system

Abstract

Provide a system. 【Solution means】 Means for receiving the identification information of an enterprise, Means for automatically collecting relevant public information based on the received identification information, Means for analyzing the collected information and hypothesizing the problems of the enterprise, Means for selecting a suitable product or service based on the hypothesized problems and generating a proposal, Means for automatically generating negotiation materials based on the generated proposal and, Means for analyzing the real-time reaction from the user and proposing the next action and, Means for inputting customer data of e-commerce and identifying the purchasing trends and preferences of consumers, A system including means for automatically generating and providing a new product proposal based on the identified purchasing trends.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern sales activities, rapid and accurate information collection and analysis are required. Salespersons need a great deal of time and effort to collect various information, analyze it, and create materials. Also, it is difficult to analyze customer reactions during business negotiations in real time and take appropriate actions. Furthermore, effort is required for organizing information necessary for follow-up activities after business negotiations and generating proposals. There is a need for a system that can efficiently solve these problems.

Means for Solving the Problems

[0005] The present invention first provides a means for receiving company identification information. Next, it provides a means for automatically collecting publicly available information related to the company based on the received company identification information. Furthermore, it provides a means for analyzing the collected information and hypothesizing the company's challenges. Based on the hypothesized challenges, it provides a means for selecting suitable products or services and generating proposals. It also provides a means for automatically generating sales materials based on the generated proposals. Furthermore, it constructs a system that includes a means for analyzing real-time customer responses and proposing the next course of action. The aim of the present invention is to streamline the entire sales process and reduce the burden on sales representatives.

[0006] "Company identification information" refers to information used to identify a specific company, and includes company name, company code, etc.

[0007] "Public information" refers to information related to a company that is publicly accessible, such as investor relations (IR) information, financial statements, stock price trends, press releases, official websites, and official social media accounts.

[0008] "Automated data collection" is the process by which a system collects information based on a program, without human intervention.

[0009] "Analysis" is the process of interpreting collected data and deriving meaning from it, and in this case, it is done using natural language processing techniques and data analysis algorithms.

[0010] "Assuming a problem" means identifying potential problems and needs of a company that can be inferred from the analysis results.

[0011] "Suitable product or service" refers to a company's product or service that can provide the most effective solution to the assumed problem.

[0012] "Generating a proposal" means constructing a sales pitch to present to the customer based on the selected product or service.

[0013] "Sales materials" refer to documents created to be presented to customers as part of sales activities, and include presentation materials and talk scripts.

[0014] "Real-time response" refers to immediate feedback and questions from customers during a business negotiation.

[0015] "Follow-up activities" refer to additional customer support and proposal activities conducted after a business negotiation, and are actions taken to deepen the relationship with the customer. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Modes for Carrying Out the Invention

[0017] 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.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0020] 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.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system for streamlining sales activities and is implemented as follows: The process begins when a user inputs company identification information through the system. The terminal transmits the corresponding company identification information to the server. Based on the company name, the server automatically collects publicly available information related to the company from the internet. This includes IR information, financial statements, stock price trends, press releases, official websites, and official social media accounts.

[0038] The server analyzes the collected information using natural language processing techniques and hypothesizes the challenges the company may be facing. Next, based on these hypothetical challenges, the server generates the most suitable suggestions from its product or service database. These suggestions are customized to the company's specific needs and circumstances.

[0039] Subsequently, the server automatically creates sales materials, talk scripts, and anticipated Q&A based on the generated proposal. The terminal displays these materials to the user, allowing them to prepare for the sales meeting. During the meeting, the terminal receives real-time responses from the customer and sends that data to the server. The server immediately analyzes this data and suggests the next steps to the user based on the customer's responses.

[0040] After a sales negotiation is completed, the server automatically generates follow-up materials based on the negotiation details and provides them to the user, supporting their next sales activities. This frees sales representatives from repetitive tasks, allowing them to focus on more strategic sales activities.

[0041] As a concrete example, consider a scenario where a user is conducting business negotiations with a company in the pharmaceutical industry. The user enters the company name into the system. The server collects publicly available information related to the pharmaceutical industry and analyzes it to determine that the target company's R&D investment is increasing. The server assumes this is a challenge and generates a proposal for its own IT solutions specifically tailored to R&D. This allows the user to easily obtain effective negotiation materials and focus on communicating with the customer. This system effectively supports the entire sales process.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user launches the system and enters the identification information of the company they are negotiating with. The terminal receives this input and sends the data to the server.

[0045] Step 2:

[0046] Based on the received company identification information, the server collects publicly available information related to the company. This involves using web scraping techniques and API access to obtain IR information, financial statements, stock price trends, press releases, official websites, and official social media information from the internet.

[0047] Step 3:

[0048] Once data collection is complete, the server analyzes the acquired information using natural language processing techniques. This analysis involves understanding the content of each piece of information, extracting keywords, associating meanings, and hypothesizing about potential challenges the company may be facing.

[0049] Step 4:

[0050] The server selects the optimal solution from its product or service database based on the assumed challenge. This selection process takes into account factors such as the company's industry, size, and the market trends it faces.

[0051] Step 5:

[0052] Based on the selected proposals, the server automatically generates sales materials, talk scripts, and anticipated Q&A. The materials are created in a presentation format, making them visually easy to understand.

[0053] Step 6:

[0054] The terminal receives sales materials and talk scripts from the server and displays them to the user. This allows the user to proceed with preparing for the sales meeting.

[0055] Step 7:

[0056] During a business negotiation, when a user enters customer feedback or questions into their terminal, the server receives that data. The server analyzes this data in real time and, based on the results, proposes the next course of action or answers to the user.

[0057] Step 8:

[0058] After a business meeting, the server reviews the meeting's content, organizes the information needed for follow-up activities, and automatically generates additional proposals and materials. The terminal then provides this information to the user, supporting further sales activities.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In modern sales activities, it is crucial to quickly understand customer needs and make appropriate proposals. However, manually gathering and analyzing company-related information, generating optimal proposals, and determining the next course of action based on customer responses is time-consuming and inefficient. This invention aims to automate these processes, enabling more effective and strategic sales activities.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for receiving organizational identification data, means for automatically collecting relevant public data, and means for analyzing the collected information to estimate potential problems. This enables sales representatives to quickly grasp customer needs, automatically generate accurate proposal materials based on those needs, and conduct effective follow-up during and after sales negotiations.

[0064] "Organizational identification data" refers to data used to uniquely identify a specific organization, and includes the organization name, identification number, etc.

[0065] "Public data" refers to information that is widely accessible to the public through the internet and other public channels, and includes corporate investor relations information, financial statements, press releases, etc.

[0066] "Potential problems" refer to the challenges and risks that an organization is currently expected to face, and are estimated through information analysis.

[0067] A "proposal document" refers to a document that outlines the details of products or services offered, based on analyzed information and tailored to specific needs.

[0068] "Real-time response" refers to dynamic feedback and behavioral data obtained from customers during business negotiations, which forms the basis for users to quickly decide on their next course of action.

[0069] "Follow-up" refers to follow-up activities and provision of materials conducted after a business negotiation to support ongoing relationship building and additional sales activities.

[0070] "Natural language processing technology" refers to the technology used to process and analyze human language using computers, enabling tasks such as text analysis, translation, and summarization.

[0071] The embodiment of the invention involves constructing a system aimed at improving the efficiency of sales activities, utilizing organizational identification data to automate the collection, analysis, and proposal generation of diverse information related to target organizations.

[0072] First, the user enters organization identification data on the terminal. The terminal sends this identification data to the server, and the process begins.

[0073] The server uses programs written in Python or Java (registered trademark) and web scraping libraries such as BeautifulSoup and Selenium to collect relevant public data from the internet. This data includes IR information, financial results, stock price information, press releases, official websites, and official social media information.

[0074] After collection, the server analyzes the data using natural language processing techniques. It processes the information using Python's NLTK and spaCy libraries to estimate potential problems within the organization. This allows users to quickly gain deep insights.

[0075] Next, the server uses machine learning algorithms (e.g., Scikit-learn or TENSORFLOW®) to generate suitable suggestions from the company's products or services based on the analysis results. These generated suggestions are optimized to the needs of the relevant organization.

[0076] The generated information is incorporated into sales materials using a template engine such as Jinja2. The terminal displays this to the user, allowing the user to proceed with preparations for the sales meeting.

[0077] To consider a concrete example, when a user interacts with an organization in the pharmaceutical industry, after entering a specific organization name, the server might analyze the organization's research and development investment trends and propose corresponding IT solutions.

[0078] An example of a prompt statement could be, "Generate optimal solution proposals based on the latest developments in Organization A." Based on this prompt, the generating AI model assists in providing specific solutions.

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

[0080] Step 1:

[0081] The user enters organization identification data via a terminal. This data is sent to the server and becomes input data for the next process. The terminal reliably transmits the data using the HTTP or HTTPS protocol, and the server receives it.

[0082] Step 2:

[0083] The server uses the received organization identification data to collect publicly available data using scripting libraries such as BeautifulSoup and Selenium. Specifically, it obtains IR information, financial statements, stock price information, press releases, and updates to official websites through web scraping. In this process, the input is organization identification data, and the output is a structured public dataset.

[0084] Step 3:

[0085] The server analyzes collected public data using natural language processing techniques. It tokenizes text data using Python's NLTK or spaCy library and performs sentiment analysis and topic modeling. The input is the collected data, and the output is the analyzed text information along with the estimated potential problem.

[0086] Step 4:

[0087] The server generates proposals using machine learning algorithms based on the analysis results. The models used are created with Scikit-learn or TensorFlow, and the input is the analysis data, while the output is a product or service proposal optimized for the organization's needs.

[0088] Step 5:

[0089] The server automatically generates sales materials using a template engine such as Jinja2 based on the proposed content. These materials include not only the proposal but also a talk script and anticipated Q&A. The input is the generated proposal, and the output is a complete set of sales materials.

[0090] Step 6:

[0091] The terminal displays the generated sales negotiation materials to the user. The user can then use these materials to prepare for the negotiation. Specifically, the terminal screen provides materials with interactive navigation functions.

[0092] Step 7:

[0093] During a business negotiation, the terminal collects real-time customer responses and sends them to the server. The server analyzes this response data to estimate the customer's emotions and level of interest. The input is customer response data, and the output is improvement suggestions or next course of action.

[0094] Step 8:

[0095] After a business negotiation concludes, the server generates follow-up materials based on the negotiation details and customer feedback. These materials include information and supplementary materials for use in future negotiations. The input is negotiation record data, and the output is the follow-up materials.

[0096] (Application Example 1)

[0097] 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."

[0098] In modern business transactions and sales activities, it is essential to quickly and accurately understand customer needs and make effective proposals. However, accurately analyzing diverse customer purchasing trends and real-time feedback, and providing individually optimized proposals, is extremely difficult. Furthermore, efficiently conducting follow-up activities after sales negotiations is also a challenge.

[0099] 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.

[0100] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting relevant public information, and means for identifying consumer purchasing trends. This enables new product proposals based on information analysis and follow-up activities after business negotiations.

[0101] "Corporate identification information" refers to information used to distinguish a particular company from other companies, and includes company names, corporate identification numbers, and other similar information.

[0102] "Public information" refers to information that is accessible to the general public through the internet or other public media, including information posted on a company's website or official social media accounts.

[0103] "Sales materials" refer to documents and presentation materials used when making proposals or explanations to customers during sales activities.

[0104] "Real-time reactions" refer to the responses and feedback that customers give during business negotiations and sales activities, including their facial expressions and statements at the time.

[0105] "Consumer purchasing trends" refer to patterns of purchasing behavior and preferences that consumers have shown in the past, and are used to predict future purchasing behavior.

[0106] "Follow-up activities" refer to additional sales and support activities conducted after a business negotiation or transaction is completed, with the aim of maintaining relationships and securing future business.

[0107] This invention provides a system to support commercial transactions and sales activities. The system mainly consists of a server and user terminals, and collects and analyzes publicly available information and customer data based on company identification information.

[0108] The server first receives the company's identification information. This allows it to automatically collect relevant publicly available information from the internet. This process utilizes web scraping techniques. Next, Python and its libraries, NLTK and spaCy, are used to analyze the collected information using natural language processing techniques. Based on this analysis, the server hypothesizes potential challenges faced by the target company.

[0109] Next, the server identifies consumer purchasing trends. This involves analyzing customer data, which is performed using machine learning libraries such as TensorFlow. Based on this, it automatically generates and provides users with product recommendations and sales strategies optimized for customer needs.

[0110] User terminals have a smartphone application installed, which is used to view sales materials and communicate with customers. During sales meetings, the terminal also captures real-time customer responses and sends them to the server, allowing users to receive guidance on their next course of action.

[0111] As a concrete example, consider a company that sells organic cosmetics using this system. By entering the company name, the server automatically collects relevant market trends and customer reviews, and based on the analysis results, generates suggestions for new products and campaigns. In this process, prompts such as "Please come up with new product suggestions based on user feedback from your organic cosmetics e-commerce site" are used.

[0112] This will enable companies to quickly grasp market trends and conduct highly accurate sales activities.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The user enters the company's identification information into the terminal. The entered information is sent to the system's server. The input here includes the company name and corporate number, and the identification information is returned to the server as output, initiating the next process.

[0116] Step 2:

[0117] The server automatically collects publicly available information from the internet based on the received company identification information. Specifically, it uses web scraping technology to investigate the company's official website, social media, and industry news. In this process, the input is the identification information, and the output is the HTML data of the relevant information. This is then sent to the next analysis step.

[0118] Step 3:

[0119] The server analyzes the collected publicly available data using natural language processing techniques. It uses Python and its libraries (e.g., NLTK, spaCy) to extract current business challenges and consumer concerns from the text. The input is the information data from step 2, and the output is a list of challenges and keywords as a result of the analysis.

[0120] Step 4:

[0121] The server uses machine learning techniques to identify consumer purchasing trends based on the analyzed data. Here, a model using TensorFlow analyzes past purchase data to identify customer purchasing patterns. The input is the analysis result, and the output is the predicted purchasing trend.

[0122] Step 5:

[0123] The server generates product suggestions based on purchasing trends and assumed challenges. It utilizes a generative AI model to create prompts that provide the most suitable product suggestions to consumers, thus refining the suggestions. In this process, purchasing trends are used as input, and a list of suggestions is generated as output.

[0124] Step 6:

[0125] The terminal receives the sales materials and displays them to the user. The target user reviews the sales materials proposed by the system and prepares to communicate effectively with the customer. The input is the generated sales materials, and the output is the presentation materials ready for the user to use.

[0126] Step 7:

[0127] During a business negotiation, the terminal captures real-time responses from the customer. This includes voice input and analysis of video data. This data is transmitted to a server in real time and serves as input for the server to provide guidance on the next course of action. The output is the real-time feedback analysis results.

[0128] Step 8:

[0129] After a business meeting concludes, the server automatically generates follow-up materials and sends them to the user's terminal. This allows the user to utilize these materials for future sales efforts or approaches. Input consists of meeting history data and real-time response data, while output is the follow-up materials.

[0130] 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.

[0131] This invention relates to a system for streamlining sales activities that recognizes the emotions of users and customers and optimizes the sales process based on that recognition. While the system has basic functions for receiving company identification information and automatically collecting necessary publicly available information, it can further analyze the emotional states of users and customers by incorporating an emotion engine. The emotion engine utilizes speech recognition and natural language processing technologies to analyze emotions from spoken and written content during business negotiations.

[0132] The user accesses the system and starts the process by entering the identification information of the company they are trying to sell to. The terminal sends this input to the server. The server collects publicly available information based on the received information, analyzes it, and hypothesizes the company's challenges.

[0133] The emotion engine analyzes voice or text data acquired from users and customers during sales negotiations. This allows for real-time identification of emotional states based on the flow and content of the conversation. For example, it can determine whether a customer is interested or dissatisfied and adjust sales strategies accordingly.

[0134] Based on input from the emotion engine, the server has the capability to dynamically modify the content of sales materials and talk scripts. If necessary, it can generate new proposals during a sales meeting or adjust existing proposals.

[0135] As a concrete example, if the emotion engine detects a waning interest in a customer during a sales negotiation based on the customer's tone of voice and word choice, the server will suggest a talk script that emphasizes a different perspective or the advantages of a new product. In this way, interactions with customers in sales situations can be controlled more effectively. Furthermore, after the negotiation, follow-up materials are automatically generated, and advice is provided on how to continue building a relationship with the customer based on the results of the emotion analysis.

[0136] This system is expected to enable sales representatives to build deeper relationships with customers, thereby improving their performance.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user accesses the system interface and enters the identification information of the company with which they have a business meeting scheduled. The terminal receives this information and quickly sends it to the server.

[0140] Step 2:

[0141] Based on the received company identification information, the server efficiently collects publicly available information related to the company. Specifically, it crawls information sources such as IR information, financial results, stock price trends, press releases, official websites, and official social media accounts, and aggregates the necessary data.

[0142] Step 3:

[0143] The server analyzes the collected information. Utilizing natural language processing technology, it extracts key keywords from text data and uses them to hypothesize potential challenges facing the company.

[0144] Step 4:

[0145] Based on the assumed challenges, the server derives the optimal proposal from its solution database and generates the proposed content. This process includes selecting products and services that take into account the company's needs and market environment.

[0146] Step 5:

[0147] The server activates an emotion engine to analyze voice or text data acquired from users and customers during sales negotiations. This analysis allows for real-time recognition of the customer's emotional state and the adaptation of the sales process accordingly.

[0148] Step 6:

[0149] Based on the customer's emotional state recognized by the emotion engine, the server automatically and dynamically adjusts the content of sales materials and talk scripts. For example, if the customer's interest is waning, the content will be changed to emphasize a different proposal or new benefits.

[0150] Step 7:

[0151] The terminal provides users with pre-configured sales materials and talk scripts. Users can use these materials to respond flexibly according to the flow of the sales negotiation.

[0152] Step 8:

[0153] Once a business negotiation concludes, the server automatically generates follow-up materials based on the negotiation content and sentiment analysis results. The terminal then provides these materials to the user, supporting the next steps in building long-term relationships with the customer.

[0154] (Example 2)

[0155] 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".

[0156] In sales activities, accurately understanding customer emotions and providing flexible sales materials and proposals tailored to those emotions is difficult. Furthermore, appropriate advice based on emotion analysis is required during post-sales follow-up, but current systems lack the means to efficiently perform this task.

[0157] 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.

[0158] In this invention, the server includes means for receiving corporate identification information, means for collecting publicly available information, means for analyzing emotional states, means for dynamically updating sales materials, and means for generating follow-up materials. This enables flexible sales activities and accurate follow-up based on customer emotions.

[0159] "Company identification information" refers to information used to identify a specific company, and includes data such as the company name and industry.

[0160] "Public information" refers to information related to a company that can be obtained from the internet or other public sources.

[0161] A "challenge" is a hypothesis that refers to a problem or area for improvement that a particular company is facing.

[0162] "Emotional state" refers to the emotional state analyzed from a customer's or user's voice or text, and includes states of emotions such as interest and dissatisfaction.

[0163] "Business negotiation materials" refer to proposals and informational documents used in business negotiations.

[0164] "Follow-up materials" are documents containing additional information generated after a business meeting to maintain the relationship with the customer and prepare for the next meeting.

[0165] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and is used for text analysis and emotion extraction.

[0166] A "generative AI model" is an artificial intelligence model used to generate new information or suggestions based on input data.

[0167] This invention provides a configuration for implementing a system to streamline sales activities, and specifically describes the roles of the server, terminal, and user.

[0168] First, the user uses their device to enter the identification information of the company they are negotiating with. This device can be a standard computer or mobile device, and uses a dedicated web application that runs in a browser. Once the user enters the information, the device sends this information to the server via the HTTPS protocol.

[0169] The server collects relevant publicly available information from the internet based on the received company identification information. The server extracts data using web scraping techniques and processes this information using data analysis software. For example, Python libraries can be used for this processing. Based on the data analysis results, the server hypothesizes the company's challenges and constructs the necessary materials for business negotiations.

[0170] Next, the emotion engine analyzes the voice or text data acquired during the sales negotiation. The emotion engine analyzes emotional states in real time, for example, using Google® Cloud Natural Language API or IBM's speech recognition service. Based on the analysis results, the server has the functionality to dynamically update documents and dialogue content during the sales negotiation.

[0171] For example, if the emotion engine determines that a customer's interest is waning during a business negotiation, the server can use a generative AI model to generate a proposal that presents an alternative perspective. This could include text and slides that highlight the benefits from various viewpoints.

[0172] Finally, follow-up materials for the sales meeting are automatically generated by the server. These materials include advice for the next sales meeting and customer follow-up, based on insights from sentiment analysis. These follow-up materials are provided in a format that is easy for the user to review.

[0173] An example of a prompt message that can be input into the AI ​​model is, "If a customer has shown interest in the new product, generate additional information to clearly explain its details." This makes it possible to instantly obtain the necessary suggestions for advancing sales activities.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The user uses a terminal to input company identification information for the business negotiation. Specifically, the user fills in the company name and industry information in the input form on the terminal and presses the "Submit" button. This input data forms the basis for the next processing step.

[0177] Step 2:

[0178] The terminal sends the entered information to the server. The terminal securely transmits the data to the server via the HTTPS protocol. In this process, the company identification information entered by the user is passed to the server and becomes input data for the next data collection process.

[0179] Step 3:

[0180] The server extracts data from the internet based on company identification information to collect publicly available information. Specifically, it uses web scraping technology. Here, the target information sources are official websites and news articles. The publicly available information obtained through this process becomes the input data for the next analysis step.

[0181] Step 4:

[0182] The server processes the collected public information and makes assumptions about the company's challenges. The server uses text analysis algorithms to organize the obtained information and identify potential challenges. This analysis then passes the assumptions about the challenges on to the next sentiment analysis step.

[0183] Step 5:

[0184] The emotion engine analyzes voice or text data obtained from users and customers. Specifically, the server converts the voice data into text and uses natural language processing techniques to determine the emotional state. The output of this step is an evaluation of the emotions observed in the conversation.

[0185] Step 6:

[0186] The server dynamically updates sales materials and dialogue content based on sentiment analysis results. It utilizes a generative AI model to generate new proposals and points to emphasize. Prompt statements are input into the model, enabling flexible material updates. This output is presented to the user and reflected in the sales negotiation.

[0187] Step 7:

[0188] After a business meeting, the server generates follow-up materials and provides them to the user. Based on sentiment analysis data, the server automatically creates a report containing advice for future customer follow-ups. This material is delivered to the user via email or a dashboard.

[0189] (Application Example 2)

[0190] 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".

[0191] There is a growing need to optimize sales activities according to the customer's emotional state. Traditional methods have made it difficult to analyze customer emotions in real time and reflect them in the sales process. Furthermore, the optimization of visual information based on customer emotions has been very limited. As a result, there is a challenge in providing customers with attractive and effective information.

[0192] 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.

[0193] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting publicly available information, means for analyzing the collected information and hypothesizing problems, and means for dynamically changing visual information based on the user's emotional state using emotion analysis means and displaying optimized information. This enables effective sales processes and information provision that respond to customer emotions.

[0194] "Corporate identification information" is a general term for information used to identify a specific legal entity or business.

[0195] "Public information" refers to publicly available information related to a company, such as data and reports.

[0196] "Analyzing collected information" refers to a method of thoroughly investigating the obtained data and extracting hidden trends and useful insights.

[0197] "Assumed challenges" are problems that are predicted for a particular company or situation based on the results of the analysis of collected information.

[0198] "Generating proposals" means devising solutions and improvement measures based on information analysis and presenting them in a concrete form.

[0199] "Sales materials" refer to documents and presentation materials created to convey proposals and information during business negotiations and business activities.

[0200] "Real-time response" refers to the immediate reaction or feedback that a customer provides in a given situation.

[0201] "Emotional analysis tools" refer to technologies and devices used to identify and analyze emotions from sources such as voice, text, and facial expressions.

[0202] "Dynamically changing visual information" means changing the displayed information in real time and updating it to appropriate content according to the user's situation and needs.

[0203] "Optimized information" refers to information that has been processed or adjusted to best match the user's expectations and objectives.

[0204] This system automatically collects and analyzes relevant publicly available information upon receiving company identification information. The server thoroughly analyzes the collected data using speech recognition and natural language processing technologies. This identifies hypothetical challenges faced by a particular company and generates product and service proposals based on these challenges. Once proposals are generated, sales materials are automatically created based on them.

[0205] Furthermore, users can utilize sentiment analysis tools during normal business negotiations to capture real-time customer reactions. The results are processed on a server, forming the basis for adjusting sales strategies as needed and suggesting the next course of action. This sentiment analysis can be performed using hardware equipped with cameras and microphones. Once the emotional state is identified, optimized visual information is displayed, enabling a more effective approach to the customer.

[0206] For example, if a user is using smart glasses while strolling through a park and listening to music, the system will determine that the user is relaxed, and then appropriate advertisements will be displayed in the user's field of vision. The aim is to provide valuable information to both the user and the company.

[0207] Examples of prompts for a generative AI model:

[0208] "What kind of ads are suitable for users when they are relaxing?"

[0209] In this way, it becomes possible to conduct sales activities that take into account customer emotions in real time.

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The user enters company identification information into the terminal. This prepares the terminal to send that information to the server. This input data forms the basis for identifying the target company.

[0213] Step 2:

[0214] Based on the received company identification information, the server collects relevant publicly available information via the internet. This process utilizes web crawling technology to retrieve data from databases that show the company's operational status and industry trends. The collected information is then used in the next analysis step.

[0215] Step 3:

[0216] The server analyzes the collected public information and uses natural language processing techniques to hypothesize potential challenges faced by the company. This analysis extracts keywords from documents and reports, and uses them to identify potential problems the company may be facing. The output of this step is a list of hypothesized challenges.

[0217] Step 4:

[0218] The server selects appropriate products and services based on the assumed problem and generates proposals. During this process, it uses a generative AI model to refine the proposals based on past data and success stories. The output of this process is detailed information about the generated proposals.

[0219] Step 5:

[0220] The server automatically generates materials for use in sales negotiations based on the generated proposal. These materials include a summary of the proposal, its benefits, and expected effects. The negotiation materials are output in a format that sales representatives can use directly.

[0221] Step 6:

[0222] During a sales meeting, the user collects customer voice and facial expressions in real time via a terminal and transmits this data to a server. The server processes this data using sentiment analysis tools to identify the customer's emotional state. The analysis results are used to adjust the sales strategy on the spot.

[0223] Step 7:

[0224] Based on the sentiment analysis results, the server dynamically modifies the sales talk script and proposal content, and generates new proposals as needed. The output of this step is a sales strategy optimized for customer responses.

[0225] Step 8:

[0226] After a sales meeting concludes, the server generates additional information based on the data obtained during the meeting to support follow-up activities and sends it to the user. This information includes specific action ideas for maintaining the relationship with the customer.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] This invention is a system for streamlining sales activities and is implemented as follows: The process begins when a user inputs company identification information through the system. The terminal transmits the corresponding company identification information to the server. Based on the company name, the server automatically collects publicly available information related to the company from the internet. This includes IR information, financial statements, stock price trends, press releases, official websites, and official social media accounts.

[0244] The server analyzes the collected information using natural language processing techniques and hypothesizes the challenges the company may be facing. Next, based on these hypothetical challenges, the server generates the most suitable suggestions from its product or service database. These suggestions are customized to the company's specific needs and circumstances.

[0245] Subsequently, the server automatically creates sales materials, talk scripts, and anticipated Q&A based on the generated proposal. The terminal displays these materials to the user, allowing them to prepare for the sales meeting. During the meeting, the terminal receives real-time responses from the customer and sends that data to the server. The server immediately analyzes this data and suggests the next steps to the user based on the customer's responses.

[0246] After a sales negotiation is completed, the server automatically generates follow-up materials based on the negotiation details and provides them to the user, supporting their next sales activities. This frees sales representatives from repetitive tasks, allowing them to focus on more strategic sales activities.

[0247] As a concrete example, consider a scenario where a user is conducting business negotiations with a company in the pharmaceutical industry. The user enters the company name into the system. The server collects publicly available information related to the pharmaceutical industry and analyzes it to determine that the target company's R&D investment is increasing. The server assumes this is a challenge and generates a proposal for its own IT solutions specifically tailored to R&D. This allows the user to easily obtain effective negotiation materials and focus on communicating with the customer. This system effectively supports the entire sales process.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The user launches the system and enters the identification information of the company they are negotiating with. The terminal receives this input and sends the data to the server.

[0251] Step 2:

[0252] Based on the received company identification information, the server collects publicly available information related to the company. This involves using web scraping techniques and API access to obtain IR information, financial statements, stock price trends, press releases, official websites, and official social media information from the internet.

[0253] Step 3:

[0254] Once data collection is complete, the server analyzes the acquired information using natural language processing techniques. This analysis involves understanding the content of each piece of information, extracting keywords, associating meanings, and hypothesizing about potential challenges the company may be facing.

[0255] Step 4:

[0256] The server selects the optimal solution from its product or service database based on the assumed challenge. This selection process takes into account factors such as the company's industry, size, and the market trends it faces.

[0257] Step 5:

[0258] Based on the selected proposals, the server automatically generates sales materials, talk scripts, and anticipated Q&A. The materials are created in a presentation format, making them visually easy to understand.

[0259] Step 6:

[0260] The terminal receives sales materials and talk scripts from the server and displays them to the user. This allows the user to proceed with preparing for the sales meeting.

[0261] Step 7:

[0262] During a business negotiation, when a user enters customer feedback or questions into their terminal, the server receives that data. The server analyzes this data in real time and, based on the results, proposes the next course of action or answers to the user.

[0263] Step 8:

[0264] After a business meeting, the server reviews the meeting's content, organizes the information needed for follow-up activities, and automatically generates additional proposals and materials. The terminal then provides this information to the user, supporting further sales activities.

[0265] (Example 1)

[0266] 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."

[0267] In modern sales activities, it is crucial to quickly understand customer needs and make appropriate proposals. However, manually gathering and analyzing company-related information, generating optimal proposals, and determining the next course of action based on customer responses is time-consuming and inefficient. This invention aims to automate these processes, enabling more effective and strategic sales activities.

[0268] 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.

[0269] In this invention, the server includes means for receiving organizational identification data, means for automatically collecting relevant public data, and means for analyzing the collected information to estimate potential problems. This enables sales representatives to quickly grasp customer needs, automatically generate accurate proposal materials based on those needs, and conduct effective follow-up during and after sales negotiations.

[0270] "Organizational identification data" refers to data used to uniquely identify a specific organization, and includes the organization name, identification number, etc.

[0271] "Public data" refers to information that is widely accessible to the public through the internet and other public channels, and includes corporate investor relations information, financial statements, press releases, etc.

[0272] "Potential problems" refer to the challenges and risks that an organization is currently expected to face, and are estimated through information analysis.

[0273] A "proposal document" refers to a document that outlines the details of products or services offered, based on analyzed information and tailored to specific needs.

[0274] "Real-time response" refers to dynamic feedback and behavioral data obtained from customers during business negotiations, which forms the basis for users to quickly decide on their next course of action.

[0275] "Follow-up" refers to follow-up activities and provision of materials conducted after a business negotiation to support ongoing relationship building and additional sales activities.

[0276] "Natural language processing technology" refers to the technology used to process and analyze human language using computers, enabling tasks such as text analysis, translation, and summarization.

[0277] The embodiment of the invention involves constructing a system aimed at improving the efficiency of sales activities, utilizing organizational identification data to automate the collection, analysis, and proposal generation of diverse information related to target organizations.

[0278] First, the user enters organization identification data on the terminal. The terminal sends this identification data to the server, and the process begins.

[0279] The server uses programs written in Python or Java, utilizes web scraping libraries such as BeautifulSoup and Selenium, and collects relevant public data from the Internet. This data includes IR information, financial statement information, stock price information, press releases, official websites, and information from official SNS.

[0280] After collection, the server analyzes the data using natural language processing techniques. It processes the information using Python's NLTK and spaCy libraries to estimate potential problems within the organization. This enables users to quickly gain in-depth insights.

[0281] Next, the server uses machine learning algorithms (such as those using Scikit-learn or TensorFlow) to generate suitable proposals based on the analysis results for the company's products or services. These generated proposals are optimized for the needs of the relevant organization.

[0282] The generated information is incorporated into negotiation materials using a template engine such as Jinja2. The terminal displays this to the user, allowing the user to proceed with preparations for the negotiation.

[0283] As a specific example, when a user is dealing with an organization in the pharmaceutical industry, after entering a specific organization name, the server may analyze trends such as the organization's research and development investment trends and propose corresponding IT solutions.

[0284] As an example of a prompt sentence, a form such as "Generate an optimal solution proposal based on the latest trends of Organization A" can be used. Based on this prompt, the generative AI model provides support in offering specific solutions.

[0285] The flow of the specific process in Example 1 will be described using Figure 11.

[0286] Step 1:

[0287] The user enters organization identification data via a terminal. This data is sent to the server and becomes input data for the next process. The terminal reliably transmits the data using the HTTP or HTTPS protocol, and the server receives it.

[0288] Step 2:

[0289] The server uses the received organization identification data to collect publicly available data using scripting libraries such as BeautifulSoup and Selenium. Specifically, it obtains IR information, financial statements, stock price information, press releases, and updates to official websites through web scraping. In this process, the input is organization identification data, and the output is a structured public dataset.

[0290] Step 3:

[0291] The server analyzes collected public data using natural language processing techniques. It tokenizes text data using Python's NLTK or spaCy library and performs sentiment analysis and topic modeling. The input is the collected data, and the output is the analyzed text information along with the estimated potential problem.

[0292] Step 4:

[0293] The server generates proposals using machine learning algorithms based on the analysis results. The models used are created with Scikit-learn or TensorFlow, and the input is the analysis data, while the output is a product or service proposal optimized for the organization's needs.

[0294] Step 5:

[0295] The server automatically generates sales materials using a template engine such as Jinja2 based on the proposed content. These materials include not only the proposal but also a talk script and anticipated Q&A. The input is the generated proposal, and the output is a complete set of sales materials.

[0296] Step 6:

[0297] The terminal displays the generated sales negotiation materials to the user. The user can then use these materials to prepare for the negotiation. Specifically, the terminal screen provides materials with interactive navigation functions.

[0298] Step 7:

[0299] During a business negotiation, the terminal collects real-time customer responses and sends them to the server. The server analyzes this response data to estimate the customer's emotions and level of interest. The input is customer response data, and the output is improvement suggestions or next course of action.

[0300] Step 8:

[0301] After a business negotiation concludes, the server generates follow-up materials based on the negotiation details and customer feedback. These materials include information and supplementary materials for use in future negotiations. The input is negotiation record data, and the output is the follow-up materials.

[0302] (Application Example 1)

[0303] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0304] In modern business transactions and sales activities, it is essential to quickly and accurately understand customer needs and make effective proposals. However, accurately analyzing diverse customer purchasing trends and real-time feedback, and providing individually optimized proposals, is extremely difficult. Furthermore, efficiently conducting follow-up activities after sales negotiations is also a challenge.

[0305] 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.

[0306] In this invention, the server includes means for receiving the identification information of an enterprise, means for automatically collecting relevant public information, and means for identifying the purchasing tendencies of consumers. As a result, it becomes possible to propose new products based on information analysis and conduct follow-up activities after business negotiations.

[0307] The "identification information of an enterprise" is information used to distinguish a specific enterprise from other enterprises, and includes company names, corporate numbers, etc.

[0308] "Public information" is information that is generally accessible through the Internet and other publicly available media, and includes information posted on the enterprise's website and official SNS.

[0309] "Business negotiation materials" are documents and presentation materials used when making proposals and explanations to customers in business activities.

[0310] "Real-time response" is the response and feedback shown by customers during business negotiations and business activities, including on-site expressions and statements.

[0311] The "purchasing tendencies of consumers" are the patterns of purchasing behavior and preferences shown by consumers in the past, and are used to predict future purchasing behavior.

[0312] "Follow-up activities" are additional business and support activities carried out after business negotiations and transaction completions, and are activities for maintaining relationships and leading to future transactions.

[0313] This invention provides a system for supporting commercial transactions and business activities. The system is mainly composed of a server and user terminals, collects public information and customer data based on the identification information of an enterprise, and conducts analysis.

[0314] The server first receives the company's identification information. This allows it to automatically collect relevant publicly available information from the internet. This process utilizes web scraping techniques. Next, Python and its libraries, NLTK and spaCy, are used to analyze the collected information using natural language processing techniques. Based on this analysis, the server hypothesizes potential challenges faced by the target company.

[0315] Next, the server identifies consumer purchasing trends. This involves analyzing customer data, which is performed using machine learning libraries such as TensorFlow. Based on this, it automatically generates and provides users with product recommendations and sales strategies optimized for customer needs.

[0316] User terminals have a smartphone application installed, which is used to view sales materials and communicate with customers. During sales meetings, the terminal also captures real-time customer responses and sends them to the server, allowing users to receive guidance on their next course of action.

[0317] As a concrete example, consider a company that sells organic cosmetics using this system. By entering the company name, the server automatically collects relevant market trends and customer reviews, and based on the analysis results, generates suggestions for new products and campaigns. In this process, prompts such as "Please come up with new product suggestions based on user feedback from your organic cosmetics e-commerce site" are used.

[0318] This will enable companies to quickly grasp market trends and conduct highly accurate sales activities.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The user enters the company's identification information into the terminal. The entered information is sent to the system's server. The input here includes the company name and corporate number, and the identification information is returned to the server as output, initiating the next process.

[0322] Step 2:

[0323] The server automatically collects publicly available information from the internet based on the received company identification information. Specifically, it uses web scraping technology to investigate the company's official website, social media, and industry news. In this process, the input is the identification information, and the output is the HTML data of the relevant information. This is then sent to the next analysis step.

[0324] Step 3:

[0325] The server analyzes the collected publicly available data using natural language processing techniques. It uses Python and its libraries (e.g., NLTK, spaCy) to extract current business challenges and consumer concerns from the text. The input is the information data from step 2, and the output is a list of challenges and keywords as a result of the analysis.

[0326] Step 4:

[0327] The server uses machine learning techniques to identify consumer purchasing trends based on the analyzed data. Here, a model using TensorFlow analyzes past purchase data to identify customer purchasing patterns. The input is the analysis result, and the output is the predicted purchasing trend.

[0328] Step 5:

[0329] The server generates product suggestions based on purchasing trends and assumed challenges. It utilizes a generative AI model to create prompts that provide the most suitable product suggestions to consumers, thus refining the suggestions. In this process, purchasing trends are used as input, and a list of suggestions is generated as output.

[0330] Step 6:

[0331] The terminal receives the sales materials and displays them to the user. The target user reviews the sales materials proposed by the system and prepares to communicate effectively with the customer. The input is the generated sales materials, and the output is the presentation materials ready for the user to use.

[0332] Step 7:

[0333] During a business negotiation, the terminal captures real-time responses from the customer. This includes voice input and analysis of video data. This data is transmitted to a server in real time and serves as input for the server to provide guidance on the next course of action. The output is the real-time feedback analysis results.

[0334] Step 8:

[0335] After a business meeting concludes, the server automatically generates follow-up materials and sends them to the user's terminal. This allows the user to utilize these materials for future sales efforts or approaches. Input consists of meeting history data and real-time response data, while output is the follow-up materials.

[0336] 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.

[0337] This invention relates to a system for streamlining sales activities that recognizes the emotions of users and customers and optimizes the sales process based on that recognition. While the system has basic functions for receiving company identification information and automatically collecting necessary publicly available information, it can further analyze the emotional states of users and customers by incorporating an emotion engine. The emotion engine utilizes speech recognition and natural language processing technologies to analyze emotions from spoken and written content during business negotiations.

[0338] The user accesses the system and starts the process by entering the identification information of the company they are trying to sell to. The terminal sends this input to the server. The server collects publicly available information based on the received information, analyzes it, and hypothesizes the company's challenges.

[0339] The emotion engine analyzes voice or text data acquired from users and customers during sales negotiations. This allows for real-time identification of emotional states based on the flow and content of the conversation. For example, it can determine whether a customer is interested or dissatisfied and adjust sales strategies accordingly.

[0340] Based on input from the emotion engine, the server has the capability to dynamically modify the content of sales materials and talk scripts. If necessary, it can generate new proposals during a sales meeting or adjust existing proposals.

[0341] As a concrete example, if the emotion engine detects a waning interest in a customer during a sales negotiation based on the customer's tone of voice and word choice, the server will suggest a talk script that emphasizes a different perspective or the advantages of a new product. In this way, interactions with customers in sales situations can be controlled more effectively. Furthermore, after the negotiation, follow-up materials are automatically generated, and advice is provided on how to continue building a relationship with the customer based on the results of the emotion analysis.

[0342] This system is expected to enable sales representatives to build deeper relationships with customers, thereby improving their performance.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] The user accesses the system interface and enters the identification information of the company with which they have a business meeting scheduled. The terminal receives this information and quickly sends it to the server.

[0346] Step 2:

[0347] Based on the received company identification information, the server efficiently collects publicly available information related to the company. Specifically, it crawls information sources such as IR information, financial results, stock price trends, press releases, official websites, and official social media accounts, and aggregates the necessary data.

[0348] Step 3:

[0349] The server analyzes the collected information. Utilizing natural language processing technology, it extracts key keywords from text data and uses them to hypothesize potential challenges facing the company.

[0350] Step 4:

[0351] Based on the assumed challenges, the server derives the optimal proposal from its solution database and generates the proposed content. This process includes selecting products and services that take into account the company's needs and market environment.

[0352] Step 5:

[0353] The server activates an emotion engine to analyze voice or text data acquired from users and customers during sales negotiations. This analysis allows for real-time recognition of the customer's emotional state and the adaptation of the sales process accordingly.

[0354] Step 6:

[0355] Based on the customer's emotional state recognized by the emotion engine, the server automatically and dynamically adjusts the content of sales materials and talk scripts. For example, if the customer's interest is waning, the content will be changed to emphasize a different proposal or new benefits.

[0356] Step 7:

[0357] The terminal provides users with pre-configured sales materials and talk scripts. Users can use these materials to respond flexibly according to the flow of the sales negotiation.

[0358] Step 8:

[0359] Once a business negotiation concludes, the server automatically generates follow-up materials based on the negotiation content and sentiment analysis results. The terminal then provides these materials to the user, supporting the next steps in building long-term relationships with the customer.

[0360] (Example 2)

[0361] 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".

[0362] In sales activities, accurately understanding customer emotions and providing flexible sales materials and proposals tailored to those emotions is difficult. Furthermore, appropriate advice based on emotion analysis is required during post-sales follow-up, but current systems lack the means to efficiently perform this task.

[0363] 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.

[0364] In this invention, the server includes means for receiving corporate identification information, means for collecting publicly available information, means for analyzing emotional states, means for dynamically updating sales materials, and means for generating follow-up materials. This enables flexible sales activities and accurate follow-up based on customer emotions.

[0365] "Company identification information" refers to information used to identify a specific company, and includes data such as the company name and industry.

[0366] "Public information" refers to information related to a company that can be obtained from the internet or other public sources.

[0367] A "challenge" is a hypothesis that refers to a problem or area for improvement that a particular company is facing.

[0368] "Emotional state" refers to the emotional state analyzed from a customer's or user's voice or text, and includes states of emotions such as interest and dissatisfaction.

[0369] "Business negotiation materials" refer to proposals and informational documents used in business negotiations.

[0370] "Follow-up materials" are documents containing additional information generated after a business meeting to maintain the relationship with the customer and prepare for the next meeting.

[0371] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and is used for text analysis and emotion extraction.

[0372] A "generative AI model" is an artificial intelligence model used to generate new information or suggestions based on input data.

[0373] This invention provides a configuration for implementing a system to streamline sales activities, and specifically describes the roles of the server, terminal, and user.

[0374] First, the user uses their device to enter the identification information of the company they are negotiating with. This device can be a standard computer or mobile device, and uses a dedicated web application that runs in a browser. Once the user enters the information, the device sends this information to the server via the HTTPS protocol.

[0375] The server collects relevant publicly available information from the internet based on the received company identification information. The server extracts data using web scraping techniques and processes this information using data analysis software. For example, Python libraries can be used for this processing. Based on the data analysis results, the server hypothesizes the company's challenges and constructs the necessary materials for business negotiations.

[0376] Next, the emotion engine analyzes the voice or text data acquired during the sales meeting. The emotion engine analyzes emotional states in real time, for example, using the Google Cloud Natural Language API or IBM's speech recognition service. Based on the analysis results, the server has the capability to dynamically update documents and dialogue content from the sales meeting.

[0377] For example, if the emotion engine determines that a customer's interest is waning during a business negotiation, the server can use a generative AI model to generate a proposal that presents an alternative perspective. This could include text and slides that highlight the benefits from various viewpoints.

[0378] Finally, follow-up materials for the sales meeting are automatically generated by the server. These materials include advice for the next sales meeting and customer follow-up, based on insights from sentiment analysis. These follow-up materials are provided in a format that is easy for the user to review.

[0379] An example of a prompt message that can be input into the AI ​​model is, "If a customer has shown interest in the new product, generate additional information to clearly explain its details." This makes it possible to instantly obtain the necessary suggestions for advancing sales activities.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] The user uses a terminal to input company identification information for the business negotiation. Specifically, the user fills in the company name and industry information in the input form on the terminal and presses the "Submit" button. This input data forms the basis for the next processing step.

[0383] Step 2:

[0384] The terminal sends the entered information to the server. The terminal securely transmits the data to the server via the HTTPS protocol. In this process, the company identification information entered by the user is passed to the server and becomes input data for the next data collection process.

[0385] Step 3:

[0386] The server extracts data from the internet based on company identification information to collect publicly available information. Specifically, it uses web scraping technology. Here, the target information sources are official websites and news articles. The publicly available information obtained through this process becomes the input data for the next analysis step.

[0387] Step 4:

[0388] The server processes the collected public information and makes assumptions about the company's challenges. The server uses text analysis algorithms to organize the obtained information and identify potential challenges. This analysis then passes the assumptions about the challenges on to the next sentiment analysis step.

[0389] Step 5:

[0390] The emotion engine analyzes voice or text data obtained from users and customers. Specifically, the server converts the voice data into text and uses natural language processing techniques to determine the emotional state. The output of this step is an evaluation of the emotions observed in the conversation.

[0391] Step 6:

[0392] The server dynamically updates sales materials and dialogue content based on sentiment analysis results. It utilizes a generative AI model to generate new proposals and points to emphasize. Prompt statements are input into the model, enabling flexible material updates. This output is presented to the user and reflected in the sales negotiation.

[0393] Step 7:

[0394] After a business meeting, the server generates follow-up materials and provides them to the user. Based on sentiment analysis data, the server automatically creates a report containing advice for future customer follow-ups. This material is delivered to the user via email or a dashboard.

[0395] (Application Example 2)

[0396] 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."

[0397] There is a growing need to optimize sales activities according to the customer's emotional state. Traditional methods have made it difficult to analyze customer emotions in real time and reflect them in the sales process. Furthermore, the optimization of visual information based on customer emotions has been very limited. As a result, there is a challenge in providing customers with attractive and effective information.

[0398] 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.

[0399] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting publicly available information, means for analyzing the collected information and hypothesizing problems, and means for dynamically changing visual information based on the user's emotional state using emotion analysis means and displaying optimized information. This enables effective sales processes and information provision that respond to customer emotions.

[0400] "Corporate identification information" is a general term for information used to identify a specific legal entity or business.

[0401] "Public information" refers to publicly available information related to a company, such as data and reports.

[0402] "Analyzing collected information" refers to a method of thoroughly investigating the obtained data and extracting hidden trends and useful insights.

[0403] "Assumed challenges" are problems that are predicted for a particular company or situation based on the results of the analysis of collected information.

[0404] "Generating proposals" means devising solutions and improvement measures based on information analysis and presenting them in a concrete form.

[0405] "Sales materials" refer to documents and presentation materials created to convey proposals and information during business negotiations and business activities.

[0406] "Real-time response" refers to the immediate reaction or feedback that a customer provides in a given situation.

[0407] "Emotional analysis tools" refer to technologies and devices used to identify and analyze emotions from sources such as voice, text, and facial expressions.

[0408] "Dynamically changing visual information" means changing the displayed information in real time and updating it to appropriate content according to the user's situation and needs.

[0409] "Optimized information" refers to information that has been processed or adjusted to best match the user's expectations and objectives.

[0410] This system automatically collects and analyzes relevant publicly available information upon receiving company identification information. The server thoroughly analyzes the collected data using speech recognition and natural language processing technologies. This identifies hypothetical challenges faced by a particular company and generates product and service proposals based on these challenges. Once proposals are generated, sales materials are automatically created based on them.

[0411] Furthermore, users can utilize sentiment analysis tools during normal business negotiations to capture real-time customer reactions. The results are processed on a server, forming the basis for adjusting sales strategies as needed and suggesting the next course of action. This sentiment analysis can be performed using hardware equipped with cameras and microphones. Once the emotional state is identified, optimized visual information is displayed, enabling a more effective approach to the customer.

[0412] For example, if a user is using smart glasses while strolling through a park and listening to music, the system will determine that the user is relaxed, and then appropriate advertisements will be displayed in the user's field of vision. The aim is to provide valuable information to both the user and the company.

[0413] Examples of prompts for a generative AI model:

[0414] "What kind of ads are suitable for users when they are relaxing?"

[0415] In this way, it becomes possible to conduct sales activities that take into account customer emotions in real time.

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The user enters company identification information into the terminal. This prepares the terminal to send that information to the server. This input data forms the basis for identifying the target company.

[0419] Step 2:

[0420] Based on the received company identification information, the server collects relevant publicly available information via the internet. This process utilizes web crawling technology to retrieve data from databases that show the company's operational status and industry trends. The collected information is then used in the next analysis step.

[0421] Step 3:

[0422] The server analyzes the collected public information and uses natural language processing techniques to hypothesize potential challenges faced by the company. This analysis extracts keywords from documents and reports, and uses them to identify potential problems the company may be facing. The output of this step is a list of hypothesized challenges.

[0423] Step 4:

[0424] The server selects appropriate products and services based on the assumed problem and generates proposals. During this process, it uses a generative AI model to refine the proposals based on past data and success stories. The output of this process is detailed information about the generated proposals.

[0425] Step 5:

[0426] The server automatically generates materials for use in sales negotiations based on the generated proposal. These materials include a summary of the proposal, its benefits, and expected effects. The negotiation materials are output in a format that sales representatives can use directly.

[0427] Step 6:

[0428] During a sales meeting, the user collects customer voice and facial expressions in real time via a terminal and transmits this data to a server. The server processes this data using sentiment analysis tools to identify the customer's emotional state. The analysis results are used to adjust the sales strategy on the spot.

[0429] Step 7:

[0430] Based on the sentiment analysis results, the server dynamically modifies the sales talk script and proposal content, and generates new proposals as needed. The output of this step is a sales strategy optimized for customer responses.

[0431] Step 8:

[0432] After a sales meeting concludes, the server generates additional information based on the data obtained during the meeting to support follow-up activities and sends it to the user. This information includes specific action ideas for maintaining the relationship with the customer.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] [Third Embodiment]

[0437] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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".

[0449] This invention is a system for streamlining sales activities and is implemented as follows: The process begins when a user inputs company identification information through the system. The terminal transmits the corresponding company identification information to the server. Based on the company name, the server automatically collects publicly available information related to the company from the internet. This includes IR information, financial statements, stock price trends, press releases, official websites, and official social media accounts.

[0450] The server analyzes the collected information using natural language processing techniques and hypothesizes the challenges the company may be facing. Next, based on these hypothetical challenges, the server generates the most suitable suggestions from its product or service database. These suggestions are customized to the company's specific needs and circumstances.

[0451] Subsequently, the server automatically creates sales materials, talk scripts, and anticipated Q&A based on the generated proposal. The terminal displays these materials to the user, allowing them to prepare for the sales meeting. During the meeting, the terminal receives real-time responses from the customer and sends that data to the server. The server immediately analyzes this data and suggests the next steps to the user based on the customer's responses.

[0452] After a sales negotiation is completed, the server automatically generates follow-up materials based on the negotiation details and provides them to the user, supporting their next sales activities. This frees sales representatives from repetitive tasks, allowing them to focus on more strategic sales activities.

[0453] As a concrete example, consider a scenario where a user is conducting business negotiations with a company in the pharmaceutical industry. The user enters the company name into the system. The server collects publicly available information related to the pharmaceutical industry and analyzes it to determine that the target company's R&D investment is increasing. The server assumes this is a challenge and generates a proposal for its own IT solutions specifically tailored to R&D. This allows the user to easily obtain effective negotiation materials and focus on communicating with the customer. This system effectively supports the entire sales process.

[0454] The following describes the processing flow.

[0455] Step 1:

[0456] The user launches the system and enters the identification information of the company they are negotiating with. The terminal receives this input and sends the data to the server.

[0457] Step 2:

[0458] Based on the received company identification information, the server collects publicly available information related to the company. This involves using web scraping techniques and API access to obtain IR information, financial statements, stock price trends, press releases, official websites, and official social media information from the internet.

[0459] Step 3:

[0460] Once data collection is complete, the server analyzes the acquired information using natural language processing techniques. This analysis involves understanding the content of each piece of information, extracting keywords, associating meanings, and hypothesizing about potential challenges the company may be facing.

[0461] Step 4:

[0462] The server selects the optimal solution from its product or service database based on the assumed challenge. This selection process takes into account factors such as the company's industry, size, and the market trends it faces.

[0463] Step 5:

[0464] Based on the selected proposals, the server automatically generates sales materials, talk scripts, and anticipated Q&A. The materials are created in a presentation format, making them visually easy to understand.

[0465] Step 6:

[0466] The terminal receives sales materials and talk scripts from the server and displays them to the user. This allows the user to proceed with preparing for the sales meeting.

[0467] Step 7:

[0468] During a business negotiation, when a user enters customer feedback or questions into their terminal, the server receives that data. The server analyzes this data in real time and, based on the results, proposes the next course of action or answers to the user.

[0469] Step 8:

[0470] After a business meeting, the server reviews the meeting's content, organizes the information needed for follow-up activities, and automatically generates additional proposals and materials. The terminal then provides this information to the user, supporting further sales activities.

[0471] (Example 1)

[0472] 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."

[0473] In modern sales activities, it is crucial to quickly understand customer needs and make appropriate proposals. However, manually gathering and analyzing company-related information, generating optimal proposals, and determining the next course of action based on customer responses is time-consuming and inefficient. This invention aims to automate these processes, enabling more effective and strategic sales activities.

[0474] 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.

[0475] In this invention, the server includes means for receiving organizational identification data, means for automatically collecting relevant public data, and means for analyzing the collected information to estimate potential problems. This enables sales representatives to quickly grasp customer needs, automatically generate accurate proposal materials based on those needs, and conduct effective follow-up during and after sales negotiations.

[0476] "Organizational identification data" refers to data used to uniquely identify a specific organization, and includes the organization name, identification number, etc.

[0477] "Public data" refers to information that is widely accessible to the public through the internet and other public channels, and includes corporate investor relations information, financial statements, press releases, etc.

[0478] "Potential problems" refer to the challenges and risks that an organization is currently expected to face, and are estimated through information analysis.

[0479] A "proposal document" refers to a document that outlines the details of products or services offered, based on analyzed information and tailored to specific needs.

[0480] "Real-time response" refers to dynamic feedback and behavioral data obtained from customers during business negotiations, which forms the basis for users to quickly decide on their next course of action.

[0481] "Follow-up" refers to follow-up activities and provision of materials conducted after a business negotiation to support ongoing relationship building and additional sales activities.

[0482] "Natural language processing technology" refers to the technology used to process and analyze human language using computers, enabling tasks such as text analysis, translation, and summarization.

[0483] The embodiment of the invention involves constructing a system aimed at improving the efficiency of sales activities, utilizing organizational identification data to automate the collection, analysis, and proposal generation of diverse information related to target organizations.

[0484] First, the user enters organization identification data on the terminal. The terminal sends this identification data to the server, and the process begins.

[0485] The server uses programs written in Python or Java, along with web scraping libraries such as BeautifulSoup and Selenium, to collect relevant public data from the internet. This data includes IR information, financial statements, stock price information, press releases, official websites, and official social media information.

[0486] After collection, the server analyzes the data using natural language processing techniques. It processes the information using Python's NLTK and spaCy libraries to estimate potential problems within the organization. This allows users to quickly gain deep insights.

[0487] Next, the server uses machine learning algorithms (such as Scikit-learn or TensorFlow) to generate suitable suggestions from the company's products or services based on the analysis results. These generated suggestions are optimized to the needs of the relevant organization.

[0488] The generated information is incorporated into sales materials using a template engine such as Jinja2. The terminal displays this to the user, allowing the user to proceed with preparations for the sales meeting.

[0489] To consider a concrete example, when a user interacts with an organization in the pharmaceutical industry, after entering a specific organization name, the server might analyze the organization's research and development investment trends and propose corresponding IT solutions.

[0490] An example of a prompt statement could be, "Generate optimal solution proposals based on the latest developments in Organization A." Based on this prompt, the generating AI model assists in providing specific solutions.

[0491] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0492] Step 1:

[0493] The user enters organization identification data via a terminal. This data is sent to the server and becomes input data for the next process. The terminal reliably transmits the data using the HTTP or HTTPS protocol, and the server receives it.

[0494] Step 2:

[0495] The server uses the received organization identification data to collect publicly available data using scripting libraries such as BeautifulSoup and Selenium. Specifically, it obtains IR information, financial statements, stock price information, press releases, and updates to official websites through web scraping. In this process, the input is organization identification data, and the output is a structured public dataset.

[0496] Step 3:

[0497] The server analyzes collected public data using natural language processing techniques. It tokenizes text data using Python's NLTK or spaCy library and performs sentiment analysis and topic modeling. The input is the collected data, and the output is the analyzed text information along with the estimated potential problem.

[0498] Step 4:

[0499] The server generates proposals using machine learning algorithms based on the analysis results. The models used are created with Scikit-learn or TensorFlow, and the input is the analysis data, while the output is a product or service proposal optimized for the organization's needs.

[0500] Step 5:

[0501] The server automatically generates sales materials using a template engine such as Jinja2 based on the proposed content. These materials include not only the proposal but also a talk script and anticipated Q&A. The input is the generated proposal, and the output is a complete set of sales materials.

[0502] Step 6:

[0503] The terminal displays the generated sales negotiation materials to the user. The user can then use these materials to prepare for the negotiation. Specifically, the terminal screen provides materials with interactive navigation functions.

[0504] Step 7:

[0505] During a business negotiation, the terminal collects real-time customer responses and sends them to the server. The server analyzes this response data to estimate the customer's emotions and level of interest. The input is customer response data, and the output is improvement suggestions or next course of action.

[0506] Step 8:

[0507] After a business negotiation concludes, the server generates follow-up materials based on the negotiation details and customer feedback. These materials include information and supplementary materials for use in future negotiations. The input is negotiation record data, and the output is the follow-up materials.

[0508] (Application Example 1)

[0509] 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."

[0510] In modern business transactions and sales activities, it is essential to quickly and accurately understand customer needs and make effective proposals. However, accurately analyzing diverse customer purchasing trends and real-time feedback, and providing individually optimized proposals, is extremely difficult. Furthermore, efficiently conducting follow-up activities after sales negotiations is also a challenge.

[0511] 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.

[0512] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting relevant public information, and means for identifying consumer purchasing trends. This enables new product proposals based on information analysis and follow-up activities after business negotiations.

[0513] "Corporate identification information" refers to information used to distinguish a particular company from other companies, and includes company names, corporate identification numbers, and other similar information.

[0514] "Public information" refers to information that is accessible to the general public through the internet or other public media, including information posted on a company's website or official social media accounts.

[0515] "Sales materials" refer to documents and presentation materials used when making proposals or explanations to customers during sales activities.

[0516] "Real-time reactions" refer to the responses and feedback that customers give during business negotiations and sales activities, including their facial expressions and statements at the time.

[0517] "Consumer purchasing trends" refer to patterns of purchasing behavior and preferences that consumers have shown in the past, and are used to predict future purchasing behavior.

[0518] "Follow-up activities" refer to additional sales and support activities conducted after a business negotiation or transaction is completed, with the aim of maintaining relationships and securing future business.

[0519] This invention provides a system to support commercial transactions and sales activities. The system mainly consists of a server and user terminals, and collects and analyzes publicly available information and customer data based on company identification information.

[0520] The server first receives the company's identification information. This allows it to automatically collect relevant publicly available information from the internet. This process utilizes web scraping techniques. Next, Python and its libraries, NLTK and spaCy, are used to analyze the collected information using natural language processing techniques. Based on this analysis, the server hypothesizes potential challenges faced by the target company.

[0521] Next, the server identifies consumer purchasing trends. This involves analyzing customer data, which is performed using machine learning libraries such as TensorFlow. Based on this, it automatically generates and provides users with product recommendations and sales strategies optimized for customer needs.

[0522] User terminals have a smartphone application installed, which is used to view sales materials and communicate with customers. During sales meetings, the terminal also captures real-time customer responses and sends them to the server, allowing users to receive guidance on their next course of action.

[0523] As a concrete example, consider a company that sells organic cosmetics using this system. By entering the company name, the server automatically collects relevant market trends and customer reviews, and based on the analysis results, generates suggestions for new products and campaigns. In this process, prompts such as "Please come up with new product suggestions based on user feedback from your organic cosmetics e-commerce site" are used.

[0524] This will enable companies to quickly grasp market trends and conduct highly accurate sales activities.

[0525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0526] Step 1:

[0527] The user enters the company's identification information into the terminal. The entered information is sent to the system's server. The input here includes the company name and corporate number, and the identification information is returned to the server as output, initiating the next process.

[0528] Step 2:

[0529] The server automatically collects publicly available information from the internet based on the received company identification information. Specifically, it uses web scraping technology to investigate the company's official website, social media, and industry news. In this process, the input is the identification information, and the output is the HTML data of the relevant information. This is then sent to the next analysis step.

[0530] Step 3:

[0531] The server analyzes the collected publicly available data using natural language processing techniques. It uses Python and its libraries (e.g., NLTK, spaCy) to extract current business challenges and consumer concerns from the text. The input is the information data from step 2, and the output is a list of challenges and keywords as a result of the analysis.

[0532] Step 4:

[0533] The server uses machine learning techniques to identify consumer purchasing trends based on the analyzed data. Here, a model using TensorFlow analyzes past purchase data to identify customer purchasing patterns. The input is the analysis result, and the output is the predicted purchasing trend.

[0534] Step 5:

[0535] The server generates product suggestions based on purchasing trends and assumed challenges. It utilizes a generative AI model to create prompts that provide the most suitable product suggestions to consumers, thus refining the suggestions. In this process, purchasing trends are used as input, and a list of suggestions is generated as output.

[0536] Step 6:

[0537] The terminal receives the sales materials and displays them to the user. The target user reviews the sales materials proposed by the system and prepares to communicate effectively with the customer. The input is the generated sales materials, and the output is the presentation materials ready for the user to use.

[0538] Step 7:

[0539] During a business negotiation, the terminal captures real-time responses from the customer. This includes voice input and analysis of video data. This data is transmitted to a server in real time and serves as input for the server to provide guidance on the next course of action. The output is the real-time feedback analysis results.

[0540] Step 8:

[0541] After a business meeting concludes, the server automatically generates follow-up materials and sends them to the user's terminal. This allows the user to utilize these materials for future sales efforts or approaches. Input consists of meeting history data and real-time response data, while output is the follow-up materials.

[0542] 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.

[0543] This invention relates to a system for streamlining sales activities that recognizes the emotions of users and customers and optimizes the sales process based on that recognition. While the system has basic functions for receiving company identification information and automatically collecting necessary publicly available information, it can further analyze the emotional states of users and customers by incorporating an emotion engine. The emotion engine utilizes speech recognition and natural language processing technologies to analyze emotions from spoken and written content during business negotiations.

[0544] The user accesses the system and starts the process by entering the identification information of the company they are trying to sell to. The terminal sends this input to the server. The server collects publicly available information based on the received information, analyzes it, and hypothesizes the company's challenges.

[0545] The emotion engine analyzes voice or text data acquired from users and customers during sales negotiations. This allows for real-time identification of emotional states based on the flow and content of the conversation. For example, it can determine whether a customer is interested or dissatisfied and adjust sales strategies accordingly.

[0546] Based on input from the emotion engine, the server has the capability to dynamically modify the content of sales materials and talk scripts. If necessary, it can generate new proposals during a sales meeting or adjust existing proposals.

[0547] As a concrete example, if the emotion engine detects a waning interest in a customer during a sales negotiation based on the customer's tone of voice and word choice, the server will suggest a talk script that emphasizes a different perspective or the advantages of a new product. In this way, interactions with customers in sales situations can be controlled more effectively. Furthermore, after the negotiation, follow-up materials are automatically generated, and advice is provided on how to continue building a relationship with the customer based on the results of the emotion analysis.

[0548] This system is expected to enable sales representatives to build deeper relationships with customers, thereby improving their performance.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] The user accesses the system interface and enters the identification information of the company with which they have a business meeting scheduled. The terminal receives this information and quickly sends it to the server.

[0552] Step 2:

[0553] Based on the received company identification information, the server efficiently collects publicly available information related to the company. Specifically, it crawls information sources such as IR information, financial results, stock price trends, press releases, official websites, and official social media accounts, and aggregates the necessary data.

[0554] Step 3:

[0555] The server analyzes the collected information. Utilizing natural language processing technology, it extracts key keywords from text data and uses them to hypothesize potential challenges facing the company.

[0556] Step 4:

[0557] Based on the assumed challenges, the server derives the optimal proposal from its solution database and generates the proposed content. This process includes selecting products and services that take into account the company's needs and market environment.

[0558] Step 5:

[0559] The server activates an emotion engine to analyze voice or text data acquired from users and customers during sales negotiations. This analysis allows for real-time recognition of the customer's emotional state and the adaptation of the sales process accordingly.

[0560] Step 6:

[0561] Based on the customer's emotional state recognized by the emotion engine, the server automatically and dynamically adjusts the content of sales materials and talk scripts. For example, if the customer's interest is waning, the content will be changed to emphasize a different proposal or new benefits.

[0562] Step 7:

[0563] The terminal provides users with pre-configured sales materials and talk scripts. Users can use these materials to respond flexibly according to the flow of the sales negotiation.

[0564] Step 8:

[0565] Once a business negotiation concludes, the server automatically generates follow-up materials based on the negotiation content and sentiment analysis results. The terminal then provides these materials to the user, supporting the next steps in building long-term relationships with the customer.

[0566] (Example 2)

[0567] 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."

[0568] In sales activities, accurately understanding customer emotions and providing flexible sales materials and proposals tailored to those emotions is difficult. Furthermore, appropriate advice based on emotion analysis is required during post-sales follow-up, but current systems lack the means to efficiently perform this task.

[0569] 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.

[0570] In this invention, the server includes means for receiving corporate identification information, means for collecting publicly available information, means for analyzing emotional states, means for dynamically updating sales materials, and means for generating follow-up materials. This enables flexible sales activities and accurate follow-up based on customer emotions.

[0571] "Company identification information" refers to information used to identify a specific company, and includes data such as the company name and industry.

[0572] "Public information" refers to information related to a company that can be obtained from the internet or other public sources.

[0573] A "challenge" is a hypothesis that refers to a problem or area for improvement that a particular company is facing.

[0574] "Emotional state" refers to the emotional state analyzed from a customer's or user's voice or text, and includes states of emotions such as interest and dissatisfaction.

[0575] "Business negotiation materials" refer to proposals and informational documents used in business negotiations.

[0576] "Follow-up materials" are documents containing additional information generated after a business meeting to maintain the relationship with the customer and prepare for the next meeting.

[0577] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and is used for text analysis and emotion extraction.

[0578] A "generative AI model" is an artificial intelligence model used to generate new information or suggestions based on input data.

[0579] This invention provides a configuration for implementing a system to streamline sales activities, and specifically describes the roles of the server, terminal, and user.

[0580] First, the user uses their device to enter the identification information of the company they are negotiating with. This device can be a standard computer or mobile device, and uses a dedicated web application that runs in a browser. Once the user enters the information, the device sends this information to the server via the HTTPS protocol.

[0581] The server collects relevant publicly available information from the internet based on the received company identification information. The server extracts data using web scraping techniques and processes this information using data analysis software. For example, Python libraries can be used for this processing. Based on the data analysis results, the server hypothesizes the company's challenges and constructs the necessary materials for business negotiations.

[0582] Next, the emotion engine analyzes the voice or text data acquired during the sales meeting. The emotion engine analyzes emotional states in real time, for example, using the Google Cloud Natural Language API or IBM's speech recognition service. Based on the analysis results, the server has the capability to dynamically update documents and dialogue content from the sales meeting.

[0583] For example, if the emotion engine determines that a customer's interest is waning during a business negotiation, the server can use a generative AI model to generate a proposal that presents an alternative perspective. This could include text and slides that highlight the benefits from various viewpoints.

[0584] Finally, follow-up materials for the sales meeting are automatically generated by the server. These materials include advice for the next sales meeting and customer follow-up, based on insights from sentiment analysis. These follow-up materials are provided in a format that is easy for the user to review.

[0585] An example of a prompt message that can be input into the AI ​​model is, "If a customer has shown interest in the new product, generate additional information to clearly explain its details." This makes it possible to instantly obtain the necessary suggestions for advancing sales activities.

[0586] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0587] Step 1:

[0588] The user uses a terminal to input company identification information for the business negotiation. Specifically, the user fills in the company name and industry information in the input form on the terminal and presses the "Submit" button. This input data forms the basis for the next processing step.

[0589] Step 2:

[0590] The terminal sends the entered information to the server. The terminal securely transmits the data to the server via the HTTPS protocol. In this process, the company identification information entered by the user is passed to the server and becomes input data for the next data collection process.

[0591] Step 3:

[0592] The server extracts data from the internet based on company identification information to collect publicly available information. Specifically, it uses web scraping technology. Here, the target information sources are official websites and news articles. The publicly available information obtained through this process becomes the input data for the next analysis step.

[0593] Step 4:

[0594] The server processes the collected public information and makes assumptions about the company's challenges. The server uses text analysis algorithms to organize the obtained information and identify potential challenges. This analysis then passes the assumptions about the challenges on to the next sentiment analysis step.

[0595] Step 5:

[0596] The emotion engine analyzes voice or text data obtained from users and customers. Specifically, the server converts the voice data into text and uses natural language processing techniques to determine the emotional state. The output of this step is an evaluation of the emotions observed in the conversation.

[0597] Step 6:

[0598] The server dynamically updates sales materials and dialogue content based on sentiment analysis results. It utilizes a generative AI model to generate new proposals and points to emphasize. Prompt statements are input into the model, enabling flexible material updates. This output is presented to the user and reflected in the sales negotiation.

[0599] Step 7:

[0600] After a business meeting, the server generates follow-up materials and provides them to the user. Based on sentiment analysis data, the server automatically creates a report containing advice for future customer follow-ups. This material is delivered to the user via email or a dashboard.

[0601] (Application Example 2)

[0602] 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."

[0603] There is a growing need to optimize sales activities according to the customer's emotional state. Traditional methods have made it difficult to analyze customer emotions in real time and reflect them in the sales process. Furthermore, the optimization of visual information based on customer emotions has been very limited. As a result, there is a challenge in providing customers with attractive and effective information.

[0604] 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.

[0605] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting publicly available information, means for analyzing the collected information and hypothesizing problems, and means for dynamically changing visual information based on the user's emotional state using emotion analysis means and displaying optimized information. This enables effective sales processes and information provision that respond to customer emotions.

[0606] "Corporate identification information" is a general term for information used to identify a specific legal entity or business.

[0607] "Public information" refers to publicly available information related to a company, such as data and reports.

[0608] "Analyzing collected information" refers to a method of thoroughly investigating the obtained data and extracting hidden trends and useful insights.

[0609] "Assumed challenges" are problems that are predicted for a particular company or situation based on the results of the analysis of collected information.

[0610] "Generating proposals" means devising solutions and improvement measures based on information analysis and presenting them in a concrete form.

[0611] "Sales materials" refer to documents and presentation materials created to convey proposals and information during business negotiations and business activities.

[0612] "Real-time response" refers to the immediate reaction or feedback that a customer provides in a given situation.

[0613] "Emotional analysis tools" refer to technologies and devices used to identify and analyze emotions from sources such as voice, text, and facial expressions.

[0614] "Dynamically changing visual information" means changing the displayed information in real time and updating it to appropriate content according to the user's situation and needs.

[0615] "Optimized information" refers to information that has been processed or adjusted to best match the user's expectations and objectives.

[0616] This system automatically collects and analyzes relevant publicly available information upon receiving company identification information. The server thoroughly analyzes the collected data using speech recognition and natural language processing technologies. This identifies hypothetical challenges faced by a particular company and generates product and service proposals based on these challenges. Once proposals are generated, sales materials are automatically created based on them.

[0617] Furthermore, users can utilize sentiment analysis tools during normal business negotiations to capture real-time customer reactions. The results are processed on a server, forming the basis for adjusting sales strategies as needed and suggesting the next course of action. This sentiment analysis can be performed using hardware equipped with cameras and microphones. Once the emotional state is identified, optimized visual information is displayed, enabling a more effective approach to the customer.

[0618] For example, if a user is using smart glasses while strolling through a park and listening to music, the system will determine that the user is relaxed, and then appropriate advertisements will be displayed in the user's field of vision. The aim is to provide valuable information to both the user and the company.

[0619] Examples of prompts for a generative AI model:

[0620] "What kind of ads are suitable for users when they are relaxing?"

[0621] In this way, it becomes possible to conduct sales activities that take into account customer emotions in real time.

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The user enters company identification information into the terminal. This prepares the terminal to send that information to the server. This input data forms the basis for identifying the target company.

[0625] Step 2:

[0626] Based on the received company identification information, the server collects relevant publicly available information via the internet. This process utilizes web crawling technology to retrieve data from databases that show the company's operational status and industry trends. The collected information is then used in the next analysis step.

[0627] Step 3:

[0628] The server analyzes the collected public information and uses natural language processing techniques to hypothesize potential challenges faced by the company. This analysis extracts keywords from documents and reports, and uses them to identify potential problems the company may be facing. The output of this step is a list of hypothesized challenges.

[0629] Step 4:

[0630] The server selects appropriate products and services based on the assumed problem and generates proposals. During this process, it uses a generative AI model to refine the proposals based on past data and success stories. The output of this process is detailed information about the generated proposals.

[0631] Step 5:

[0632] The server automatically generates materials for use in sales negotiations based on the generated proposal. These materials include a summary of the proposal, its benefits, and expected effects. The negotiation materials are output in a format that sales representatives can use directly.

[0633] Step 6:

[0634] During a sales meeting, the user collects customer voice and facial expressions in real time via a terminal and transmits this data to a server. The server processes this data using sentiment analysis tools to identify the customer's emotional state. The analysis results are used to adjust the sales strategy on the spot.

[0635] Step 7:

[0636] Based on the sentiment analysis results, the server dynamically modifies the sales talk script and proposal content, and generates new proposals as needed. The output of this step is a sales strategy optimized for customer responses.

[0637] Step 8:

[0638] After a sales meeting concludes, the server generates additional information based on the data obtained during the meeting to support follow-up activities and sends it to the user. This information includes specific action ideas for maintaining the relationship with the customer.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] 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.

[0645] 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).

[0646] 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.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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".

[0656] This invention is a system for streamlining sales activities and is implemented as follows: The process begins when a user inputs company identification information through the system. The terminal transmits the corresponding company identification information to the server. Based on the company name, the server automatically collects publicly available information related to the company from the internet. This includes IR information, financial statements, stock price trends, press releases, official websites, and official social media accounts.

[0657] The server analyzes the collected information using natural language processing techniques and hypothesizes the challenges the company may be facing. Next, based on these hypothetical challenges, the server generates the most suitable suggestions from its product or service database. These suggestions are customized to the company's specific needs and circumstances.

[0658] Subsequently, the server automatically creates sales materials, talk scripts, and anticipated Q&A based on the generated proposal. The terminal displays these materials to the user, allowing them to prepare for the sales meeting. During the meeting, the terminal receives real-time responses from the customer and sends that data to the server. The server immediately analyzes this data and suggests the next steps to the user based on the customer's responses.

[0659] After a sales negotiation is completed, the server automatically generates follow-up materials based on the negotiation details and provides them to the user, supporting their next sales activities. This frees sales representatives from repetitive tasks, allowing them to focus on more strategic sales activities.

[0660] As a concrete example, consider a scenario where a user is conducting business negotiations with a company in the pharmaceutical industry. The user enters the company name into the system. The server collects publicly available information related to the pharmaceutical industry and analyzes it to determine that the target company's R&D investment is increasing. The server assumes this is a challenge and generates a proposal for its own IT solutions specifically tailored to R&D. This allows the user to easily obtain effective negotiation materials and focus on communicating with the customer. This system effectively supports the entire sales process.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] The user launches the system and enters the identification information of the company they are negotiating with. The terminal receives this input and sends the data to the server.

[0664] Step 2:

[0665] Based on the received company identification information, the server collects publicly available information related to the company. This involves using web scraping techniques and API access to obtain IR information, financial statements, stock price trends, press releases, official websites, and official social media information from the internet.

[0666] Step 3:

[0667] Once data collection is complete, the server analyzes the acquired information using natural language processing techniques. This analysis involves understanding the content of each piece of information, extracting keywords, associating meanings, and hypothesizing about potential challenges the company may be facing.

[0668] Step 4:

[0669] The server selects the optimal solution from its product or service database based on the assumed challenge. This selection process takes into account factors such as the company's industry, size, and the market trends it faces.

[0670] Step 5:

[0671] Based on the selected proposals, the server automatically generates sales materials, talk scripts, and anticipated Q&A. The materials are created in a presentation format, making them visually easy to understand.

[0672] Step 6:

[0673] The terminal receives sales materials and talk scripts from the server and displays them to the user. This allows the user to proceed with preparing for the sales meeting.

[0674] Step 7:

[0675] During a business negotiation, when a user enters customer feedback or questions into their terminal, the server receives that data. The server analyzes this data in real time and, based on the results, proposes the next course of action or answers to the user.

[0676] Step 8:

[0677] After a business meeting, the server reviews the meeting's content, organizes the information needed for follow-up activities, and automatically generates additional proposals and materials. The terminal then provides this information to the user, supporting further sales activities.

[0678] (Example 1)

[0679] 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".

[0680] In modern sales activities, it is crucial to quickly understand customer needs and make appropriate proposals. However, manually gathering and analyzing company-related information, generating optimal proposals, and determining the next course of action based on customer responses is time-consuming and inefficient. This invention aims to automate these processes, enabling more effective and strategic sales activities.

[0681] 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.

[0682] In this invention, the server includes means for receiving organizational identification data, means for automatically collecting relevant public data, and means for analyzing the collected information to estimate potential problems. This enables sales representatives to quickly grasp customer needs, automatically generate accurate proposal materials based on those needs, and conduct effective follow-up during and after sales negotiations.

[0683] "Organizational identification data" refers to data used to uniquely identify a specific organization, and includes the organization name, identification number, etc.

[0684] "Public data" refers to information that is widely accessible to the public through the internet and other public channels, and includes corporate investor relations information, financial statements, press releases, etc.

[0685] "Potential problems" refer to the challenges and risks that an organization is currently expected to face, and are estimated through information analysis.

[0686] A "proposal document" refers to a document that outlines the details of products or services offered, based on analyzed information and tailored to specific needs.

[0687] "Real-time response" refers to dynamic feedback and behavioral data obtained from customers during business negotiations, which forms the basis for users to quickly decide on their next course of action.

[0688] "Follow-up" refers to follow-up activities and provision of materials conducted after a business negotiation to support ongoing relationship building and additional sales activities.

[0689] "Natural language processing technology" refers to the technology used to process and analyze human language using computers, enabling tasks such as text analysis, translation, and summarization.

[0690] The embodiment of the invention involves constructing a system aimed at improving the efficiency of sales activities, utilizing organizational identification data to automate the collection, analysis, and proposal generation of diverse information related to target organizations.

[0691] First, the user enters organization identification data on the terminal. The terminal sends this identification data to the server, and the process begins.

[0692] The server uses programs written in Python or Java, along with web scraping libraries such as BeautifulSoup and Selenium, to collect relevant public data from the internet. This data includes IR information, financial statements, stock price information, press releases, official websites, and official social media information.

[0693] After collection, the server analyzes the data using natural language processing techniques. It processes the information using Python's NLTK and spaCy libraries to estimate potential problems within the organization. This allows users to quickly gain deep insights.

[0694] Next, the server uses machine learning algorithms (such as Scikit-learn or TensorFlow) to generate suitable suggestions from the company's products or services based on the analysis results. These generated suggestions are optimized to the needs of the relevant organization.

[0695] The generated information is incorporated into sales materials using a template engine such as Jinja2. The terminal displays this to the user, allowing the user to proceed with preparations for the sales meeting.

[0696] To consider a concrete example, when a user interacts with an organization in the pharmaceutical industry, after entering a specific organization name, the server might analyze the organization's research and development investment trends and propose corresponding IT solutions.

[0697] An example of a prompt statement could be, "Generate optimal solution proposals based on the latest developments in Organization A." Based on this prompt, the generating AI model assists in providing specific solutions.

[0698] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0699] Step 1:

[0700] The user enters organization identification data via a terminal. This data is sent to the server and becomes input data for the next process. The terminal reliably transmits the data using the HTTP or HTTPS protocol, and the server receives it.

[0701] Step 2:

[0702] The server uses the received organization identification data to collect publicly available data using scripting libraries such as BeautifulSoup and Selenium. Specifically, it obtains IR information, financial statements, stock price information, press releases, and updates to official websites through web scraping. In this process, the input is organization identification data, and the output is a structured public dataset.

[0703] Step 3:

[0704] The server analyzes collected public data using natural language processing techniques. It tokenizes text data using Python's NLTK or spaCy library and performs sentiment analysis and topic modeling. The input is the collected data, and the output is the analyzed text information along with the estimated potential problem.

[0705] Step 4:

[0706] The server generates proposals using machine learning algorithms based on the analysis results. The models used are created with Scikit-learn or TensorFlow, and the input is the analysis data, while the output is a product or service proposal optimized for the organization's needs.

[0707] Step 5:

[0708] The server automatically generates sales materials using a template engine such as Jinja2 based on the proposed content. These materials include not only the proposal but also a talk script and anticipated Q&A. The input is the generated proposal, and the output is a complete set of sales materials.

[0709] Step 6:

[0710] The terminal displays the generated sales negotiation materials to the user. The user can then use these materials to prepare for the negotiation. Specifically, the terminal screen provides materials with interactive navigation functions.

[0711] Step 7:

[0712] During a business negotiation, the terminal collects real-time customer responses and sends them to the server. The server analyzes this response data to estimate the customer's emotions and level of interest. The input is customer response data, and the output is improvement suggestions or next course of action.

[0713] Step 8:

[0714] After a business negotiation concludes, the server generates follow-up materials based on the negotiation details and customer feedback. These materials include information and supplementary materials for use in future negotiations. The input is negotiation record data, and the output is the follow-up materials.

[0715] (Application Example 1)

[0716] 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".

[0717] In modern business transactions and sales activities, it is essential to quickly and accurately understand customer needs and make effective proposals. However, accurately analyzing diverse customer purchasing trends and real-time feedback, and providing individually optimized proposals, is extremely difficult. Furthermore, efficiently conducting follow-up activities after sales negotiations is also a challenge.

[0718] 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.

[0719] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting relevant public information, and means for identifying consumer purchasing trends. This enables new product proposals based on information analysis and follow-up activities after business negotiations.

[0720] "Corporate identification information" refers to information used to distinguish a particular company from other companies, and includes company names, corporate identification numbers, and other similar information.

[0721] "Public information" refers to information that is accessible to the general public through the internet or other public media, including information posted on a company's website or official social media accounts.

[0722] "Sales materials" refer to documents and presentation materials used when making proposals or explanations to customers during sales activities.

[0723] "Real-time reactions" refer to the responses and feedback that customers give during business negotiations and sales activities, including their facial expressions and statements at the time.

[0724] "Consumer purchasing trends" refer to patterns of purchasing behavior and preferences that consumers have shown in the past, and are used to predict future purchasing behavior.

[0725] "Follow-up activities" refer to additional sales and support activities conducted after a business negotiation or transaction is completed, with the aim of maintaining relationships and securing future business.

[0726] This invention provides a system to support commercial transactions and sales activities. The system mainly consists of a server and user terminals, and collects and analyzes publicly available information and customer data based on company identification information.

[0727] The server first receives the company's identification information. This allows it to automatically collect relevant publicly available information from the internet. This process utilizes web scraping techniques. Next, Python and its libraries, NLTK and spaCy, are used to analyze the collected information using natural language processing techniques. Based on this analysis, the server hypothesizes potential challenges faced by the target company.

[0728] Next, the server identifies consumer purchasing trends. This involves analyzing customer data, which is performed using machine learning libraries such as TensorFlow. Based on this, it automatically generates and provides users with product recommendations and sales strategies optimized for customer needs.

[0729] User terminals have a smartphone application installed, which is used to view sales materials and communicate with customers. During sales meetings, the terminal also captures real-time customer responses and sends them to the server, allowing users to receive guidance on their next course of action.

[0730] As a concrete example, consider a company that sells organic cosmetics using this system. By entering the company name, the server automatically collects relevant market trends and customer reviews, and based on the analysis results, generates suggestions for new products and campaigns. In this process, prompts such as "Please come up with new product suggestions based on user feedback from your organic cosmetics e-commerce site" are used.

[0731] This will enable companies to quickly grasp market trends and conduct highly accurate sales activities.

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0733] Step 1:

[0734] The user enters the company's identification information into the terminal. The entered information is sent to the system's server. The input here includes the company name and corporate number, and the identification information is returned to the server as output, initiating the next process.

[0735] Step 2:

[0736] The server automatically collects publicly available information from the internet based on the received company identification information. Specifically, it uses web scraping technology to investigate the company's official website, social media, and industry news. In this process, the input is the identification information, and the output is the HTML data of the relevant information. This is then sent to the next analysis step.

[0737] Step 3:

[0738] The server analyzes the collected publicly available data using natural language processing techniques. It uses Python and its libraries (e.g., NLTK, spaCy) to extract current business challenges and consumer concerns from the text. The input is the information data from step 2, and the output is a list of challenges and keywords as a result of the analysis.

[0739] Step 4:

[0740] The server uses machine learning techniques to identify consumer purchasing trends based on the analyzed data. Here, a model using TensorFlow analyzes past purchase data to identify customer purchasing patterns. The input is the analysis result, and the output is the predicted purchasing trend.

[0741] Step 5:

[0742] The server generates product suggestions based on purchasing trends and assumed challenges. It utilizes a generative AI model to create prompts that provide the most suitable product suggestions to consumers, thus refining the suggestions. In this process, purchasing trends are used as input, and a list of suggestions is generated as output.

[0743] Step 6:

[0744] The terminal receives the sales materials and displays them to the user. The target user reviews the sales materials proposed by the system and prepares to communicate effectively with the customer. The input is the generated sales materials, and the output is the presentation materials ready for the user to use.

[0745] Step 7:

[0746] During a business negotiation, the terminal captures real-time responses from the customer. This includes voice input and analysis of video data. This data is transmitted to a server in real time and serves as input for the server to provide guidance on the next course of action. The output is the real-time feedback analysis results.

[0747] Step 8:

[0748] After a business meeting concludes, the server automatically generates follow-up materials and sends them to the user's terminal. This allows the user to utilize these materials for future sales efforts or approaches. Input consists of meeting history data and real-time response data, while output is the follow-up materials.

[0749] 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.

[0750] This invention relates to a system for streamlining sales activities that recognizes the emotions of users and customers and optimizes the sales process based on that recognition. While the system has basic functions for receiving company identification information and automatically collecting necessary publicly available information, it can further analyze the emotional states of users and customers by incorporating an emotion engine. The emotion engine utilizes speech recognition and natural language processing technologies to analyze emotions from spoken and written content during business negotiations.

[0751] The user accesses the system and starts the process by entering the identification information of the company they are trying to sell to. The terminal sends this input to the server. The server collects publicly available information based on the received information, analyzes it, and hypothesizes the company's challenges.

[0752] The emotion engine analyzes voice or text data acquired from users and customers during sales negotiations. This allows for real-time identification of emotional states based on the flow and content of the conversation. For example, it can determine whether a customer is interested or dissatisfied and adjust sales strategies accordingly.

[0753] Based on input from the emotion engine, the server has the capability to dynamically modify the content of sales materials and talk scripts. If necessary, it can generate new proposals during a sales meeting or adjust existing proposals.

[0754] As a concrete example, if the emotion engine detects a waning interest in a customer during a sales negotiation based on the customer's tone of voice and word choice, the server will suggest a talk script that emphasizes a different perspective or the advantages of a new product. In this way, interactions with customers in sales situations can be controlled more effectively. Furthermore, after the negotiation, follow-up materials are automatically generated, and advice is provided on how to continue building a relationship with the customer based on the results of the emotion analysis.

[0755] This system is expected to enable sales representatives to build deeper relationships with customers, thereby improving their performance.

[0756] The following describes the processing flow.

[0757] Step 1:

[0758] The user accesses the system interface and enters the identification information of the company with which they have a business meeting scheduled. The terminal receives this information and quickly sends it to the server.

[0759] Step 2:

[0760] Based on the received company identification information, the server efficiently collects publicly available information related to the company. Specifically, it crawls information sources such as IR information, financial results, stock price trends, press releases, official websites, and official social media accounts, and aggregates the necessary data.

[0761] Step 3:

[0762] The server analyzes the collected information. Utilizing natural language processing technology, it extracts key keywords from text data and uses them to hypothesize potential challenges facing the company.

[0763] Step 4:

[0764] Based on the assumed challenges, the server derives the optimal proposal from its solution database and generates the proposed content. This process includes selecting products and services that take into account the company's needs and market environment.

[0765] Step 5:

[0766] The server activates an emotion engine to analyze voice or text data acquired from users and customers during sales negotiations. This analysis allows for real-time recognition of the customer's emotional state and the adaptation of the sales process accordingly.

[0767] Step 6:

[0768] Based on the customer's emotional state recognized by the emotion engine, the server automatically and dynamically adjusts the content of sales materials and talk scripts. For example, if the customer's interest is waning, the content will be changed to emphasize a different proposal or new benefits.

[0769] Step 7:

[0770] The terminal provides users with pre-configured sales materials and talk scripts. Users can use these materials to respond flexibly according to the flow of the sales negotiation.

[0771] Step 8:

[0772] Once a business negotiation concludes, the server automatically generates follow-up materials based on the negotiation content and sentiment analysis results. The terminal then provides these materials to the user, supporting the next steps in building long-term relationships with the customer.

[0773] (Example 2)

[0774] 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".

[0775] In sales activities, accurately understanding customer emotions and providing flexible sales materials and proposals tailored to those emotions is difficult. Furthermore, appropriate advice based on emotion analysis is required during post-sales follow-up, but current systems lack the means to efficiently perform this task.

[0776] 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.

[0777] In this invention, the server includes means for receiving corporate identification information, means for collecting publicly available information, means for analyzing emotional states, means for dynamically updating sales materials, and means for generating follow-up materials. This enables flexible sales activities and accurate follow-up based on customer emotions.

[0778] "Company identification information" refers to information used to identify a specific company, and includes data such as the company name and industry.

[0779] "Public information" refers to information related to a company that can be obtained from the internet or other public sources.

[0780] A "challenge" is a hypothesis that refers to a problem or area for improvement that a particular company is facing.

[0781] "Emotional state" refers to the emotional state analyzed from a customer's or user's voice or text, and includes states of emotions such as interest and dissatisfaction.

[0782] "Business negotiation materials" refer to proposals and informational documents used in business negotiations.

[0783] "Follow-up materials" are documents containing additional information generated after a business meeting to maintain the relationship with the customer and prepare for the next meeting.

[0784] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and is used for text analysis and emotion extraction.

[0785] A "generative AI model" is an artificial intelligence model used to generate new information or suggestions based on input data.

[0786] This invention provides a configuration for implementing a system to streamline sales activities, and specifically describes the roles of the server, terminal, and user.

[0787] First, the user uses their device to enter the identification information of the company they are negotiating with. This device can be a standard computer or mobile device, and uses a dedicated web application that runs in a browser. Once the user enters the information, the device sends this information to the server via the HTTPS protocol.

[0788] The server collects relevant publicly available information from the internet based on the received company identification information. The server extracts data using web scraping techniques and processes this information using data analysis software. For example, Python libraries can be used for this processing. Based on the data analysis results, the server hypothesizes the company's challenges and constructs the necessary materials for business negotiations.

[0789] Next, the emotion engine analyzes the voice or text data acquired during the sales meeting. The emotion engine analyzes emotional states in real time, for example, using the Google Cloud Natural Language API or IBM's speech recognition service. Based on the analysis results, the server has the capability to dynamically update documents and dialogue content from the sales meeting.

[0790] For example, if the emotion engine determines that a customer's interest is waning during a business negotiation, the server can use a generative AI model to generate a proposal that presents an alternative perspective. This could include text and slides that highlight the benefits from various viewpoints.

[0791] Finally, follow-up materials for the sales meeting are automatically generated by the server. These materials include advice for the next sales meeting and customer follow-up, based on insights from sentiment analysis. These follow-up materials are provided in a format that is easy for the user to review.

[0792] An example of a prompt message that can be input into the AI ​​model is, "If a customer has shown interest in the new product, generate additional information to clearly explain its details." This makes it possible to instantly obtain the necessary suggestions for advancing sales activities.

[0793] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0794] Step 1:

[0795] The user uses a terminal to input company identification information for the business negotiation. Specifically, the user fills in the company name and industry information in the input form on the terminal and presses the "Submit" button. This input data forms the basis for the next processing step.

[0796] Step 2:

[0797] The terminal sends the entered information to the server. The terminal securely transmits the data to the server via the HTTPS protocol. In this process, the company identification information entered by the user is passed to the server and becomes input data for the next data collection process.

[0798] Step 3:

[0799] The server extracts data from the internet based on company identification information to collect publicly available information. Specifically, it uses web scraping technology. Here, the target information sources are official websites and news articles. The publicly available information obtained through this process becomes the input data for the next analysis step.

[0800] Step 4:

[0801] The server processes the collected public information and makes assumptions about the company's challenges. The server uses text analysis algorithms to organize the obtained information and identify potential challenges. This analysis then passes the assumptions about the challenges on to the next sentiment analysis step.

[0802] Step 5:

[0803] The emotion engine analyzes voice or text data obtained from users and customers. Specifically, the server converts the voice data into text and uses natural language processing techniques to determine the emotional state. The output of this step is an evaluation of the emotions observed in the conversation.

[0804] Step 6:

[0805] The server dynamically updates sales materials and dialogue content based on sentiment analysis results. It utilizes a generative AI model to generate new proposals and points to emphasize. Prompt statements are input into the model, enabling flexible material updates. This output is presented to the user and reflected in the sales negotiation.

[0806] Step 7:

[0807] After a business meeting, the server generates follow-up materials and provides them to the user. Based on sentiment analysis data, the server automatically creates a report containing advice for future customer follow-ups. This material is delivered to the user via email or a dashboard.

[0808] (Application Example 2)

[0809] 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".

[0810] There is a growing need to optimize sales activities according to the customer's emotional state. Traditional methods have made it difficult to analyze customer emotions in real time and reflect them in the sales process. Furthermore, the optimization of visual information based on customer emotions has been very limited. As a result, there is a challenge in providing customers with attractive and effective information.

[0811] 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.

[0812] In this invention, the server includes means for receiving corporate identification information, means for automatically collecting publicly available information, means for analyzing the collected information and hypothesizing problems, and means for dynamically changing visual information based on the user's emotional state using emotion analysis means and displaying optimized information. This enables effective sales processes and information provision that respond to customer emotions.

[0813] "Corporate identification information" is a general term for information used to identify a specific legal entity or business.

[0814] "Public information" refers to publicly available information related to a company, such as data and reports.

[0815] "Analyzing collected information" refers to a method of thoroughly investigating the obtained data and extracting hidden trends and useful insights.

[0816] "Assumed challenges" are problems that are predicted for a particular company or situation based on the results of the analysis of collected information.

[0817] "Generating proposals" means devising solutions and improvement measures based on information analysis and presenting them in a concrete form.

[0818] "Sales materials" refer to documents and presentation materials created to convey proposals and information during business negotiations and business activities.

[0819] "Real-time response" refers to the immediate reaction or feedback that a customer provides in a given situation.

[0820] "Emotional analysis tools" refer to technologies and devices used to identify and analyze emotions from sources such as voice, text, and facial expressions.

[0821] "Dynamically changing visual information" means changing the displayed information in real time and updating it to appropriate content according to the user's situation and needs.

[0822] "Optimized information" refers to information that has been processed or adjusted to best match the user's expectations and objectives.

[0823] This system automatically collects and analyzes relevant publicly available information upon receiving company identification information. The server thoroughly analyzes the collected data using speech recognition and natural language processing technologies. This identifies hypothetical challenges faced by a particular company and generates product and service proposals based on these challenges. Once proposals are generated, sales materials are automatically created based on them.

[0824] Furthermore, users can utilize sentiment analysis tools during normal business negotiations to capture real-time customer reactions. The results are processed on a server, forming the basis for adjusting sales strategies as needed and suggesting the next course of action. This sentiment analysis can be performed using hardware equipped with cameras and microphones. Once the emotional state is identified, optimized visual information is displayed, enabling a more effective approach to the customer.

[0825] For example, if a user is using smart glasses while strolling through a park and listening to music, the system will determine that the user is relaxed, and then appropriate advertisements will be displayed in the user's field of vision. The aim is to provide valuable information to both the user and the company.

[0826] Examples of prompts for a generative AI model:

[0827] "What kind of ads are suitable for users when they are relaxing?"

[0828] In this way, it becomes possible to conduct sales activities that take into account customer emotions in real time.

[0829] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0830] Step 1:

[0831] The user enters company identification information into the terminal. This prepares the terminal to send that information to the server. This input data forms the basis for identifying the target company.

[0832] Step 2:

[0833] Based on the received company identification information, the server collects relevant publicly available information via the internet. This process utilizes web crawling technology to retrieve data from databases that show the company's operational status and industry trends. The collected information is then used in the next analysis step.

[0834] Step 3:

[0835] The server analyzes the collected public information and uses natural language processing techniques to hypothesize potential challenges faced by the company. This analysis extracts keywords from documents and reports, and uses them to identify potential problems the company may be facing. The output of this step is a list of hypothesized challenges.

[0836] Step 4:

[0837] The server selects appropriate products and services based on the assumed problem and generates proposals. During this process, it uses a generative AI model to refine the proposals based on past data and success stories. The output of this process is detailed information about the generated proposals.

[0838] Step 5:

[0839] The server automatically generates materials for use in sales negotiations based on the generated proposal. These materials include a summary of the proposal, its benefits, and expected effects. The negotiation materials are output in a format that sales representatives can use directly.

[0840] Step 6:

[0841] During a sales meeting, the user collects customer voice and facial expressions in real time via a terminal and transmits this data to a server. The server processes this data using sentiment analysis tools to identify the customer's emotional state. The analysis results are used to adjust the sales strategy on the spot.

[0842] Step 7:

[0843] Based on the sentiment analysis results, the server dynamically modifies the sales talk script and proposal content, and generates new proposals as needed. The output of this step is a sales strategy optimized for customer responses.

[0844] Step 8:

[0845] After a sales meeting concludes, the server generates additional information based on the data obtained during the meeting to support follow-up activities and sends it to the user. This information includes specific action ideas for maintaining the relationship with the customer.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] Means of receiving corporate identification information,

[0870] A means for automatically collecting publicly available information related to a company based on the received company identification information,

[0871] A means of analyzing the collected information and hypothesizing the challenges facing the company,

[0872] A means for selecting suitable products or services and generating proposals based on a hypothetical problem,

[0873] A means for automatically generating sales materials based on the generated proposals,

[0874] A system that includes means for analyzing real-time customer responses and suggesting the next course of action.

[0875] (Claim 2)

[0876] The system according to claim 1, characterized in that the information analysis means processes publicly available information collected using natural language processing technology.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for generating and transmitting additional information to support follow-up activities after a business negotiation.

[0879] "Example 1"

[0880] (Claim 1)

[0881] Means of receiving organizational identification data,

[0882] A means of automatically collecting relevant public data based on the received organization identification data,

[0883] A means of analyzing the collected information to estimate the potential problems of the organization,

[0884] A means for selecting suitable products or services and generating proposals based on the estimated problem,

[0885] A means for automatically generating sales materials based on the generated proposals,

[0886] A means of analyzing real-time customer responses and suggesting the next course of action,

[0887] To support follow-up after business negotiations, a means of generating and providing additional materials,

[0888] In the process from collecting publicly available information to generating proposals, the means of using natural language processing technology,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, characterized in that the user can strategically plan sales activities based on the generated sales materials and suggested next actions.

[0892] (Claim 3)

[0893] The system according to claim 1, characterized by analyzing real-time data obtained through business negotiations with customers and dynamically presenting countermeasures to the user during the negotiation based on the results.

[0894] "Application Example 1"

[0895] (Claim 1)

[0896] Means of receiving corporate identification information,

[0897] A means of automatically collecting relevant public information based on the received identification information,

[0898] A means of analyzing collected information and hypothesizing the company's challenges,

[0899] A means for selecting suitable products or services and generating proposals based on a hypothetical problem,

[0900] A means for automatically generating sales negotiation materials based on the generated proposal,

[0901] A means of analyzing real-time responses from users and proposing the next course of action,

[0902] A means of inputting e-commerce customer data and identifying consumer purchasing trends and preferences,

[0903] A system that includes means for automatically generating and providing new product suggestions based on identified purchasing trends.

[0904] (Claim 2)

[0905] The system according to claim 1, characterized in that the information analysis means processes publicly available information and purchase data collected using natural language processing technology.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising means for supporting follow-up activities after a business negotiation and generating and transmitting additional information for use in future sales activities.

[0908] "Example 2 of combining an emotion engine"

[0909] (Claim 1)

[0910] Means of receiving corporate identification information,

[0911] A means of collecting publicly available information related to the company based on the received company identification information,

[0912] A means of processing the collected information and hypothesizing the company's challenges,

[0913] A means of analyzing emotional states from audio or text data acquired during business negotiations,

[0914] A means of dynamically updating sales materials and dialogue scripts according to the analyzed emotional state,

[0915] A system that includes means for generating follow-up materials after a business negotiation and providing advice on relationship building.

[0916] (Claim 2)

[0917] The system according to claim 1, characterized in that the information processing means performs sentiment analysis using natural language processing technology.

[0918] (Claim 3)

[0919] The system according to claim 1, further comprising means for adjusting the proposal using a generative AI model based on the generated sentiment analysis results.

[0920] "Application example 2 when combining with an emotional engine"

[0921] (Claim 1)

[0922] Means of receiving corporate identification information,

[0923] A means for automatically collecting publicly available information related to a company based on the received company identification information,

[0924] A means of analyzing the collected information and hypothesizing the challenges facing the company,

[0925] A means for selecting suitable products or services and generating proposals based on a hypothetical problem,

[0926] A means of automatically generating sales materials based on the generated proposals,

[0927] A means of analyzing real-time customer responses and proposing the next course of action,

[0928] A means for dynamically changing visual information based on the user's emotional state using emotion analysis means and displaying optimized information,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, characterized in that the information analysis means processes publicly available information collected using natural language processing technology.

[0932] (Claim 3)

[0933] The system according to claim 1, further comprising means for generating and transmitting additional information to support follow-up activities after a business negotiation. [Explanation of Symbols]

[0934] 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. Means of receiving corporate identification information, A means of automatically collecting relevant public information based on the received identification information, A means of analyzing collected information and hypothesizing the company's challenges, A means for selecting suitable products or services and generating proposals based on a hypothetical problem, A means for automatically generating sales negotiation materials based on the generated proposal, A means of analyzing real-time responses from users and proposing the next course of action, A means of inputting e-commerce customer data and identifying consumer purchasing trends and preferences, A system that includes means for automatically generating and providing new product suggestions based on identified purchasing trends.

2. The system according to claim 1, characterized in that the information analysis means processes publicly available information and purchase data collected using natural language processing technology.

3. The system according to claim 1, further comprising means for supporting follow-up activities after a business negotiation and generating and transmitting additional information for use in future sales activities.

Images