze the user's past trading history and the latest market information. This analysis automatically generates an asset management plan and investment advice that best suits the user's needs.

[0432] The generated plans and advice are sent to the user's device as text messages and displayed to them. Based on this information, the user can develop a concrete asset management plan. Furthermore, they can obtain more detailed information by asking further questions as needed.

[0433] For example, if a user enters "I want to know about future investment strategies," the server analyzes past investment trends and the latest market developments and generates advice such as "Conservative bond investments are safe in the current market." This allows users to obtain concrete action plans and improve their financial literacy.

[0434] This system allows users to easily deepen their understanding of asset management and conduct financial activities with peace of mind.

[0435] The following describes the processing flow.

[0436] Step 1:

[0437] The user enters questions or requests using voice or text via the device. In the case of voice input, the device uses speech recognition technology to convert it into text data and prepares it for transmission to the server.

[0438] Step 2:

[0439] The terminal sends text data from the user to the server. The server receives the data and prepares it for the next analysis.

[0440] Step 3:

[0441] The server uses generative AI to perform natural language analysis on text data received from users, identifying the intent behind the user's questions and the information they are seeking. It also determines whether additional information is needed to clarify any ambiguities.

[0442] Step 4:

[0443] The server searches the database to retrieve the user's past transaction data and related market information. During this process, it extracts the necessary data based on the identified user's needs.

[0444] Step 5:

[0445] The server analyzes the data acquired using generative AI and generates an asset management plan or investment advice best suited to the user's needs. Various statistical analyses and predictive algorithms are applied at this stage.

[0446] Step 6:

[0447] The server converts the generated advice into text format and sends it to the user's connected device.

[0448] Step 7:

[0449] The terminal displays advice received from the server to the user. The user can view the presented information and develop a concrete action plan. Furthermore, if they have further questions, they can ask them again.

[0450] (Example 1)

[0451] 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."

[0452] For users, efficiently obtaining information on asset management and investment, and receiving advice tailored to their individual needs, is not easy. In particular, many users feel anxious due to market changes and their own lack of financial knowledge. Therefore, it is necessary to provide a system that addresses these challenges and allows users to manage their assets with peace of mind.

[0453] 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.

[0454] In this invention, the server includes means for acquiring voice or text input from a user and transmitting it to a computer; means for the computer to perform natural language analysis on the received user input and clarify the user's purpose; and means for the computer to acquire and analyze the user's past transaction records and market information. This makes it possible to provide the user with an optimal asset management plan and investment advice tailored to their individual needs and current market conditions.

[0455] "Users" refers to individuals or organizations seeking information and advice regarding asset management and investment.

[0456] "Voice or text input" refers to voice or text data used by users to send questions or information related to asset management or investment to their devices.

[0457] A "computer" refers to a central processing system that receives input from users and performs data analysis, generates advice, and so on.

[0458] "Natural language processing" refers to the process of understanding the intent behind text data from users and converting it into a format that a computer can understand.

[0459] "Clarifying the objective" refers to the process by which a computer analyzes the information it receives from a user and identifies the specific information or advice the user is seeking.

[0460] "Transaction records" refer to historical data of financial transactions conducted by a user in the past.

[0461] "Market information" refers to data that shows the current situation and trends in financial markets.

[0462] "Analyzing" refers to the process of generating optimal asset management plans and investment advice based on acquired data.

[0463] An "asset management plan" refers to a specific strategy proposed by a computer to effectively manage a user's assets.

[0464] "Investment advice" refers to specific suggestions provided by a computer to help users effectively increase their assets.

[0465] "Terminal" refers to a communication device used by a user for voice or text input.

[0466] This invention is a system that provides users with advice on asset management and investment. Users can input their financial situation and questions through a device they use daily, either by voice or text. Specifically, devices such as smartphones and personal computers are used, and when voice input is performed, voice recognition software (e.g., a general voice recognition API) performs the function of converting it into text data.

[0467] The terminal has the function of sending the converted text data to the server, which processes the received data using advanced natural language processing. In this analysis, a generative AI model (e.g., a general natural language processing model) is used to identify the specific asset management information and investment advice that the user is seeking.

[0468] The server then accesses a database that stores the user's past transaction records and current market information. In this step, it comprehensively analyzes the acquired data using a database management system and data analysis tools (e.g., a general data analysis library). Based on the results of this analysis, the server generates an optimal operational plan and advice tailored to individual needs and market conditions.

[0469] The generated advice is sent to the user's device as a text message and presented to them. This allows the user to develop a concrete investment strategy and improve their financial literacy. Furthermore, if the user asks another question, they can enter "I want to know about future investment strategies" as a prompt, and the system will analyze past investment trends and the latest market trends to provide specific suggestions such as "Conservative bond investments are safe in the current market." In this way, users can receive support to conduct financial activities with confidence.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] Users input questions about asset management and investment into the terminal in either voice or text format. The input data includes specific questions, such as "I want to know about future investment strategies." When voice input is received, the terminal uses speech recognition software to convert the voice into text. This conversion generates text data.

[0473] Step 2:

[0474] The terminal sends the generated text data to the server. This data is transmitted via HTTP request. The server receives the text data and saves its contents in preparation for the next processing step.

[0475] Step 3:

[0476] The server performs natural language processing using a generative AI model based on the received text data. Specifically, it uses generative AI models such as the GPT series or BERT to extract the user's intent from the text data. Through this process, the server can identify what information the user is looking for and stores the results internally.

[0477] Step 4:

[0478] Based on the analyzed intent, the server accesses a database containing the user's past transaction records and current market information. The server retrieves this information using SQL queries and other methods, preparing it for analysis. The retrieved data is collected in a way that aligns with the user's intent.

[0479] Step 5:

[0480] The server performs data analysis using the acquired data. It uses data analysis libraries such as Python's Pandas and NumPy to numerically analyze past trading trends and market movements. Based on the results, the server generates an optimal asset management plan or investment advice. For example, it might generate a specific suggestion such as, "In the current market, conservative bond investments are safe."

[0481] Step 6:

[0482] The server sends the generated advice as a text message to the terminal. The terminal displays the received text message and presents it to the user. The user can then use this advice to create their own investment plan. If the user requires further information, they can ask new questions to receive additional advice.

[0483] (Application Example 1)

[0484] 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."

[0485] In recent years, there has been a growing demand for accurate and timely advice regarding personal asset management and investment strategies. However, it is not easy for ordinary households to obtain this information appropriately without specialized knowledge. Therefore, there is a need for a method that uses voice input to provide optimal investment advice tailored to individual asset situations.

[0486] 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.

[0487] In this invention, the server includes means for recognizing voice input from a user and converting it into data, means for transmitting the converted data to an external processing unit, and means for the external processing unit to perform natural language analysis on the received user input and identify the user's intent. This enables an assistant device installed in the home to provide the user with timely and personalized asset management plans and investment advice.

[0488] A "user" is an individual who seeks information related to asset management and investment by inputting voice or data.

[0489] "Voice input" is a method of communicating with a system by having the user speak.

[0490] "Data conversion" is the process of analyzing voice input and converting it into a format that can be processed by a machine.

[0491] An "external processing device" is a device, including a server, that analyzes and processes voice input data.

[0492] "Natural language processing" is a technology that analyzes a user's voice input to understand their intentions and requests.

[0493] "Identifying intent" means identifying user requests and desires through natural language processing.

[0494] "Information analysis" is a method of generating appropriate advice based on the user's past trading data and market information.

[0495] An "asset management plan" is the process of developing a strategy for efficiently managing a user's assets.

[0496] "Investment advice" refers to providing information to guide users in finding the most appropriate investment strategy.

[0497] A "display device" is a device that visually presents generated advice and information to the user.

[0498] In implementing this invention, the user provides voice input regarding asset management and investment advice to a home-use support device. The support device is equipped with a voice recognition function, which is implemented using the Google Cloud Speech-to-Text API. The voice information is converted into digital text and sent to the server.

[0499] The server receives text data and analyzes the user's intent through Azure's natural language processing service. This provides specific analytical information to address the user's questions. Based on the analysis results, the server uses data processing libraries such as NumPy and Pandas to analyze the user's past trading data and the latest market information. This generates asset management plans and investment advice tailored to the individual's situation.

[0500] The generated advice is sent to the display unit of the support device, allowing the user to review it visually. This is implemented using the LINE Messaging API. Users can use this information to plan their asset management. Furthermore, by asking repeated questions, they can obtain more detailed advice, allowing for flexible responses tailored to the user's needs.

[0501] For example, if a user asks the support device, "I want to know the right investment methods to prepare for my children's education expenses," the server can analyze the user's trading history and market conditions and provide specific advice from multiple perspectives, such as, "Consider investing in a safe, long-term index fund."

[0502] The AI ​​generation model uses prompts to respond accurately and quickly to user requests. An example of a prompt might be: "The user is seeking advice on saving for education expenses. Please provide appropriate investment advice considering the user's past trading history and market conditions." This prompt sets the context for the AI ​​to generate accurate advice.

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The user voice-inputs questions into the assistive device, and the voice information is captured by the terminal. The terminal uses the Google Cloud Speech-to-Text API to convert the voice into digital text. The input is the user's voice information, and the output is data in text format.

[0506] Step 2:

[0507] The terminal sends the converted text data to the server. The server receives this text data and uses Azure's natural language processing service to analyze the text and identify the user's intent. The input is the text data, and the output is the analyzed user intent. In this step, the server performs syntactic and semantic analysis of the text.

[0508] Step 3:

[0509] Based on the analyzed intent, the server retrieves the user's past trading data and market information. Using this information, the server performs statistical and evaluative data analysis with NumPy and Pandas. The input is the user's trading history and market data, and the output is the analysis results and their interpretation. Here, the server performs data aggregation and pattern recognition.

[0510] Step 4:

[0511] The server generates appropriate asset management plans and investment advice through a generative AI model based on the analysis results. In this process, prompts are used to effectively guide the AI ​​model's responses. The input consists of the analysis results and appropriate prompts, while the output is the generated advice. Through this process, the server provides instructions to the model to generate the optimal solution.

[0512] Step 5:

[0513] The server sends the generated advice back to the device using the LINE Messaging API. The device then displays this information to the user. The input is the generated advice, and the output is the advice provided to the user visually or audibly. The device is responsible for displaying the received text in the most appropriate format.

[0514] 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.

[0515] This invention combines an emotion engine with a system that receives user voice or text input, analyzes its content, and provides asset management and investment advice. The user inputs financial questions or instructions using a terminal. The terminal then transmits the user input to the server.

[0516] The server performs natural language analysis on received user input to identify the user's intent. Furthermore, it uses an emotion engine to recognize the user's emotional state based on the user's tone of voice and text wording. For example, it can identify emotional states such as tension, anxiety, and relief.

[0517] Based on this information, the server retrieves and analyzes the user's past trading data and market information. Taking into account the user's emotional state, it generates an optimal asset management plan or investment advice. In this process, if the user is feeling anxious, the server can adjust the recommendations accordingly, such as recommending a lower-risk plan.

[0518] The generated advice is sent to the user's device in text format and displayed to the user. Users can utilize this information to manage their assets in a more emotionally conscious way. Furthermore, new emotional data can be collected as user feedback to improve the accuracy of the advice.

[0519] For example, if a user enters "I'm a little worried about future investments," the server uses an emotion engine to recognize this feeling of "anxiety" and suggests a conservative investment strategy that is appropriate for it. The user can then use the suggested advice to make investment decisions with greater confidence.

[0520] This system configuration enables flexible asset management and the provision of financial information that takes into account the user's emotions.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The user enters questions or requests regarding asset management via voice or text through the device. In the case of voice input, the device converts it to text using a speech recognition device and prepares to send the data to the server.

[0524] Step 2:

[0525] The terminal sends user input data to the server. The server receives this data and prepares for the next analysis process.

[0526] Step 3:

[0527] The server uses a generative AI to perform natural language analysis on the received user input and identify the user's intent. Based on the analysis results, it estimates what information is needed.

[0528] Step 4:

[0529] The server uses an emotion engine to analyze the user's emotional state from their voice tone and text context. It identifies emotions such as tension, anxiety, and relief to understand the user's state.

[0530] Step 5:

[0531] The server retrieves the user's past transaction data and market information from the database. Based on the identified user's needs and emotional state, it extracts relevant data.

[0532] Step 6:

[0533] The server integrates emotional states and data analysis results to generate an optimal asset management plan or investment advice for the user. For example, if anxiety is detected, it will suggest low-risk options.

[0534] Step 7:

[0535] The server formats the generated advice into a text message and sends it to the user's terminal.

[0536] Step 8:

[0537] The device displays advice received from the server to the user. Based on the provided information, the user can develop a concrete action plan and make emotionally conscious decisions. Furthermore, the device can provide additional input, including further questions and feedback.

[0538] (Example 2)

[0539] 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."

[0540] In modern asset management, there is a lack of advice that takes into account the emotional state and subjective anxieties of clients. As a result, clients may feel anxious when making investment decisions and may make inappropriate decisions. Furthermore, efficient asset management is not being carried out because changing market conditions and past transaction history are not being fully utilized.

[0541] 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.

[0542] In this invention, the server includes means for receiving information input from a user and transmitting it to an information processing device, means for analyzing the emotional state based on the voice tone and expression of the information input, and means for adjusting the recommended content of the advice based on the emotional state. This makes it possible to provide flexible and personalized asset management advice while taking into consideration the user's emotions.

[0543] A "user" is an entity that utilizes the system to receive asset management or investment advice.

[0544] "Information input" refers to voice or text data that users provide to the system.

[0545] An "information processing device" refers to a device or program that analyzes user input data received and performs the necessary processing.

[0546] "Linguistic analysis" is a technology that converts text and voice input from users into a format that computers can understand and identifies their intent.

[0547] "Identifying intent" means that the computer understands the true purpose and request from the user's input.

[0548] "Transaction information" refers to the historical data of transactions that a user has made in the past.

[0549] "Market information" refers to external information, including fluctuations in financial markets and related data.

[0550] "Emotional state" refers to information that indicates the user's mental state, and is analyzed from voice tone and text expression.

[0551] "Advice" refers to the guidelines and suggestions provided to users regarding their asset management.

[0552] "Recommended content" refers to a specific asset management plan proposed based on analysis results and the user's sentiment.

[0553] "Response" refers to the evaluation or opinion that a user gives to the advice provided by the system.

[0554] "Financial understanding" refers to the level of a user's knowledge and judgment regarding finance.

[0555] The system in this invention receives user input, analyzes it, and provides emotion-based asset management advice. The embodiments for carrying out the invention are described in detail below.

[0556] First, the user uses a device to input questions and instructions regarding asset management in either voice or text format. In the case of voice input, speech recognition software is used to convert it into text data. Specifically, general speech recognition technology is implemented as the software.

[0557] The terminal sends user input data to the server. The server uses the received text data to perform natural language processing (NLP) techniques. Specifically, it utilizes technologies such as the Google Cloud Natural Language API to analyze the input content and identify the user's intent.

[0558] Furthermore, the server utilizes an emotion analysis engine to determine the user's emotional state from their input. In this process, software such as IBM Watson Tone Analyzer is used to analyze whether the user's emotions are in a state of anxiety or reassurance.

[0559] The server collects users' past transaction information and the latest market information, and combines and analyzes this data. The technologies used for this analysis include data processing libraries such as Python's Pandas.

[0560] Based on the analysis results and sentiment analysis, the server uses a generative AI model to generate the optimal asset management plan or investment advice for the user. An example of a prompt to the generative AI model would be, "Generate the best investment advice based on the user's emotional state."

[0561] The generated advice is sent from the server to the terminal and displayed to the user. The user can manage their assets based on this information and send feedback on the provided advice back to the server via the terminal. Based on this feedback, the server can further improve the accuracy of future advice.

[0562] This will enable users to perform flexible asset management that takes their emotions into consideration, resulting in a system that allows them to engage in investment activities with greater peace of mind.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] Users input questions and instructions regarding asset management into the terminal in either voice or text format. If the input is voice, it is converted to text by speech recognition software. The input data includes the user's specific questions and instructions.

[0566] Step 2:

[0567] The terminal transmits user input data to the server as digital data. In this process, the input data is securely transferred using encryption technology.

[0568] Step 3:

[0569] After receiving text input, the server begins analyzing the data using natural language processing (NLP) tools. Specifically, it uses the Google Cloud Natural Language API to analyze the input data and identify the user's intent. In this process, the input data is analyzed, and the user's intent and requests are clarified.

[0570] Step 4:

[0571] The server utilizes an emotion analysis engine based on voice tone and text expression to reveal the user's emotional state. For example, it uses IBM Watson Tone Analyzer to identify emotions such as anxiety and reassurance. The input to this analysis is the characteristics of the received text and voice, and the output is the identification of the user's emotional state.

[0572] Step 5:

[0573] The server retrieves the user's historical trading data and the latest market information from internal databases and external data sources, and integrates and analyzes this data. The analysis uses libraries such as Python's Pandas library, and the data is processed statistically. The output provides the user's past performance and market trends as analysis results.

[0574] Step 6:

[0575] The server uses a generative AI model to generate optimal asset management plans and investment advice based on the analysis results and sentiment analysis results. The generative AI model is given a prompt such as, "Generate optimal investment advice based on the user's emotional state." The output is investment advice optimized for the user.

[0576] Step 7:

[0577] The server sends the generated advice to the terminal in text format, and the terminal displays it to the user. The user can then review the presented information and manage their assets based on it.

[0578] Step 8:

[0579] Users send feedback on the advice they receive back to the server via their device. The server stores this feedback as new sentiment data and uses it to improve the advice generation process for future sessions. The input for this feedback is the user's evaluation and impressions, and the output is data that contributes to system improvement.

[0580] (Application Example 2)

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

[0582] Traditional asset management systems have struggled to provide advice that takes users' emotions into account, often leading to emotional anxiety and tension. This resulted in a challenge in making optimal investment decisions.

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

[0584] In this invention, the server includes means for using an emotion engine to recognize the user's emotional state, means for generating an asset management plan or investment advice based on the analysis results and emotional state, and means for providing the user with financial knowledge, generating information to improve financial literacy, and making suggestions that take the emotional state into consideration. This makes it possible to provide flexible and accurate asset management and investment advice that takes the user's emotions into consideration.

[0585] "Voice or text input" refers to voice or text data used by a user to communicate their intentions to a system.

[0586] A "server" is a computer system that processes information received from a user, generates results, and sends them to the user's terminal.

[0587] "Natural language processing" is a technology that analyzes data in natural language form input by users and interprets its meaning and intent.

[0588] An "emotion engine" is a technology that identifies a user's emotional state from their voice or text and provides information to the system based on that state.

[0589] "Past transaction data" refers to information about financial transactions that a user has previously made, and serves as basic data for asset management and investment advice.

[0590] "Market information" refers to the latest data and trends related to financial markets, and is used for asset management and investment decisions.

[0591] An "asset management plan or investment advice" is a proposal outlining how to manage a user's assets or what investments they should make.

[0592] "Financial literacy" refers to the ability or aptitude to improve an individual's financial knowledge and understanding, and to make better financial decisions.

[0593] The system implementing this invention consists of a terminal that receives user voice or text input, a cloud-based server, an emotion engine, a natural language processing engine, and financial data analysis software. The terminal can be a smartphone or a computer, and it sends the voice or text input by the user to the server.

[0594] The server is located in the cloud and uses a natural language processing engine to identify the user's intent. This process can utilize software such as the Google Cloud Natural Language API. The server then uses an emotion engine to analyze the user's emotions from their tone of voice and word choice. Various emotion models and tools are used for emotion analysis to identify the user's approximate emotional state—for example, "anxiety" or "reassurance."

[0595] Along with this data, the server analyzes the user's past transaction data and the latest market information using financial data analysis software. As a result, it generates asset management plans and investment advice that take into account the user's emotions and current economic situation. This generated advice is sent to the terminal in text format and displayed to the user.

[0596] For example, if a user sends the input "I'm worried because of the market instability" to the server, the emotion engine recognizes "anxiety" from this statement. In this case, the financial data analysis software suggests low-risk investment options and asset management plans that prioritize stability. Along with displaying this information to the user, it also provides additional financial knowledge to improve financial literacy.

[0597] An example of a prompt might be, "Asset management assistant, I'd like some advice on my investment situation. I'm concerned about market trends." This allows the user to express their feelings while receiving appropriate advice.

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The user provides voice or text input to the device. This input is captured through the device's interface. The input voice data is converted to text data and then sent to the server. As output of the input data, the voice is converted to text format.

[0601] Step 2:

[0602] The server analyzes the received text data using a natural language processing engine. This process utilizes software such as the Google Cloud Natural Language API to extract the user's intent. Text data is used as input, and user intent information is obtained as output. The analysis clarifies specific needs and questions.

[0603] Step 3:

[0604] The server uses an emotion engine to analyze the emotions in text data. The tone of voice in audio data is also considered to identify the user's emotions (e.g., "anxious," "relieved"). Input is emotional information in text or audio, and output is data related to the emotional state. The analysis evaluates the user's current psychological state.

[0605] Step 4:

[0606] The server retrieves the user's past trading data and market information, and performs financial data analysis based on this data. Past trading data and real-time market data are used as input data, and asset management plans or investment advice are generated as output. Financial data analysis software is utilized to calculate the optimal recommendations tailored to the user's situation.

[0607] Step 5:

[0608] The server sends an asset management plan or investment advice generated based on the emotional state and analysis results to the terminal. This data is displayed to the user in text format and presented in an easy-to-understand manner. The output data suggests what actions the user should take next.

[0609] Step 6:

[0610] Based on the information received, users can provide additional feedback or ask questions. This user feedback is then sent back to the server via the device. This allows the server to continuously improve the accuracy of its advice and helps the generative AI model generate more sophisticated responses through prompts.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] [Fourth Embodiment]

[0615] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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".

[0628] This invention is a system that provides asset management and investment advice using a device that the user uses in their daily life. The user inputs their financial situation and questions into the device via voice or text. The device converts this into text data and sends it to the server.

[0629] The server receives this data and uses generative AI to perform natural language processing. After identifying the user's intent, it accesses trading and market databases to query and analyze the user's past trading history and the latest market information. This analysis automatically generates an asset management plan and investment advice that best suits the user's needs.

[0630] The generated plans and advice are sent to the user's device as text messages and displayed to them. Based on this information, the user can develop a concrete asset management plan. Furthermore, they can obtain more detailed information by asking further questions as needed.

[0631] For example, if a user enters "I want to know about future investment strategies," the server analyzes past investment trends and the latest market developments and generates advice such as "Conservative bond investments are safe in the current market." This allows users to obtain concrete action plans and improve their financial literacy.

[0632] This system allows users to easily deepen their understanding of asset management and conduct financial activities with peace of mind.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The user enters questions or requests using voice or text via the device. In the case of voice input, the device uses speech recognition technology to convert it into text data and prepares it for transmission to the server.

[0636] Step 2:

[0637] The terminal sends text data from the user to the server. The server receives the data and prepares it for the next analysis.

[0638] Step 3:

[0639] The server uses generative AI to perform natural language analysis on text data received from users, identifying the intent behind the user's questions and the information they are seeking. It also determines whether additional information is needed to clarify any ambiguities.

[0640] Step 4:

[0641] The server searches the database to retrieve the user's past transaction data and related market information. During this process, it extracts the necessary data based on the identified user's needs.

[0642] Step 5:

[0643] The server analyzes the data acquired using generative AI and generates an asset management plan or investment advice best suited to the user's needs. Various statistical analyses and predictive algorithms are applied at this stage.

[0644] Step 6:

[0645] The server converts the generated advice into text format and sends it to the user's connected device.

[0646] Step 7:

[0647] The terminal displays advice received from the server to the user. The user can view the presented information and develop a concrete action plan. Furthermore, if they have further questions, they can ask them again.

[0648] (Example 1)

[0649] 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".

[0650] For users, efficiently obtaining information on asset management and investment, and receiving advice tailored to their individual needs, is not easy. In particular, many users feel anxious due to market changes and their own lack of financial knowledge. Therefore, it is necessary to provide a system that addresses these challenges and allows users to manage their assets with peace of mind.

[0651] 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.

[0652] In this invention, the server includes means for acquiring voice or text input from a user and transmitting it to a computer; means for the computer to perform natural language analysis on the received user input and clarify the user's purpose; and means for the computer to acquire and analyze the user's past transaction records and market information. This makes it possible to provide the user with an optimal asset management plan and investment advice tailored to their individual needs and current market conditions.

[0653] "Users" refers to individuals or organizations seeking information and advice regarding asset management and investment.

[0654] "Voice or text input" refers to voice or text data used by users to send questions or information related to asset management or investment to their devices.

[0655] A "computer" refers to a central processing system that receives input from users and performs data analysis, generates advice, and so on.

[0656] "Natural language processing" refers to the process of understanding the intent behind text data from users and converting it into a format that a computer can understand.

[0657] "Clarifying the objective" refers to the process by which a computer analyzes the information it receives from a user and identifies the specific information or advice the user is seeking.

[0658] "Transaction records" refer to historical data of financial transactions conducted by a user in the past.

[0659] "Market information" refers to data that shows the current situation and trends in financial markets.

[0660] "Analyzing" refers to the process of generating optimal asset management plans and investment advice based on acquired data.

[0661] An "asset management plan" refers to a specific strategy proposed by a computer to effectively manage a user's assets.

[0662] "Investment advice" refers to specific suggestions provided by a computer to help users effectively increase their assets.

[0663] "Terminal" refers to a communication device used by a user for voice or text input.

[0664] This invention is a system that provides users with advice on asset management and investment. Users can input their financial situation and questions through a device they use daily, either by voice or text. Specifically, devices such as smartphones and personal computers are used, and when voice input is performed, voice recognition software (e.g., a general voice recognition API) performs the function of converting it into text data.

[0665] The terminal has the function of sending the converted text data to the server, which processes the received data using advanced natural language processing. In this analysis, a generative AI model (e.g., a general natural language processing model) is used to identify the specific asset management information and investment advice that the user is seeking.

[0666] The server then accesses a database that stores the user's past transaction records and current market information. In this step, it comprehensively analyzes the acquired data using a database management system and data analysis tools (e.g., a general data analysis library). Based on the results of this analysis, the server generates an optimal operational plan and advice tailored to individual needs and market conditions.

[0667] The generated advice is sent to the user's device as a text message and presented to them. This allows the user to develop a concrete investment strategy and improve their financial literacy. Furthermore, if the user asks another question, they can enter "I want to know about future investment strategies" as a prompt, and the system will analyze past investment trends and the latest market trends to provide specific suggestions such as "Conservative bond investments are safe in the current market." In this way, users can receive support to conduct financial activities with confidence.

[0668] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0669] Step 1:

[0670] Users input questions about asset management and investment into the terminal in either voice or text format. The input data includes specific questions, such as "I want to know about future investment strategies." When voice input is received, the terminal uses speech recognition software to convert the voice into text. This conversion generates text data.

[0671] Step 2:

[0672] The terminal sends the generated text data to the server. This data is transmitted via HTTP request. The server receives the text data and saves its contents in preparation for the next processing step.

[0673] Step 3:

[0674] The server performs natural language processing using a generative AI model based on the received text data. Specifically, it uses generative AI models such as the GPT series or BERT to extract the user's intent from the text data. Through this process, the server can identify what information the user is looking for and stores the results internally.

[0675] Step 4:

[0676] Based on the analyzed intent, the server accesses a database containing the user's past transaction records and current market information. The server retrieves this information using SQL queries and other methods, preparing it for analysis. The retrieved data is collected in a way that aligns with the user's intent.

[0677] Step 5:

[0678] The server performs data analysis using the acquired data. It uses data analysis libraries such as Python's Pandas and NumPy to numerically analyze past trading trends and market movements. Based on the results, the server generates an optimal asset management plan or investment advice. For example, it might generate a specific suggestion such as, "In the current market, conservative bond investments are safe."

[0679] Step 6:

[0680] The server sends the generated advice as a text message to the terminal. The terminal displays the received text message and presents it to the user. The user can then use this advice to create their own investment plan. If the user requires further information, they can ask new questions to receive additional advice.

[0681] (Application Example 1)

[0682] 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".

[0683] In recent years, there has been a growing demand for accurate and timely advice regarding personal asset management and investment strategies. However, it is not easy for ordinary households to obtain this information appropriately without specialized knowledge. Therefore, there is a need for a method that uses voice input to provide optimal investment advice tailored to individual asset situations.

[0684] 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.

[0685] In this invention, the server includes means for recognizing voice input from a user and converting it into data, means for transmitting the converted data to an external processing unit, and means for the external processing unit to perform natural language analysis on the received user input and identify the user's intent. This enables an assistant device installed in the home to provide the user with timely and personalized asset management plans and investment advice.

[0686] A "user" is an individual who seeks information related to asset management and investment by inputting voice or data.

[0687] "Voice input" is a method of communicating with a system by having the user speak.

[0688] "Data conversion" is the process of analyzing voice input and converting it into a format that can be processed by a machine.

[0689] An "external processing device" is a device, including a server, that analyzes and processes voice input data.

[0690] "Natural language processing" is a technology that analyzes a user's voice input to understand their intentions and requests.

[0691] "Identifying intent" means identifying user requests and desires through natural language processing.

[0692] "Information analysis" is a method of generating appropriate advice based on the user's past trading data and market information.

[0693] An "asset management plan" is the process of developing a strategy for efficiently managing a user's assets.

[0694] "Investment advice" refers to providing information to guide users in finding the most appropriate investment strategy.

[0695] A "display device" is a device that visually presents generated advice and information to the user.

[0696] In implementing this invention, the user provides voice input regarding asset management and investment advice to a home-use support device. The support device is equipped with a voice recognition function, which is implemented using the Google Cloud Speech-to-Text API. The voice information is converted into digital text and sent to the server.

[0697] The server receives text data and analyzes the user's intent through Azure's natural language processing service. This provides specific analytical information to address the user's questions. Based on the analysis results, the server uses data processing libraries such as NumPy and Pandas to analyze the user's past trading data and the latest market information. This generates asset management plans and investment advice tailored to the individual's situation.

[0698] The generated advice is sent to the display unit of the support device, allowing the user to review it visually. This is implemented using the LINE Messaging API. Users can use this information to plan their asset management. Furthermore, by asking repeated questions, they can obtain more detailed advice, allowing for flexible responses tailored to the user's needs.

[0699] For example, if a user asks the support device, "I want to know the right investment methods to prepare for my children's education expenses," the server can analyze the user's trading history and market conditions and provide specific advice from multiple perspectives, such as, "Consider investing in a safe, long-term index fund."

[0700] The AI ​​generation model uses prompts to respond accurately and quickly to user requests. An example of a prompt might be: "The user is seeking advice on saving for education expenses. Please provide appropriate investment advice considering the user's past trading history and market conditions." This prompt sets the context for the AI ​​to generate accurate advice.

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The user voice-inputs questions into the assistive device, and the voice information is captured by the terminal. The terminal uses the Google Cloud Speech-to-Text API to convert the voice into digital text. The input is the user's voice information, and the output is data in text format.

[0704] Step 2:

[0705] The terminal sends the converted text data to the server. The server receives this text data and uses Azure's natural language processing service to analyze the text and identify the user's intent. The input is the text data, and the output is the analyzed user intent. In this step, the server performs syntactic and semantic analysis of the text.

[0706] Step 3:

[0707] Based on the analyzed intent, the server retrieves the user's past trading data and market information. Using this information, the server performs statistical and evaluative data analysis with NumPy and Pandas. The input is the user's trading history and market data, and the output is the analysis results and their interpretation. Here, the server performs data aggregation and pattern recognition.

[0708] Step 4:

[0709] The server generates appropriate asset management plans and investment advice through a generative AI model based on the analysis results. In this process, prompts are used to effectively guide the AI ​​model's responses. The input consists of the analysis results and appropriate prompts, while the output is the generated advice. Through this process, the server provides instructions to the model to generate the optimal solution.

[0710] Step 5:

[0711] The server sends the generated advice back to the device using the LINE Messaging API. The device then displays this information to the user. The input is the generated advice, and the output is the advice provided to the user visually or audibly. The device is responsible for displaying the received text in the most appropriate format.

[0712] 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.

[0713] This invention combines an emotion engine with a system that receives user voice or text input, analyzes its content, and provides asset management and investment advice. The user inputs financial questions or instructions using a terminal. The terminal then transmits the user input to the server.

[0714] The server performs natural language analysis on received user input to identify the user's intent. Furthermore, it uses an emotion engine to recognize the user's emotional state based on the user's tone of voice and text wording. For example, it can identify emotional states such as tension, anxiety, and relief.

[0715] Based on this information, the server retrieves and analyzes the user's past trading data and market information. Taking into account the user's emotional state, it generates an optimal asset management plan or investment advice. In this process, if the user is feeling anxious, the server can adjust the recommendations accordingly, such as recommending a lower-risk plan.

[0716] The generated advice is sent to the user's device in text format and displayed to the user. Users can utilize this information to manage their assets in a more emotionally conscious way. Furthermore, new emotional data can be collected as user feedback to improve the accuracy of the advice.

[0717] For example, if a user enters "I'm a little worried about future investments," the server uses an emotion engine to recognize this feeling of "anxiety" and suggests a conservative investment strategy that is appropriate for it. The user can then use the suggested advice to make investment decisions with greater confidence.

[0718] This system configuration enables flexible asset management and the provision of financial information that takes into account the user's emotions.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] The user enters questions or requests regarding asset management via voice or text through the device. In the case of voice input, the device converts it to text using a speech recognition device and prepares to send the data to the server.

[0722] Step 2:

[0723] The terminal sends user input data to the server. The server receives this data and prepares for the next analysis process.

[0724] Step 3:

[0725] The server uses a generative AI to perform natural language analysis on the received user input and identify the user's intent. Based on the analysis results, it estimates what information is needed.

[0726] Step 4:

[0727] The server uses an emotion engine to analyze the user's emotional state from their voice tone and text context. It identifies emotions such as tension, anxiety, and relief to understand the user's state.

[0728] Step 5:

[0729] The server retrieves the user's past transaction data and market information from the database. Based on the identified user's needs and emotional state, it extracts relevant data.

[0730] Step 6:

[0731] The server integrates emotional states and data analysis results to generate an optimal asset management plan or investment advice for the user. For example, if anxiety is detected, it will suggest low-risk options.

[0732] Step 7:

[0733] The server formats the generated advice into a text message and sends it to the user's terminal.

[0734] Step 8:

[0735] The device displays advice received from the server to the user. Based on the provided information, the user can develop a concrete action plan and make emotionally conscious decisions. Furthermore, the device can provide additional input, including further questions and feedback.

[0736] (Example 2)

[0737] 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".

[0738] In modern asset management, there is a lack of advice that takes into account the emotional state and subjective anxieties of clients. As a result, clients may feel anxious when making investment decisions and may make inappropriate decisions. Furthermore, efficient asset management is not being carried out because changing market conditions and past transaction history are not being fully utilized.

[0739] 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.

[0740] In this invention, the server includes means for receiving information input from a user and transmitting it to an information processing device, means for analyzing the emotional state based on the voice tone and expression of the information input, and means for adjusting the recommended content of the advice based on the emotional state. This makes it possible to provide flexible and personalized asset management advice while taking into consideration the user's emotions.

[0741] A "user" is an entity that utilizes the system to receive asset management or investment advice.

[0742] "Information input" refers to voice or text data that users provide to the system.

[0743] An "information processing device" refers to a device or program that analyzes user input data received and performs the necessary processing.

[0744] "Linguistic analysis" is a technology that converts text and voice input from users into a format that computers can understand and identifies their intent.

[0745] "Identifying intent" means that the computer understands the true purpose and request from the user's input.

[0746] "Transaction information" refers to the historical data of transactions that a user has made in the past.

[0747] "Market information" refers to external information, including fluctuations in financial markets and related data.

[0748] "Emotional state" refers to information that indicates the user's mental state, and is analyzed from voice tone and text expression.

[0749] "Advice" refers to the guidelines and suggestions provided to users regarding their asset management.

[0750] "Recommended content" refers to a specific asset management plan proposed based on analysis results and the user's sentiment.

[0751] "Response" refers to the evaluation or opinion that a user gives to the advice provided by the system.

[0752] "Financial understanding" refers to the level of a user's knowledge and judgment regarding finance.

[0753] The system in this invention receives user input, analyzes it, and provides emotion-based asset management advice. The embodiments for carrying out the invention are described in detail below.

[0754] First, the user uses a device to input questions and instructions regarding asset management in either voice or text format. In the case of voice input, speech recognition software is used to convert it into text data. Specifically, general speech recognition technology is implemented as the software.

[0755] The terminal sends user input data to the server. The server uses the received text data to perform natural language processing (NLP) techniques. Specifically, it utilizes technologies such as the Google Cloud Natural Language API to analyze the input content and identify the user's intent.

[0756] Furthermore, the server utilizes an emotion analysis engine to determine the user's emotional state from their input. In this process, software such as IBM Watson Tone Analyzer is used to analyze whether the user's emotions are in a state of anxiety or reassurance.

[0757] The server collects users' past transaction information and the latest market information, and combines and analyzes this data. The technologies used for this analysis include data processing libraries such as Python's Pandas.

[0758] Based on the analysis results and sentiment analysis, the server uses a generative AI model to generate the optimal asset management plan or investment advice for the user. An example of a prompt to the generative AI model would be, "Generate the best investment advice based on the user's emotional state."

[0759] The generated advice is sent from the server to the terminal and displayed to the user. The user can manage their assets based on this information and send feedback on the provided advice back to the server via the terminal. Based on this feedback, the server can further improve the accuracy of future advice.

[0760] This will enable users to perform flexible asset management that takes their emotions into consideration, resulting in a system that allows them to engage in investment activities with greater peace of mind.

[0761] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0762] Step 1:

[0763] Users input questions and instructions regarding asset management into the terminal in either voice or text format. If the input is voice, it is converted to text by speech recognition software. The input data includes the user's specific questions and instructions.

[0764] Step 2:

[0765] The terminal transmits user input data to the server as digital data. In this process, the input data is securely transferred using encryption technology.

[0766] Step 3:

[0767] After receiving text input, the server begins analyzing the data using natural language processing (NLP) tools. Specifically, it uses the Google Cloud Natural Language API to analyze the input data and identify the user's intent. In this process, the input data is analyzed, and the user's intent and requests are clarified.

[0768] Step 4:

[0769] The server utilizes an emotion analysis engine based on voice tone and text expression to reveal the user's emotional state. For example, it uses IBM Watson Tone Analyzer to identify emotions such as anxiety and reassurance. The input to this analysis is the characteristics of the received text and voice, and the output is the identification of the user's emotional state.

[0770] Step 5:

[0771] The server retrieves the user's historical trading data and the latest market information from internal databases and external data sources, and integrates and analyzes this data. The analysis uses libraries such as Python's Pandas library, and the data is processed statistically. The output provides the user's past performance and market trends as analysis results.

[0772] Step 6:

[0773] The server uses a generative AI model to generate optimal asset management plans and investment advice based on the analysis results and sentiment analysis results. The generative AI model is given a prompt such as, "Generate optimal investment advice based on the user's emotional state." The output is investment advice optimized for the user.

[0774] Step 7:

[0775] The server sends the generated advice to the terminal in text format, and the terminal displays it to the user. The user can then review the presented information and manage their assets based on it.

[0776] Step 8:

[0777] Users send feedback on the advice they receive back to the server via their device. The server stores this feedback as new sentiment data and uses it to improve the advice generation process for future sessions. The input for this feedback is the user's evaluation and impressions, and the output is data that contributes to system improvement.

[0778] (Application Example 2)

[0779] 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".

[0780] Traditional asset management systems have struggled to provide advice that takes users' emotions into account, often leading to emotional anxiety and tension. This resulted in a challenge in making optimal investment decisions.

[0781] 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.

[0782] In this invention, the server includes means for using an emotion engine to recognize the user's emotional state, means for generating an asset management plan or investment advice based on the analysis results and emotional state, and means for providing the user with financial knowledge, generating information to improve financial literacy, and making suggestions that take the emotional state into consideration. This makes it possible to provide flexible and accurate asset management and investment advice that takes the user's emotions into consideration.

[0783] "Voice or text input" refers to voice or text data used by a user to communicate their intentions to a system.

[0784] A "server" is a computer system that processes information received from a user, generates results, and sends them to the user's terminal.

[0785] "Natural language processing" is a technology that analyzes data in natural language form input by users and interprets its meaning and intent.

[0786] An "emotion engine" is a technology that identifies a user's emotional state from their voice or text and provides information to the system based on that state.

[0787] "Past transaction data" refers to information about financial transactions that a user has previously made, and serves as basic data for asset management and investment advice.

[0788] "Market information" refers to the latest data and trends related to financial markets, and is used for asset management and investment decisions.

[0789] An "asset management plan or investment advice" is a proposal outlining how to manage a user's assets or what investments they should make.

[0790] "Financial literacy" refers to the ability or aptitude to improve an individual's financial knowledge and understanding, and to make better financial decisions.

[0791] The system implementing this invention consists of a terminal that receives user voice or text input, a cloud-based server, an emotion engine, a natural language processing engine, and financial data analysis software. The terminal can be a smartphone or a computer, and it sends the voice or text input by the user to the server.

[0792] The server is located in the cloud and uses a natural language processing engine to identify the user's intent. This process can utilize software such as the Google Cloud Natural Language API. The server then uses an emotion engine to analyze the user's emotions from their tone of voice and word choice. Various emotion models and tools are used for emotion analysis to identify the user's approximate emotional state—for example, "anxiety" or "reassurance."

[0793] Along with this data, the server analyzes the user's past transaction data and the latest market information using financial data analysis software. As a result, it generates asset management plans and investment advice that take into account the user's emotions and current economic situation. This generated advice is sent to the terminal in text format and displayed to the user.

[0794] For example, if a user sends the input "I'm worried because of the market instability" to the server, the emotion engine recognizes "anxiety" from this statement. In this case, the financial data analysis software suggests low-risk investment options and asset management plans that prioritize stability. Along with displaying this information to the user, it also provides additional financial knowledge to improve financial literacy.

[0795] An example of a prompt might be, "Asset management assistant, I'd like some advice on my investment situation. I'm concerned about market trends." This allows the user to express their feelings while receiving appropriate advice.

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The user provides voice or text input to the device. This input is captured through the device's interface. The input voice data is converted to text data and then sent to the server. As output of the input data, the voice is converted to text format.

[0799] Step 2:

[0800] The server analyzes the received text data using a natural language processing engine. This process utilizes software such as the Google Cloud Natural Language API to extract the user's intent. Text data is used as input, and user intent information is obtained as output. The analysis clarifies specific needs and questions.

[0801] Step 3:

[0802] The server uses an emotion engine to analyze the emotions in text data. The tone of voice in audio data is also considered to identify the user's emotions (e.g., "anxious," "relieved"). Input is emotional information in text or audio, and output is data related to the emotional state. The analysis evaluates the user's current psychological state.

[0803] Step 4:

[0804] The server retrieves the user's past trading data and market information, and performs financial data analysis based on this data. Past trading data and real-time market data are used as input data, and asset management plans or investment advice are generated as output. Financial data analysis software is utilized to calculate the optimal recommendations tailored to the user's situation.

[0805] Step 5:

[0806] The server sends an asset management plan or investment advice generated based on the emotional state and analysis results to the terminal. This data is displayed to the user in text format and presented in an easy-to-understand manner. The output data suggests what actions the user should take next.

[0807] Step 6:

[0808] Based on the information received, users can provide additional feedback or ask questions. This user feedback is then sent back to the server via the device. This allows the server to continuously improve the accuracy of its advice and helps the generative AI model generate more sophisticated responses through prompts.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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."

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] The following is further disclosed regarding the embodiments described above.

[0831] (Claim 1)

[0832] A means of receiving voice or text input from a user and sending it to a server,

[0833] A means of performing natural language analysis on user input received by the server to identify the user's intent,

[0834] A server provides a means for acquiring and analyzing users' past transaction data and market information,

[0835] A server provides means for generating an asset management plan or investment advice based on the analysis results,

[0836] A means of sending the generated advice to the user's terminal and displaying it to the user,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, wherein the server receives feedback from the user regarding asset management and improves the advice.

[0840] (Claim 3)

[0841] The system according to claim 1, which provides users with financial knowledge and generates information to improve their financial literacy.

[0842] "Example 1"

[0843] (Claim 1)

[0844] A means of acquiring voice or text input from a user and transmitting it to a computer,

[0845] A means of clarifying the user's purpose by performing natural language analysis on user input received by a computer,

[0846] A means by which a computer acquires and analyzes the user's past transaction records and market information,

[0847] A means by which a computer constructs an asset management plan or investment advice based on the analysis results,

[0848] A means of sending the constructed advice to the user's terminal and presenting it to the user,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the computer obtains feedback on the user's asset management and improves its advice.

[0852] (Claim 3)

[0853] The system according to claim 1, which provides users with financial knowledge and generates information to improve their financial knowledge.

[0854] "Application Example 1"

[0855] (Claim 1)

[0856] A means of recognizing voice input from the user and converting it into data,

[0857] Means for transmitting the converted data to an external processing device,

[0858] An external processing unit performs natural language analysis on user input received and identifies the intent,

[0859] An external processing unit acquires the user's past transaction data and market information, and provides means for analyzing the information.

[0860] An external processing unit provides means for generating an asset management plan or investment advice based on the analysis results,

[0861] A means for transmitting and presenting the generated advice to a display device,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, wherein an external processing unit receives feedback related to the user's asset management and improves the advice.

[0865] (Claim 3)

[0866] The system according to claim 1, which generates and presents information to provide users with financial knowledge and improve their financial literacy.

[0867] "Example 2 of combining an emotion engine"

[0868] (Claim 1)

[0869] A means for receiving information input from a user and transmitting it to an information processing device,

[0870] A means for an information processing device to perform linguistic analysis on user input received and identify the user's intent,

[0871] The information processing device has means for acquiring and analyzing the user's past transaction information and market information,

[0872] An information processing device provides means for generating an asset management plan or investment advice based on analysis results,

[0873] A means of sending the generated advice to the user's terminal and displaying it to the user,

[0874] A method for analyzing emotional states based on the voice tone and expression of information input,

[0875] A means of adjusting the recommendations for advice based on emotional state,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, wherein the information processing device receives feedback from the user regarding asset management and improves the advice.

[0879] (Claim 3)

[0880] The system according to claim 1, which provides users with financial knowledge and generates information to improve their financial understanding.

[0881] "Application example 2 when combining with an emotional engine"

[0882] (Claim 1)

[0883] A means of receiving voice or text input from a user and sending it to a server,

[0884] A means of performing natural language analysis on user input received by the server to identify the user's intent,

[0885] A means by which a server uses an emotion engine to recognize the user's emotional state,

[0886] A server provides a means for acquiring and analyzing users' past transaction data and market information,

[0887] A server provides means for generating an asset management plan or investment advice based on analysis results and emotional state,

[0888] A means of sending the generated advice to the user's terminal and displaying it to the user,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, wherein the server receives feedback from the user regarding asset management and improves the advice.

[0892] (Claim 3)

[0893] The system according to claim 1, which provides users with financial knowledge, generates information to improve financial literacy, and makes suggestions that take into account their emotional state. [Explanation of symbols]

[0894] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving voice or text input from a user and sending it to a server, A means of performing natural language analysis on user input received by the server to identify the user's intent, A server provides a means for acquiring and analyzing users' past transaction data and market information, A server provides means for generating an asset management plan or investment advice based on the analysis results, A means of sending the generated advice to the user's terminal and displaying it to the user, A system that includes this.

2. The system according to claim 1, wherein the server receives feedback from the user regarding asset management and improves the advice.

3. The system according to claim 1, which provides users with financial knowledge and generates information to improve their financial literacy.

Images