system

Abstract

We provide the system. [Solution] A means for collecting audio data in real time and performing transcription, A means for extracting important points from the transcribed text data and generating meeting minutes or summaries, A means of automatically inputting generated meeting minutes and summaries into an external system, A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history, A means of generating recommendations for optimal services and products based on identified customer needs, A method for automatically generating the outline of the next proposal, A system that includes this.

Description

Technical Field

[0002] , , , , , , , ,

[0004] , , , , , , ,

[0005] , , , , , ,

[0003] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 business activities, it is required to accurately record the content of business negotiations and quickly and accurately grasp the needs of customers. This can reduce the burden on sales staff and enable efficient business activities. However, manually recording and analyzing conversations during business negotiations to make optimal proposals is time-consuming and laborious, and information leakage and misunderstandings are likely to occur. Furthermore, it also requires a great deal of time to create the next proposal document. Therefore, there is a need for a system that automatically records the content of business negotiations and provides optimal proposals based on customer needs in real time.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for analyzing customer statements and identifying customer needs by referring to an industry trend database and past sales negotiation history; means for generating recommendations for optimal services and products based on the identified customer needs; and means for automatically generating the outline of the next proposal. This enables sales representatives to efficiently record conversations during sales negotiations, make optimal proposals in real time, and create next proposals quickly and accurately.

[0006] "Audio data" refers to audio information collected during business negotiations, and this information is recorded by recording devices or terminals.

[0007] "Transcription" refers to the process of converting collected audio data into text data, and is carried out using speech recognition technology.

[0008] "Key points" are keywords and phrases extracted from the content of a business negotiation that deserve particular attention, and represent important information for sales strategies and proposals.

[0009] "Meeting minutes and summaries" are documents that concisely summarize the content of a business negotiation, organizing the overall picture of the conversation and the important points.

[0010] "External systems" refer to other software or databases, such as sales opportunity management or customer relationship management (CRM) systems, that can automatically input information into these systems.

[0011] "Customer statements" refer to the content of discussions, needs, and feedback expressed by the customer during business negotiations.

[0012] An "industry trend database" refers to a database that collects and stores the latest trends, developments, and statistical information related to a specific industry.

[0013] "Past business negotiation history" refers to data that saves records and details of past business negotiations, and by referring to this data, it is possible to understand ongoing interactions with customers.

[0014] "Customer needs" refer to the demands, challenges, and desired features of services or products that customers express during business negotiations.

[0015] "Recommendation" refers to advice and suggestions provided by a system that proposes the most suitable services or products based on customer needs.

[0016] "The outline of the proposal" refers to a summary of the main points and structure of the proposal prepared for the next business negotiation or presentation. [Brief explanation of the drawing]

[0017] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] 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.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0039] The specific program processing is as follows:

[0040] Audio data collection and transcription

[0041] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects audio data from the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0042] Extracting key points and generating meeting minutes

[0043] The server uses natural language processing (NLP) algorithms to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary provides a quick overview of the conversation and highlights key points. The generated minutes and summary are automatically entered by the server into an external system.

[0044] Analysis of statements and generation of recommendations

[0045] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. Based on customer statements, the server gathers relevant information by cross-referencing with the latest industry trend database and past sales history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the sales meeting while referring to the recommendations.

[0046] Generating the outline for the next proposal

[0047] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0048] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0049] Through the above processes, sales activities become more efficient, enabling a quicker response to customer needs.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation and sends it to the server in real time.

[0053] Step 2:

[0054] The server transcribes the received audio data using a speech recognition API. The transcribed text data is temporarily stored on the server.

[0055] Step 3:

[0056] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary.

[0057] Step 4:

[0058] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0059] Step 5:

[0060] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0061] Step 6:

[0062] The server analyzes the customer's statements received and gathers relevant information by referencing industry trend databases and past sales history. This helps identify the customer's needs and challenges.

[0063] Step 7:

[0064] The server generates recommendations for the most suitable services and products based on identified needs and challenges. These recommendations are then sent from the server to the device.

[0065] Step 8:

[0066] The device displays recommendations to the user in real time. Based on this information, the user leads business negotiations and makes concrete proposals to customers.

[0067] Step 9:

[0068] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0069] Step 10:

[0070] The server analyzes the sales negotiation data and feedback after the meeting and extracts elements that should be included in the next proposal. Based on this, it automatically generates the outline of the proposal.

[0071] Step 11:

[0072] The generated proposal outline is sent to the terminal. The user can modify this outline or enter additional information as needed.

[0073] By following these steps, negotiation information will be efficiently recorded, and optimal proposals tailored to customer needs will be made quickly.

[0074] (Example 1)

[0075] 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."

[0076] In modern sales activities, it is essential to efficiently record the content of business negotiations, quickly grasp customer needs, and make appropriate proposals. However, manually transcribing audio data, creating meeting minutes, analyzing customer needs, and writing proposals is time-consuming and labor-intensive. Therefore, a system is needed to reduce the burden on sales representatives and streamline sales activities. Furthermore, there is a need for a means to analyze customer statements in real time and immediately propose the most suitable services and products.

[0077] 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.

[0078] In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for collecting customer statements through a terminal during a business negotiation and analyzing those statements; and means for generating an outline of the next proposal using a generation AI model based on the analyzed statements. This enables efficient recording of negotiation content, extraction of important points, automatic generation of meeting minutes, immediate understanding of customer needs, and rapid generation of appropriate proposals.

[0079] "Audio data" refers to data that records human voices in digital format.

[0080] "Real-time" means that data and information are processed immediately.

[0081] "Transcription" is the process of converting audio data into text data.

[0082] "Text data" refers to data that represents character information in a digital format.

[0083] "Key points" are keywords or phrases that deserve particular attention in discussions, business negotiations, etc.

[0084] "Meeting minutes" are documents that record the content of meetings or business negotiations and organize them in a way that allows for later reference.

[0085] A "summary" is a short, concise piece of text that extracts the most important parts from a large amount of information.

[0086] An "external system" is an information processing system provided by a third party other than the company's own system.

[0087] "Customer statements" refer to words spoken by customers during business negotiations or meetings.

[0088] An "industry trend database" is a database that compiles the latest information and statistical data related to a specific industry.

[0089] A "sales negotiation history" is a database that records past sales negotiations and their contents.

[0090] "Customer needs" refer to the products or services that customers require, or the problems they want to solve.

[0091] "Recommendation" is the process of suggesting appropriate products and services based on customer conditions and needs.

[0092] A "proposal" is a document that summarizes future actions and proposed plans based on the results of business negotiations or meetings.

[0093] "Terminals" refer to digital devices such as laptops and smartphones used by sales representatives.

[0094] A "server" is a remote computer system that stores and processes data.

[0095] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information and suggestions from data.

[0096] A "prompt statement" is an instruction given to a generative AI model, serving as a guide to obtain specific output.

[0097] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0098] Next, we will explain the specific steps for implementing this system.

[0099] First, the user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). This device has a dedicated application installed and collects audio data of the negotiation in real time. The collected audio data is sent to a server using a secure communication protocol (e.g., HTTPS). The server transcribes the received audio data using a speech recognition API, such as Google® Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server.

[0100] Next, the server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary is designed to provide a quick overview of the conversation and highlight key points. The generated minutes and summary are then automatically entered by the server into external systems such as Salesforce.

[0101] During sales negotiations, the server analyzes customer statements entered by sales representatives and continuously collected voice data in real time. Based on customer statements, the server gathers relevant information by cross-referencing with industry trend databases (e.g., Crunchbase) and past sales negotiation history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the negotiation while referring to the recommendations.

[0102] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0103] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0104] Example of a prompt:

[0105] 1. Transcription of audio data: "Please transcribe this audio data."

[0106] 2. Summary Generation: "Extract the key points from this text data and generate a summary."

[0107] 3. Speech Analysis and Recommendation: "Analyze customer comments and recommend relevant services and products."

[0108] 4. Proposal Outline Generation: "Based on the negotiation content and feedback, please generate an outline for the next proposal."

[0109] Through the above process, sales activities become more efficient, enabling a quicker response to customer needs.

[0110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0111] Step 1: Activate the recording function

[0112] The user initiates a business meeting and activates the recording function on their device (laptop or smartphone). This involves opening a dedicated application for the meeting and tapping the "Start Recording" button. The user's actions are the input, and the device begins recording as the output.

[0113] Step 2: Collecting audio data

[0114] The terminal collects audio data of the business negotiation in real time through its recording function. The collected audio data is temporarily stored on the terminal. The input is the user's voice, and the output is the audio data corresponding to that voice. The terminal displays "Business negotiation started."

[0115] Step 3: Sending audio data

[0116] The terminal sends the collected audio data to the server in real time. This process uses a secure communication protocol (e.g., HTTPS). The input is the collected audio data, and the output is the audio data sent to the server. The terminal displays "Sending audio data to server...".

[0117] Step 4: Transcribing the audio data

[0118] The server transcribes the received audio data using a speech recognition API such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server. The input is the transmitted audio data, and the output is the transcribed text data. The server records a status in the server log indicating "Transcription in progress...".

[0119] Step 5: Extraction of key keywords

[0120] The server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. The input is the transcribed text data, and the output is the important keywords and phrases. The server generates a log message saying "Extracting important keywords...".

[0121] Step 6: Generating a summary

[0122] The server generates a summary based on the extracted information. A text summarization algorithm is used for summary generation. The input consists of key keywords and phrases, and the output is a summary text. The server logs "Summary generated" and displays the summary.

[0123] Step 7: Automatic Input

[0124] The server automatically inputs the generated meeting minutes and summaries into external systems such as Salesforce. The input is the generated meeting minutes and summaries, and the output is the data input to the external system. The server records "Data has been input into Salesforce."

[0125] Step 8: Collecting Customer Feedback

[0126] The server analyzes customer statements entered by sales representatives during negotiations, as well as continuously collected audio data, in real time. Input consists of customer statements and audio data, while output is the analysis results of this data. The server displays "Collecting customer statements...".

[0127] Step 9: Gather relevant information

[0128] The server uses customer statements to collect relevant information by cross-referencing them with industry trend databases (e.g., Crunchbase) and past sales history. The input is the analyzed customer statements, and the output is the relevant information. The server displays "Collecting relevant information...".

[0129] Step 10: Identifying Needs and Challenges

[0130] The server identifies customer needs and challenges. The input is the relevant information collected, and the output is the customer needs and challenges. The server logs "Customer needs identified."

[0131] Step 11: Provide recommendations

[0132] The server generates recommendations for the most suitable services and products based on the identified customer's needs. The generated recommendations are sent to the device. The input is the customer's needs or challenges, and the output is the recommendations. The server displays "Recommendations sent to device" and notifies the device with "New recommendations available."

[0133] Step 12: Entering Feedback

[0134] After a business meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to the server. The input is the feedback and notes entered by the sales representative, and the output is the data sent to the server. The terminal displays "Feedback sent to server."

[0135] Step 13: Data Analysis

[0136] The server analyzes sales negotiation details, customer feedback, and past proposals. This analysis uses machine learning models (e.g., text classification models). Input is feedback and notes sent to the server, and output is the analysis results. The server displays a status of "Analyzing data...".

[0137] Step 14: Generating the Outline of the Proposal

[0138] The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on them. This generation uses a template-based approach. The input is the analysis results, and the output is the proposal outline. The server logs "Proposal outline generated" and generates a template.

[0139] Step 15: Submitting the Proposal

[0140] The server sends the generated proposal outline to the terminal. The input is the proposal outline, and the output is the proposal outline sent to the terminal. The server records "Proposal outline sent to terminal" and the terminal receives a notification saying "Please review the proposal."

[0141] Following the above steps, sales activities become more efficient, and it becomes possible to respond quickly to customer needs.

[0142] (Application Example 1)

[0143] 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."

[0144] Traditional sales support and customer service systems have faced challenges in recording and analyzing customer statements in real time and providing optimal recommendations on the spot. Furthermore, they lack the ability to automatically generate next-time proposals based on conversation content, resulting in increased effort required to improve the quality of customer service. Additionally, a lack of tools for store staff to quickly respond to customer needs contributes to decreased customer satisfaction.

[0145] 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.

[0146] In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate meeting minutes or summaries, and means for automatically inputting the generated meeting minutes or summaries into an external system. This makes it possible for store staff to record customer statements in real time while interacting with customers, recommend related products based on that information, and prepare suggestions for the next visit. Furthermore, by automatically generating the necessary suggestions using a generation AI model, the quality of customer service can be improved and customer satisfaction can be increased.

[0147] "Audio data" refers to a digital representation of acoustic signals, including human speech and environmental sounds.

[0148] "Transcription" is the process of analyzing audio data and converting its content into text data.

[0149] "Text data" refers to digital data that contains character information, and generally refers to documents or memory contents.

[0150] "Key points" refer to keywords or phrases that deserve particular attention in a conversation or document.

[0151] "Meeting minutes" are documents that record important statements and decisions made during meetings, business negotiations, and other similar events.

[0152] A "summary" is a concise compilation of the original text's content.

[0153] An "external system" is a system that exists separately from the internal system and is used for data linkage and information exchange.

[0154] "Customer statements" refer to opinions, requests, questions, etc., expressed by customers during business negotiations or interactions.

[0155] An "industry trend database" is a database that compiles the latest trends and developments information related to a specific industry.

[0156] "Past business negotiation history" refers to a compilation of records, content, and results of business negotiations that have taken place in the past.

[0157] "Customer needs" refer to the products, services, or problems that customers want to solve.

[0158] "Recommending services and products" refers to suggesting the most suitable products and services to meet customer needs.

[0159] "Outline of the next proposal" is an overview of the main items and structure of the next proposal to be submitted.

[0160] "Store staff" refers to employees who handle customer service at physical stores.

[0161] A "generative AI model" is a model that uses artificial intelligence technology to perform tasks such as text generation and data analysis.

[0162] This invention is a system for streamlining sales activities and customer service. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0163] System program

[0164] The user (store staff or sales representative) activates the recording function on their device (smartphone or tablet) when starting a customer interaction or business negotiation. The device collects audio data of the negotiation or customer interaction and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API) and temporarily stores the generated text data. A speech recognition algorithm is used in this process of transcribing audio data.

[0165] Extracting key points and generating meeting minutes

[0166] The server uses natural language processing (NLP) algorithms (such as spaCy) on text data to extract important keywords and phrases. Based on the extracted information, it generates a summary using a text summarization model (transformers' summarizer model). The generated meeting minutes and summaries are automatically entered by the server into external systems (such as CRM systems).

[0167] Analysis of statements and generation of recommendations

[0168] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. This identifies customer needs and generates recommendations for the most suitable services and products based on those needs. These recommendations are displayed in real time on the terminals of store staff or sales representatives, guiding sales negotiations and customer interactions.

[0169] Proposal outline generation

[0170] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify or add to it as needed.

[0171] Specific example

[0172] If a customer says "I'd like to discuss a new smartphone" during a business meeting, the statement is transcribed and the keyword "smartphone" is extracted. Then, based on the identified keyword, new products related to "smartphones" are recommended. Furthermore, the core of the proposal for the next visit will include the features and benefits of the new smartphone.

[0173] Example of a prompt

[0174] Next Proposal Generation: Based on the following summary, please create a concise outline for your next proposal.

[0175] Customer requests:

[0176] The customer expressed interest in a new smartphone. They are interested in ease of use and the latest technology.

[0177] summary:

[0178] Since customers are interested in the ease of use and latest technology of new smartphones, it is important to offer them the latest models.

[0179] This invention allows store staff and sales representatives to record customer comments in real time, provide optimal recommendations on the spot, and prepare for future visits. Furthermore, by utilizing a generative AI model, proposal creation can be automated, significantly improving the efficiency of sales activities.

[0180] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0181] Step 1:

[0182] When a user initiates a customer interaction or business negotiation, they activate the recording function on their device (smartphone or tablet). The device collects audio data in real time and sends it to a server. The input is the audio data of the conversation between the customer and the user, and the output is the audio data sent to the server. This step includes an audio collection device and a means of communication.

[0183] Step 2:

[0184] The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API). The generated text data is temporarily stored. The input is the audio data sent to the server, and the output is the transcribed text data. This step involves a speech recognition algorithm.

[0185] Step 3:

[0186] The server uses natural language processing (NLP) algorithms (such as spaCy) on the transcribed text data to extract important keywords and phrases. Based on the extracted information, a text summarization model (transformers' summarizer model) is used to generate a summary. The input is the transcribed text data, and the output is the summarized text and important keywords. This step involves natural language processing algorithms and a text summarization model.

[0187] Step 4:

[0188] The generated meeting minutes or summary are automatically entered by the server into an external system (such as a CRM system). The input consists of the summary text and key keywords, while the output is the data stored in the external system. This step involves API calls for automated data entry.

[0189] Step 5:

[0190] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. The input is transcribed text data, and the output is identified customer needs and recommendations for services and products based on those needs. This step involves database lookup and analysis algorithms.

[0191] Step 6:

[0192] Recommendations generated based on customer needs are displayed in real time on the terminals of store staff or sales representatives. The inputs are the identified customer needs and the generated recommendations, while the output is the recommendation information displayed on the terminal. This step includes a user interface for data display.

[0193] Step 7:

[0194] After a business negotiation concludes, the user enters feedback and notes about the negotiation into their terminal. This data is sent to a server, which analyzes the negotiation details, customer feedback, and past proposals. The input consists of the user's feedback and notes, while the output is the analyzed negotiation details and feedback data. This step includes a feedback input form and data storage functionality.

[0195] Step 8:

[0196] The server automatically generates key elements to be included in the next proposal using a generation AI model (such as GPT-3®). The generated proposal outline is sent to the terminal, where the user can modify or add to it as needed. The input is customer needs and feedback data, and the output is the automatically generated outline of the next proposal. This step includes the generation AI model and data transmission functionality.

[0197] 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.

[0198] This invention is a system designed to support sales activities and improve their efficiency and effectiveness. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs.

[0199] Furthermore, this invention incorporates an emotion engine that identifies emotions from customer statements and voice data and uses this information for analysis, enabling more accurate recommendations and suggestions.

[0200] The specific program processing is as follows:

[0201] Audio data collection and transcription

[0202] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0203] Extracting key points and generating meeting minutes

[0204] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary. This summary is designed to quickly grasp the overall picture and key points of the conversation. The generated minutes and summaries are automatically entered by the server into external systems (e.g., customer relationship management systems) via API.

[0205] Analysis of statements using an emotion engine

[0206] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. During this process, the server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0207] Recommendation generation and display

[0208] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0209] Generating the outline for the next proposal

[0210] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0211] For example, if a customer expresses concern about data security during a business meeting and speaks with an unstable tone, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0212] Through the above process, negotiation information is efficiently recorded, and optimal proposals that take into account the customer's emotional state can be made quickly.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation in real time.

[0216] Step 2:

[0217] The device sends the collected audio data to the server in real time. The server transcribes the received audio data using a speech recognition API.

[0218] Step 3:

[0219] The server temporarily stores the transcribed text data. The stored text data is then analyzed using natural language processing (NLP) algorithms to extract important keywords and phrases.

[0220] Step 4:

[0221] The server generates a summary based on the extracted information. This summary is designed to quickly grasp the overall picture and key points of a business deal.

[0222] Step 5:

[0223] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0224] Step 6:

[0225] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0226] Step 7:

[0227] The server analyzes the customer's statements. The server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, tone of voice, pitch, etc., to determine the customer's emotional state.

[0228] Step 8:

[0229] Based on the sentiment information identified by the sentiment engine, the server comprehensively identifies customer needs and challenges by referencing industry trend databases and past sales history to gather relevant information.

[0230] Step 9:

[0231] The server creates recommendations for the most suitable services and products based on identified needs and emotions. These recommendations are then sent from the server to the device.

[0232] Step 10:

[0233] The device displays recommendations to the user in real time. The user then uses the displayed recommendations to lead sales negotiations and make proposals to customers.

[0234] Step 11:

[0235] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0236] Step 12:

[0237] The server comprehensively analyzes emotional information, including post-meeting sales data and feedback. It then extracts key elements to include in the next proposal and automatically generates a draft based on these elements.

[0238] Step 13:

[0239] The generated proposal outline is sent to the terminal. The user can modify this outline and enter additional information as needed.

[0240] By following these steps, negotiation information will be efficiently recorded, and optimal proposals that take into account the customer's emotional state will be made quickly.

[0241] (Example 2)

[0242] 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".

[0243] In traditional sales activities, recording and summarizing negotiation details is often done manually, which is not only inefficient but also prone to overlooking important information and recording errors. Furthermore, there are few means to grasp what customers say and their emotional state in real time, making it difficult to make proposals that are best suited to each individual customer. In addition, creating proposals after negotiations requires a great deal of time and effort, so a quick response is required.

[0244] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data using natural language processing to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for analyzing customer statements and identifying customer needs by referring to an industry trend database and past business negotiation history; means for generating recommendations for optimal services and products based on the identified customer needs and emotional state; and means for automatically generating the outline of the next proposal. This enables efficient recording and summarization of business negotiation content, optimal proposals that take into account the customer's emotional state, and rapid generation of the next proposal.

[0245] "Audio data" refers to audio signals collected during business negotiations, meetings, and other similar events.

[0246] "Transcription" refers to the process of converting audio data into text format.

[0247] "Natural language processing" refers to the technology of analyzing text data and making it understandable to human language.

[0248] "Meeting minutes" refers to a document that records the details of a business negotiation or meeting.

[0249] A "summary" refers to a text that extracts the key points from a longer text and presents them concisely.

[0250] "External systems" refer to databases and applications that exist outside of the system.

[0251] "Customer statements" refers to words spoken by the customer during a business negotiation.

[0252] An "industry trend database" refers to a database that stores data on trends and developments in a specific industry or market.

[0253] "Sales negotiation history" refers to records related to past sales negotiations.

[0254] "Customer needs" refer to the demands and expectations that customers have regarding the products and services they seek.

[0255] "Emotional state" refers to the emotional state that can be inferred from a customer's statements and actions.

[0256] "Recommendation" refers to the suggestion of the most suitable products or services based on the customer's needs and emotional state.

[0257] "The outline of a proposal" refers to the basic structure of a document that contains important elements for the next business negotiation or proposal.

[0258] A "speech recognition API" refers to an application programming interface for converting speech data into text.

[0259] This invention is a system that supports sales activities by collecting and analyzing audio data from business negotiations and meetings, and automatically generating optimal proposals, thereby improving efficiency and effectiveness. This system has the function of collecting audio data in real time, transcribing it, extracting important points to generate meeting minutes and summaries, and automatically inputting them into an external system. It also has the function of analyzing customer statements, referring to industry trend databases and past business negotiation history, and providing recommendations for optimal services and products based on customer needs. Furthermore, this invention incorporates an emotion engine, which identifies emotions from customer statements and audio data and uses this for analysis, enabling more accurate recommendations and proposal adjustments.

[0260] The user (sales representative) initiates a sales meeting and activates the recording function on their device (laptop or smartphone). The device collects audio data from the meeting and sends it to the server in real time. The HTTPS protocol is used for communication to ensure data security. The server transcribes the received audio data using a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe) and temporarily stores the generated text data. This uses cloud storage such as AWS® S3 buckets.

[0261] The server analyzes the stored text data using natural language processing (NLP) algorithms (e.g., Hugging Face's transformers library) to extract important keywords and phrases. Based on the extracted information, the server generates a summary. The TextRank algorithm is used for summary generation. The generated meeting minutes and summaries are automatically input by the server into external systems (e.g., customer relationship management systems such as Salesforce and HubSpot) via API.

[0262] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. The server uses an emotion engine (e.g., IBM Watson® Tone Analyzer or Microsoft® Azure® Text Analytics) to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0263] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0264] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0265] For example, if a customer expresses concern about data security during a business meeting, and their tone is shaky, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0266] A concrete example of a prompt message for a generative AI model can be written as follows:

[0267] "Convert the following audio data to text, extract key points and emotional states, and generate optimal product recommendations. Audio data: 'The customer said they were concerned about data security.'"

[0268] Through the above processing, the system according to the present invention can efficiently record negotiation information and quickly provide optimal proposals that take into account the customer's emotional state.

[0269] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0270] Step 1: Collect audio data

[0271] The user (sales representative) begins the business negotiation and activates the recording function on their device (laptop or smartphone).

[0272] Input: Audio after the start of the business negotiation

[0273] The device collects audio data from this business negotiation in real time.

[0274] Output: Collected audio data

[0275] Step 2: Sending the audio data

[0276] The device transmits the collected voice data to the server in real time. The HTTPS protocol is used for communication to ensure data security.

[0277] Input: Collected audio data

[0278] Output: Audio data sent to the server

[0279] Step 3: Perform transcription

[0280] The server performs speech recognition on the received voice data using a speech recognition API (such as Google Cloud Speech-to-Text or Amazon Transcribe).

[0281] Input: Transmitted voice data

[0282] The server temporarily stores the generated text data. This utilizes cloud storage such as an AWS S3 bucket.

[0283] Output: Stored text data

[0284] Step 4: Analysis of text data

[0285] The server analyzes the stored text data using natural language processing (NLP) algorithms (such as the transformers library from Hugging Face) to extract important keywords and phrases.

[0286] Input: Stored text data

[0287] The server generates a summary based on the extracted information. The TextRank algorithm is used for summary generation.

[0288] Output: Extracted keywords and phrases, generated summary

[0289] [[ID=:36]]Step 5: Automatic input of meeting minutes

[0290] The server inputs the generated meeting minutes and summary into an external system (such as a customer relationship management system like Salesforce or HubSpot) through an API.

[0291] Input: Generated meeting minutes and summary

[0292] Output: Meeting minutes and summary input into the external system

[0293] Step 6: Perform Sentiment Analysis

[0294] The server analyzes the collected speech data using a sentiment engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's sentiment.

[0295] Input: Speech data during negotiation

[0296] The server analyzes linguistic features, voice tone, pitch, etc. to determine the customer's emotional state.

[0297] Output: Identified sentiment information

[0298] <00009​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​

[0309] The device displays these recommendations to the user in real time.

[0310] Output: Recommendations displayed to the user

[0311] Step 10: Collecting feedback after the business negotiation

[0312] Users input feedback and notes about business negotiations into their devices. This includes customer reactions and requests for future meetings.

[0313] Input: Feedback or notes

[0314] The device sends this data to the server.

[0315] Output: Feedback and notes sent to the server

[0316] Step 11: Analysis of feedback and generation of proposal outline

[0317] The server comprehensively analyzes sales negotiation details, customer feedback, and sentiment information.

[0318] Input: Sales negotiation details, feedback, sentiment information

[0319] The server extracts the key elements that should be included in the next proposal and automatically generates the outline of the proposal based on them.

[0320] Output: Outline of the generated proposal

[0321] Step 12: View and revise the proposal outline.

[0322] The server sends the outline of the generated proposal to the terminal.

[0323] Input: Outline of the generated proposal

[0324] The terminal displays this outline to the user, who can modify it or enter additional information as needed.

[0325] Output: Outline of the proposal with modifications or additional information added by the user.

[0326] (Application Example 2)

[0327] 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".

[0328] Traditional e-commerce sites have struggled to provide optimal purchasing support to customers due to a lack of appropriate information and emotionally-based recommendations. Furthermore, customer support has faced challenges in providing effective assistance through real-time dialogue. This can lead to decreased customer satisfaction and a decline in purchasing intent.

[0329] 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. In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate minutes or summaries, means for identifying the customer's emotional state and adjusting recommendations based on the identified emotional information, and means for providing product information in real time while interacting with the customer. This makes it possible to provide optimal product recommendations and purchase support based on the customer's statements and emotions, thereby improving customer satisfaction and increasing purchasing intent.

[0330] "Voice data" refers to audio signals collected during conversations between customers and the system, and serves as basic data for analyzing the content of speech and emotional states.

[0331] "Transcription" is the process of converting collected audio data into text data, and is a pre-processing step for analysis and creating meeting minutes.

[0332] "Text data" refers to data in sentence format generated through transcription, and is used for extracting key points and sentiment analysis.

[0333] "Key points" are particularly noteworthy keywords and phrases extracted from text data, providing information useful for generating meeting minutes and summaries.

[0334] Meeting minutes are a document that concisely summarizes the overall picture of a business negotiation or meeting, and they contain important points.

[0335] A "summary" is a document that concisely summarizes the content of a conversation, focusing on the most important points.

[0336] "External systems" refer to related systems that exist outside the main system, such as customer relationship management systems and databases.

[0337] "Customer needs" refer to the requests and challenges customers have regarding the products and services they desire, and are directly related to the objectives of business negotiations and support.

[0338] "Recommendation" refers to suggesting the most suitable products or services based on customer needs and emotional states.

[0339] "Emotional state" refers to the psychological state identified from the customer's statements and voice, and is used to adjust service provision and recommendations.

[0340] "Real-time" refers to a state where processing and responses occur almost simultaneously, with minimal delay.

[0341] A "terminal" is a device used by users or sales representatives, and is used for collecting voice data and displaying recommendations.

[0342] A "server" is a computer system that processes and stores data, and is responsible for analyzing audio data and generating recommendations.

[0343] This invention aims to effectively realize a virtual shopping assistant system for e-commerce websites. This system is configured as an application installed on a smartphone and provides optimal product information and recommendations through voice interaction with the customer. The following details an embodiment of this system.

[0344] The server uses speech recognition APIs and natural language processing algorithms to collect and analyze audio data. Specifically, audio data collected by a smartphone's microphone is transcribed in real time using the Google Cloud Speech-to-Text API. The resulting text data is then analyzed by Amazon Comprehend via AWS Lambda to extract key points. The summaries and meeting minutes generated by this process are immediately stored in internal and external data storage.

[0345] The server also uses an emotion engine to identify emotional states from customer statements and voice. IBM Watson Tone Analyzer is used here to analyze emotions such as joy, anger, sadness, and anxiety from customer statements in real time. This emotion data is sent directly to the server, where recommendation generation algorithms adjust the actual recommendations.

[0346] Based on customer comments and emotional information, the server uses Amazon Personalize to generate optimal product recommendations, which are displayed in real time on the smartphone application screen. This allows users to receive the most relevant product information at the right time, supporting their purchase decisions.

[0347] Furthermore, after a business negotiation or purchasing support session is completed, feedback and notes are entered into the smartphone and sent to the server, which automatically generates the outline of the next proposal. This automatic generation again utilizes Amazon Comprehend and a generative AI model, and the server creates the basic structure of the proposal. This proposal is displayed on the smartphone screen so that the user can easily modify and complete it.

[0348] For example, if a customer says, "My home Wi-Fi is slow and it's causing problems," this system extracts keywords like "Wi-Fi" and "slow," and identifies their anxiety from the tone of voice. Then, it displays recommendations for the latest Wi-Fi routers on the screen. In this way, users can instantly receive appropriate product information.

[0349] Examples of prompt statements are as follows:

[0350] "My home Wi-Fi is slow. What products are available?"

[0351] "I'm worried about security. Do you have any smartphone recommendations?"

[0352] Based on the above, the present invention provides optimal product recommendations that accurately capture customer needs and emotions, thereby improving customer satisfaction and increasing purchasing intent on e-commerce sites.

[0353] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0354] Step 1:

[0355] The user (customer) launches a smartphone application and speaks using the microphone function. The smartphone's microphone collects this audio data in real time and sends it to the server. The input is the customer's audio data, and the output is the audio data sent to the server.

[0356] Step 2:

[0357] The server transcribes the received audio data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is transcribed text data. This text data is temporarily stored on the server.

[0358] Step 3:

[0359] The server uses AWS Lambda to analyze the transcribed text data with Amazon Comprehend, extracting key points and keywords. The input is text data, and the output is extracted key keywords and summary information. These key keywords are used to generate meeting minutes and summaries.

[0360] Step 4:

[0361] The server uses IBM Watson Tone Analyzer to identify the customer's emotional state from transcribed text data. Input is text data, and output is emotional state information. Emotions are categorized into joy, anger, sadness, anxiety, etc., and this information is used to refine recommendations.

[0362] Step 5:

[0363] The server uses Amazon Personalize to generate optimal product recommendations based on the customer's emotional state and extracted keywords. The input is emotional state information and key keywords, and the output is a list of recommended products. Recommendations are generated in real time.

[0364] Step 6:

[0365] The generated product recommendations are sent from the server to the smartphone application. The input is a product list generated on the server, and the output is product information displayed on the smartphone screen. The user selects products based on this information.

[0366] Step 7:

[0367] After a business meeting ends, the user (customer) enters feedback and notes into their smartphone. The entered data is sent to the server. The input is the feedback and notes entered by the user, and the output is the feedback data sent to the server.

[0368] Step 8:

[0369] The server uses Amazon Comprehend again to generate the outline for the next proposal based on the submitted feedback and notes. The input is the feedback data, and the output is the proposal outline. The generated proposal outline is sent to the user's smartphone and displayed in the application.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] [Second Embodiment]

[0374] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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".

[0386] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0387] The specific program processing is as follows:

[0388] Audio data collection and transcription

[0389] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects audio data from the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0390] Extracting key points and generating meeting minutes

[0391] The server uses natural language processing (NLP) algorithms to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary provides a quick overview of the conversation and highlights key points. The generated minutes and summary are automatically entered by the server into an external system.

[0392] Analysis of statements and generation of recommendations

[0393] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. Based on customer statements, the server gathers relevant information by cross-referencing with the latest industry trend database and past sales history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the sales meeting while referring to the recommendations.

[0394] Generating the outline for the next proposal

[0395] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0396] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0397] Through the above processes, sales activities become more efficient, enabling a quicker response to customer needs.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation and sends it to the server in real time.

[0401] Step 2:

[0402] The server transcribes the received audio data using a speech recognition API. The transcribed text data is temporarily stored on the server.

[0403] Step 3:

[0404] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary.

[0405] Step 4:

[0406] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0407] Step 5:

[0408] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0409] Step 6:

[0410] The server analyzes the customer's statements received and gathers relevant information by referencing industry trend databases and past sales history. This helps identify the customer's needs and challenges.

[0411] Step 7:

[0412] The server generates recommendations for the most suitable services and products based on identified needs and challenges. These recommendations are then sent from the server to the device.

[0413] Step 8:

[0414] The device displays recommendations to the user in real time. Based on this information, the user leads business negotiations and makes concrete proposals to customers.

[0415] Step 9:

[0416] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0417] Step 10:

[0418] The server analyzes the sales negotiation data and feedback after the meeting and extracts elements that should be included in the next proposal. Based on this, it automatically generates the outline of the proposal.

[0419] Step 11:

[0420] The generated proposal outline is sent to the terminal. The user can modify this outline or enter additional information as needed.

[0421] By following these steps, negotiation information will be efficiently recorded, and optimal proposals tailored to customer needs will be made quickly.

[0422] (Example 1)

[0423] 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."

[0424] In modern sales activities, it is essential to efficiently record the content of business negotiations, quickly grasp customer needs, and make appropriate proposals. However, manually transcribing audio data, creating meeting minutes, analyzing customer needs, and writing proposals is time-consuming and labor-intensive. Therefore, a system is needed to reduce the burden on sales representatives and streamline sales activities. Furthermore, there is a need for a means to analyze customer statements in real time and immediately propose the most suitable services and products.

[0425] 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.

[0426] In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for collecting customer statements through a terminal during a business negotiation and analyzing those statements; and means for generating an outline of the next proposal using a generation AI model based on the analyzed statements. This enables efficient recording of negotiation content, extraction of important points, automatic generation of meeting minutes, immediate understanding of customer needs, and rapid generation of appropriate proposals.

[0427] "Audio data" refers to data that records human voices in digital format.

[0428] "Real-time" means that data and information are processed immediately.

[0429] "Transcription" is the process of converting audio data into text data.

[0430] "Text data" refers to data that represents character information in a digital format.

[0431] "Key points" are keywords or phrases that deserve particular attention in discussions, business negotiations, etc.

[0432] "Meeting minutes" are documents that record the content of meetings or business negotiations and organize them in a way that allows for later reference.

[0433] A "summary" is a short, concise piece of text that extracts the most important parts from a large amount of information.

[0434] An "external system" is an information processing system provided by a third party other than the company's own system.

[0435] "Customer statements" refer to words spoken by customers during business negotiations or meetings.

[0436] An "industry trend database" is a database that compiles the latest information and statistical data related to a specific industry.

[0437] A "sales negotiation history" is a database that records past sales negotiations and their contents.

[0438] "Customer needs" refer to the products or services that customers require, or the problems they want to solve.

[0439] "Recommendation" is the process of suggesting appropriate products and services based on customer conditions and needs.

[0440] A "proposal" is a document that summarizes future actions and proposed plans based on the results of business negotiations or meetings.

[0441] "Terminals" refer to digital devices such as laptops and smartphones used by sales representatives.

[0442] A "server" is a remote computer system that stores and processes data.

[0443] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information and suggestions from data.

[0444] A "prompt statement" is an instruction given to a generative AI model, serving as a guide to obtain specific output.

[0445] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0446] Next, we will explain the specific steps for implementing this system.

[0447] First, the user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). This device has a dedicated application installed and collects audio data of the negotiation in real time. The collected audio data is sent to a server using a secure communication protocol (e.g., HTTPS). The server transcribes the received audio data using a speech recognition API, such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server.

[0448] Next, the server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary is designed to provide a quick overview of the conversation and highlight key points. The generated minutes and summary are then automatically entered by the server into external systems such as Salesforce.

[0449] During sales negotiations, the server analyzes customer statements entered by sales representatives and continuously collected voice data in real time. Based on customer statements, the server gathers relevant information by cross-referencing with industry trend databases (e.g., Crunchbase) and past sales negotiation history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the negotiation while referring to the recommendations.

[0450] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0451] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0452] Example of a prompt:

[0453] 1. Transcription of audio data: "Please transcribe this audio data."

[0454] 2. Summary Generation: "Extract the key points from this text data and generate a summary."

[0455] 3. Speech Analysis and Recommendation: "Analyze customer comments and recommend relevant services and products."

[0456] 4. Proposal Outline Generation: "Based on the negotiation content and feedback, please generate an outline for the next proposal."

[0457] Through the above process, sales activities become more efficient, enabling a quicker response to customer needs.

[0458] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0459] Step 1: Activate the recording function

[0460] The user initiates a business meeting and activates the recording function on their device (laptop or smartphone). This involves opening a dedicated application for the meeting and tapping the "Start Recording" button. The user's actions are the input, and the device begins recording as the output.

[0461] Step 2: Collecting audio data

[0462] The terminal collects audio data of the business negotiation in real time through its recording function. The collected audio data is temporarily stored on the terminal. The input is the user's voice, and the output is the audio data corresponding to that voice. The terminal displays "Business negotiation started."

[0463] Step 3: Sending audio data

[0464] The terminal sends the collected audio data to the server in real time. This process uses a secure communication protocol (e.g., HTTPS). The input is the collected audio data, and the output is the audio data sent to the server. The terminal displays "Sending audio data to server...".

[0465] Step 4: Transcribing the audio data

[0466] The server transcribes the received audio data using a speech recognition API such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server. The input is the transmitted audio data, and the output is the transcribed text data. The server records a status in the server log indicating "Transcription in progress...".

[0467] Step 5: Extraction of key keywords

[0468] The server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. The input is the transcribed text data, and the output is the important keywords and phrases. The server generates a log message saying "Extracting important keywords...".

[0469] Step 6: Generating a summary

[0470] The server generates a summary based on the extracted information. A text summarization algorithm is used for summary generation. The input consists of key keywords and phrases, and the output is a summary text. The server logs "Summary generated" and displays the summary.

[0471] Step 7: Automatic Input

[0472] The server automatically inputs the generated meeting minutes and summaries into external systems such as Salesforce. The input is the generated meeting minutes and summaries, and the output is the data input to the external system. The server records "Data has been input into Salesforce."

[0473] Step 8: Collecting Customer Feedback

[0474] The server analyzes customer statements entered by sales representatives during negotiations, as well as continuously collected audio data, in real time. Input consists of customer statements and audio data, while output is the analysis results of this data. The server displays "Collecting customer statements...".

[0475] Step 9: Gather relevant information

[0476] The server uses customer statements to collect relevant information by cross-referencing them with industry trend databases (e.g., Crunchbase) and past sales history. The input is the analyzed customer statements, and the output is the relevant information. The server displays "Collecting relevant information...".

[0477] Step 10: Identifying Needs and Challenges

[0478] The server identifies customer needs and challenges. The input is the relevant information collected, and the output is the customer needs and challenges. The server logs "Customer needs identified."

[0479] Step 11: Provide recommendations

[0480] The server generates recommendations for the most suitable services and products based on the identified customer's needs. The generated recommendations are sent to the device. The input is the customer's needs or challenges, and the output is the recommendations. The server displays "Recommendations sent to device" and notifies the device with "New recommendations available."

[0481] Step 12: Entering Feedback

[0482] After a business meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to the server. The input is the feedback and notes entered by the sales representative, and the output is the data sent to the server. The terminal displays "Feedback sent to server."

[0483] Step 13: Data Analysis

[0484] The server analyzes sales negotiation details, customer feedback, and past proposals. This analysis uses machine learning models (e.g., text classification models). Input is feedback and notes sent to the server, and output is the analysis results. The server displays a status of "Analyzing data...".

[0485] Step 14: Generating the Outline of the Proposal

[0486] The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on them. This generation uses a template-based approach. The input is the analysis results, and the output is the proposal outline. The server logs "Proposal outline generated" and generates a template.

[0487] Step 15: Submitting the Proposal

[0488] The server sends the generated proposal outline to the terminal. The input is the proposal outline, and the output is the proposal outline sent to the terminal. The server records "Proposal outline sent to terminal" and the terminal receives a notification saying "Please review the proposal."

[0489] Following the above steps, sales activities become more efficient, and it becomes possible to respond quickly to customer needs.

[0490] (Application Example 1)

[0491] 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."

[0492] Traditional sales support and customer service systems have faced challenges in recording and analyzing customer statements in real time and providing optimal recommendations on the spot. Furthermore, they lack the ability to automatically generate next-time proposals based on conversation content, resulting in increased effort required to improve the quality of customer service. Additionally, a lack of tools for store staff to quickly respond to customer needs contributes to decreased customer satisfaction.

[0493] 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.

[0494] In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate meeting minutes or summaries, and means for automatically inputting the generated meeting minutes or summaries into an external system. This makes it possible for store staff to record customer statements in real time while interacting with customers, recommend related products based on that information, and prepare suggestions for the next visit. Furthermore, by automatically generating the necessary suggestions using a generation AI model, the quality of customer service can be improved and customer satisfaction can be increased.

[0495] "Audio data" refers to a digital representation of acoustic signals, including human speech and environmental sounds.

[0496] "Transcription" is the process of analyzing audio data and converting its content into text data.

[0497] "Text data" refers to digital data that contains character information, and generally refers to documents or memory contents.

[0498] "Key points" refer to keywords or phrases that deserve particular attention in a conversation or document.

[0499] "Meeting minutes" are documents that record important statements and decisions made during meetings, business negotiations, and other similar events.

[0500] A "summary" is a concise compilation of the original text's content.

[0501] An "external system" is a system that exists separately from the internal system and is used for data linkage and information exchange.

[0502] "Customer statements" refer to opinions, requests, questions, etc., expressed by customers during business negotiations or interactions.

[0503] An "industry trend database" is a database that compiles the latest trends and developments information related to a specific industry.

[0504] "Past business negotiation history" refers to a compilation of records, content, and results of business negotiations that have taken place in the past.

[0505] "Customer needs" refer to the products, services, or problems that customers want to solve.

[0506] "Recommending services and products" refers to suggesting the most suitable products and services to meet customer needs.

[0507] "Outline of the next proposal" is an overview of the main items and structure of the next proposal to be submitted.

[0508] "Store staff" refers to employees who handle customer service at physical stores.

[0509] A "generative AI model" is a model that uses artificial intelligence technology to perform tasks such as text generation and data analysis.

[0510] This invention is a system for streamlining sales activities and customer service. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0511] System program

[0512] The user (store staff or sales representative) activates the recording function on their device (smartphone or tablet) when starting a customer interaction or business negotiation. The device collects audio data of the negotiation or customer interaction and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API) and temporarily stores the generated text data. A speech recognition algorithm is used in this process of transcribing audio data.

[0513] Extracting key points and generating meeting minutes

[0514] The server uses natural language processing (NLP) algorithms (such as spaCy) on text data to extract important keywords and phrases. Based on the extracted information, it generates a summary using a text summarization model (transformers' summarizer model). The generated meeting minutes and summaries are automatically entered by the server into external systems (such as CRM systems).

[0515] Analysis of statements and generation of recommendations

[0516] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. This identifies customer needs and generates recommendations for the most suitable services and products based on those needs. These recommendations are displayed in real time on the terminals of store staff or sales representatives, guiding sales negotiations and customer interactions.

[0517] Proposal outline generation

[0518] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify or add to it as needed.

[0519] Specific example

[0520] If a customer says "I'd like to discuss a new smartphone" during a business meeting, the statement is transcribed and the keyword "smartphone" is extracted. Then, based on the identified keyword, new products related to "smartphones" are recommended. Furthermore, the core of the proposal for the next visit will include the features and benefits of the new smartphone.

[0521] Example of a prompt

[0522] Next Proposal Generation: Based on the following summary, please create a concise outline for your next proposal.

[0523] Customer requests:

[0524] The customer expressed interest in a new smartphone. They are interested in ease of use and the latest technology.

[0525] summary:

[0526] Since customers are interested in the ease of use and latest technology of new smartphones, it is important to offer them the latest models.

[0527] This invention allows store staff and sales representatives to record customer comments in real time, provide optimal recommendations on the spot, and prepare for future visits. Furthermore, by utilizing a generative AI model, proposal creation can be automated, significantly improving the efficiency of sales activities.

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] When a user initiates a customer interaction or business negotiation, they activate the recording function on their device (smartphone or tablet). The device collects audio data in real time and sends it to a server. The input is the audio data of the conversation between the customer and the user, and the output is the audio data sent to the server. This step includes an audio collection device and a means of communication.

[0531] Step 2:

[0532] The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API). The generated text data is temporarily stored. The input is the audio data sent to the server, and the output is the transcribed text data. This step involves a speech recognition algorithm.

[0533] Step 3:

[0534] The server uses natural language processing (NLP) algorithms (such as spaCy) on the transcribed text data to extract important keywords and phrases. Based on the extracted information, a text summarization model (transformers' summarizer model) is used to generate a summary. The input is the transcribed text data, and the output is the summarized text and important keywords. This step involves natural language processing algorithms and a text summarization model.

[0535] Step 4:

[0536] The generated meeting minutes or summary are automatically entered by the server into an external system (such as a CRM system). The input consists of the summary text and key keywords, while the output is the data stored in the external system. This step involves API calls for automated data entry.

[0537] Step 5:

[0538] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. The input is transcribed text data, and the output is identified customer needs and recommendations for services and products based on those needs. This step involves database lookup and analysis algorithms.

[0539] Step 6:

[0540] Recommendations generated based on customer needs are displayed in real time on the terminals of store staff or sales representatives. The inputs are the identified customer needs and the generated recommendations, while the output is the recommendation information displayed on the terminal. This step includes a user interface for data display.

[0541] Step 7:

[0542] After a business negotiation concludes, the user enters feedback and notes about the negotiation into their terminal. This data is sent to a server, which analyzes the negotiation details, customer feedback, and past proposals. The input consists of the user's feedback and notes, while the output is the analyzed negotiation details and feedback data. This step includes a feedback input form and data storage functionality.

[0543] Step 8:

[0544] The server automatically generates key elements to include in the next proposal using a generation AI model (such as GPT-3). The generated proposal outline is sent to the terminal, where the user can modify or add to it as needed. The input is customer needs and feedback data, and the output is the automatically generated outline of the next proposal. This step includes a generation AI model and data transmission functionality.

[0545] 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.

[0546] This invention is a system designed to support sales activities and improve their efficiency and effectiveness. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs.

[0547] Furthermore, this invention incorporates an emotion engine that identifies emotions from customer statements and voice data and uses this information for analysis, enabling more accurate recommendations and suggestions.

[0548] The specific program processing is as follows:

[0549] Audio data collection and transcription

[0550] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0551] Extracting key points and generating meeting minutes

[0552] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary. This summary is designed to quickly grasp the overall picture and key points of the conversation. The generated minutes and summaries are automatically entered by the server into external systems (e.g., customer relationship management systems) via API.

[0553] Analysis of statements using an emotion engine

[0554] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. During this process, the server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0555] Recommendation generation and display

[0556] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0557] Generating the outline for the next proposal

[0558] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0559] For example, if a customer expresses concern about data security during a business meeting and speaks with an unstable tone, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0560] Through the above process, negotiation information is efficiently recorded, and optimal proposals that take into account the customer's emotional state can be made quickly.

[0561] The following describes the processing flow.

[0562] Step 1:

[0563] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation in real time.

[0564] Step 2:

[0565] The device sends the collected audio data to the server in real time. The server transcribes the received audio data using a speech recognition API.

[0566] Step 3:

[0567] The server temporarily stores the transcribed text data. The stored text data is then analyzed using natural language processing (NLP) algorithms to extract important keywords and phrases.

[0568] Step 4:

[0569] The server generates a summary based on the extracted information. This summary is designed to quickly grasp the overall picture and key points of a business deal.

[0570] Step 5:

[0571] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0572] Step 6:

[0573] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0574] Step 7:

[0575] The server analyzes the customer's statements. The server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, tone of voice, pitch, etc., to determine the customer's emotional state.

[0576] Step 8:

[0577] Based on the sentiment information identified by the sentiment engine, the server comprehensively identifies customer needs and challenges by referencing industry trend databases and past sales history to gather relevant information.

[0578] Step 9:

[0579] The server creates recommendations for the most suitable services and products based on identified needs and emotions. These recommendations are then sent from the server to the device.

[0580] Step 10:

[0581] The device displays recommendations to the user in real time. The user then uses the displayed recommendations to lead sales negotiations and make proposals to customers.

[0582] Step 11:

[0583] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0584] Step 12:

[0585] The server comprehensively analyzes emotional information, including post-meeting sales data and feedback. It then extracts key elements to include in the next proposal and automatically generates a draft based on these elements.

[0586] Step 13:

[0587] The generated proposal outline is sent to the terminal. The user can modify this outline and enter additional information as needed.

[0588] By following these steps, negotiation information will be efficiently recorded, and optimal proposals that take into account the customer's emotional state will be made quickly.

[0589] (Example 2)

[0590] 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".

[0591] In traditional sales activities, recording and summarizing negotiation details is often done manually, which is not only inefficient but also prone to overlooking important information and recording errors. Furthermore, there are few means to grasp what customers say and their emotional state in real time, making it difficult to make proposals that are best suited to each individual customer. In addition, creating proposals after negotiations requires a great deal of time and effort, so a quick response is required.

[0592] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data using natural language processing to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for analyzing customer statements and identifying customer needs by referring to an industry trend database and past business negotiation history; means for generating recommendations for optimal services and products based on the identified customer needs and emotional state; and means for automatically generating the outline of the next proposal. This enables efficient recording and summarization of business negotiation content, optimal proposals that take into account the customer's emotional state, and rapid generation of the next proposal.

[0593] "Audio data" refers to audio signals collected during business negotiations, meetings, and other similar events.

[0594] "Transcription" refers to the process of converting audio data into text format.

[0595] "Natural language processing" refers to the technology of analyzing text data and making it understandable to human language.

[0596] "Meeting minutes" refers to a document that records the details of a business negotiation or meeting.

[0597] A "summary" refers to a text that extracts the key points from a longer text and presents them concisely.

[0598] "External systems" refer to databases and applications that exist outside of the system.

[0599] "Customer statements" refers to words spoken by the customer during a business negotiation.

[0600] An "industry trend database" refers to a database that stores data on trends and developments in a specific industry or market.

[0601] "Sales negotiation history" refers to records related to past sales negotiations.

[0602] "Customer needs" refer to the demands and expectations that customers have regarding the products and services they seek.

[0603] "Emotional state" refers to the emotional state that can be inferred from a customer's statements and actions.

[0604] "Recommendation" refers to the suggestion of the most suitable products or services based on the customer's needs and emotional state.

[0605] "The outline of a proposal" refers to the basic structure of a document that contains important elements for the next business negotiation or proposal.

[0606] A "speech recognition API" refers to an application programming interface for converting speech data into text.

[0607] This invention is a system that supports sales activities by collecting and analyzing audio data from business negotiations and meetings, and automatically generating optimal proposals, thereby improving efficiency and effectiveness. This system has the function of collecting audio data in real time, transcribing it, extracting important points to generate meeting minutes and summaries, and automatically inputting them into an external system. It also has the function of analyzing customer statements, referring to industry trend databases and past business negotiation history, and providing recommendations for optimal services and products based on customer needs. Furthermore, this invention incorporates an emotion engine, which identifies emotions from customer statements and audio data and uses this for analysis, enabling more accurate recommendations and proposal adjustments.

[0608] The user (sales representative) initiates a sales meeting and activates the recording function on their device (laptop or smartphone). The device collects audio data from the meeting and sends it to the server in real time. The HTTPS protocol is used for communication to ensure data security. The server transcribes the received audio data using a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe) and temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[0609] The server analyzes the stored text data using natural language processing (NLP) algorithms (e.g., Hugging Face's transformers library) to extract important keywords and phrases. Based on the extracted information, the server generates a summary. The TextRank algorithm is used for summary generation. The generated meeting minutes and summaries are automatically input by the server into external systems (e.g., customer relationship management systems such as Salesforce and HubSpot) via API.

[0610] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. The server uses an emotion engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0611] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0612] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0613] For example, if a customer expresses concern about data security during a business meeting, and their tone is shaky, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0614] A concrete example of a prompt message for a generative AI model can be written as follows:

[0615] "Convert the following audio data to text, extract key points and emotional states, and generate optimal product recommendations. Audio data: 'The customer said they were concerned about data security.'"

[0616] Through the above processing, the system according to the present invention can efficiently record negotiation information and quickly provide optimal proposals that take into account the customer's emotional state.

[0617] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0618] Step 1: Collect audio data

[0619] The user (sales representative) begins the business negotiation and activates the recording function on their device (laptop or smartphone).

[0620] Input: Audio after the start of the business negotiation

[0621] The device collects audio data from this business negotiation in real time.

[0622] Output: Collected audio data

[0623] Step 2: Sending the audio data

[0624] The device transmits the collected voice data to the server in real time. The HTTPS protocol is used for communication to ensure data security.

[0625] Input: Collected audio data

[0626] Output: Audio data sent to the server

[0627] Step 3: Perform transcription

[0628] The server transcribes the received audio data using a speech recognition API (such as Google Cloud Speech-to-Text or Amazon Transcribe).

[0629] Input: Sent audio data

[0630] The server temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[0631] Output: Saved text data

[0632] Step 4: Analyzing Text Data

[0633] The server analyzes the stored text data using natural language processing (NLP) algorithms (for example, Hugging Face's transformers library) to extract important keywords and phrases.

[0634] Input: Saved text data

[0635] The server generates a summary based on the extracted information. The TextRank algorithm is used for summary generation.

[0636] Output: Extracted keywords and phrases, generated summary

[0637] Step 5: Automated entry of meeting minutes

[0638] The server inputs the generated meeting minutes and summaries into external systems (such as customer relationship management systems like Salesforce or HubSpot) via API.

[0639] Input: Generated meeting minutes or summaries

[0640] Output: Meeting minutes and summaries entered into an external system.

[0641] Step 6: Performing Sentiment Analysis

[0642] The server analyzes the collected speech data using a sentiment engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions.

[0643] Input: Data of conversations during business negotiations

[0644] The server analyzes linguistic features, tone of voice, pitch, etc., to identify the customer's emotional state.

[0645] Output: Identified sentiment information

[0646] Step 7: Gather relevant information

[0647] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referring to industry trend databases and past sales history.

[0648] Input: Identified sentiment information

[0649] Output: Related Information

[0650] Step 8: Create recommendations

[0651] The server creates recommendations for the most suitable services and products based on identified needs and emotions.

[0652] Input: Related information, identified sentiment information

[0653] Output: Generated recommendations

[0654] Step 9: Display Recommendations

[0655] The server sends the generated recommendations to the device.

[0656] Input: Generated recommendations

[0657] The device displays these recommendations to the user in real time.

[0658] Output: Recommendations displayed to the user

[0659] Step 10: Collecting feedback after the business negotiation

[0660] Users input feedback and notes about business negotiations into their devices. This includes customer reactions and requests for future meetings.

[0661] Input: Feedback or notes

[0662] The device sends this data to the server.

[0663] Output: Feedback and notes sent to the server

[0664] Step 11: Analysis of feedback and generation of proposal outline

[0665] The server comprehensively analyzes sales negotiation details, customer feedback, and sentiment information.

[0666] Input: Sales negotiation details, feedback, sentiment information

[0667] The server extracts the key elements that should be included in the next proposal and automatically generates the outline of the proposal based on them.

[0668] Output: Outline of the generated proposal

[0669] Step 12: View and revise the proposal outline.

[0670] The server sends the outline of the generated proposal to the terminal.

[0671] Input: Outline of the generated proposal

[0672] The terminal displays this outline to the user, who can modify it or enter additional information as needed.

[0673] Output: Outline of the proposal with modifications or additional information added by the user.

[0674] (Application Example 2)

[0675] 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."

[0676] Traditional e-commerce sites have struggled to provide optimal purchasing support to customers due to a lack of appropriate information and emotionally-based recommendations. Furthermore, customer support has faced challenges in providing effective assistance through real-time dialogue. This can lead to decreased customer satisfaction and a decline in purchasing intent.

[0677] 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. In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate minutes or summaries, means for identifying the customer's emotional state and adjusting recommendations based on the identified emotional information, and means for providing product information in real time while interacting with the customer. This makes it possible to provide optimal product recommendations and purchase support based on the customer's statements and emotions, thereby improving customer satisfaction and increasing purchasing intent.

[0678] "Voice data" refers to audio signals collected during conversations between customers and the system, and serves as basic data for analyzing the content of speech and emotional states.

[0679] "Transcription" is the process of converting collected audio data into text data, and is a pre-processing step for analysis and creating meeting minutes.

[0680] "Text data" refers to data in sentence format generated through transcription, and is used for extracting key points and sentiment analysis.

[0681] "Key points" are particularly noteworthy keywords and phrases extracted from text data, providing information useful for generating meeting minutes and summaries.

[0682] Meeting minutes are a document that concisely summarizes the overall picture of a business negotiation or meeting, and they contain important points.

[0683] A "summary" is a document that concisely summarizes the content of a conversation, focusing on the most important points.

[0684] "External systems" refer to related systems that exist outside the main system, such as customer relationship management systems and databases.

[0685] "Customer needs" refer to the requests and challenges customers have regarding the products and services they desire, and are directly related to the objectives of business negotiations and support.

[0686] "Recommendation" refers to suggesting the most suitable products or services based on customer needs and emotional states.

[0687] "Emotional state" refers to the psychological state identified from the customer's statements and voice, and is used to adjust service provision and recommendations.

[0688] "Real-time" refers to a state where processing and responses occur almost simultaneously, with minimal delay.

[0689] A "terminal" is a device used by users or sales representatives, and is used for collecting voice data and displaying recommendations.

[0690] A "server" is a computer system that processes and stores data, and is responsible for analyzing audio data and generating recommendations.

[0691] This invention aims to effectively realize a virtual shopping assistant system for e-commerce websites. This system is configured as an application installed on a smartphone and provides optimal product information and recommendations through voice interaction with the customer. The following details an embodiment of this system.

[0692] The server uses speech recognition APIs and natural language processing algorithms to collect and analyze audio data. Specifically, audio data collected by a smartphone's microphone is transcribed in real time using the Google Cloud Speech-to-Text API. The resulting text data is then analyzed by Amazon Comprehend via AWS Lambda to extract key points. The summaries and meeting minutes generated by this process are immediately stored in internal and external data storage.

[0693] The server also uses an emotion engine to identify emotional states from customer statements and voice. IBM Watson Tone Analyzer is used here to analyze emotions such as joy, anger, sadness, and anxiety from customer statements in real time. This emotion data is sent directly to the server, where recommendation generation algorithms adjust the actual recommendations.

[0694] Based on customer comments and emotional information, the server uses Amazon Personalize to generate optimal product recommendations, which are displayed in real time on the smartphone application screen. This allows users to receive the most relevant product information at the right time, supporting their purchase decisions.

[0695] Furthermore, after a business negotiation or purchasing support session is completed, feedback and notes are entered into the smartphone and sent to the server, which automatically generates the outline of the next proposal. This automatic generation again utilizes Amazon Comprehend and a generative AI model, and the server creates the basic structure of the proposal. This proposal is displayed on the smartphone screen so that the user can easily modify and complete it.

[0696] For example, if a customer says, "My home Wi-Fi is slow and it's causing problems," this system extracts keywords like "Wi-Fi" and "slow," and identifies their anxiety from the tone of voice. Then, it displays recommendations for the latest Wi-Fi routers on the screen. In this way, users can instantly receive appropriate product information.

[0697] Examples of prompt statements are as follows:

[0698] "My home Wi-Fi is slow. What products are available?"

[0699] "I'm worried about security. Do you have any smartphone recommendations?"

[0700] Based on the above, the present invention provides optimal product recommendations that accurately capture customer needs and emotions, thereby improving customer satisfaction and increasing purchasing intent on e-commerce sites.

[0701] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0702] Step 1:

[0703] The user (customer) launches a smartphone application and speaks using the microphone function. The smartphone's microphone collects this audio data in real time and sends it to the server. The input is the customer's audio data, and the output is the audio data sent to the server.

[0704] Step 2:

[0705] The server transcribes the received audio data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is transcribed text data. This text data is temporarily stored on the server.

[0706] Step 3:

[0707] The server uses AWS Lambda to analyze the transcribed text data with Amazon Comprehend, extracting key points and keywords. The input is text data, and the output is extracted key keywords and summary information. These key keywords are used to generate meeting minutes and summaries.

[0708] Step 4:

[0709] The server uses IBM Watson Tone Analyzer to identify the customer's emotional state from transcribed text data. Input is text data, and output is emotional state information. Emotions are categorized into joy, anger, sadness, anxiety, etc., and this information is used to refine recommendations.

[0710] Step 5:

[0711] The server uses Amazon Personalize to generate optimal product recommendations based on the customer's emotional state and extracted keywords. The input is emotional state information and key keywords, and the output is a list of recommended products. Recommendations are generated in real time.

[0712] Step 6:

[0713] The generated product recommendations are sent from the server to the smartphone application. The input is a product list generated on the server, and the output is product information displayed on the smartphone screen. The user selects products based on this information.

[0714] Step 7:

[0715] After a business meeting ends, the user (customer) enters feedback and notes into their smartphone. The entered data is sent to the server. The input is the feedback and notes entered by the user, and the output is the feedback data sent to the server.

[0716] Step 8:

[0717] The server uses Amazon Comprehend again to generate the outline for the next proposal based on the submitted feedback and notes. The input is the feedback data, and the output is the proposal outline. The generated proposal outline is sent to the user's smartphone and displayed in the application.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] [Third Embodiment]

[0722] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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".

[0734] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0735] The specific program processing is as follows:

[0736] Audio data collection and transcription

[0737] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects audio data from the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0738] Extracting key points and generating meeting minutes

[0739] The server uses natural language processing (NLP) algorithms to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary provides a quick overview of the conversation and highlights key points. The generated minutes and summary are automatically entered by the server into an external system.

[0740] Analysis of statements and generation of recommendations

[0741] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. Based on customer statements, the server gathers relevant information by cross-referencing with the latest industry trend database and past sales history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the sales meeting while referring to the recommendations.

[0742] Generating the outline for the next proposal

[0743] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0744] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0745] Through the above processes, sales activities become more efficient, enabling a quicker response to customer needs.

[0746] The following describes the processing flow.

[0747] Step 1:

[0748] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation and sends it to the server in real time.

[0749] Step 2:

[0750] The server transcribes the received audio data using a speech recognition API. The transcribed text data is temporarily stored on the server.

[0751] Step 3:

[0752] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary.

[0753] Step 4:

[0754] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0755] Step 5:

[0756] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0757] Step 6:

[0758] The server analyzes the customer's statements received and gathers relevant information by referencing industry trend databases and past sales history. This helps identify the customer's needs and challenges.

[0759] Step 7:

[0760] The server generates recommendations for the most suitable services and products based on identified needs and challenges. These recommendations are then sent from the server to the device.

[0761] Step 8:

[0762] The device displays recommendations to the user in real time. Based on this information, the user leads business negotiations and makes concrete proposals to customers.

[0763] Step 9:

[0764] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0765] Step 10:

[0766] The server analyzes the sales negotiation data and feedback after the meeting and extracts elements that should be included in the next proposal. Based on this, it automatically generates the outline of the proposal.

[0767] Step 11:

[0768] The generated proposal outline is sent to the terminal. The user can modify this outline or enter additional information as needed.

[0769] By following these steps, negotiation information will be efficiently recorded, and optimal proposals tailored to customer needs will be made quickly.

[0770] (Example 1)

[0771] 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."

[0772] In modern sales activities, it is essential to efficiently record the content of business negotiations, quickly grasp customer needs, and make appropriate proposals. However, manually transcribing audio data, creating meeting minutes, analyzing customer needs, and writing proposals is time-consuming and labor-intensive. Therefore, a system is needed to reduce the burden on sales representatives and streamline sales activities. Furthermore, there is a need for a means to analyze customer statements in real time and immediately propose the most suitable services and products.

[0773] 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.

[0774] In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for collecting customer statements through a terminal during a business negotiation and analyzing those statements; and means for generating an outline of the next proposal using a generation AI model based on the analyzed statements. This enables efficient recording of negotiation content, extraction of important points, automatic generation of meeting minutes, immediate understanding of customer needs, and rapid generation of appropriate proposals.

[0775] "Audio data" refers to data that records human voices in digital format.

[0776] "Real-time" means that data and information are processed immediately.

[0777] "Transcription" is the process of converting audio data into text data.

[0778] "Text data" refers to data that represents character information in a digital format.

[0779] "Key points" are keywords or phrases that deserve particular attention in discussions, business negotiations, etc.

[0780] "Meeting minutes" are documents that record the content of meetings or business negotiations and organize them in a way that allows for later reference.

[0781] A "summary" is a short, concise piece of text that extracts the most important parts from a large amount of information.

[0782] An "external system" is an information processing system provided by a third party other than the company's own system.

[0783] "Customer statements" refer to words spoken by customers during business negotiations or meetings.

[0784] An "industry trend database" is a database that compiles the latest information and statistical data related to a specific industry.

[0785] A "sales negotiation history" is a database that records past sales negotiations and their contents.

[0786] "Customer needs" refer to the products or services that customers require, or the problems they want to solve.

[0787] "Recommendation" is the process of suggesting appropriate products and services based on customer conditions and needs.

[0788] A "proposal" is a document that summarizes future actions and proposed plans based on the results of business negotiations or meetings.

[0789] "Terminals" refer to digital devices such as laptops and smartphones used by sales representatives.

[0790] A "server" is a remote computer system that stores and processes data.

[0791] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information and suggestions from data.

[0792] A "prompt statement" is an instruction given to a generative AI model, serving as a guide to obtain specific output.

[0793] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0794] Next, we will explain the specific steps for implementing this system.

[0795] First, the user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). This device has a dedicated application installed and collects audio data of the negotiation in real time. The collected audio data is sent to a server using a secure communication protocol (e.g., HTTPS). The server transcribes the received audio data using a speech recognition API, such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server.

[0796] Next, the server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary is designed to provide a quick overview of the conversation and highlight key points. The generated minutes and summary are then automatically entered by the server into external systems such as Salesforce.

[0797] During sales negotiations, the server analyzes customer statements entered by sales representatives and continuously collected voice data in real time. Based on customer statements, the server gathers relevant information by cross-referencing with industry trend databases (e.g., Crunchbase) and past sales negotiation history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the negotiation while referring to the recommendations.

[0798] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[0799] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[0800] Example of a prompt:

[0801] 1. Transcription of audio data: "Please transcribe this audio data."

[0802] 2. Summary Generation: "Extract the key points from this text data and generate a summary."

[0803] 3. Speech Analysis and Recommendation: "Analyze customer comments and recommend relevant services and products."

[0804] 4. Proposal Outline Generation: "Based on the negotiation content and feedback, please generate an outline for the next proposal."

[0805] Through the above process, sales activities become more efficient, enabling a quicker response to customer needs.

[0806] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0807] Step 1: Activate the recording function

[0808] The user initiates a business meeting and activates the recording function on their device (laptop or smartphone). This involves opening a dedicated application for the meeting and tapping the "Start Recording" button. The user's actions are the input, and the device begins recording as the output.

[0809] Step 2: Collecting audio data

[0810] The terminal collects audio data of the business negotiation in real time through its recording function. The collected audio data is temporarily stored on the terminal. The input is the user's voice, and the output is the audio data corresponding to that voice. The terminal displays "Business negotiation started."

[0811] Step 3: Sending audio data

[0812] The terminal sends the collected audio data to the server in real time. This process uses a secure communication protocol (e.g., HTTPS). The input is the collected audio data, and the output is the audio data sent to the server. The terminal displays "Sending audio data to server...".

[0813] Step 4: Transcribing the audio data

[0814] The server transcribes the received audio data using a speech recognition API such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server. The input is the transmitted audio data, and the output is the transcribed text data. The server records a status in the server log indicating "Transcription in progress...".

[0815] Step 5: Extraction of key keywords

[0816] The server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. The input is the transcribed text data, and the output is the important keywords and phrases. The server generates a log message saying "Extracting important keywords...".

[0817] Step 6: Generating a summary

[0818] The server generates a summary based on the extracted information. A text summarization algorithm is used for summary generation. The input consists of key keywords and phrases, and the output is a summary text. The server logs "Summary generated" and displays the summary.

[0819] Step 7: Automatic Input

[0820] The server automatically inputs the generated meeting minutes and summaries into external systems such as Salesforce. The input is the generated meeting minutes and summaries, and the output is the data input to the external system. The server records "Data has been input into Salesforce."

[0821] Step 8: Collecting Customer Feedback

[0822] The server analyzes customer statements entered by sales representatives during negotiations, as well as continuously collected audio data, in real time. Input consists of customer statements and audio data, while output is the analysis results of this data. The server displays "Collecting customer statements...".

[0823] Step 9: Gather relevant information

[0824] The server uses customer statements to collect relevant information by cross-referencing them with industry trend databases (e.g., Crunchbase) and past sales history. The input is the analyzed customer statements, and the output is the relevant information. The server displays "Collecting relevant information...".

[0825] Step 10: Identifying Needs and Challenges

[0826] The server identifies customer needs and challenges. The input is the relevant information collected, and the output is the customer needs and challenges. The server logs "Customer needs identified."

[0827] Step 11: Provide recommendations

[0828] The server generates recommendations for the most suitable services and products based on the identified customer's needs. The generated recommendations are sent to the device. The input is the customer's needs or challenges, and the output is the recommendations. The server displays "Recommendations sent to device" and notifies the device with "New recommendations available."

[0829] Step 12: Entering Feedback

[0830] After a business meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to the server. The input is the feedback and notes entered by the sales representative, and the output is the data sent to the server. The terminal displays "Feedback sent to server."

[0831] Step 13: Data Analysis

[0832] The server analyzes sales negotiation details, customer feedback, and past proposals. This analysis uses machine learning models (e.g., text classification models). Input is feedback and notes sent to the server, and output is the analysis results. The server displays a status of "Analyzing data...".

[0833] Step 14: Generating the Outline of the Proposal

[0834] The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on them. This generation uses a template-based approach. The input is the analysis results, and the output is the proposal outline. The server logs "Proposal outline generated" and generates a template.

[0835] Step 15: Submitting the Proposal

[0836] The server sends the generated proposal outline to the terminal. The input is the proposal outline, and the output is the proposal outline sent to the terminal. The server records "Proposal outline sent to terminal" and the terminal receives a notification saying "Please review the proposal."

[0837] Following the above steps, sales activities become more efficient, and it becomes possible to respond quickly to customer needs.

[0838] (Application Example 1)

[0839] 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."

[0840] Traditional sales support and customer service systems have faced challenges in recording and analyzing customer statements in real time and providing optimal recommendations on the spot. Furthermore, they lack the ability to automatically generate next-time proposals based on conversation content, resulting in increased effort required to improve the quality of customer service. Additionally, a lack of tools for store staff to quickly respond to customer needs contributes to decreased customer satisfaction.

[0841] 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.

[0842] In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate meeting minutes or summaries, and means for automatically inputting the generated meeting minutes or summaries into an external system. This makes it possible for store staff to record customer statements in real time while interacting with customers, recommend related products based on that information, and prepare suggestions for the next visit. Furthermore, by automatically generating the necessary suggestions using a generation AI model, the quality of customer service can be improved and customer satisfaction can be increased.

[0843] "Audio data" refers to a digital representation of acoustic signals, including human speech and environmental sounds.

[0844] "Transcription" is the process of analyzing audio data and converting its content into text data.

[0845] "Text data" refers to digital data that contains character information, and generally refers to documents or memory contents.

[0846] "Key points" refer to keywords or phrases that deserve particular attention in a conversation or document.

[0847] "Meeting minutes" are documents that record important statements and decisions made during meetings, business negotiations, and other similar events.

[0848] A "summary" is a concise compilation of the original text's content.

[0849] An "external system" is a system that exists separately from the internal system and is used for data linkage and information exchange.

[0850] "Customer statements" refer to opinions, requests, questions, etc., expressed by customers during business negotiations or interactions.

[0851] An "industry trend database" is a database that compiles the latest trends and developments information related to a specific industry.

[0852] "Past business negotiation history" refers to a compilation of records, content, and results of business negotiations that have taken place in the past.

[0853] "Customer needs" refer to the products, services, or problems that customers want to solve.

[0854] "Recommending services and products" refers to suggesting the most suitable products and services to meet customer needs.

[0855] "Outline of the next proposal" is an overview of the main items and structure of the next proposal to be submitted.

[0856] "Store staff" refers to employees who handle customer service at physical stores.

[0857] A "generative AI model" is a model that uses artificial intelligence technology to perform tasks such as text generation and data analysis.

[0858] This invention is a system for streamlining sales activities and customer service. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[0859] System program

[0860] The user (store staff or sales representative) activates the recording function on their device (smartphone or tablet) when starting a customer interaction or business negotiation. The device collects audio data of the negotiation or customer interaction and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API) and temporarily stores the generated text data. A speech recognition algorithm is used in this process of transcribing audio data.

[0861] Extracting key points and generating meeting minutes

[0862] The server uses natural language processing (NLP) algorithms (such as spaCy) on text data to extract important keywords and phrases. Based on the extracted information, it generates a summary using a text summarization model (transformers' summarizer model). The generated meeting minutes and summaries are automatically entered by the server into external systems (such as CRM systems).

[0863] Analysis of statements and generation of recommendations

[0864] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. This identifies customer needs and generates recommendations for the most suitable services and products based on those needs. These recommendations are displayed in real time on the terminals of store staff or sales representatives, guiding sales negotiations and customer interactions.

[0865] Proposal outline generation

[0866] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify or add to it as needed.

[0867] Specific example

[0868] If a customer says "I'd like to discuss a new smartphone" during a business meeting, the statement is transcribed and the keyword "smartphone" is extracted. Then, based on the identified keyword, new products related to "smartphones" are recommended. Furthermore, the core of the proposal for the next visit will include the features and benefits of the new smartphone.

[0869] Example of a prompt

[0870] Next Proposal Generation: Based on the following summary, please create a concise outline for your next proposal.

[0871] Customer requests:

[0872] The customer expressed interest in a new smartphone. They are interested in ease of use and the latest technology.

[0873] summary:

[0874] Since customers are interested in the ease of use and latest technology of new smartphones, it is important to offer them the latest models.

[0875] This invention allows store staff and sales representatives to record customer comments in real time, provide optimal recommendations on the spot, and prepare for future visits. Furthermore, by utilizing a generative AI model, proposal creation can be automated, significantly improving the efficiency of sales activities.

[0876] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0877] Step 1:

[0878] When a user initiates a customer interaction or business negotiation, they activate the recording function on their device (smartphone or tablet). The device collects audio data in real time and sends it to a server. The input is the audio data of the conversation between the customer and the user, and the output is the audio data sent to the server. This step includes an audio collection device and a means of communication.

[0879] Step 2:

[0880] The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API). The generated text data is temporarily stored. The input is the audio data sent to the server, and the output is the transcribed text data. This step involves a speech recognition algorithm.

[0881] Step 3:

[0882] The server uses natural language processing (NLP) algorithms (such as spaCy) on the transcribed text data to extract important keywords and phrases. Based on the extracted information, a text summarization model (transformers' summarizer model) is used to generate a summary. The input is the transcribed text data, and the output is the summarized text and important keywords. This step involves natural language processing algorithms and a text summarization model.

[0883] Step 4:

[0884] The generated meeting minutes or summary are automatically entered by the server into an external system (such as a CRM system). The input consists of the summary text and key keywords, while the output is the data stored in the external system. This step involves API calls for automated data entry.

[0885] Step 5:

[0886] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. The input is transcribed text data, and the output is identified customer needs and recommendations for services and products based on those needs. This step involves database lookup and analysis algorithms.

[0887] Step 6:

[0888] Recommendations generated based on customer needs are displayed in real time on the terminals of store staff or sales representatives. The inputs are the identified customer needs and the generated recommendations, while the output is the recommendation information displayed on the terminal. This step includes a user interface for data display.

[0889] Step 7:

[0890] After a business negotiation concludes, the user enters feedback and notes about the negotiation into their terminal. This data is sent to a server, which analyzes the negotiation details, customer feedback, and past proposals. The input consists of the user's feedback and notes, while the output is the analyzed negotiation details and feedback data. This step includes a feedback input form and data storage functionality.

[0891] Step 8:

[0892] The server automatically generates key elements to include in the next proposal using a generation AI model (such as GPT-3). The generated proposal outline is sent to the terminal, where the user can modify or add to it as needed. The input is customer needs and feedback data, and the output is the automatically generated outline of the next proposal. This step includes a generation AI model and data transmission functionality.

[0893] 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.

[0894] This invention is a system designed to support sales activities and improve their efficiency and effectiveness. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs.

[0895] Furthermore, this invention incorporates an emotion engine that identifies emotions from customer statements and voice data and uses this information for analysis, enabling more accurate recommendations and suggestions.

[0896] The specific program processing is as follows:

[0897] Audio data collection and transcription

[0898] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[0899] Extracting key points and generating meeting minutes

[0900] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary. This summary is designed to quickly grasp the overall picture and key points of the conversation. The generated minutes and summaries are automatically entered by the server into external systems (e.g., customer relationship management systems) via API.

[0901] Analysis of statements using an emotion engine

[0902] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. During this process, the server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0903] Recommendation generation and display

[0904] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0905] Generating the outline for the next proposal

[0906] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0907] For example, if a customer expresses concern about data security during a business meeting and speaks with an unstable tone, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0908] Through the above process, negotiation information is efficiently recorded, and optimal proposals that take into account the customer's emotional state can be made quickly.

[0909] The following describes the processing flow.

[0910] Step 1:

[0911] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation in real time.

[0912] Step 2:

[0913] The device sends the collected audio data to the server in real time. The server transcribes the received audio data using a speech recognition API.

[0914] Step 3:

[0915] The server temporarily stores the transcribed text data. The stored text data is then analyzed using natural language processing (NLP) algorithms to extract important keywords and phrases.

[0916] Step 4:

[0917] The server generates a summary based on the extracted information. This summary is designed to quickly grasp the overall picture and key points of a business deal.

[0918] Step 5:

[0919] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[0920] Step 6:

[0921] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[0922] Step 7:

[0923] The server analyzes the customer's statements. The server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, tone of voice, pitch, etc., to determine the customer's emotional state.

[0924] Step 8:

[0925] Based on the sentiment information identified by the sentiment engine, the server comprehensively identifies customer needs and challenges by referencing industry trend databases and past sales history to gather relevant information.

[0926] Step 9:

[0927] The server creates recommendations for the most suitable services and products based on identified needs and emotions. These recommendations are then sent from the server to the device.

[0928] Step 10:

[0929] The device displays recommendations to the user in real time. The user then uses the displayed recommendations to lead sales negotiations and make proposals to customers.

[0930] Step 11:

[0931] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[0932] Step 12:

[0933] The server comprehensively analyzes emotional information, including post-meeting sales data and feedback. It then extracts key elements to include in the next proposal and automatically generates a draft based on these elements.

[0934] Step 13:

[0935] The generated proposal outline is sent to the terminal. The user can modify this outline and enter additional information as needed.

[0936] By following these steps, negotiation information will be efficiently recorded, and optimal proposals that take into account the customer's emotional state will be made quickly.

[0937] (Example 2)

[0938] 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."

[0939] In traditional sales activities, recording and summarizing negotiation details is often done manually, which is not only inefficient but also prone to overlooking important information and recording errors. Furthermore, there are few means to grasp what customers say and their emotional state in real time, making it difficult to make proposals that are best suited to each individual customer. In addition, creating proposals after negotiations requires a great deal of time and effort, so a quick response is required.

[0940] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data using natural language processing to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for analyzing customer statements and identifying customer needs by referring to an industry trend database and past business negotiation history; means for generating recommendations for optimal services and products based on the identified customer needs and emotional state; and means for automatically generating the outline of the next proposal. This enables efficient recording and summarization of business negotiation content, optimal proposals that take into account the customer's emotional state, and rapid generation of the next proposal.

[0941] "Audio data" refers to audio signals collected during business negotiations, meetings, and other similar events.

[0942] "Transcription" refers to the process of converting audio data into text format.

[0943] "Natural language processing" refers to the technology of analyzing text data and making it understandable to human language.

[0944] "Meeting minutes" refers to a document that records the details of a business negotiation or meeting.

[0945] A "summary" refers to a text that extracts the key points from a longer text and presents them concisely.

[0946] "External systems" refer to databases and applications that exist outside of the system.

[0947] "Customer statements" refers to words spoken by the customer during a business negotiation.

[0948] An "industry trend database" refers to a database that stores data on trends and developments in a specific industry or market.

[0949] "Sales negotiation history" refers to records related to past sales negotiations.

[0950] "Customer needs" refer to the demands and expectations that customers have regarding the products and services they seek.

[0951] "Emotional state" refers to the emotional state that can be inferred from a customer's statements and actions.

[0952] "Recommendation" refers to the suggestion of the most suitable products or services based on the customer's needs and emotional state.

[0953] "The outline of a proposal" refers to the basic structure of a document that contains important elements for the next business negotiation or proposal.

[0954] A "speech recognition API" refers to an application programming interface for converting speech data into text.

[0955] This invention is a system that supports sales activities by collecting and analyzing audio data from business negotiations and meetings, and automatically generating optimal proposals, thereby improving efficiency and effectiveness. This system has the function of collecting audio data in real time, transcribing it, extracting important points to generate meeting minutes and summaries, and automatically inputting them into an external system. It also has the function of analyzing customer statements, referring to industry trend databases and past business negotiation history, and providing recommendations for optimal services and products based on customer needs. Furthermore, this invention incorporates an emotion engine, which identifies emotions from customer statements and audio data and uses this for analysis, enabling more accurate recommendations and proposal adjustments.

[0956] The user (sales representative) initiates a sales meeting and activates the recording function on their device (laptop or smartphone). The device collects audio data from the meeting and sends it to the server in real time. The HTTPS protocol is used for communication to ensure data security. The server transcribes the received audio data using a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe) and temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[0957] The server analyzes the stored text data using natural language processing (NLP) algorithms (e.g., Hugging Face's transformers library) to extract important keywords and phrases. Based on the extracted information, the server generates a summary. The TextRank algorithm is used for summary generation. The generated meeting minutes and summaries are automatically input by the server into external systems (e.g., customer relationship management systems such as Salesforce and HubSpot) via API.

[0958] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. The server uses an emotion engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[0959] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[0960] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[0961] For example, if a customer expresses concern about data security during a business meeting, and their tone is shaky, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[0962] A concrete example of a prompt message for a generative AI model can be written as follows:

[0963] "Convert the following audio data to text, extract key points and emotional states, and generate optimal product recommendations. Audio data: 'The customer said they were concerned about data security.'"

[0964] Through the above processing, the system according to the present invention can efficiently record negotiation information and quickly provide optimal proposals that take into account the customer's emotional state.

[0965] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0966] Step 1: Collect audio data

[0967] The user (sales representative) begins the business negotiation and activates the recording function on their device (laptop or smartphone).

[0968] Input: Audio after the start of the business negotiation

[0969] The device collects audio data from this business negotiation in real time.

[0970] Output: Collected audio data

[0971] Step 2: Sending the audio data

[0972] The device transmits the collected voice data to the server in real time. The HTTPS protocol is used for communication to ensure data security.

[0973] Input: Collected audio data

[0974] Output: Audio data sent to the server

[0975] Step 3: Perform transcription

[0976] The server transcribes the received audio data using a speech recognition API (such as Google Cloud Speech-to-Text or Amazon Transcribe).

[0977] Input: Sent audio data

[0978] The server temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[0979] Output: Saved text data

[0980] Step 4: Analyzing Text Data

[0981] The server analyzes the stored text data using natural language processing (NLP) algorithms (for example, Hugging Face's transformers library) to extract important keywords and phrases.

[0982] Input: Saved text data

[0983] The server generates a summary based on the extracted information. The TextRank algorithm is used for summary generation.

[0984] Output: Extracted keywords and phrases, generated summary

[0985] Step 5: Automated entry of meeting minutes

[0986] The server inputs the generated meeting minutes and summaries into external systems (such as customer relationship management systems like Salesforce or HubSpot) via API.

[0987] Input: Generated meeting minutes or summaries

[0988] Output: Meeting minutes and summaries entered into an external system.

[0989] Step 6: Performing Sentiment Analysis

[0990] The server analyzes the collected speech data using a sentiment engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions.

[0991] Input: Data of conversations during business negotiations

[0992] The server analyzes linguistic features, tone of voice, pitch, etc., to identify the customer's emotional state.

[0993] Output: Identified sentiment information

[0994] Step 7: Gather relevant information

[0995] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referring to industry trend databases and past sales history.

[0996] Input: Identified sentiment information

[0997] Output: Related Information

[0998] Step 8: Create recommendations

[0999] The server creates recommendations for the most suitable services and products based on identified needs and emotions.

[1000] Input: Related information, identified sentiment information

[1001] Output: Generated recommendations

[1002] Step 9: Display Recommendations

[1003] The server sends the generated recommendations to the device.

[1004] Input: Generated recommendations

[1005] The device displays these recommendations to the user in real time.

[1006] Output: Recommendations displayed to the user

[1007] Step 10: Collecting feedback after the business negotiation

[1008] Users input feedback and notes about business negotiations into their devices. This includes customer reactions and requests for future meetings.

[1009] Input: Feedback or notes

[1010] The device sends this data to the server.

[1011] Output: Feedback and notes sent to the server

[1012] Step 11: Analysis of feedback and generation of proposal outline

[1013] The server comprehensively analyzes sales negotiation details, customer feedback, and sentiment information.

[1014] Input: Sales negotiation details, feedback, sentiment information

[1015] The server extracts the key elements that should be included in the next proposal and automatically generates the outline of the proposal based on them.

[1016] Output: Outline of the generated proposal

[1017] Step 12: View and revise the proposal outline.

[1018] The server sends the outline of the generated proposal to the terminal.

[1019] Input: Outline of the generated proposal

[1020] The terminal displays this outline to the user, who can modify it or enter additional information as needed.

[1021] Output: Outline of the proposal with modifications or additional information added by the user.

[1022] (Application Example 2)

[1023] 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."

[1024] Traditional e-commerce sites have struggled to provide optimal purchasing support to customers due to a lack of appropriate information and emotionally-based recommendations. Furthermore, customer support has faced challenges in providing effective assistance through real-time dialogue. This can lead to decreased customer satisfaction and a decline in purchasing intent.

[1025] 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. In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate minutes or summaries, means for identifying the customer's emotional state and adjusting recommendations based on the identified emotional information, and means for providing product information in real time while interacting with the customer. This makes it possible to provide optimal product recommendations and purchase support based on the customer's statements and emotions, thereby improving customer satisfaction and increasing purchasing intent.

[1026] "Voice data" refers to audio signals collected during conversations between customers and the system, and serves as basic data for analyzing the content of speech and emotional states.

[1027] "Transcription" is the process of converting collected audio data into text data, and is a pre-processing step for analysis and creating meeting minutes.

[1028] "Text data" refers to data in sentence format generated through transcription, and is used for extracting key points and sentiment analysis.

[1029] "Key points" are particularly noteworthy keywords and phrases extracted from text data, providing information useful for generating meeting minutes and summaries.

[1030] Meeting minutes are a document that concisely summarizes the overall picture of a business negotiation or meeting, and they contain important points.

[1031] A "summary" is a document that concisely summarizes the content of a conversation, focusing on the most important points.

[1032] "External systems" refer to related systems that exist outside the main system, such as customer relationship management systems and databases.

[1033] "Customer needs" refer to the requests and challenges customers have regarding the products and services they desire, and are directly related to the objectives of business negotiations and support.

[1034] "Recommendation" refers to suggesting the most suitable products or services based on customer needs and emotional states.

[1035] "Emotional state" refers to the psychological state identified from the customer's statements and voice, and is used to adjust service provision and recommendations.

[1036] "Real-time" refers to a state where processing and responses occur almost simultaneously, with minimal delay.

[1037] A "terminal" is a device used by users or sales representatives, and is used for collecting voice data and displaying recommendations.

[1038] A "server" is a computer system that processes and stores data, and is responsible for analyzing audio data and generating recommendations.

[1039] This invention aims to effectively realize a virtual shopping assistant system for e-commerce websites. This system is configured as an application installed on a smartphone and provides optimal product information and recommendations through voice interaction with the customer. The following details an embodiment of this system.

[1040] The server uses speech recognition APIs and natural language processing algorithms to collect and analyze audio data. Specifically, audio data collected by a smartphone's microphone is transcribed in real time using the Google Cloud Speech-to-Text API. The resulting text data is then analyzed by Amazon Comprehend via AWS Lambda to extract key points. The summaries and meeting minutes generated by this process are immediately stored in internal and external data storage.

[1041] The server also uses an emotion engine to identify emotional states from customer statements and voice. IBM Watson Tone Analyzer is used here to analyze emotions such as joy, anger, sadness, and anxiety from customer statements in real time. This emotion data is sent directly to the server, where recommendation generation algorithms adjust the actual recommendations.

[1042] Based on customer comments and emotional information, the server uses Amazon Personalize to generate optimal product recommendations, which are displayed in real time on the smartphone application screen. This allows users to receive the most relevant product information at the right time, supporting their purchase decisions.

[1043] Furthermore, after a business negotiation or purchasing support session is completed, feedback and notes are entered into the smartphone and sent to the server, which automatically generates the outline of the next proposal. This automatic generation again utilizes Amazon Comprehend and a generative AI model, and the server creates the basic structure of the proposal. This proposal is displayed on the smartphone screen so that the user can easily modify and complete it.

[1044] For example, if a customer says, "My home Wi-Fi is slow and it's causing problems," this system extracts keywords like "Wi-Fi" and "slow," and identifies their anxiety from the tone of voice. Then, it displays recommendations for the latest Wi-Fi routers on the screen. In this way, users can instantly receive appropriate product information.

[1045] Examples of prompt statements are as follows:

[1046] "My home Wi-Fi is slow. What products are available?"

[1047] "I'm worried about security. Do you have any smartphone recommendations?"

[1048] Based on the above, the present invention provides optimal product recommendations that accurately capture customer needs and emotions, thereby improving customer satisfaction and increasing purchasing intent on e-commerce sites.

[1049] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1050] Step 1:

[1051] The user (customer) launches a smartphone application and speaks using the microphone function. The smartphone's microphone collects this audio data in real time and sends it to the server. The input is the customer's audio data, and the output is the audio data sent to the server.

[1052] Step 2:

[1053] The server transcribes the received audio data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is transcribed text data. This text data is temporarily stored on the server.

[1054] Step 3:

[1055] The server uses AWS Lambda to analyze the transcribed text data with Amazon Comprehend, extracting key points and keywords. The input is text data, and the output is extracted key keywords and summary information. These key keywords are used to generate meeting minutes and summaries.

[1056] Step 4:

[1057] The server uses IBM Watson Tone Analyzer to identify the customer's emotional state from transcribed text data. Input is text data, and output is emotional state information. Emotions are categorized into joy, anger, sadness, anxiety, etc., and this information is used to refine recommendations.

[1058] Step 5:

[1059] The server uses Amazon Personalize to generate optimal product recommendations based on the customer's emotional state and extracted keywords. The input is emotional state information and key keywords, and the output is a list of recommended products. Recommendations are generated in real time.

[1060] Step 6:

[1061] The generated product recommendations are sent from the server to the smartphone application. The input is a product list generated on the server, and the output is product information displayed on the smartphone screen. The user selects products based on this information.

[1062] Step 7:

[1063] After a business meeting ends, the user (customer) enters feedback and notes into their smartphone. The entered data is sent to the server. The input is the feedback and notes entered by the user, and the output is the feedback data sent to the server.

[1064] Step 8:

[1065] The server uses Amazon Comprehend again to generate the outline for the next proposal based on the submitted feedback and notes. The input is the feedback data, and the output is the proposal outline. The generated proposal outline is sent to the user's smartphone and displayed in the application.

[1066] 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.

[1067] 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.

[1068] 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.

[1069] [Fourth Embodiment]

[1070] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1071] 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.

[1072] 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).

[1073] 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.

[1074] 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.

[1075] 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).

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] 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".

[1083] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[1084] The specific program processing is as follows:

[1085] Audio data collection and transcription

[1086] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects audio data from the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[1087] Extracting key points and generating meeting minutes

[1088] The server uses natural language processing (NLP) algorithms to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary provides a quick overview of the conversation and highlights key points. The generated minutes and summary are automatically entered by the server into an external system.

[1089] Analysis of statements and generation of recommendations

[1090] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. Based on customer statements, the server gathers relevant information by cross-referencing with the latest industry trend database and past sales history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the sales meeting while referring to the recommendations.

[1091] Generating the outline for the next proposal

[1092] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[1093] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[1094] Through the above processes, sales activities become more efficient, enabling a quicker response to customer needs.

[1095] The following describes the processing flow.

[1096] Step 1:

[1097] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation and sends it to the server in real time.

[1098] Step 2:

[1099] The server transcribes the received audio data using a speech recognition API. The transcribed text data is temporarily stored on the server.

[1100] Step 3:

[1101] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary.

[1102] Step 4:

[1103] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[1104] Step 5:

[1105] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[1106] Step 6:

[1107] The server analyzes the customer's statements received and gathers relevant information by referencing industry trend databases and past sales history. This helps identify the customer's needs and challenges.

[1108] Step 7:

[1109] The server generates recommendations for the most suitable services and products based on identified needs and challenges. These recommendations are then sent from the server to the device.

[1110] Step 8:

[1111] The device displays recommendations to the user in real time. Based on this information, the user leads business negotiations and makes concrete proposals to customers.

[1112] Step 9:

[1113] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[1114] Step 10:

[1115] The server analyzes the sales negotiation data and feedback after the meeting and extracts elements that should be included in the next proposal. Based on this, it automatically generates the outline of the proposal.

[1116] Step 11:

[1117] The generated proposal outline is sent to the terminal. The user can modify this outline or enter additional information as needed.

[1118] By following these steps, negotiation information will be efficiently recorded, and optimal proposals tailored to customer needs will be made quickly.

[1119] (Example 1)

[1120] 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".

[1121] In modern sales activities, it is essential to efficiently record the content of business negotiations, quickly grasp customer needs, and make appropriate proposals. However, manually transcribing audio data, creating meeting minutes, analyzing customer needs, and writing proposals is time-consuming and labor-intensive. Therefore, a system is needed to reduce the burden on sales representatives and streamline sales activities. Furthermore, there is a need for a means to analyze customer statements in real time and immediately propose the most suitable services and products.

[1122] 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.

[1123] In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for collecting customer statements through a terminal during a business negotiation and analyzing those statements; and means for generating an outline of the next proposal using a generation AI model based on the analyzed statements. This enables efficient recording of negotiation content, extraction of important points, automatic generation of meeting minutes, immediate understanding of customer needs, and rapid generation of appropriate proposals.

[1124] "Audio data" refers to data that records human voices in digital format.

[1125] "Real-time" means that data and information are processed immediately.

[1126] "Transcription" is the process of converting audio data into text data.

[1127] "Text data" refers to data that represents character information in a digital format.

[1128] "Key points" are keywords or phrases that deserve particular attention in discussions, business negotiations, etc.

[1129] "Meeting minutes" are documents that record the content of meetings or business negotiations and organize them in a way that allows for later reference.

[1130] A "summary" is a short, concise piece of text that extracts the most important parts from a large amount of information.

[1131] An "external system" is an information processing system provided by a third party other than the company's own system.

[1132] "Customer statements" refer to words spoken by customers during business negotiations or meetings.

[1133] An "industry trend database" is a database that compiles the latest information and statistical data related to a specific industry.

[1134] A "sales negotiation history" is a database that records past sales negotiations and their contents.

[1135] "Customer needs" refer to the products or services that customers require, or the problems they want to solve.

[1136] "Recommendation" is the process of suggesting appropriate products and services based on customer conditions and needs.

[1137] A "proposal" is a document that summarizes future actions and proposed plans based on the results of business negotiations or meetings.

[1138] "Terminals" refer to digital devices such as laptops and smartphones used by sales representatives.

[1139] A "server" is a remote computer system that stores and processes data.

[1140] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information and suggestions from data.

[1141] A "prompt statement" is an instruction given to a generative AI model, serving as a guide to obtain specific output.

[1142] This invention is a system designed to support and improve the efficiency of sales activities. This system features the ability to collect audio data in real time, transcribe it, extract key points to generate meeting minutes and summaries, and automatically input them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[1143] Next, we will explain the specific steps for implementing this system.

[1144] First, the user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). This device has a dedicated application installed and collects audio data of the negotiation in real time. The collected audio data is sent to a server using a secure communication protocol (e.g., HTTPS). The server transcribes the received audio data using a speech recognition API, such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server.

[1145] Next, the server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. Based on the extracted information, the server generates a summary. This summary is designed to provide a quick overview of the conversation and highlight key points. The generated minutes and summary are then automatically entered by the server into external systems such as Salesforce.

[1146] During sales negotiations, the server analyzes customer statements entered by sales representatives and continuously collected voice data in real time. Based on customer statements, the server gathers relevant information by cross-referencing with industry trend databases (e.g., Crunchbase) and past sales negotiation history to identify customer needs and challenges. Based on the identified needs, the server generates recommendations for the most suitable services and products and sends them to the terminal. Sales representatives then lead the negotiation while referring to the recommendations.

[1147] After a sales meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, where the sales representative can make revisions and additions as needed.

[1148] For example, if a customer expresses concern about data security during a business meeting, the server analyzes the statement and recommends relevant, up-to-date security solutions. Furthermore, the proposal outline is generated to emphasize data security solutions.

[1149] Example of a prompt:

[1150] 1. Transcription of audio data: "Please transcribe this audio data."

[1151] 2. Summary Generation: "Extract the key points from this text data and generate a summary."

[1152] 3. Speech Analysis and Recommendation: "Analyze customer comments and recommend relevant services and products."

[1153] 4. Proposal Outline Generation: "Based on the negotiation content and feedback, please generate an outline for the next proposal."

[1154] Through the above process, sales activities become more efficient, enabling a quicker response to customer needs.

[1155] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1156] Step 1: Activate the recording function

[1157] The user initiates a business meeting and activates the recording function on their device (laptop or smartphone). This involves opening a dedicated application for the meeting and tapping the "Start Recording" button. The user's actions are the input, and the device begins recording as the output.

[1158] Step 2: Collecting audio data

[1159] The terminal collects audio data of the business negotiation in real time through its recording function. The collected audio data is temporarily stored on the terminal. The input is the user's voice, and the output is the audio data corresponding to that voice. The terminal displays "Business negotiation started."

[1160] Step 3: Sending audio data

[1161] The terminal sends the collected audio data to the server in real time. This process uses a secure communication protocol (e.g., HTTPS). The input is the collected audio data, and the output is the audio data sent to the server. The terminal displays "Sending audio data to server...".

[1162] Step 4: Transcribing the audio data

[1163] The server transcribes the received audio data using a speech recognition API such as the Google Cloud Speech-to-Text API. The transcribed text data is temporarily stored on the server. The input is the transmitted audio data, and the output is the transcribed text data. The server records a status in the server log indicating "Transcription in progress...".

[1164] Step 5: Extraction of key keywords

[1165] The server uses NLP (Natural Language Processing) algorithms (e.g., Google Cloud Natural Language API) to extract important keywords and phrases from the transcribed data. The input is the transcribed text data, and the output is the important keywords and phrases. The server generates a log message saying "Extracting important keywords...".

[1166] Step 6: Generating a summary

[1167] The server generates a summary based on the extracted information. A text summarization algorithm is used for summary generation. The input consists of key keywords and phrases, and the output is a summary text. The server logs "Summary generated" and displays the summary.

[1168] Step 7: Automatic Input

[1169] The server automatically inputs the generated meeting minutes and summaries into external systems such as Salesforce. The input is the generated meeting minutes and summaries, and the output is the data input to the external system. The server records "Data has been input into Salesforce."

[1170] Step 8: Collecting Customer Feedback

[1171] The server analyzes customer statements entered by sales representatives during negotiations, as well as continuously collected audio data, in real time. Input consists of customer statements and audio data, while output is the analysis results of this data. The server displays "Collecting customer statements...".

[1172] Step 9: Gather relevant information

[1173] The server uses customer statements to collect relevant information by cross-referencing them with industry trend databases (e.g., Crunchbase) and past sales history. The input is the analyzed customer statements, and the output is the relevant information. The server displays "Collecting relevant information...".

[1174] Step 10: Identifying Needs and Challenges

[1175] The server identifies customer needs and challenges. The input is the relevant information collected, and the output is the customer needs and challenges. The server logs "Customer needs identified."

[1176] Step 11: Provide recommendations

[1177] The server generates recommendations for the most suitable services and products based on the identified customer's needs. The generated recommendations are sent to the device. The input is the customer's needs or challenges, and the output is the recommendations. The server displays "Recommendations sent to device" and notifies the device with "New recommendations available."

[1178] Step 12: Entering Feedback

[1179] After a business meeting concludes, the sales representative enters feedback and notes about the meeting into their terminal. This data is sent to the server. The input is the feedback and notes entered by the sales representative, and the output is the data sent to the server. The terminal displays "Feedback sent to server."

[1180] Step 13: Data Analysis

[1181] The server analyzes sales negotiation details, customer feedback, and past proposals. This analysis uses machine learning models (e.g., text classification models). Input is feedback and notes sent to the server, and output is the analysis results. The server displays a status of "Analyzing data...".

[1182] Step 14: Generating the Outline of the Proposal

[1183] The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on them. This generation uses a template-based approach. The input is the analysis results, and the output is the proposal outline. The server logs "Proposal outline generated" and generates a template.

[1184] Step 15: Submitting the Proposal

[1185] The server sends the generated proposal outline to the terminal. The input is the proposal outline, and the output is the proposal outline sent to the terminal. The server records "Proposal outline sent to terminal" and the terminal receives a notification saying "Please review the proposal."

[1186] Following the above steps, sales activities become more efficient, and it becomes possible to respond quickly to customer needs.

[1187] (Application Example 1)

[1188] 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".

[1189] Traditional sales support and customer service systems have faced challenges in recording and analyzing customer statements in real time and providing optimal recommendations on the spot. Furthermore, they lack the ability to automatically generate next-time proposals based on conversation content, resulting in increased effort required to improve the quality of customer service. Additionally, a lack of tools for store staff to quickly respond to customer needs contributes to decreased customer satisfaction.

[1190] 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.

[1191] In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate meeting minutes or summaries, and means for automatically inputting the generated meeting minutes or summaries into an external system. This makes it possible for store staff to record customer statements in real time while interacting with customers, recommend related products based on that information, and prepare suggestions for the next visit. Furthermore, by automatically generating the necessary suggestions using a generation AI model, the quality of customer service can be improved and customer satisfaction can be increased.

[1192] "Audio data" refers to a digital representation of acoustic signals, including human speech and environmental sounds.

[1193] "Transcription" is the process of analyzing audio data and converting its content into text data.

[1194] "Text data" refers to digital data that contains character information, and generally refers to documents or memory contents.

[1195] "Key points" refer to keywords or phrases that deserve particular attention in a conversation or document.

[1196] "Meeting minutes" are documents that record important statements and decisions made during meetings, business negotiations, and other similar events.

[1197] A "summary" is a concise compilation of the original text's content.

[1198] An "external system" is a system that exists separately from the internal system and is used for data linkage and information exchange.

[1199] "Customer statements" refer to opinions, requests, questions, etc., expressed by customers during business negotiations or interactions.

[1200] An "industry trend database" is a database that compiles the latest trends and developments information related to a specific industry.

[1201] "Past business negotiation history" refers to a compilation of records, content, and results of business negotiations that have taken place in the past.

[1202] "Customer needs" refer to the products, services, or problems that customers want to solve.

[1203] "Recommending services and products" refers to suggesting the most suitable products and services to meet customer needs.

[1204] "Outline of the next proposal" is an overview of the main items and structure of the next proposal to be submitted.

[1205] "Store staff" refers to employees who handle customer service at physical stores.

[1206] A "generative AI model" is a model that uses artificial intelligence technology to perform tasks such as text generation and data analysis.

[1207] This invention is a system for streamlining sales activities and customer service. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs. Furthermore, it offers a function to automatically generate the outline of the next proposal.

[1208] System program

[1209] The user (store staff or sales representative) activates the recording function on their device (smartphone or tablet) when starting a customer interaction or business negotiation. The device collects audio data of the negotiation or customer interaction and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API) and temporarily stores the generated text data. A speech recognition algorithm is used in this process of transcribing audio data.

[1210] Extracting key points and generating meeting minutes

[1211] The server uses natural language processing (NLP) algorithms (such as spaCy) on text data to extract important keywords and phrases. Based on the extracted information, it generates a summary using a text summarization model (transformers' summarizer model). The generated meeting minutes and summaries are automatically entered by the server into external systems (such as CRM systems).

[1212] Analysis of statements and generation of recommendations

[1213] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. This identifies customer needs and generates recommendations for the most suitable services and products based on those needs. These recommendations are displayed in real time on the terminals of store staff or sales representatives, guiding sales negotiations and customer interactions.

[1214] Proposal outline generation

[1215] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is sent to a server, which analyzes the meeting details, customer feedback, and past proposals. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify or add to it as needed.

[1216] Specific example

[1217] If a customer says "I'd like to discuss a new smartphone" during a business meeting, the statement is transcribed and the keyword "smartphone" is extracted. Then, based on the identified keyword, new products related to "smartphones" are recommended. Furthermore, the core of the proposal for the next visit will include the features and benefits of the new smartphone.

[1218] Example of a prompt

[1219] Next Proposal Generation: Based on the following summary, please create a concise outline for your next proposal.

[1220] Customer requests:

[1221] The customer expressed interest in a new smartphone. They are interested in ease of use and the latest technology.

[1222] summary:

[1223] Since customers are interested in the ease of use and latest technology of new smartphones, it is important to offer them the latest models.

[1224] This invention allows store staff and sales representatives to record customer comments in real time, provide optimal recommendations on the spot, and prepare for future visits. Furthermore, by utilizing a generative AI model, proposal creation can be automated, significantly improving the efficiency of sales activities.

[1225] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1226] Step 1:

[1227] When a user initiates a customer interaction or business negotiation, they activate the recording function on their device (smartphone or tablet). The device collects audio data in real time and sends it to a server. The input is the audio data of the conversation between the customer and the user, and the output is the audio data sent to the server. This step includes an audio collection device and a means of communication.

[1228] Step 2:

[1229] The server transcribes the received audio data using a speech recognition API (such as the Google Cloud Speech-to-Text API). The generated text data is temporarily stored. The input is the audio data sent to the server, and the output is the transcribed text data. This step involves a speech recognition algorithm.

[1230] Step 3:

[1231] The server uses natural language processing (NLP) algorithms (such as spaCy) on the transcribed text data to extract important keywords and phrases. Based on the extracted information, a text summarization model (transformers' summarizer model) is used to generate a summary. The input is the transcribed text data, and the output is the summarized text and important keywords. This step involves natural language processing algorithms and a text summarization model.

[1232] Step 4:

[1233] The generated meeting minutes or summary are automatically entered by the server into an external system (such as a CRM system). The input consists of the summary text and key keywords, while the output is the data stored in the external system. This step involves API calls for automated data entry.

[1234] Step 5:

[1235] The server analyzes customer speech and continuously collected voice data in real time. This analysis utilizes speech analysis algorithms, industry trend databases, and past sales history. The input is transcribed text data, and the output is identified customer needs and recommendations for services and products based on those needs. This step involves database lookup and analysis algorithms.

[1236] Step 6:

[1237] Recommendations generated based on customer needs are displayed in real time on the terminals of store staff or sales representatives. The inputs are the identified customer needs and the generated recommendations, while the output is the recommendation information displayed on the terminal. This step includes a user interface for data display.

[1238] Step 7:

[1239] After a business negotiation concludes, the user enters feedback and notes about the negotiation into their terminal. This data is sent to a server, which analyzes the negotiation details, customer feedback, and past proposals. The input consists of the user's feedback and notes, while the output is the analyzed negotiation details and feedback data. This step includes a feedback input form and data storage functionality.

[1240] Step 8:

[1241] The server automatically generates key elements to include in the next proposal using a generation AI model (such as GPT-3). The generated proposal outline is sent to the terminal, where the user can modify or add to it as needed. The input is customer needs and feedback data, and the output is the automatically generated outline of the next proposal. This step includes a generation AI model and data transmission functionality.

[1242] 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.

[1243] This invention is a system designed to support sales activities and improve their efficiency and effectiveness. The system collects audio data in real time, transcribes it, extracts key points to generate meeting minutes and summaries, and automatically inputs them into an external system. It also analyzes customer statements, references industry trend databases and past sales history, and provides recommendations for optimal services and products based on customer needs.

[1244] Furthermore, this invention incorporates an emotion engine that identifies emotions from customer statements and voice data and uses this information for analysis, enabling more accurate recommendations and suggestions.

[1245] The specific program processing is as follows:

[1246] Audio data collection and transcription

[1247] The user (sales representative) starts a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of the negotiation and sends it to the server in real time. The server transcribes the received audio data using a speech recognition API and temporarily stores the generated text data.

[1248] Extracting key points and generating meeting minutes

[1249] The server analyzes the stored text data using natural language processing (NLP) algorithms to extract important keywords and phrases. Based on the extracted information, the server generates a summary. This summary is designed to quickly grasp the overall picture and key points of the conversation. The generated minutes and summaries are automatically entered by the server into external systems (e.g., customer relationship management systems) via API.

[1250] Analysis of statements using an emotion engine

[1251] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. During this process, the server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[1252] Recommendation generation and display

[1253] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[1254] Generating the outline for the next proposal

[1255] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[1256] For example, if a customer expresses concern about data security during a business meeting and speaks with an unstable tone, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[1257] Through the above process, negotiation information is efficiently recorded, and optimal proposals that take into account the customer's emotional state can be made quickly.

[1258] The following describes the processing flow.

[1259] Step 1:

[1260] The user (sales representative) begins a business negotiation and activates the recording function on their device (laptop or smartphone). The device collects the audio data of this negotiation in real time.

[1261] Step 2:

[1262] The device sends the collected audio data to the server in real time. The server transcribes the received audio data using a speech recognition API.

[1263] Step 3:

[1264] The server temporarily stores the transcribed text data. The stored text data is then analyzed using natural language processing (NLP) algorithms to extract important keywords and phrases.

[1265] Step 4:

[1266] The server generates a summary based on the extracted information. This summary is designed to quickly grasp the overall picture and key points of a business deal.

[1267] Step 5:

[1268] The generated summary is automatically entered by the server into an external system (e.g., a customer relationship management system) via an API.

[1269] Step 6:

[1270] During business negotiations, users use their devices to input customer comments and other important information in real time. This data is also sent to the server.

[1271] Step 7:

[1272] The server analyzes the customer's statements. The server uses an emotion engine to identify the customer's emotions. The emotion engine analyzes linguistic features, tone of voice, pitch, etc., to determine the customer's emotional state.

[1273] Step 8:

[1274] Based on the sentiment information identified by the sentiment engine, the server comprehensively identifies customer needs and challenges by referencing industry trend databases and past sales history to gather relevant information.

[1275] Step 9:

[1276] The server creates recommendations for the most suitable services and products based on identified needs and emotions. These recommendations are then sent from the server to the device.

[1277] Step 10:

[1278] The device displays recommendations to the user in real time. The user then uses the displayed recommendations to lead sales negotiations and make proposals to customers.

[1279] Step 11:

[1280] After the business negotiation concludes, the user enters feedback and notes about the negotiation into their device. This data is then sent back to the server.

[1281] Step 12:

[1282] The server comprehensively analyzes emotional information, including post-meeting sales data and feedback. It then extracts key elements to include in the next proposal and automatically generates a draft based on these elements.

[1283] Step 13:

[1284] The generated proposal outline is sent to the terminal. The user can modify this outline and enter additional information as needed.

[1285] By following these steps, negotiation information will be efficiently recorded, and optimal proposals that take into account the customer's emotional state will be made quickly.

[1286] (Example 2)

[1287] 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".

[1288] In traditional sales activities, recording and summarizing negotiation details is often done manually, which is not only inefficient but also prone to overlooking important information and recording errors. Furthermore, there are few means to grasp what customers say and their emotional state in real time, making it difficult to make proposals that are best suited to each individual customer. In addition, creating proposals after negotiations requires a great deal of time and effort, so a quick response is required.

[1289] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting audio data in real time and transcribing it; means for extracting important points from the transcribed text data using natural language processing to generate meeting minutes and summaries; means for automatically inputting the generated meeting minutes and summaries into an external system; means for analyzing customer statements and identifying customer needs by referring to an industry trend database and past business negotiation history; means for generating recommendations for optimal services and products based on the identified customer needs and emotional state; and means for automatically generating the outline of the next proposal. This enables efficient recording and summarization of business negotiation content, optimal proposals that take into account the customer's emotional state, and rapid generation of the next proposal.

[1290] "Audio data" refers to audio signals collected during business negotiations, meetings, and other similar events.

[1291] "Transcription" refers to the process of converting audio data into text format.

[1292] "Natural language processing" refers to the technology of analyzing text data and making it understandable to human language.

[1293] "Meeting minutes" refers to a document that records the details of a business negotiation or meeting.

[1294] A "summary" refers to a text that extracts the key points from a longer text and presents them concisely.

[1295] "External systems" refer to databases and applications that exist outside of the system.

[1296] "Customer statements" refers to words spoken by the customer during a business negotiation.

[1297] An "industry trend database" refers to a database that stores data on trends and developments in a specific industry or market.

[1298] "Sales negotiation history" refers to records related to past sales negotiations.

[1299] "Customer needs" refer to the demands and expectations that customers have regarding the products and services they seek.

[1300] "Emotional state" refers to the emotional state that can be inferred from a customer's statements and actions.

[1301] "Recommendation" refers to the suggestion of the most suitable products or services based on the customer's needs and emotional state.

[1302] "The outline of a proposal" refers to the basic structure of a document that contains important elements for the next business negotiation or proposal.

[1303] A "speech recognition API" refers to an application programming interface for converting speech data into text.

[1304] This invention is a system that supports sales activities by collecting and analyzing audio data from business negotiations and meetings, and automatically generating optimal proposals, thereby improving efficiency and effectiveness. This system has the function of collecting audio data in real time, transcribing it, extracting important points to generate meeting minutes and summaries, and automatically inputting them into an external system. It also has the function of analyzing customer statements, referring to industry trend databases and past business negotiation history, and providing recommendations for optimal services and products based on customer needs. Furthermore, this invention incorporates an emotion engine, which identifies emotions from customer statements and audio data and uses this for analysis, enabling more accurate recommendations and proposal adjustments.

[1305] The user (sales representative) initiates a sales meeting and activates the recording function on their device (laptop or smartphone). The device collects audio data from the meeting and sends it to the server in real time. The HTTPS protocol is used for communication to ensure data security. The server transcribes the received audio data using a speech recognition API (e.g., Google Cloud Speech-to-Text or Amazon Transcribe) and temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[1306] The server analyzes the stored text data using natural language processing (NLP) algorithms (e.g., Hugging Face's transformers library) to extract important keywords and phrases. Based on the extracted information, the server generates a summary. The TextRank algorithm is used for summary generation. The generated meeting minutes and summaries are automatically input by the server into external systems (e.g., customer relationship management systems such as Salesforce and HubSpot) via API.

[1307] The server analyzes customer statements entered by sales representatives during sales meetings, as well as continuously collected voice data, in real time. The server uses an emotion engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions. The emotion engine analyzes linguistic features, voice tone, pitch, etc., to determine the customer's emotional state.

[1308] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referencing industry trend databases and past sales history. This allows for a comprehensive identification of customer needs and challenges. Based on the identified needs and sentiments, the server creates recommendations for the most suitable services and products and sends these recommendations to the terminal. The terminal displays these recommendations to the user in real time, and the user uses this information to lead the sales negotiation and make more accurate proposals.

[1309] After a business meeting concludes, the user enters feedback and notes about the meeting into their terminal. This data is then sent back to the server, which comprehensively analyzes the meeting content, customer feedback, and sentiment information. The server extracts key elements to include in the next proposal and automatically generates a proposal outline based on these elements. The generated proposal outline is sent to the terminal, and the user can modify it or enter additional information as needed.

[1310] For example, if a customer expresses concern about data security during a business meeting, and their tone is shaky, the server uses an emotion engine to identify their level of anxiety. Based on this information, the server generates recommendations that highlight the latest security solutions. Furthermore, the proposal outline is instructed to include detailed information about data security solutions.

[1311] A concrete example of a prompt message for a generative AI model can be written as follows:

[1312] "Convert the following audio data to text, extract key points and emotional states, and generate optimal product recommendations. Audio data: 'The customer said they were concerned about data security.'"

[1313] Through the above processing, the system according to the present invention can efficiently record negotiation information and quickly provide optimal proposals that take into account the customer's emotional state.

[1314] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1315] Step 1: Collect audio data

[1316] The user (sales representative) begins the business negotiation and activates the recording function on their device (laptop or smartphone).

[1317] Input: Audio after the start of the business negotiation

[1318] The device collects audio data from this business negotiation in real time.

[1319] Output: Collected audio data

[1320] Step 2: Sending the audio data

[1321] The device transmits the collected voice data to the server in real time. The HTTPS protocol is used for communication to ensure data security.

[1322] Input: Collected audio data

[1323] Output: Audio data sent to the server

[1324] Step 3: Perform transcription

[1325] The server transcribes the received audio data using a speech recognition API (such as Google Cloud Speech-to-Text or Amazon Transcribe).

[1326] Input: Sent audio data

[1327] The server temporarily stores the generated text data. This uses cloud storage such as an AWS S3 bucket.

[1328] Output: Saved text data

[1329] Step 4: Analyzing Text Data

[1330] The server analyzes the stored text data using natural language processing (NLP) algorithms (for example, Hugging Face's transformers library) to extract important keywords and phrases.

[1331] Input: Saved text data

[1332] The server generates a summary based on the extracted information. The TextRank algorithm is used for summary generation.

[1333] Output: Extracted keywords and phrases, generated summary

[1334] Step 5: Automated entry of meeting minutes

[1335] The server inputs the generated meeting minutes and summaries into external systems (such as customer relationship management systems like Salesforce or HubSpot) via API.

[1336] Input: Generated meeting minutes or summaries

[1337] Output: Meeting minutes and summaries entered into an external system.

[1338] Step 6: Performing Sentiment Analysis

[1339] The server analyzes the collected speech data using a sentiment engine (such as IBM Watson Tone Analyzer or Microsoft Azure Text Analytics) to identify the customer's emotions.

[1340] Input: Data of conversations during business negotiations

[1341] The server analyzes linguistic features, tone of voice, pitch, etc., to identify the customer's emotional state.

[1342] Output: Identified sentiment information

[1343] Step 7: Gather relevant information

[1344] Based on the sentiment information identified by the sentiment engine, the server collects relevant information by referring to industry trend databases and past sales history.

[1345] Input: Identified sentiment information

[1346] Output: Related Information

[1347] Step 8: Create recommendations

[1348] The server creates recommendations for the most suitable services and products based on identified needs and emotions.

[1349] Input: Related information, identified sentiment information

[1350] Output: Generated recommendations

[1351] Step 9: Display Recommendations

[1352] The server sends the generated recommendations to the device.

[1353] Input: Generated recommendations

[1354] The device displays these recommendations to the user in real time.

[1355] Output: Recommendations displayed to the user

[1356] Step 10: Collecting feedback after the business negotiation

[1357] Users input feedback and notes about business negotiations into their devices. This includes customer reactions and requests for future meetings.

[1358] Input: Feedback or notes

[1359] The device sends this data to the server.

[1360] Output: Feedback and notes sent to the server

[1361] Step 11: Analysis of feedback and generation of proposal outline

[1362] The server comprehensively analyzes sales negotiation details, customer feedback, and sentiment information.

[1363] Input: Sales negotiation details, feedback, sentiment information

[1364] The server extracts the key elements that should be included in the next proposal and automatically generates the outline of the proposal based on them.

[1365] Output: Outline of the generated proposal

[1366] Step 12: View and revise the proposal outline.

[1367] The server sends the outline of the generated proposal to the terminal.

[1368] Input: Outline of the generated proposal

[1369] The terminal displays this outline to the user, who can modify it or enter additional information as needed.

[1370] Output: Outline of the proposal with modifications or additional information added by the user.

[1371] (Application Example 2)

[1372] 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".

[1373] Traditional e-commerce sites have struggled to provide optimal purchasing support to customers due to a lack of appropriate information and emotionally-based recommendations. Furthermore, customer support has faced challenges in providing effective assistance through real-time dialogue. This can lead to decreased customer satisfaction and a decline in purchasing intent.

[1374] 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. In this invention, the server includes means for collecting audio data in real time and transcribing it, means for extracting important points from the transcribed text data to generate minutes or summaries, means for identifying the customer's emotional state and adjusting recommendations based on the identified emotional information, and means for providing product information in real time while interacting with the customer. This makes it possible to provide optimal product recommendations and purchase support based on the customer's statements and emotions, thereby improving customer satisfaction and increasing purchasing intent.

[1375] "Voice data" refers to audio signals collected during conversations between customers and the system, and serves as basic data for analyzing the content of speech and emotional states.

[1376] "Transcription" is the process of converting collected audio data into text data, and is a pre-processing step for analysis and creating meeting minutes.

[1377] "Text data" refers to data in sentence format generated through transcription, and is used for extracting key points and sentiment analysis.

[1378] "Key points" are particularly noteworthy keywords and phrases extracted from text data, providing information useful for generating meeting minutes and summaries.

[1379] Meeting minutes are a document that concisely summarizes the overall picture of a business negotiation or meeting, and they contain important points.

[1380] A "summary" is a document that concisely summarizes the content of a conversation, focusing on the most important points.

[1381] "External systems" refer to related systems that exist outside the main system, such as customer relationship management systems and databases.

[1382] "Customer needs" refer to the requests and challenges customers have regarding the products and services they desire, and are directly related to the objectives of business negotiations and support.

[1383] "Recommendation" refers to suggesting the most suitable products or services based on customer needs and emotional states.

[1384] "Emotional state" refers to the psychological state identified from the customer's statements and voice, and is used to adjust service provision and recommendations.

[1385] "Real-time" refers to a state where processing and responses occur almost simultaneously, with minimal delay.

[1386] A "terminal" is a device used by users or sales representatives, and is used for collecting voice data and displaying recommendations.

[1387] A "server" is a computer system that processes and stores data, and is responsible for analyzing audio data and generating recommendations.

[1388] This invention aims to effectively realize a virtual shopping assistant system for e-commerce websites. This system is configured as an application installed on a smartphone and provides optimal product information and recommendations through voice interaction with the customer. The following details an embodiment of this system.

[1389] The server uses speech recognition APIs and natural language processing algorithms to collect and analyze audio data. Specifically, audio data collected by a smartphone's microphone is transcribed in real time using the Google Cloud Speech-to-Text API. The resulting text data is then analyzed by Amazon Comprehend via AWS Lambda to extract key points. The summaries and meeting minutes generated by this process are immediately stored in internal and external data storage.

[1390] The server also uses an emotion engine to identify emotional states from customer statements and voice. IBM Watson Tone Analyzer is used here to analyze emotions such as joy, anger, sadness, and anxiety from customer statements in real time. This emotion data is sent directly to the server, where recommendation generation algorithms adjust the actual recommendations.

[1391] Based on customer comments and emotional information, the server uses Amazon Personalize to generate optimal product recommendations, which are displayed in real time on the smartphone application screen. This allows users to receive the most relevant product information at the right time, supporting their purchase decisions.

[1392] Furthermore, after a business negotiation or purchasing support session is completed, feedback and notes are entered into the smartphone and sent to the server, which automatically generates the outline of the next proposal. This automatic generation again utilizes Amazon Comprehend and a generative AI model, and the server creates the basic structure of the proposal. This proposal is displayed on the smartphone screen so that the user can easily modify and complete it.

[1393] For example, if a customer says, "My home Wi-Fi is slow and it's causing problems," this system extracts keywords like "Wi-Fi" and "slow," and identifies their anxiety from the tone of voice. Then, it displays recommendations for the latest Wi-Fi routers on the screen. In this way, users can instantly receive appropriate product information.

[1394] Examples of prompt statements are as follows:

[1395] "My home Wi-Fi is slow. What products are available?"

[1396] "I'm worried about security. Do you have any smartphone recommendations?"

[1397] Based on the above, the present invention provides optimal product recommendations that accurately capture customer needs and emotions, thereby improving customer satisfaction and increasing purchasing intent on e-commerce sites.

[1398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1399] Step 1:

[1400] The user (customer) launches a smartphone application and speaks using the microphone function. The smartphone's microphone collects this audio data in real time and sends it to the server. The input is the customer's audio data, and the output is the audio data sent to the server.

[1401] Step 2:

[1402] The server transcribes the received audio data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is transcribed text data. This text data is temporarily stored on the server.

[1403] Step 3:

[1404] The server uses AWS Lambda to analyze the transcribed text data with Amazon Comprehend, extracting key points and keywords. The input is text data, and the output is extracted key keywords and summary information. These key keywords are used to generate meeting minutes and summaries.

[1405] Step 4:

[1406] The server uses IBM Watson Tone Analyzer to identify the customer's emotional state from transcribed text data. Input is text data, and output is emotional state information. Emotions are categorized into joy, anger, sadness, anxiety, etc., and this information is used to refine recommendations.

[1407] Step 5:

[1408] The server uses Amazon Personalize to generate optimal product recommendations based on the customer's emotional state and extracted keywords. The input is emotional state information and key keywords, and the output is a list of recommended products. Recommendations are generated in real time.

[1409] Step 6:

[1410] The generated product recommendations are sent from the server to the smartphone application. The input is a product list generated on the server, and the output is product information displayed on the smartphone screen. The user selects products based on this information.

[1411] Step 7:

[1412] After a business meeting ends, the user (customer) enters feedback and notes into their smartphone. The entered data is sent to the server. The input is the feedback and notes entered by the user, and the output is the feedback data sent to the server.

[1413] Step 8:

[1414] The server uses Amazon Comprehend again to generate the outline for the next proposal based on the submitted feedback and notes. The input is the feedback data, and the output is the proposal outline. The generated proposal outline is sent to the user's smartphone and displayed in the application.

[1415] 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.

[1416] 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.

[1417] 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 robot 414.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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."

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] The following is further disclosed regarding the embodiments described above.

[1437] (Claim 1)

[1438] A method for collecting audio data in real time and transcribing it,

[1439] A means for extracting important points from the transcribed text data and generating meeting minutes or summaries,

[1440] A means of automatically inputting generated meeting minutes and summaries into an external system,

[1441] A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history,

[1442] A means of generating recommendations for optimal services and products based on identified customer needs,

[1443] A method for automatically generating the outline of the next proposal,

[1444] A system that includes this.

[1445] (Claim 2)

[1446] A means for collecting the aforementioned audio data in real time and transcribing it is,

[1447] The system according to claim 1, comprising transmitting voice data from a sales representative's terminal to a server.

[1448] (Claim 3)

[1449] The system according to claim 1, further comprising means for displaying the aforementioned recommendations on the sales representative's terminal in real time, enabling the sales representative to lead the sales negotiation.

[1450] "Example 1"

[1451] (Claim 1)

[1452] A method for collecting audio data in real time and transcribing it,

[1453] A means for extracting important points from the transcribed text data and generating meeting minutes or summaries,

[1454] A means of automatically inputting generated meeting minutes and summaries into an external system,

[1455] A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history,

[1456] A means of generating recommendations for optimal services and products based on identified customer needs,

[1457] A method for automatically generating the outline of the next proposal,

[1458] A means of collecting customer statements via a terminal during a business negotiation and analyzing those statements,

[1459] A means for generating the outline of the next proposal using a generative AI model based on the analyzed statements,

[1460] A system that includes this.

[1461] (Claim 2)

[1462] A means for collecting the aforementioned audio data in real time and transcribing it is,

[1463] The system according to claim 1, comprising transmitting voice data from a sales representative's terminal to a server.

[1464] (Claim 3)

[1465] The system according to claim 1, further comprising means for displaying the aforementioned recommendations on the sales representative's terminal in real time, enabling the sales representative to lead the sales negotiation.

[1466] "Application Example 1"

[1467] (Claim 1)

[1468] A method for collecting audio data in real time and transcribing it,

[1469] A means for extracting important points from the transcribed text data and generating meeting minutes or summaries,

[1470] A means of automatically inputting generated meeting minutes and summaries into an external system,

[1471] A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history,

[1472] A means of generating recommendations for optimal services and products based on identified customer needs,

[1473] A method for automatically generating the outline of the next proposal,

[1474] A system that allows store staff to record customer comments in real time while assisting customers, recommend related products based on that information, and prepare suggestions for future visits.

[1475] A means of automatically generating necessary proposals using a generative AI model,

[1476] A system that includes this.

[1477] (Claim 2)

[1478] The system according to claim 1, wherein the means for collecting the aforementioned audio data in real time and transcribing it includes transmitting the audio data from a terminal of a sales representative or store staff member to a server.

[1479] (Claim 3)

[1480] The system according to claim 1, further comprising means for displaying the aforementioned recommendations in real time on the terminals of sales representatives or store staff to lead business negotiations or customer interactions.

[1481] "Example 2 of combining an emotion engine"

[1482] (Claim 1)

[1483] A method for collecting audio data in real time and transcribing it,

[1484] A means for extracting important points from the transcribed text data using natural language processing to generate meeting minutes or summaries,

[1485] A means of automatically inputting generated meeting minutes and summaries into an external system,

[1486] A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history,

[1487] A means for generating recommendations for optimal services and products based on identified customer needs and emotional states,

[1488] A method for automatically generating the outline of the next proposal,

[1489] A system that includes this.

[1490] (Claim 2)

[1491] The system according to claim 1, comprising sending voice data from a sales representative's terminal to a server using a speech recognition API.

[1492] (Claim 3)

[1493] The system according to claim 1, further comprising means for displaying the aforementioned recommendations on the sales representative's terminal in real time, enabling the sales representative to lead the sales negotiation.

[1494] "Application example 2 when combining with an emotional engine"

[1495] (Claim 1)

[1496] A method for collecting audio data in real time and transcribing it,

[1497] A means for extracting important points from the transcribed text data and generating meeting minutes or summaries,

[1498] A means of automatically inputting generated meeting minutes and summaries into an external system,

[1499] A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history,

[1500] A means for generating recommendations for optimal products and services based on identified customer needs,

[1501] A method for automatically generating the outline of the next proposal,

[1502] A means for identifying the customer's emotional state and adjusting recommendations based on the identified emotional information,

[1503] A means of providing product information in real time while interacting with customers,

[1504] A system that includes this.

[1505] (Claim 2)

[1506] The system according to claim 1, wherein the means for collecting the aforementioned audio data in real time and transcribing it includes transmitting the audio data from the user's terminal to a server.

[1507] (Claim 3)

[1508] The system according to claim 1, further comprising means for displaying the aforementioned recommendations on the user's terminal in real time and enabling the user to lead business negotiations and guidance. [Explanation of Symbols]

[1509] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for collecting audio data in real time and transcribing it, A means for extracting important points from the transcribed text data and generating meeting minutes or summaries, A means of automatically inputting generated meeting minutes and summaries into an external system, A means of identifying customer needs by analyzing customer statements and referring to industry trend databases and past sales negotiation history, A means of generating recommendations for optimal services and products based on identified customer needs, A method for automatically generating the outline of the next proposal, A system that includes this.

2. A means for collecting the aforementioned audio data in real time and transcribing it is, The system according to claim 1, further comprising transmitting voice data from a sales representative's terminal to a server.

3. The system according to claim 1, further comprising means for displaying the aforementioned recommendations on the sales representative's terminal in real time, and enabling the sales representative to lead the business negotiation.

Images