system

Abstract

We provide the system. [Solution] Methods for converting voice input to text, A means of analyzing transcribed dialogue, A means for generating product proposals based on analysis results, A means of displaying the generated product suggestions, An information processing system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In business activities, there are problems that the quality of business negotiations varies depending on the skills and experience of salespersons, and effective communication with customers cannot be carried out. There is also a problem that past customer data cannot be fully utilized, and it is difficult to make highly accurate sales forecasts and formulate effective business strategies.

Means for Solving the Problems

[0005] This invention includes an analysis device that instantly records conversations during business negotiations using a device that converts voice input to text, and analyzes that text to understand customer needs. It also combines a generation device and a display device that generate appropriate proposals based on the analysis results and provide real-time advice to sales representatives. Furthermore, by collecting and analyzing past customer data, it enables sales forecasting and sales strategy proposals, and retrains the AI ​​model using negotiation results and feedback. This effectively supports sales activities and aims to improve sales efficiency and closing rates.

[0006] A "speech input to text conversion device" is a device that converts information entered in speech format into text data.

[0007] An "analytical device for analyzing transcribed conversations" is a system that analyzes text-based data to identify content and needs.

[0008] A "generation device that generates proposals based on analysis results" is a mechanism that utilizes data obtained from an analysis device to create appropriate proposals for the user.

[0009] A "display device for displaying generated proposals" is a device that visually presents proposals created by a generation device to the user.

[0010] A "sales support system" is a comprehensive platform designed to streamline and enhance the effectiveness of sales activities.

[0011] "Means of storing information in a database" refers to the technologies and methods for organizing and saving collected information.

[0012] "Methods for forecasting sales" refer to methods and algorithms for predicting future sales trends based on past data.

[0013] "Methods for proposing strategies" refer to methods for formulating plans for effective sales and marketing activities based on data analysis results.

[0014] "A means of receiving negotiation results and user feedback and recording them in a database" refers to a system for collecting and saving the results of negotiations and the opinions of the person in charge.

[0015] "Methods for retraining AI models" refer to methods of updating models to improve the accuracy of AI predictions and analyses by utilizing newly collected data. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that utilizes advanced AI technology to support sales activities. This system has the ability to convert speech to text and analyze conversations in real time, thereby improving the quality of business negotiations. Furthermore, it can improve sales efficiency by predicting future trends using past data and assisting in strategic decision-making.

[0038] This system primarily consists of three components: a server, terminals, and users. The server accesses the database and is responsible for collecting and analyzing customer information and sales history. The terminals have speech recognition and text conversion capabilities, instantly recording conversations during sales meetings and converting them into an analyzable format. Users, i.e., sales representatives, can utilize the system's advice to communicate more effectively with customers.

[0039] For example, when a user is conducting a business negotiation with a customer, the terminal receives the conversation as voice input in real time and continuously converts it into text data. Subsequently, an analysis device analyzes the conversation content and provides the user with insights to understand the customer's needs and interests. Based on this analysis, a generation device instantly creates an optimal product proposal and presents it to the user via a display device.

[0040] Furthermore, after a business negotiation is completed, the server collects feedback and negotiation results entered by the user and records them in a database. Based on this information, the server can retrain the AI ​​model, continuously improving the prediction accuracy and proposal quality for future negotiations.

[0041] In this manner, the entire system works in conjunction to support sales activities, enabling effective negotiations and strategic decision-making.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects customer information and past sales history from the database and prepares a basic dataset for analysis.

[0045] Step 2:

[0046] The terminal receives the conversation between the user and the customer as voice input during a business meeting. Using speech recognition technology, this voice is instantly converted into text data.

[0047] Step 3:

[0048] Text data is sent to an analysis device, and the terminal identifies customer needs and intentions based on the analysis results. In this process, natural language processing technology is used to understand the context.

[0049] Step 4:

[0050] The generation device, upon receiving the analysis results, generates optimal product suggestions and responses for the user. These suggestions are based on historical data and pre-configured sales strategies.

[0051] Step 5:

[0052] The terminal's display shows the generated proposals to the user in real time. The user uses this information to advance the conversation and improve the effectiveness of the business negotiation.

[0053] Step 6:

[0054] After a business meeting, the user enters the meeting results and customer feedback into their device. This feedback is added to the database as evidence of the meeting's success or failure and the lessons learned.

[0055] Step 7:

[0056] The server retrains the AI ​​model using newly collected sales opportunity data to improve the accuracy of future sales opportunity support. This process is performed continuously to enhance the model's predictive power.

[0057] (Example 1)

[0058] 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."

[0059] In modern sales activities, it is essential to understand customer needs and interests in real time and quickly provide optimal proposals. However, traditional methods lack a system that efficiently transcribes voice data into text, performs in-depth analysis based on that transcription, and integrates predictions and strategic proposals. As a result, it is difficult for sales representatives to quickly obtain the necessary insights during negotiations, leading to a problem of unimproved negotiation quality.

[0060] 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.

[0061] In this invention, the server includes means for converting voice data into text information, means for analyzing the text information to identify customer interests and needs, and means for generating proposal information based on the analyzed information. This enables sales representatives to receive insights generated in real time during sales negotiations and to make effective and appropriate proposals to customers.

[0062] "Audio data" refers to information recorded in digital format from human speech.

[0063] "Text information" refers to information obtained by converting audio data into a string format.

[0064] "Methods for identifying customer interests and needs" refers to methods that use analytical techniques to extract the interests and needs that customers express during business negotiations.

[0065] "Generating means for generating proposal information" refers to a method that automatically creates product and service proposals suitable for the customer based on analysis results.

[0066] "Means for displaying generated proposal information on a user device" refers to a method for visually presenting the generated proposal content, which sales representatives can review during business negotiations.

[0067] "Past customer information" refers to the collective data obtained from past business negotiations and customer interactions.

[0068] A "memory device" is a device used to store information for a long period of time.

[0069] "Methods for making sales forecasts" refer to methods of predicting the results of future sales activities by analyzing past data.

[0070] "Methods for proposing sales strategies" refer to methods for proposing the direction and plan of sales activities.

[0071] "Sales negotiation results information" refers to data regarding the outcomes and actions taken after a sales negotiation has concluded.

[0072] "User feedback information" refers to the opinions and evaluations that users provide regarding the system or business negotiations.

[0073] "Methods for retraining machine learning models" refer to methods for improving the accuracy and efficiency of existing models by adding new data and performing further training.

[0074] This invention is an advanced information processing system that supports sales activities and is mainly composed of three components: a server, a terminal, and a user.

[0075] The server manages customer information and sales history using a database system. Specifically, the server uses a high-performance computer (commonly known as a server machine) and employs a relational database as its database management system. This server utilizes an API to convert audio data into text information, and analyzes the converted text information to extract customer interests and needs. This analysis employs a natural language processing model, and based on the analysis results, a generative AI model is used to generate suggestion information.

[0076] The terminal receives voice input from the user during a business negotiation, converts it to text using speech recognition software, and sends it to the server in real time. Google® Cloud Speech-to-Text API is one example of the specific software that can be used. The terminal visually presents the generated proposal information to the user, helping them to effectively advance the business negotiation.

[0077] Users utilize this system to advance sales negotiations. For example, when asking a customer, "Are you interested in our new product?", the terminal receives the conversation as audio, instantly converts it to text, and analyzes it. This allows the system to generate optimal product suggestions tailored to the customer's interests and provide them to the user immediately. As a specific example, the prompt message might read, "Prompt for the next negotiation: Based on the history of this negotiation and customer feedback, generate the next proposal for customer Y."

[0078] In this way, the entire system works together, enabling users to improve the quality of their sales negotiations and realize strategic sales activities.

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

[0080] Step 1:

[0081] The terminal accepts voice input as soon as a business negotiation begins. The input is the audio conversation between the user and the customer. The terminal converts this audio data into text information using the Google Cloud Speech-to-Text API. This conversion allows the content of the negotiation to be immediately obtained as text data. The output is the transcribed conversation data.

[0082] Step 2:

[0083] The server receives text information sent from the terminal. The input is text data converted from speech. The server analyzes this text information using natural language processing (NLP) algorithms. The purpose of the analysis is to identify the customer's interests and needs. For example, keywords are extracted from the text, and these are used to determine the customer's areas of interest. The output is the analyzed insight information.

[0084] Step 3:

[0085] The server uses the analysis results to launch a generative AI model. The input is insight information. The generative AI model generates the optimal proposal by referring to past similar deal data. At this stage, a prompt is used to determine the direction of the proposal. For example, "Prompt for the next deal: Based on the history of this deal and customer feedback, generate the next proposal for customer Y." The output is specific proposal information.

[0086] Step 4:

[0087] The terminal displays proposal information received from the server to the user. The input is the generated proposal information. The display is visual, allowing the user to review it during negotiations. This enables the user to make effective proposals to customers at the appropriate time. The output is a display of proposal information that the user can review and use.

[0088] Step 5:

[0089] When a business negotiation ends, the user inputs feedback information about the negotiation results and customer reactions into the terminal. This input is feedback information. The terminal sends this information to the server, which records it in a database. The AI ​​model is then retrained based on this information. This retraining enables more accurate proposals in future negotiations. The output is the feedback information recorded in the database.

[0090] (Application Example 1)

[0091] 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."

[0092] There is a need to improve real-time customer service in face-to-face sales activities and to quickly and accurately grasp customer needs. In particular, during customer service, it is necessary to propose products that meet the customer's needs, but store staff have to make quick decisions with limited information, so the quality of proposals is inconsistent, which is a challenge.

[0093] 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.

[0094] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed dialogue, and means for generating product suggestions based on the analysis results. This enables real-time optimal product suggestions based on conversations in stores.

[0095] "Means of converting voice input to text" refers to a device or program that uses technology to convert voice information into text information.

[0096] "Means for analyzing transcribed dialogue" refers to technologies or devices that, after transcribing voice input into text, analyze the content of the dialogue based on that text to identify areas of interest and needs.

[0097] "Means for generating product proposals" refers to technology or equipment that selects the most suitable products or services based on analyzed dialogue content and creates information for proposing them.

[0098] "Means of storing information in an information collection" refers to technologies or devices that record and manage data such as customer usage history and feedback in an information collection.

[0099] "Means of demand forecasting" refers to technologies or devices that analyze accumulated data to predict future demand and trends.

[0100] A "generative AI model" refers to an artificial intelligence model that uses machine learning to learn from data and make suggestions and decisions in response to new situations.

[0101] In this embodiment of the invention, the information processing system mainly consists of three components: a server, a terminal, and a user. The server is responsible for collecting user data, including customer information, and storing it in an information aggregate. The terminal incorporates a means for converting voice input using a speech recognition API into text, and smartphones or tablet devices are employed.

[0102] The device uses speech recognition APIs such as Google Speech-to-Text to convert customer interactions into text data in real time. This text data can be analyzed using natural language processing libraries such as spaCy and TENSORFLOW® to interpret customer needs. The analysis results are sent back to the server, where a generative AI model generates optimal product suggestions. These generated product suggestions are presented to the user through the display device of the device or smart glasses.

[0103] Users, i.e., store staff, can immediately provide feedback to customers based on product suggestions provided from the terminal. This makes it possible to provide appropriate product information in real time during customer interactions and improve the quality of customer service. Furthermore, user feedback and conversation results are returned to the server, and the generated AI model is retrained based on the accumulated information to improve the accuracy of future suggestions.

[0104] To give a concrete example, if a customer is looking for a mystery novel in a bookstore, the terminal can capture the conversation, analyze it, and then suggest the latest related books. An example of input to the generating AI model would be a prompt sentence like, "What related books can we recommend to a customer looking for this mystery novel?"

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The device acquires customer interactions as voice input. The input voice data is captured through the microphone of a commercially available smart device. Upon receiving the voice data, the device uses a speech recognition API (e.g., Google Speech-to-Text) to convert this voice data into text data. The output of this conversion process is a text-based transcript of the conversation.

[0108] Step 2:

[0109] The terminal uses the converted text data to apply natural language processing libraries (e.g., spaCy, TensorFlow) and analyze the conversation content. Based on the text data received as input, it utilizes NLP techniques to extract the customer's intent and needs. The output of this analysis is information about the customer's potential interests and needs. Specifically, it performs tasks such as keyword extraction and contextual understanding.

[0110] Step 3:

[0111] The server receives the analysis results sent from the terminal and inputs them into the generating AI model. Based on this input data, the AI ​​model generates product suggestions. The AI ​​model is trained to make more accurate suggestions based on previously accumulated data. The generated suggestions include a list of products and information that explains why specific products are recommended.

[0112] Step 4:

[0113] The terminal receives product information suggested by the server and displays the suggested products on its screen. It receives product suggestion data from the server as input and presents it visually to the user through the user interface. This allows store staff, who are the users, to provide immediate feedback to customers. Specifically, it performs the immediate display of information on the screen.

[0114] Step 5:

[0115] The user engages in further interaction with the customer and sends the results as feedback to the server. This feedback includes the customer's reactions and acceptance of suggestions. Based on this feedback, the server accumulates data in an information database and further retrains the generative AI model. This improves the accuracy of future product suggestions. Specifically, this involves recording information in the database and updating the model.

[0116] 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.

[0117] This invention is a system for supporting sales activities, and in particular, by combining it with an emotion engine that recognizes the emotions of users and customers, it further improves the quality and effectiveness of sales negotiations. This system supports sales negotiations in real time by converting speech to text and further analyzing the content and emotions of the text.

[0118] The entire system consists of server, terminal, emotion engine, and user components, all working in conjunction with each other. First, the terminal collects audio information from conversations during business negotiations and transcribes that audio into text in real time. Next, the emotion engine identifies the emotional state of the user and customer from the transcribed conversation and the audio itself, and generates emotion data.

[0119] Next, this emotional data is processed by an analysis device in combination with content analysis to generate optimal proposals that take into account not only the customer's interests and needs, but also their emotional state. The generated proposals are displayed on the terminal's display device, allowing the user to utilize them during business negotiations and respond flexibly to the customer's emotions.

[0120] For example, if a customer shows anxiety while a user is introducing a new product, the emotion engine immediately detects this emotion, and the analysis device takes that data into account to generate a proposal that includes additional information and benefits to alleviate the anxiety. In this way, users can conduct business negotiations while being mindful of the customer's emotions, improving the success rate.

[0121] Furthermore, after a business negotiation is completed, the server collects the final outcome of the negotiation and user feedback, and stores it in a database as comprehensive negotiation data, including sentiment data. This data is also used to retrain the AI ​​model, enabling continuous improvement of the system's performance.

[0122] By implementing this invention, sales representatives can grasp customer emotions in a timely manner and conduct strategic and empathetic sales activities based on that information.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The terminal receives the user's and customer's conversation as voice input at the start of a business negotiation and converts it to text in real time.

[0126] Step 2:

[0127] The emotion engine analyzes voice and text data to identify the emotional state of users and customers. Voice tone and language choices are considered in determining the emotion.

[0128] Step 3:

[0129] The analysis device receives the transcribed conversation and emotional data and performs an analysis of the customer's needs and emotions. The results of this analysis are used to evaluate the customer's purchasing intent and concerns.

[0130] Step 4:

[0131] The generating device constructs emotionally sensitive product proposals and sales strategies based on the analysis data, and transmits them to the terminal.

[0132] Step 5:

[0133] The terminal's display screen shows proposals generated for the user in real time, which the user can use as a guide to conduct business negotiations in a way that aligns with the customer's emotions.

[0134] Step 6:

[0135] After the business negotiation concludes, the user enters feedback on the negotiation results and customer reactions into the terminal. This information will be used in future business negotiations.

[0136] Step 7:

[0137] The server stores new business negotiation information and sentiment data in its database, which is then used to retrain the AI ​​model for future business negotiations. This continuously improves the system's analytical capabilities.

[0138] (Example 2)

[0139] 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".

[0140] Traditional sales activities have made it difficult to accurately understand customer emotions and thereby facilitate smooth business negotiations. Furthermore, there has been a lack of efficient methods to utilize data after negotiations to improve the success rate of future negotiations. This has limited effective responses necessary to maximize sales results.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for acquiring and digitizing voice information; means for analyzing the digitized content and identifying emotions; means for generating suggestions based on the identified emotion data and content; means for presenting the generated suggestions; means for enabling flexible responses that adapt to the emotions of the user and the customer; means for collecting and recording results and feedback after the conclusion of a business negotiation; and means for retraining the model based on the recorded data to improve performance. This enables quick and accurate responses that respond to the customer's emotions, thereby increasing the success rate of business negotiations.

[0143] "Audio information" refers to sound data acquired during business negotiations and conversations, and forms the basis for analyzing human speech.

[0144] "Data conversion" refers to the process of converting acquired audio information into text or other data formats, which forms the basis for analysis.

[0145] "Identifying emotions" refers to the process of identifying the emotional state of a person having a conversation based on digitized information.

[0146] "Generating proposals" refers to the process of automatically creating optimal sales strategies and response plans based on identified sentiment data and negotiation details.

[0147] "To present" refers to providing generated suggestions or information visually or audibly so that the user can review them.

[0148] "Flexible response" refers to the ability to implement adaptive communication that matches the customer's emotions during a business negotiation, based on immediate feedback and situational assessment.

[0149] "Recording" refers to saving the process and results of business negotiations, as well as user feedback, in a database or similar system for later analysis and learning.

[0150] "Retraining" refers to the process of improving the algorithm of a generative AI model based on recorded data, thereby enhancing the accuracy of suggestions and sentiment recognition.

[0151] This invention is a system specifically designed for sales support, assisting in business negotiations by analyzing voice information and providing optimal suggestions based on the results. Specific embodiments are shown below.

[0152] System Configuration

[0153] The system is comprised of various components, including servers, terminals, emotion engines, and users. Specifically, the server is responsible for overall data management and model retraining, while the terminals collect audio and display suggestions.

[0154] Implementation environment

[0155] Users conduct business negotiations using a terminal. The terminal requires a microphone device for high-quality voice capture. Natural language processing technology is used to convert the voice data into text, and specifically, a generally available voice recognition service can be used as voice recognition software.

[0156] Data Analysis

[0157] The device converts acquired audio information into text in real time. This process utilizes publicly available speech recognition APIs. The emotion engine then analyzes the text data to identify the customer's and user's emotions. Common text analysis services can be incorporated into this analysis.

[0158] Proposal generation

[0159] The analyzed sentiment data and conversation content are sent to a server, where an optimal business proposal is created through a proposal generation device. This generation process requires rapid data processing, and a server-based AI model is employed. This proposal is displayed on the terminal in real time, allowing the user to utilize it to guide the business negotiation.

[0160] As a concrete example, if a customer expresses concern about the price during a sales meeting where a user is introducing a new product, the system can instantly identify that emotion from the voice and suggest promotional information to alleviate the concern. Furthermore, an example of a prompt the generating AI model might respond to is, "The customer seems concerned about the price of the new product. What kind of suggestion would alleviate his concerns?" The system would then suggest appropriate price explanations or trial campaigns.

[0161] In this way, it becomes possible to improve the quality and effectiveness of business negotiations.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The terminal acquires voice information from the user and the customer during a business negotiation. This input data is an audio signal, and the input device used here is a microphone for voice recognition. Specifically, the terminal captures the audio in real time through the microphone.

[0165] Step 2:

[0166] The terminal converts acquired audio information into text data in real time. In this step, speech recognition software analyzes the audio signal and generates the corresponding text. This generated text data becomes the output. The process involves analyzing the audio waveform and representing it as a string using a language model.

[0167] Step 3:

[0168] The emotion engine within the device receives text data and analyzes the emotions of the user and customer. The input is text data, and the emotion analysis algorithm analyzes it and outputs an emotional state (e.g., joy, anxiety, anger). Specifically, natural language processing techniques are used to score the emotions within the text.

[0169] Step 4:

[0170] The server integrates sentiment data and conversation content and generates optimal suggestions through a suggestion generator. The input for this step is sentiment data and text data, and the output is suggestion information. Specifically, the process involves a generation AI model constructing suggestion content based on past data.

[0171] Step 5:

[0172] The generated proposals are displayed on the terminal's display device. Output from the server is passed to the terminal as input, and the user can review it during the business negotiation. Specifically, the generated proposals are visualized and presented to the user in an easy-to-understand UI.

[0173] Step 6:

[0174] After a business negotiation concludes, the server collects the negotiation results and user feedback, and records this information in a database. The input consists of negotiation results data and feedback, while the output is saving the data to the database. This specific operation includes data format conversion and saving.

[0175] Step 7:

[0176] The recorded data is used to retrain the AI ​​model on the server. The input is the recorded data, and the output is the updated generative AI model. Specifically, retraining is performed using machine learning algorithms to improve the model's accuracy.

[0177] (Application Example 2)

[0178] 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".

[0179] In modern face-to-face sales and customer service, employees are required to instantly grasp the emotions of individual customers and respond flexibly and effectively based on that understanding. Especially in the busy environment of a physical store, maintaining high-quality service for multiple customers requires quick decision-making within limited timeframes. However, there are limitations to employees' subjective emotional judgment, and there is a lack of technical support to improve the accuracy and consistency of these judgments.

[0180] 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.

[0181] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed conversation and identifying the customer's emotional state, means for generating suggestions based on the analysis results and the customer's emotional state, means for displaying the generated suggestions on a display device, and means for capturing the customer's facial expressions and complementing the emotional analysis. This makes it possible to grasp the customer's emotions in real time and immediately provide optimal suggestions tailored to their individual needs.

[0182] "Methods for converting voice input to text" refer to technologies that convert voice data into textual information through digital processing.

[0183] "Methods for analyzing transcribed conversations and identifying emotional states" refers to technologies that infer emotions from text data based on vocabulary and context, and then explicitly represent those emotions as data.

[0184] "Means for generating suggestions based on analysis results and customer emotional states" refers to technologies that utilize analyzed emotional data to recommend actions and products optimized for customer needs.

[0185] "Means for presenting generated proposals on a display device" refers to a technology that displays the proposed information on a display in a format that allows for visual confirmation.

[0186] "A means of capturing customer facial expressions and complementing emotion analysis" refers to a technology that analyzes customer facial expression data to make emotion analysis of voice data more accurate.

[0187] The system program for implementing this invention realizes the conversion of voice data into text, sentiment analysis, suggestion generation, and result display as a series of steps. The system is operated as follows:

[0188] First, software is run on the device to acquire voice input and convert it to text. Specifically, the Google Cloud Speech-to-Text API is used to analyze customer-staff conversations in real time.

[0189] Next, the server analyzes this transcribed conversation to identify the emotional state. Sentiment analysis utilizes Microsoft® Azure® Text Analytics, which determines the user's and customer's emotions based on words and context.

[0190] Based on the analyzed sentiment data, the server generates suggestions. This generation process utilizes a generative AI model, enabling the suggestion of products and services optimized to the customer's needs and emotions. At this stage, the suggestions are refined through prompt messages to obtain customized output.

[0191] The generated proposals are ultimately displayed on the terminal's display. This allows users to utilize real-time proposals during business negotiations and respond in a way that aligns with the customer's intentions.

[0192] For example, if a customer in a physical store says, "I'm interested in the new product, but I'm concerned about the price," and the analyzed emotion is determined to be "anxiety," the system can use this information to automatically display a suggestion such as, "We have discount options available to put your mind at ease regarding the price."

[0193] An example of a prompt message would be, "Suggest accessories that would suit a customer wearing a casual jacket." In this way, a system that strongly supports customer service in physical stores is realized.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The device collects audio of customer and staff conversations using a microphone. The input is real-time audio data, which is converted into text data using the Google Cloud Speech-to-Text API. The output is this text data.

[0197] Step 2:

[0198] The server receives transcribed conversation data and analyzes the emotional state using Microsoft Azure Text Analytics. The input is the text data from Step 1, and through this data, words and context are analyzed to identify emotions (e.g., interest, anxiety, satisfaction, etc.). The output is the emotional analysis data.

[0199] Step 3:

[0200] The server uses sentiment analysis data as input to generate customer suggestions using a generative AI model. In this step, prompts are used to provide appropriate instructions to the generative AI model, resulting in customized suggestions. The output is the suggested content.

[0201] Step 4:

[0202] The terminal displays the generated proposal content on its screen. The input is the proposal content from step 3, which is provided to the user as visual information in real time. The output is the visualized proposal.

[0203] This process allows the system to analyze customer emotions in real time, generate and display optimized suggestions, and help users respond immediately during business negotiations.

[0204] 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.

[0205] Data generation model 58 is a type of 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] This invention is a system that utilizes advanced AI technology to support sales activities. This system has the ability to convert speech to text and analyze conversations in real time, thereby improving the quality of business negotiations. Furthermore, it can improve sales efficiency by predicting future trends using past data and assisting in strategic decision-making.

[0221] This system primarily consists of three components: a server, terminals, and users. The server accesses the database and is responsible for collecting and analyzing customer information and sales history. The terminals have speech recognition and text conversion capabilities, instantly recording conversations during sales meetings and converting them into an analyzable format. Users, i.e., sales representatives, can utilize the system's advice to communicate more effectively with customers.

[0222] For example, when a user is conducting a business negotiation with a customer, the terminal receives the conversation as voice input in real time and continuously converts it into text data. Subsequently, an analysis device analyzes the conversation content and provides the user with insights to understand the customer's needs and interests. Based on this analysis, a generation device instantly creates an optimal product proposal and presents it to the user via a display device.

[0223] Furthermore, after a business negotiation is completed, the server collects feedback and negotiation results entered by the user and records them in a database. Based on this information, the server can retrain the AI ​​model, continuously improving the prediction accuracy and proposal quality for future negotiations.

[0224] In this form of implementing the invention, the entire system works together to support sales activities, enabling effective negotiations and strategic decision-making.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server collects customer information and past sales history from the database and prepares a basic dataset for analysis.

[0228] Step 2:

[0229] The terminal receives the conversation between the user and the customer as voice input during a business meeting. Using speech recognition technology, this voice is instantly converted into text data.

[0230] Step 3:

[0231] Text data is sent to an analysis device, and the terminal identifies customer needs and intentions based on the analysis results. In this process, natural language processing technology is used to understand the context.

[0232] Step 4:

[0233] The generation device, upon receiving the analysis results, generates optimal product suggestions and responses for the user. These suggestions are based on historical data and pre-configured sales strategies.

[0234] Step 5:

[0235] The terminal's display shows the generated proposals to the user in real time. The user uses this information to advance the conversation and improve the effectiveness of the business negotiation.

[0236] Step 6:

[0237] After a business meeting, the user enters the meeting results and customer feedback into their device. This feedback is added to the database as evidence of the meeting's success or failure and the lessons learned.

[0238] Step 7:

[0239] The server retrains the AI ​​model using newly collected sales opportunity data to improve the accuracy of future sales opportunity support. This process is performed continuously to enhance the model's predictive power.

[0240] (Example 1)

[0241] 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".

[0242] In modern sales activities, it is essential to understand customer needs and interests in real time and quickly provide optimal proposals. However, traditional methods lack a system that efficiently transcribes voice data into text, performs in-depth analysis based on that transcription, and integrates predictions and strategic proposals. As a result, it is difficult for sales representatives to quickly obtain the necessary insights during negotiations, leading to a problem of unimproved negotiation quality.

[0243] 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.

[0244] In this invention, the server includes means for converting voice data into text information, means for analyzing the text information to identify customer interests and needs, and means for generating proposal information based on the analyzed information. This enables sales representatives to receive insights generated in real time during sales negotiations and to make effective and appropriate proposals to customers.

[0245] "Audio data" refers to information recorded in digital format from human speech.

[0246] "Text information" refers to information obtained by converting audio data into a string format.

[0247] "Methods for identifying customer interests and needs" refers to methods that use analytical techniques to extract the interests and needs that customers express during business negotiations.

[0248] "Generating means for generating proposal information" refers to a method that automatically creates product and service proposals suitable for the customer based on analysis results.

[0249] "Means for displaying generated proposal information on a user device" refers to a method for visually presenting the generated proposal content, which sales representatives can review during business negotiations.

[0250] "Past customer information" refers to the collective data obtained from past business negotiations and customer interactions.

[0251] A "memory device" is a device used to store information for a long period of time.

[0252] "Methods for making sales forecasts" refer to methods of predicting the results of future sales activities by analyzing past data.

[0253] "Methods for proposing sales strategies" refer to methods for proposing the direction and plan of sales activities.

[0254] "Sales negotiation results information" refers to data regarding the outcomes and actions taken after a sales negotiation has concluded.

[0255] "User feedback information" refers to the opinions and evaluations that users provide regarding the system or business negotiations.

[0256] "Methods for retraining machine learning models" refer to methods for improving the accuracy and efficiency of existing models by adding new data and performing further training.

[0257] This invention is an advanced information processing system that supports sales activities and is mainly composed of three components: a server, a terminal, and a user.

[0258] The server manages customer information and sales history using a database system. Specifically, the server uses a high-performance computer (commonly known as a server machine) and employs a relational database as its database management system. This server utilizes an API to convert audio data into text information, and analyzes the converted text information to extract customer interests and needs. This analysis employs a natural language processing model, and based on the analysis results, a generative AI model is used to generate suggestion information.

[0259] The terminal receives voice input from the user during a business negotiation, converts it to text using speech recognition software, and sends it to the server in real time. Google Cloud Speech-to-Text API is one example of the software that can be used. The terminal visually presents the generated proposal information to the user, helping them to effectively advance the business negotiation.

[0260] Users utilize this system to advance sales negotiations. For example, when asking a customer, "Are you interested in our new product?", the terminal receives the conversation as audio, instantly converts it to text, and analyzes it. This allows the system to generate optimal product suggestions tailored to the customer's interests and provide them to the user immediately. As a specific example, the prompt message might read, "Prompt for the next negotiation: Based on the history of this negotiation and customer feedback, generate the next proposal for customer Y."

[0261] In this way, the entire system works together, enabling users to improve the quality of their sales negotiations and realize strategic sales activities.

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The terminal accepts voice input as soon as a business negotiation begins. The input is the audio conversation between the user and the customer. The terminal converts this audio data into text information using the Google Cloud Speech-to-Text API. This conversion allows the content of the negotiation to be immediately obtained as text data. The output is the transcribed conversation data.

[0265] Step 2:

[0266] The server receives text information sent from the terminal. The input is text data converted from speech. The server analyzes this text information using natural language processing (NLP) algorithms. The purpose of the analysis is to identify the customer's interests and needs. For example, keywords are extracted from the text, and these are used to determine the customer's areas of interest. The output is the analyzed insight information.

[0267] Step 3:

[0268] The server uses the analysis results to launch a generative AI model. The input is insight information. The generative AI model generates the optimal proposal by referring to past similar deal data. At this stage, a prompt is used to determine the direction of the proposal. For example, "Prompt for the next deal: Based on the history of this deal and customer feedback, generate the next proposal for customer Y." The output is specific proposal information.

[0269] Step 4:

[0270] The terminal displays proposal information received from the server to the user. The input is the generated proposal information. The display is visual, allowing the user to review it during negotiations. This enables the user to make effective proposals to customers at the appropriate time. The output is a display of proposal information that the user can review and use.

[0271] Step 5:

[0272] When a business negotiation ends, the user inputs feedback information about the negotiation results and customer reactions into the terminal. This input is feedback information. The terminal sends this information to the server, which records it in a database. The AI ​​model is then retrained based on this information. This retraining enables more accurate proposals in future negotiations. The output is the feedback information recorded in the database.

[0273] (Application Example 1)

[0274] 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."

[0275] There is a need to improve real-time customer service in face-to-face sales activities and to quickly and accurately grasp customer needs. In particular, during customer service, it is necessary to propose products that meet the customer's needs, but store staff have to make quick decisions with limited information, so the quality of proposals is inconsistent, which is a challenge.

[0276] 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.

[0277] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed dialogue, and means for generating product suggestions based on the analysis results. This enables real-time optimal product suggestions based on conversations in stores.

[0278] "Means of converting voice input to text" refers to a device or program that uses technology to convert voice information into text information.

[0279] "Means for analyzing transcribed dialogue" refers to technologies or devices that, after transcribing voice input into text, analyze the content of the dialogue based on that text to identify areas of interest and needs.

[0280] "Means for generating product proposals" refers to technology or equipment that selects the most suitable products or services based on analyzed dialogue content and creates information for proposing them.

[0281] "Means of storing information in an information collection" refers to technologies or devices that record and manage data such as customer usage history and feedback in an information collection.

[0282] The "means for demand prediction" refers to a technology or device that analyzes accumulated data to predict future demand and trends.

[0283] The "generative AI model" refers to an artificial intelligence model that uses machine learning to learn from data and make proposals and judgments according to new situations.

[0284] In the form for implementing this invention, the information processing system is mainly composed of three parties: a server, a terminal, and a user. The server is responsible for collecting user data including customer information and storing it in an information aggregate. The terminal is incorporated with means for converting voice input using a voice recognition API into text, and smartphones and tablet devices are adopted.

[0285] The terminal uses a voice recognition API such as Google Speech-to-Text to convert the conversation with the customer into text data in real time. This text data can be used to interpret the customer's needs through analysis using natural language processing libraries such as spaCy and TensorFlow. The analysis result is sent back to the server again, and the generative AI model generates an optimal product proposal. This generated product proposal is presented to the user through the display device of the terminal or smart glasses.

[0286] The user, that is, the store staff, can immediately provide feedback to the customer based on the product proposal provided by the terminal. This makes it possible to provide appropriate product information in real time during the conversation with the customer and improve the quality of customer service. In addition, the feedback and conversation results from the user are returned to the server, and the generative AI model is re-learned based on the accumulated information to improve the proposal accuracy for the next time.

[0287] To give a concrete example, if a customer is looking for a mystery novel in a bookstore, the terminal can capture the conversation, analyze it, and then suggest the latest related books. An example of input to the generating AI model would be a prompt sentence like, "What related books can we recommend to a customer looking for this mystery novel?"

[0288] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0289] Step 1:

[0290] The device acquires customer interactions as voice input. The input voice data is captured through the microphone of a commercially available smart device. Upon receiving the voice data, the device uses a speech recognition API (e.g., Google Speech-to-Text) to convert this voice data into text data. The output of this conversion process is a text-based transcript of the conversation.

[0291] Step 2:

[0292] The terminal uses the converted text data to apply natural language processing libraries (e.g., spaCy, TensorFlow) and analyze the conversation content. Based on the text data received as input, it utilizes NLP techniques to extract the customer's intent and needs. The output of this analysis is information about the customer's potential interests and needs. Specifically, it performs tasks such as keyword extraction and contextual understanding.

[0293] Step 3:

[0294] The server receives the analysis results sent from the terminal and inputs them into the generating AI model. Based on this input data, the AI ​​model generates product suggestions. The AI ​​model is trained to make more accurate suggestions based on previously accumulated data. The generated suggestions include a list of products and information that explains why specific products are recommended.

[0295] Step 4:

[0296] The terminal receives product information suggested by the server and displays the suggested products on its screen. It receives product suggestion data from the server as input and presents it visually to the user through the user interface. This allows store staff, who are the users, to provide immediate feedback to customers. Specifically, it performs the immediate display of information on the screen.

[0297] Step 5:

[0298] The user engages in further interaction with the customer and sends the results as feedback to the server. This feedback includes the customer's reactions and acceptance of suggestions. Based on this feedback, the server accumulates data in an information database and further retrains the generative AI model. This improves the accuracy of future product suggestions. Specifically, this involves recording information in the database and updating the model.

[0299] 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.

[0300] This invention is a system for supporting sales activities, and in particular, by combining it with an emotion engine that recognizes the emotions of users and customers, it further improves the quality and effectiveness of sales negotiations. This system supports sales negotiations in real time by converting speech to text and further analyzing the content and emotions of the text.

[0301] The entire system consists of server, terminal, emotion engine, and user components, all working in conjunction with each other. First, the terminal collects audio information from conversations during business negotiations and transcribes that audio into text in real time. Next, the emotion engine identifies the emotional state of the user and customer from the transcribed conversation and the audio itself, and generates emotion data.

[0302] Next, this emotional data is processed in combination with content analysis by an analysis device, and an optimal proposal is generated considering not only the customer's concerns and needs but also their emotional state. The generated proposal is displayed on the display device of the terminal, enabling the user to utilize it during the negotiation and respond flexibly according to the customer's emotions.

[0303] For example, when the user is introducing a new product and the customer shows a nervous reaction, the emotion engine immediately detects this emotion, and the analysis device generates a proposal that incorporates additional information and benefits to relieve the anxiety considering this data. In this way, the user can conduct the negotiation while considering the customer's emotions, improving the success rate.

[0304] Furthermore, after the negotiation ends, the server collects the final result of the negotiation and the user's feedback, and accumulates it in the database as comprehensive negotiation data including emotional data. This data is also utilized for the re-learning of the AI model, enabling the system's performance to be constantly improved.

[0305] By implementing this invention, salespersons can timely grasp the emotions of customers and conduct strategic and friendly sales activities based on this information.

[0306] The following describes the processing flow.

[0307] Step 1:

[0308] The terminal receives the conversation between the user and the customer as voice input at the start of the negotiation and texturizes it in real time.

[0309] Step 2:

[0310] The emotion engine analyzes the voice and text data to identify the emotional states of the user and the customer. The tone of the voice and the choice of language are considered in the identification of emotions.

[0311] Step 3:

[0312] The analysis device receives the transcribed conversation and emotional data and performs an analysis of the customer's needs and emotions. The results of this analysis are used to evaluate the customer's purchasing intent and concerns.

[0313] Step 4:

[0314] The generating device constructs emotionally sensitive product proposals and sales strategies based on the analysis data, and transmits them to the terminal.

[0315] Step 5:

[0316] The terminal's display screen shows proposals generated for the user in real time, which the user can use as a guide to conduct business negotiations in a way that aligns with the customer's emotions.

[0317] Step 6:

[0318] After the business negotiation concludes, the user enters feedback on the negotiation results and customer reactions into the terminal. This information will be used in future business negotiations.

[0319] Step 7:

[0320] The server stores new business negotiation information and sentiment data in its database, which is then used to retrain the AI ​​model for future business negotiations. This continuously improves the system's analytical capabilities.

[0321] (Example 2)

[0322] 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".

[0323] Traditional sales activities have made it difficult to accurately understand customer emotions and thereby facilitate smooth business negotiations. Furthermore, there has been a lack of efficient methods to utilize data after negotiations to improve the success rate of future negotiations. This has limited effective responses necessary to maximize sales results.

[0324] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0325] In this invention, the server includes means for acquiring and digitizing voice information; means for analyzing the digitized content and identifying emotions; means for generating suggestions based on the identified emotion data and content; means for presenting the generated suggestions; means for enabling flexible responses that adapt to the emotions of the user and the customer; means for collecting and recording results and feedback after the conclusion of a business negotiation; and means for retraining the model based on the recorded data to improve performance. This enables quick and accurate responses that respond to the customer's emotions, thereby increasing the success rate of business negotiations.

[0326] "Audio information" refers to sound data acquired during business negotiations and conversations, and forms the basis for analyzing human speech.

[0327] "Data conversion" refers to the process of converting acquired audio information into text or other data formats, which forms the basis for analysis.

[0328] "Identifying emotions" refers to the process of identifying the emotional state of a person having a conversation based on digitized information.

[0329] "Generating proposals" refers to the process of automatically creating optimal sales strategies and response plans based on identified sentiment data and negotiation details.

[0330] "To present" refers to providing generated suggestions or information visually or audibly so that the user can review them.

[0331] "Flexible response" refers to the ability to implement adaptive communication that matches the customer's emotions during a business negotiation, based on immediate feedback and situational assessment.

[0332] "Recording" refers to saving the process and results of business negotiations, as well as user feedback, in a database or similar system for later analysis and learning.

[0333] "Retraining" refers to the process of improving the algorithm of a generative AI model based on recorded data, thereby enhancing the accuracy of suggestions and sentiment recognition.

[0334] This invention is a system specifically designed for sales support, assisting in business negotiations by analyzing voice information and providing optimal suggestions based on the results. Specific embodiments are shown below.

[0335] System Configuration

[0336] The system is comprised of various components, including servers, terminals, emotion engines, and users. Specifically, the server is responsible for overall data management and model retraining, while the terminals collect audio and display suggestions.

[0337] Implementation environment

[0338] Users conduct business negotiations using a terminal. The terminal requires a microphone device for high-quality voice capture. Natural language processing technology is used to convert the voice data into text, and specifically, a generally available voice recognition service can be used as voice recognition software.

[0339] Data Analysis

[0340] The device converts acquired audio information into text in real time. This process utilizes publicly available speech recognition APIs. The emotion engine then analyzes the text data to identify the customer's and user's emotions. Common text analysis services can be incorporated into this analysis.

[0341] Proposal generation

[0342] The analyzed sentiment data and conversation content are sent to a server, where an optimal business proposal is created through a proposal generation device. This generation process requires rapid data processing, and a server-based AI model is employed. This proposal is displayed on the terminal in real time, allowing the user to utilize it to guide the business negotiation.

[0343] As a concrete example, if a customer expresses concern about the price during a sales meeting where a user is introducing a new product, the system can instantly identify that emotion from the voice and suggest promotional information to alleviate the concern. Furthermore, an example of a prompt the generating AI model might respond to is, "The customer seems concerned about the price of the new product. What kind of suggestion would alleviate his concerns?" The system would then suggest appropriate price explanations or trial campaigns.

[0344] In this way, it becomes possible to improve the quality and effectiveness of business negotiations.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The terminal acquires voice information from the user and the customer during a business negotiation. This input data is an audio signal, and the input device used here is a microphone for voice recognition. Specifically, the terminal captures the audio in real time through the microphone.

[0348] Step 2:

[0349] The terminal converts acquired audio information into text data in real time. In this step, speech recognition software analyzes the audio signal and generates the corresponding text. This generated text data becomes the output. The process involves analyzing the audio waveform and representing it as a string using a language model.

[0350] Step 3:

[0351] The emotion engine within the device receives text data and analyzes the emotions of the user and customer. The input is text data, and the emotion analysis algorithm analyzes it and outputs an emotional state (e.g., joy, anxiety, anger). Specifically, natural language processing techniques are used to score the emotions within the text.

[0352] Step 4:

[0353] The server integrates sentiment data and conversation content and generates optimal suggestions through a suggestion generator. The input for this step is sentiment data and text data, and the output is suggestion information. Specifically, the process involves a generation AI model constructing suggestion content based on past data.

[0354] Step 5:

[0355] The generated proposals are displayed on the terminal's display device. Output from the server is passed to the terminal as input, and the user can review it during the business negotiation. Specifically, the generated proposals are visualized and presented to the user in an easy-to-understand UI.

[0356] Step 6:

[0357] After a business negotiation concludes, the server collects the negotiation results and user feedback, and records this information in a database. The input consists of negotiation results data and feedback, while the output is saving the data to the database. This specific operation includes data format conversion and saving.

[0358] Step 7:

[0359] The recorded data is used to retrain the AI ​​model on the server. The input is the recorded data, and the output is the updated generative AI model. Specifically, retraining is performed using machine learning algorithms to improve the model's accuracy.

[0360] (Application Example 2)

[0361] 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."

[0362] In modern face-to-face sales and customer service, employees are required to instantly grasp the emotions of individual customers and respond flexibly and effectively based on that understanding. Especially in the busy environment of a physical store, maintaining high-quality service for multiple customers requires quick decision-making within limited timeframes. However, there are limitations to employees' subjective emotional judgment, and there is a lack of technical support to improve the accuracy and consistency of these judgments.

[0363] 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.

[0364] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed conversation and identifying the customer's emotional state, means for generating suggestions based on the analysis results and the customer's emotional state, means for displaying the generated suggestions on a display device, and means for capturing the customer's facial expressions and complementing the emotional analysis. This makes it possible to grasp the customer's emotions in real time and immediately provide optimal suggestions tailored to their individual needs.

[0365] "Methods for converting voice input to text" refer to technologies that convert voice data into textual information through digital processing.

[0366] "Methods for analyzing transcribed conversations and identifying emotional states" refers to technologies that infer emotions from text data based on vocabulary and context, and then explicitly represent those emotions as data.

[0367] "Means for generating suggestions based on analysis results and customer emotional states" refers to technologies that utilize analyzed emotional data to recommend actions and products optimized for customer needs.

[0368] "Means for presenting generated proposals on a display device" refers to a technology that displays the proposed information on a display in a format that allows for visual confirmation.

[0369] "A means of capturing customer facial expressions and complementing emotion analysis" refers to a technology that analyzes customer facial expression data to make emotion analysis of voice data more accurate.

[0370] The system program for implementing this invention realizes the conversion of voice data into text, sentiment analysis, suggestion generation, and result display as a series of steps. The system is operated as follows:

[0371] First, software is run on the device to acquire voice input and convert it to text. Specifically, the Google Cloud Speech-to-Text API is used to analyze customer-staff conversations in real time.

[0372] Next, the server analyzes this transcribed conversation to identify the emotional state. Sentiment analysis utilizes Microsoft Azure Text Analytics to determine the user's and customer's emotions based on words and context.

[0373] Based on the analyzed sentiment data, the server generates suggestions. This generation process utilizes a generative AI model, enabling the suggestion of products and services optimized to the customer's needs and emotions. At this stage, the suggestions are refined through prompt messages to obtain customized output.

[0374] The generated proposals are ultimately displayed on the terminal's display. This allows users to utilize real-time proposals during business negotiations and respond in a way that aligns with the customer's intentions.

[0375] For example, if a customer in a physical store says, "I'm interested in the new product, but I'm concerned about the price," and the analyzed emotion is determined to be "anxiety," the system can use this information to automatically display a suggestion such as, "We have discount options available to put your mind at ease regarding the price."

[0376] An example of a prompt message would be, "Suggest accessories that would suit a customer wearing a casual jacket." In this way, a system that strongly supports customer service in physical stores is realized.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The device collects audio of customer and staff conversations using a microphone. The input is real-time audio data, which is converted into text data using the Google Cloud Speech-to-Text API. The output is this text data.

[0380] Step 2:

[0381] The server receives transcribed conversation data and analyzes the emotional state using Microsoft Azure Text Analytics. The input is the text data from Step 1, and through this data, words and context are analyzed to identify emotions (e.g., interest, anxiety, satisfaction, etc.). The output is the emotional analysis data.

[0382] Step 3:

[0383] The server uses sentiment analysis data as input to generate customer suggestions using a generative AI model. In this step, prompts are used to provide appropriate instructions to the generative AI model, resulting in customized suggestions. The output is the suggested content.

[0384] Step 4:

[0385] The terminal displays the generated proposal content on its screen. The input is the proposal content from step 3, which is provided to the user as visual information in real time. The output is the visualized proposal.

[0386] This process allows the system to analyze customer emotions in real time, generate and display optimized suggestions, and help users respond immediately during business negotiations.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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".

[0403] This invention is a system that utilizes advanced AI technology to support sales activities. This system has the ability to convert speech to text and analyze conversations in real time, thereby improving the quality of business negotiations. Furthermore, it can improve sales efficiency by predicting future trends using past data and assisting in strategic decision-making.

[0404] This system primarily consists of three components: a server, terminals, and users. The server accesses the database and is responsible for collecting and analyzing customer information and sales history. The terminals have speech recognition and text conversion capabilities, instantly recording conversations during sales meetings and converting them into an analyzable format. Users, i.e., sales representatives, can utilize the system's advice to communicate more effectively with customers.

[0405] For example, when a user is conducting a business negotiation with a customer, the terminal receives the conversation as voice input in real time and continuously converts it into text data. Subsequently, an analysis device analyzes the conversation content and provides the user with insights to understand the customer's needs and interests. Based on this analysis, a generation device instantly creates an optimal product proposal and presents it to the user via a display device.

[0406] Furthermore, after a business negotiation is completed, the server collects feedback and negotiation results entered by the user and records them in a database. Based on this information, the server can retrain the AI ​​model, continuously improving the prediction accuracy and proposal quality for future negotiations.

[0407] In this form of implementing the invention, the entire system works together to support sales activities, enabling effective negotiations and strategic decision-making.

[0408] The following describes the processing flow.

[0409] Step 1:

[0410] The server collects customer information and past sales history from the database and prepares a basic dataset for analysis.

[0411] Step 2:

[0412] The terminal receives the conversation between the user and the customer as voice input during a business meeting. Using speech recognition technology, this voice is instantly converted into text data.

[0413] Step 3:

[0414] Text data is sent to an analysis device, and the terminal identifies customer needs and intentions based on the analysis results. In this process, natural language processing technology is used to understand the context.

[0415] Step 4:

[0416] The generation device, upon receiving the analysis results, generates optimal product suggestions and responses for the user. These suggestions are based on historical data and pre-configured sales strategies.

[0417] Step 5:

[0418] The terminal's display shows the generated proposals to the user in real time. The user uses this information to advance the conversation and improve the effectiveness of the business negotiation.

[0419] Step 6:

[0420] After a business meeting, the user enters the meeting results and customer feedback into their device. This feedback is added to the database as evidence of the meeting's success or failure and the lessons learned.

[0421] Step 7:

[0422] The server retrains the AI ​​model using newly collected sales opportunity data to improve the accuracy of future sales opportunity support. This process is performed continuously to enhance the model's predictive power.

[0423] (Example 1)

[0424] 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."

[0425] In modern sales activities, it is essential to understand customer needs and interests in real time and quickly provide optimal proposals. However, traditional methods lack a system that efficiently transcribes voice data into text, performs in-depth analysis based on that transcription, and integrates predictions and strategic proposals. As a result, it is difficult for sales representatives to quickly obtain the necessary insights during negotiations, leading to a problem of unimproved negotiation quality.

[0426] 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.

[0427] In this invention, the server includes means for converting voice data into text information, means for analyzing the text information to identify customer interests and needs, and means for generating proposal information based on the analyzed information. This enables sales representatives to receive insights generated in real time during sales negotiations and to make effective and appropriate proposals to customers.

[0428] "Audio data" refers to information recorded in digital format from human speech.

[0429] "Text information" refers to information obtained by converting audio data into a string format.

[0430] "Methods for identifying customer interests and needs" refers to methods that use analytical techniques to extract the interests and needs that customers express during business negotiations.

[0431] "Generating means for generating proposal information" refers to a method that automatically creates product and service proposals suitable for the customer based on analysis results.

[0432] "Means for displaying generated proposal information on a user device" refers to a method for visually presenting the generated proposal content, which sales representatives can review during business negotiations.

[0433] "Past customer information" refers to the collective data obtained from past business negotiations and customer interactions.

[0434] A "memory device" is a device used to store information for a long period of time.

[0435] "Methods for making sales forecasts" refer to methods of predicting the results of future sales activities by analyzing past data.

[0436] "Methods for proposing sales strategies" refer to methods for proposing the direction and plan of sales activities.

[0437] "Sales negotiation results information" refers to data regarding the outcomes and actions taken after a sales negotiation has concluded.

[0438] "User feedback information" refers to the opinions and evaluations that users provide regarding the system or business negotiations.

[0439] "Methods for retraining machine learning models" refer to methods for improving the accuracy and efficiency of existing models by adding new data and performing further training.

[0440] This invention is an advanced information processing system that supports sales activities and is mainly composed of three components: a server, a terminal, and a user.

[0441] The server manages customer information and sales history using a database system. Specifically, the server uses a high-performance computer (commonly known as a server machine) and employs a relational database as its database management system. This server utilizes an API to convert audio data into text information, and analyzes the converted text information to extract customer interests and needs. This analysis employs a natural language processing model, and based on the analysis results, a generative AI model is used to generate suggestion information.

[0442] The terminal receives voice input from the user during a business negotiation, converts it to text using speech recognition software, and sends it to the server in real time. Google Cloud Speech-to-Text API is one example of the software that can be used. The terminal visually presents the generated proposal information to the user, helping them to effectively advance the business negotiation.

[0443] Users utilize this system to advance sales negotiations. For example, when asking a customer, "Are you interested in our new product?", the terminal receives the conversation as audio, instantly converts it to text, and analyzes it. This allows the system to generate optimal product suggestions tailored to the customer's interests and provide them to the user immediately. As a specific example, the prompt message might read, "Prompt for the next negotiation: Based on the history of this negotiation and customer feedback, generate the next proposal for customer Y."

[0444] In this way, the entire system works together, enabling users to improve the quality of their sales negotiations and realize strategic sales activities.

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The terminal accepts voice input as soon as a business negotiation begins. The input is the audio conversation between the user and the customer. The terminal converts this audio data into text information using the Google Cloud Speech-to-Text API. This conversion allows the content of the negotiation to be immediately obtained as text data. The output is the transcribed conversation data.

[0448] Step 2:

[0449] The server receives text information sent from the terminal. The input is text data converted from speech. The server analyzes this text information using natural language processing (NLP) algorithms. The purpose of the analysis is to identify the customer's interests and needs. For example, keywords are extracted from the text, and these are used to determine the customer's areas of interest. The output is the analyzed insight information.

[0450] Step 3:

[0451] The server uses the analysis results to launch a generative AI model. The input is insight information. The generative AI model generates the optimal proposal by referring to past similar deal data. At this stage, a prompt is used to determine the direction of the proposal. For example, "Prompt for the next deal: Based on the history of this deal and customer feedback, generate the next proposal for customer Y." The output is specific proposal information.

[0452] Step 4:

[0453] The terminal displays proposal information received from the server to the user. The input is the generated proposal information. The display is visual, allowing the user to review it during negotiations. This enables the user to make effective proposals to customers at the appropriate time. The output is a display of proposal information that the user can review and use.

[0454] Step 5:

[0455] When a business negotiation ends, the user inputs feedback information about the negotiation results and customer reactions into the terminal. This input is feedback information. The terminal sends this information to the server, which records it in a database. The AI ​​model is then retrained based on this information. This retraining enables more accurate proposals in future negotiations. The output is the feedback information recorded in the database.

[0456] (Application Example 1)

[0457] 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."

[0458] There is a need to improve real-time customer service in face-to-face sales activities and to quickly and accurately grasp customer needs. In particular, during customer service, it is necessary to propose products that meet the customer's needs, but store staff have to make quick decisions with limited information, so the quality of proposals is inconsistent, which is a challenge.

[0459] 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.

[0460] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed dialogue, and means for generating product suggestions based on the analysis results. This enables real-time optimal product suggestions based on conversations in stores.

[0461] "Means of converting voice input to text" refers to a device or program that uses technology to convert voice information into text information.

[0462] "Means for analyzing transcribed dialogue" refers to technologies or devices that, after transcribing voice input into text, analyze the content of the dialogue based on that text to identify areas of interest and needs.

[0463] "Means for generating product proposals" refers to technology or equipment that selects the most suitable products or services based on analyzed dialogue content and creates information for proposing them.

[0464] "Means of storing information in an information collection" refers to technologies or devices that record and manage data such as customer usage history and feedback in an information collection.

[0465] "Means of demand forecasting" refers to technologies or devices that analyze accumulated data to predict future demand and trends.

[0466] A "generative AI model" refers to an artificial intelligence model that uses machine learning to learn from data and make suggestions and decisions in response to new situations.

[0467] In this embodiment of the invention, the information processing system mainly consists of three components: a server, a terminal, and a user. The server is responsible for collecting user data, including customer information, and storing it in an information aggregate. The terminal incorporates a means for converting voice input using a speech recognition API into text, and smartphones or tablet devices are employed.

[0468] The device uses speech recognition APIs such as Google Speech-to-Text to convert customer interactions into text data in real time. This text data can be analyzed using natural language processing libraries such as spaCy and TensorFlow to interpret customer needs. The analysis results are sent back to the server, where a generative AI model generates optimal product suggestions. These generated product suggestions are presented to the user through the device's display or smart glasses.

[0469] Users, i.e., store staff, can immediately provide feedback to customers based on product suggestions provided from the terminal. This makes it possible to provide appropriate product information in real time during customer interactions and improve the quality of customer service. Furthermore, user feedback and conversation results are returned to the server, and the generated AI model is retrained based on the accumulated information to improve the accuracy of future suggestions.

[0470] To give a concrete example, if a customer is looking for a mystery novel in a bookstore, the terminal can capture the conversation, analyze it, and then suggest the latest related books. An example of input to the generating AI model would be a prompt sentence like, "What related books can we recommend to a customer looking for this mystery novel?"

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The device acquires customer interactions as voice input. The input voice data is captured through the microphone of a commercially available smart device. Upon receiving the voice data, the device uses a speech recognition API (e.g., Google Speech-to-Text) to convert this voice data into text data. The output of this conversion process is a text-based transcript of the conversation.

[0474] Step 2:

[0475] The terminal uses the converted text data to apply natural language processing libraries (e.g., spaCy, TensorFlow) and analyze the conversation content. Based on the text data received as input, it utilizes NLP techniques to extract the customer's intent and needs. The output of this analysis is information about the customer's potential interests and needs. Specifically, it performs tasks such as keyword extraction and contextual understanding.

[0476] Step 3:

[0477] The server receives the analysis results sent from the terminal and inputs them into the generating AI model. Based on this input data, the AI ​​model generates product suggestions. The AI ​​model is trained to make more accurate suggestions based on previously accumulated data. The generated suggestions include a list of products and information that explains why specific products are recommended.

[0478] Step 4:

[0479] The terminal receives product information suggested by the server and displays the suggested products on its screen. It receives product suggestion data from the server as input and presents it visually to the user through the user interface. This allows store staff, who are the users, to provide immediate feedback to customers. Specifically, it performs the immediate display of information on the screen.

[0480] Step 5:

[0481] The user engages in further interaction with the customer and sends the results as feedback to the server. This feedback includes the customer's reactions and acceptance of suggestions. Based on this feedback, the server accumulates data in an information database and further retrains the generative AI model. This improves the accuracy of future product suggestions. Specifically, this involves recording information in the database and updating the model.

[0482] 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.

[0483] This invention is a system for supporting sales activities, and in particular, by combining it with an emotion engine that recognizes the emotions of users and customers, it further improves the quality and effectiveness of sales negotiations. This system supports sales negotiations in real time by converting speech to text and further analyzing the content and emotions of the text.

[0484] The entire system consists of server, terminal, emotion engine, and user components, all working in conjunction with each other. First, the terminal collects audio information from conversations during business negotiations and transcribes that audio into text in real time. Next, the emotion engine identifies the emotional state of the user and customer from the transcribed conversation and the audio itself, and generates emotion data.

[0485] Next, this emotional data is processed by an analysis device in combination with content analysis to generate optimal proposals that take into account not only the customer's interests and needs, but also their emotional state. The generated proposals are displayed on the terminal's display device, allowing the user to utilize them during business negotiations and respond flexibly to the customer's emotions.

[0486] For example, if a customer shows anxiety while a user is introducing a new product, the emotion engine immediately detects this emotion, and the analysis device takes that data into account to generate a proposal that includes additional information and benefits to alleviate the anxiety. In this way, users can conduct business negotiations while being mindful of the customer's emotions, improving the success rate.

[0487] Furthermore, after a business negotiation is completed, the server collects the final outcome of the negotiation and user feedback, and stores it in a database as comprehensive negotiation data, including sentiment data. This data is also used to retrain the AI ​​model, enabling continuous improvement of the system's performance.

[0488] By implementing this invention, sales representatives can grasp customer emotions in a timely manner and conduct strategic and empathetic sales activities based on that information.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The terminal receives the user's and customer's conversation as voice input at the start of a business negotiation and converts it to text in real time.

[0492] Step 2:

[0493] The emotion engine analyzes voice and text data to identify the emotional state of users and customers. Voice tone and language choices are considered in determining the emotion.

[0494] Step 3:

[0495] The analysis device receives the transcribed conversation and sentiment data and performs an analysis of the customer's needs and emotions. The results of this analysis are used to evaluate the customer's purchasing intent and concerns.

[0496] Step 4:

[0497] The generating device constructs emotionally sensitive product proposals and sales strategies based on the analysis data, and transmits them to the terminal.

[0498] Step 5:

[0499] The terminal's display screen shows proposals generated for the user in real time, which the user can use as a guide to conduct business negotiations in a way that aligns with the customer's emotions.

[0500] Step 6:

[0501] After the business negotiation concludes, the user enters feedback on the negotiation results and customer reactions into the terminal. This information will be used in future business negotiations.

[0502] Step 7:

[0503] The server stores new business negotiation information and sentiment data in its database, which is then used to retrain the AI ​​model for future business negotiations. This continuously improves the system's analytical capabilities.

[0504] (Example 2)

[0505] 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."

[0506] Traditional sales activities have made it difficult to accurately understand customer emotions and thereby facilitate smooth business negotiations. Furthermore, there has been a lack of efficient methods to utilize data after negotiations to improve the success rate of future negotiations. This has limited effective responses necessary to maximize sales results.

[0507] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0508] In this invention, the server includes means for acquiring and digitizing voice information; means for analyzing the digitized content and identifying emotions; means for generating suggestions based on the identified emotion data and content; means for presenting the generated suggestions; means for enabling flexible responses that adapt to the emotions of the user and the customer; means for collecting and recording results and feedback after the conclusion of a business negotiation; and means for retraining the model based on the recorded data to improve performance. This enables quick and accurate responses that respond to the customer's emotions, thereby increasing the success rate of business negotiations.

[0509] "Audio information" refers to sound data acquired during business negotiations and conversations, and forms the basis for analyzing human speech.

[0510] "Data conversion" refers to the process of converting acquired audio information into text or other data formats, which forms the basis for analysis.

[0511] "Identifying emotions" refers to the process of identifying the emotional state of a person having a conversation based on digitized information.

[0512] "Generating proposals" refers to the process of automatically creating optimal sales strategies and response plans based on identified sentiment data and negotiation details.

[0513] "To present" refers to providing generated suggestions or information visually or audibly so that the user can review them.

[0514] "Flexible response" refers to the ability to implement adaptive communication that matches the customer's emotions during a business negotiation, based on immediate feedback and situational assessment.

[0515] "Recording" refers to saving the process and results of business negotiations, as well as user feedback, in a database or similar system for later analysis and learning.

[0516] "Retraining" refers to the process of improving the algorithm of a generative AI model based on recorded data, thereby enhancing the accuracy of suggestions and sentiment recognition.

[0517] This invention is a system specifically designed for sales support, assisting in business negotiations by analyzing voice information and providing optimal suggestions based on the results. Specific embodiments are shown below.

[0518] System Configuration

[0519] The system is comprised of various components, including servers, terminals, emotion engines, and users. Specifically, the server is responsible for overall data management and model retraining, while the terminals collect audio and display suggestions.

[0520] Implementation environment

[0521] Users conduct business negotiations using a terminal. The terminal requires a microphone device for high-quality voice capture. Natural language processing technology is used to convert the voice data into text, and specifically, a generally available voice recognition service can be used as voice recognition software.

[0522] Data Analysis

[0523] The device converts acquired audio information into text in real time. This process utilizes publicly available speech recognition APIs. The emotion engine then analyzes the text data to identify the customer's and user's emotions. Common text analysis services can be incorporated into this analysis.

[0524] Proposal generation

[0525] The analyzed sentiment data and conversation content are sent to a server, where an optimal business proposal is created through a proposal generation device. This generation process requires rapid data processing, and a server-based AI model is employed. This proposal is displayed on the terminal in real time, allowing the user to utilize it to guide the business negotiation.

[0526] As a concrete example, if a customer expresses concern about the price during a sales meeting where a user is introducing a new product, the system can instantly identify that emotion from the voice and suggest promotional information to alleviate the concern. Furthermore, an example of a prompt the generating AI model might respond to is, "The customer seems concerned about the price of the new product. What kind of suggestion would alleviate his concerns?" The system would then suggest appropriate price explanations or trial campaigns.

[0527] In this way, it becomes possible to improve the quality and effectiveness of business negotiations.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The terminal acquires voice information from the user and the customer during a business negotiation. This input data is an audio signal, and the input device used here is a microphone for voice recognition. Specifically, the terminal captures the audio in real time through the microphone.

[0531] Step 2:

[0532] The terminal converts acquired audio information into text data in real time. In this step, speech recognition software analyzes the audio signal and generates the corresponding text. This generated text data becomes the output. The process involves analyzing the audio waveform and representing it as a string using a language model.

[0533] Step 3:

[0534] The emotion engine within the device receives text data and analyzes the emotions of the user and customer. The input is text data, and the emotion analysis algorithm analyzes it and outputs an emotional state (e.g., joy, anxiety, anger). Specifically, natural language processing techniques are used to score the emotions within the text.

[0535] Step 4:

[0536] The server integrates sentiment data and conversation content and generates optimal suggestions through a suggestion generator. The input for this step is sentiment data and text data, and the output is suggestion information. Specifically, the process involves a generation AI model constructing suggestion content based on past data.

[0537] Step 5:

[0538] The generated proposals are displayed on the terminal's display device. Output from the server is passed to the terminal as input, and the user can review it during the business negotiation. Specifically, the generated proposals are visualized and presented to the user in an easy-to-understand UI.

[0539] Step 6:

[0540] After a business negotiation concludes, the server collects the negotiation results and user feedback, and records this information in a database. The input consists of negotiation results data and feedback, while the output is saving the data to the database. This specific operation includes data format conversion and saving.

[0541] Step 7:

[0542] The recorded data is used to retrain the AI ​​model on the server. The input is the recorded data, and the output is the updated generative AI model. Specifically, retraining is performed using machine learning algorithms to improve the model's accuracy.

[0543] (Application Example 2)

[0544] 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."

[0545] In modern face-to-face sales and customer service, employees are required to instantly grasp the emotions of individual customers and respond flexibly and effectively based on that understanding. Especially in the busy environment of a physical store, maintaining high-quality service for multiple customers requires quick decision-making within limited timeframes. However, there are limitations to employees' subjective emotional judgment, and there is a lack of technical support to improve the accuracy and consistency of these judgments.

[0546] 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.

[0547] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed conversation and identifying the customer's emotional state, means for generating suggestions based on the analysis results and the customer's emotional state, means for displaying the generated suggestions on a display device, and means for capturing the customer's facial expressions and complementing the emotional analysis. This makes it possible to grasp the customer's emotions in real time and immediately provide optimal suggestions tailored to their individual needs.

[0548] "Methods for converting voice input to text" refer to technologies that convert voice data into textual information through digital processing.

[0549] "Methods for analyzing transcribed conversations and identifying emotional states" refers to technologies that infer emotions from text data based on vocabulary and context, and then explicitly represent those emotions as data.

[0550] "Means for generating suggestions based on analysis results and customer emotional states" refers to technologies that utilize analyzed emotional data to recommend actions and products optimized for customer needs.

[0551] "Means for presenting generated proposals on a display device" refers to a technology that displays the proposed information on a display in a format that allows for visual confirmation.

[0552] "A means of capturing customer facial expressions and complementing emotion analysis" refers to a technology that analyzes customer facial expression data to make emotion analysis of voice data more accurate.

[0553] The system program for implementing this invention realizes the conversion of voice data into text, sentiment analysis, suggestion generation, and result display as a series of steps. The system is operated as follows:

[0554] First, software is run on the device to acquire voice input and convert it to text. Specifically, the Google Cloud Speech-to-Text API is used to analyze customer-staff conversations in real time.

[0555] Next, the server analyzes this transcribed conversation to identify the emotional state. Sentiment analysis utilizes Microsoft Azure Text Analytics to determine the user's and customer's emotions based on words and context.

[0556] Based on the analyzed sentiment data, the server generates suggestions. This generation process utilizes a generative AI model, enabling the suggestion of products and services optimized to the customer's needs and emotions. At this stage, the suggestions are refined through prompt messages to obtain customized output.

[0557] The generated proposals are ultimately displayed on the terminal's display. This allows users to utilize real-time proposals during business negotiations and respond in a way that aligns with the customer's intentions.

[0558] For example, if a customer in a physical store says, "I'm interested in the new product, but I'm concerned about the price," and the analyzed emotion is determined to be "anxiety," the system can use this information to automatically display a suggestion such as, "We have discount options available to put your mind at ease regarding the price."

[0559] An example of a prompt message would be, "Suggest accessories that would suit a customer wearing a casual jacket." In this way, a system that strongly supports customer service in physical stores is realized.

[0560] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0561] Step 1:

[0562] The device collects audio of customer and staff conversations using a microphone. The input is real-time audio data, which is converted into text data using the Google Cloud Speech-to-Text API. The output is this text data.

[0563] Step 2:

[0564] The server receives transcribed conversation data and analyzes the emotional state using Microsoft Azure Text Analytics. The input is the text data from Step 1, and through this data, words and context are analyzed to identify emotions (e.g., interest, anxiety, satisfaction, etc.). The output is the emotional analysis data.

[0565] Step 3:

[0566] The server uses sentiment analysis data as input to generate customer suggestions using a generative AI model. In this step, prompts are used to provide appropriate instructions to the generative AI model, resulting in customized suggestions. The output is the suggested content.

[0567] Step 4:

[0568] The terminal displays the generated proposal content on its screen. The input is the proposal content from step 3, which is provided to the user as visual information in real time. The output is the visualized proposal.

[0569] This process allows the system to analyze customer emotions in real time, generate and display optimized suggestions, and help users respond immediately during business negotiations.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] 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.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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".

[0587] This invention is a system that utilizes advanced AI technology to support sales activities. This system has the ability to convert speech to text and analyze conversations in real time, thereby improving the quality of business negotiations. Furthermore, it can improve sales efficiency by predicting future trends using past data and assisting in strategic decision-making.

[0588] This system primarily consists of three components: a server, terminals, and users. The server accesses the database and is responsible for collecting and analyzing customer information and sales history. The terminals have speech recognition and text conversion capabilities, instantly recording conversations during sales meetings and converting them into an analyzable format. Users, i.e., sales representatives, can utilize the system's advice to communicate more effectively with customers.

[0589] For example, when a user is conducting a business negotiation with a customer, the terminal receives the conversation as voice input in real time and continuously converts it into text data. Subsequently, an analysis device analyzes the conversation content and provides the user with insights to understand the customer's needs and interests. Based on this analysis, a generation device instantly creates an optimal product proposal and presents it to the user via a display device.

[0590] Furthermore, after a business negotiation is completed, the server collects feedback and negotiation results entered by the user and records them in a database. Based on this information, the server can retrain the AI ​​model, continuously improving the prediction accuracy and proposal quality for future negotiations.

[0591] In this form of implementing the invention, the entire system works together to support sales activities, enabling effective negotiations and strategic decision-making.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The server collects customer information and past sales history from the database and prepares a basic dataset for analysis.

[0595] Step 2:

[0596] The terminal receives the conversation between the user and the customer as voice input during a business meeting. Using speech recognition technology, this voice is instantly converted into text data.

[0597] Step 3:

[0598] Text data is sent to an analysis device, and the terminal identifies customer needs and intentions based on the analysis results. In this process, natural language processing technology is used to understand the context.

[0599] Step 4:

[0600] The generation device, upon receiving the analysis results, generates optimal product suggestions and responses for the user. These suggestions are based on historical data and pre-configured sales strategies.

[0601] Step 5:

[0602] The terminal's display shows the generated proposals to the user in real time. The user uses this information to advance the conversation and improve the effectiveness of the business negotiation.

[0603] Step 6:

[0604] After a business meeting, the user enters the meeting results and customer feedback into their device. This feedback is added to the database as evidence of the meeting's success or failure and the lessons learned.

[0605] Step 7:

[0606] The server retrains the AI ​​model using newly collected sales opportunity data to improve the accuracy of future sales opportunity support. This process is performed continuously to enhance the model's predictive power.

[0607] (Example 1)

[0608] 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".

[0609] In modern sales activities, it is essential to understand customer needs and interests in real time and quickly provide optimal proposals. However, traditional methods lack a system that efficiently transcribes voice data into text, performs in-depth analysis based on that transcription, and integrates predictions and strategic proposals. As a result, it is difficult for sales representatives to quickly obtain the necessary insights during negotiations, leading to a problem of unimproved negotiation quality.

[0610] 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.

[0611] In this invention, the server includes means for converting voice data into text information, means for analyzing the text information to identify customer interests and needs, and means for generating proposal information based on the analyzed information. This enables sales representatives to receive insights generated in real time during sales negotiations and to make effective and appropriate proposals to customers.

[0612] "Audio data" refers to information recorded in digital format from human speech.

[0613] "Text information" refers to information obtained by converting audio data into a string format.

[0614] "Methods for identifying customer interests and needs" refers to methods that use analytical techniques to extract the interests and needs that customers express during business negotiations.

[0615] "Generating means for generating proposal information" refers to a method that automatically creates product and service proposals suitable for the customer based on analysis results.

[0616] "Means for displaying generated proposal information on a user device" refers to a method for visually presenting the generated proposal content, which sales representatives can review during business negotiations.

[0617] "Past customer information" refers to the collective data obtained from past business negotiations and customer interactions.

[0618] A "memory device" is a device used to store information for a long period of time.

[0619] "Methods for making sales forecasts" refer to methods of predicting the results of future sales activities by analyzing past data.

[0620] "Methods for proposing sales strategies" refer to methods for proposing the direction and plan of sales activities.

[0621] "Sales negotiation results information" refers to data regarding the outcomes and actions taken after a sales negotiation has concluded.

[0622] "User feedback information" refers to the opinions and evaluations that users provide regarding the system or business negotiations.

[0623] "Methods for retraining machine learning models" refer to methods for improving the accuracy and efficiency of existing models by adding new data and performing further training.

[0624] This invention is an advanced information processing system that supports sales activities and is mainly composed of three components: a server, a terminal, and a user.

[0625] The server manages customer information and sales history using a database system. Specifically, the server uses a high-performance computer (commonly known as a server machine) and employs a relational database as its database management system. This server utilizes an API to convert audio data into text information, and analyzes the converted text information to extract customer interests and needs. This analysis employs a natural language processing model, and based on the analysis results, a generative AI model is used to generate suggestion information.

[0626] The terminal receives voice input from the user during a business negotiation, converts it to text using speech recognition software, and sends it to the server in real time. Google Cloud Speech-to-Text API is one example of the software that can be used. The terminal visually presents the generated proposal information to the user, helping them to effectively advance the business negotiation.

[0627] Users utilize this system to advance sales negotiations. For example, when asking a customer, "Are you interested in our new product?", the terminal receives the conversation as audio, instantly converts it to text, and analyzes it. This allows the system to generate optimal product suggestions tailored to the customer's interests and provide them to the user immediately. As a specific example, the prompt message might read, "Prompt for the next negotiation: Based on the history of this negotiation and customer feedback, generate the next proposal for customer Y."

[0628] In this way, the entire system works together, enabling users to improve the quality of their sales negotiations and realize strategic sales activities.

[0629] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0630] Step 1:

[0631] The terminal accepts voice input as soon as a business negotiation begins. The input is the audio conversation between the user and the customer. The terminal converts this audio data into text information using the Google Cloud Speech-to-Text API. This conversion allows the content of the negotiation to be immediately obtained as text data. The output is the transcribed conversation data.

[0632] Step 2:

[0633] The server receives text information sent from the terminal. The input is text data converted from speech. The server analyzes this text information using natural language processing (NLP) algorithms. The purpose of the analysis is to identify the customer's interests and needs. For example, keywords are extracted from the text, and these are used to determine the customer's areas of interest. The output is the analyzed insight information.

[0634] Step 3:

[0635] The server uses the analysis results to launch a generative AI model. The input is insight information. The generative AI model generates the optimal proposal by referring to past similar deal data. At this stage, a prompt is used to determine the direction of the proposal. For example, "Prompt for the next deal: Based on the history of this deal and customer feedback, generate the next proposal for customer Y." The output is specific proposal information.

[0636] Step 4:

[0637] The terminal displays proposal information received from the server to the user. The input is the generated proposal information. The display is visual, allowing the user to review it during negotiations. This enables the user to make effective proposals to customers at the appropriate time. The output is a display of proposal information that the user can review and use.

[0638] Step 5:

[0639] When a business negotiation ends, the user inputs feedback information about the negotiation results and customer reactions into the terminal. This input is feedback information. The terminal sends this information to the server, which records it in a database. The AI ​​model is then retrained based on this information. This retraining enables more accurate proposals in future negotiations. The output is the feedback information recorded in the database.

[0640] (Application Example 1)

[0641] 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".

[0642] There is a need to improve real-time customer service in face-to-face sales activities and to quickly and accurately grasp customer needs. In particular, during customer service, it is necessary to propose products that meet the customer's needs, but store staff have to make quick decisions with limited information, so the quality of proposals is inconsistent, which is a challenge.

[0643] 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.

[0644] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed dialogue, and means for generating product suggestions based on the analysis results. This enables real-time optimal product suggestions based on conversations in stores.

[0645] "Means of converting voice input to text" refers to a device or program that uses technology to convert voice information into text information.

[0646] "Means for analyzing transcribed dialogue" refers to technologies or devices that, after transcribing voice input into text, analyze the content of the dialogue based on that text to identify areas of interest and needs.

[0647] "Means for generating product proposals" refers to technology or equipment that selects the most suitable products or services based on analyzed dialogue content and creates information for proposing them.

[0648] "Means of storing information in an information collection" refers to technologies or devices that record and manage data such as customer usage history and feedback in an information collection.

[0649] "Means of demand forecasting" refers to technologies or devices that analyze accumulated data to predict future demand and trends.

[0650] A "generative AI model" refers to an artificial intelligence model that uses machine learning to learn from data and make suggestions and decisions in response to new situations.

[0651] In this embodiment of the invention, the information processing system mainly consists of three components: a server, a terminal, and a user. The server is responsible for collecting user data, including customer information, and storing it in an information aggregate. The terminal incorporates a means for converting voice input using a speech recognition API into text, and smartphones or tablet devices are employed.

[0652] The device uses speech recognition APIs such as Google Speech-to-Text to convert customer interactions into text data in real time. This text data can be analyzed using natural language processing libraries such as spaCy and TensorFlow to interpret customer needs. The analysis results are sent back to the server, where a generative AI model generates optimal product suggestions. These generated product suggestions are presented to the user through the device's display or smart glasses.

[0653] Users, i.e., store staff, can immediately provide feedback to customers based on product suggestions provided from the terminal. This makes it possible to provide appropriate product information in real time during customer interactions and improve the quality of customer service. Furthermore, user feedback and conversation results are returned to the server, and the generated AI model is retrained based on the accumulated information to improve the accuracy of future suggestions.

[0654] To give a concrete example, if a customer is looking for a mystery novel in a bookstore, the terminal can capture the conversation, analyze it, and then suggest the latest related books. An example of input to the generating AI model would be a prompt sentence like, "What related books can we recommend to a customer looking for this mystery novel?"

[0655] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0656] Step 1:

[0657] The device acquires customer interactions as voice input. The input voice data is captured through the microphone of a commercially available smart device. Upon receiving the voice data, the device uses a speech recognition API (e.g., Google Speech-to-Text) to convert this voice data into text data. The output of this conversion process is a text-based transcript of the conversation.

[0658] Step 2:

[0659] The terminal uses the converted text data to apply natural language processing libraries (e.g., spaCy, TensorFlow) and analyze the conversation content. Based on the text data received as input, it utilizes NLP techniques to extract the customer's intent and needs. The output of this analysis is information about the customer's potential interests and needs. Specifically, it performs tasks such as keyword extraction and contextual understanding.

[0660] Step 3:

[0661] The server receives the analysis results sent from the terminal and inputs them into the generating AI model. Based on this input data, the AI ​​model generates product suggestions. The AI ​​model is trained to make more accurate suggestions based on previously accumulated data. The generated suggestions include a list of products and information that explains why specific products are recommended.

[0662] Step 4:

[0663] The terminal receives product information suggested by the server and displays the suggested products on its screen. It receives product suggestion data from the server as input and presents it visually to the user through the user interface. This allows store staff, who are the users, to provide immediate feedback to customers. Specifically, it performs the immediate display of information on the screen.

[0664] Step 5:

[0665] The user engages in further interaction with the customer and sends the results as feedback to the server. This feedback includes the customer's reactions and acceptance of suggestions. Based on this feedback, the server accumulates data in an information database and further retrains the generative AI model. This improves the accuracy of future product suggestions. Specifically, this involves recording information in the database and updating the model.

[0666] 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.

[0667] This invention is a system for supporting sales activities, and in particular, by combining it with an emotion engine that recognizes the emotions of users and customers, it further improves the quality and effectiveness of sales negotiations. This system supports sales negotiations in real time by converting speech to text and further analyzing the content and emotions of the text.

[0668] The entire system consists of server, terminal, emotion engine, and user components, all working in conjunction with each other. First, the terminal collects audio information from conversations during business negotiations and transcribes that audio into text in real time. Next, the emotion engine identifies the emotional state of the user and customer from the transcribed conversation and the audio itself, and generates emotion data.

[0669] Next, this emotional data is processed by an analysis device in combination with content analysis to generate optimal proposals that take into account not only the customer's interests and needs, but also their emotional state. The generated proposals are displayed on the terminal's display device, allowing the user to utilize them during business negotiations and respond flexibly to the customer's emotions.

[0670] For example, if a customer shows anxiety while a user is introducing a new product, the emotion engine immediately detects this emotion, and the analysis device takes that data into account to generate a proposal that includes additional information and benefits to alleviate the anxiety. In this way, users can conduct business negotiations while being mindful of the customer's emotions, improving the success rate.

[0671] Furthermore, after a business negotiation is completed, the server collects the final outcome of the negotiation and user feedback, and stores it in a database as comprehensive negotiation data, including sentiment data. This data is also used to retrain the AI ​​model, enabling continuous improvement of the system's performance.

[0672] By implementing this invention, sales representatives can grasp customer emotions in a timely manner and conduct strategic and empathetic sales activities based on that information.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The terminal receives the user's and customer's conversation as voice input at the start of a business negotiation and converts it to text in real time.

[0676] Step 2:

[0677] The emotion engine analyzes voice and text data to identify the emotional state of users and customers. Voice tone and language choices are considered in determining the emotion.

[0678] Step 3:

[0679] The analysis device receives the transcribed conversation and sentiment data and performs an analysis of the customer's needs and emotions. The results of this analysis are used to evaluate the customer's purchasing intent and concerns.

[0680] Step 4:

[0681] The generating device constructs emotionally sensitive product proposals and sales strategies based on the analysis data, and transmits them to the terminal.

[0682] Step 5:

[0683] The terminal's display screen shows proposals generated for the user in real time, which the user can use as a guide to conduct business negotiations in a way that aligns with the customer's emotions.

[0684] Step 6:

[0685] After the business negotiation concludes, the user enters feedback on the negotiation results and customer reactions into the terminal. This information will be used in future business negotiations.

[0686] Step 7:

[0687] The server stores new business negotiation information and sentiment data in its database, which is then used to retrain the AI ​​model for future business negotiations. This continuously improves the system's analytical capabilities.

[0688] (Example 2)

[0689] 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".

[0690] Traditional sales activities have made it difficult to accurately understand customer emotions and thereby facilitate smooth business negotiations. Furthermore, there has been a lack of efficient methods to utilize data after negotiations to improve the success rate of future negotiations. This has limited effective responses necessary to maximize sales results.

[0691] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0692] In this invention, the server includes means for acquiring and digitizing voice information; means for analyzing the digitized content and identifying emotions; means for generating suggestions based on the identified emotion data and content; means for presenting the generated suggestions; means for enabling flexible responses that adapt to the emotions of the user and the customer; means for collecting and recording results and feedback after the conclusion of a business negotiation; and means for retraining the model based on the recorded data to improve performance. This enables quick and accurate responses that respond to the customer's emotions, thereby increasing the success rate of business negotiations.

[0693] "Audio information" refers to sound data acquired during business negotiations and conversations, and forms the basis for analyzing human speech.

[0694] "Data conversion" refers to the process of converting acquired audio information into text or other data formats, which forms the basis for analysis.

[0695] "Identifying emotions" refers to the process of identifying the emotional state of a person having a conversation based on digitized information.

[0696] "Generating proposals" refers to the process of automatically creating optimal sales strategies and response plans based on identified sentiment data and negotiation details.

[0697] "To present" refers to providing generated suggestions or information visually or audibly so that the user can review them.

[0698] "Flexible response" refers to the ability to implement adaptive communication that matches the customer's emotions during a business negotiation, based on immediate feedback and situational assessment.

[0699] "Recording" refers to saving the process and results of business negotiations, as well as user feedback, in a database or similar system for later analysis and learning.

[0700] "Retraining" refers to the process of improving the algorithm of a generative AI model based on recorded data, thereby enhancing the accuracy of suggestions and sentiment recognition.

[0701] This invention is a system specifically designed for sales support, assisting in business negotiations by analyzing voice information and providing optimal suggestions based on the results. Specific embodiments are shown below.

[0702] System Configuration

[0703] The system is comprised of various components, including servers, terminals, emotion engines, and users. Specifically, the server is responsible for overall data management and model retraining, while the terminals collect audio and display suggestions.

[0704] Implementation environment

[0705] Users conduct business negotiations using a terminal. The terminal requires a microphone device for high-quality voice capture. Natural language processing technology is used to convert the voice data into text, and specifically, a generally available voice recognition service can be used as voice recognition software.

[0706] Data Analysis

[0707] The device converts acquired audio information into text in real time. This process utilizes publicly available speech recognition APIs. The emotion engine then analyzes the text data to identify the customer's and user's emotions. Common text analysis services can be incorporated into this analysis.

[0708] Proposal generation

[0709] The analyzed sentiment data and conversation content are sent to a server, where an optimal business proposal is created through a proposal generation device. This generation process requires rapid data processing, and a server-based AI model is employed. This proposal is displayed on the terminal in real time, allowing the user to utilize it to guide the business negotiation.

[0710] As a concrete example, if a customer expresses concern about the price during a sales meeting where a user is introducing a new product, the system can instantly identify that emotion from the voice and suggest promotional information to alleviate the concern. Furthermore, an example of a prompt the generating AI model might respond to is, "The customer seems concerned about the price of the new product. What kind of suggestion would alleviate his concerns?" The system would then suggest appropriate price explanations or trial campaigns.

[0711] In this way, it becomes possible to improve the quality and effectiveness of business negotiations.

[0712] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0713] Step 1:

[0714] The terminal acquires voice information from the user and the customer during a business negotiation. This input data is an audio signal, and the input device used here is a microphone for voice recognition. Specifically, the terminal captures the audio in real time through the microphone.

[0715] Step 2:

[0716] The terminal converts acquired audio information into text data in real time. In this step, speech recognition software analyzes the audio signal and generates the corresponding text. This generated text data becomes the output. The process involves analyzing the audio waveform and representing it as a string using a language model.

[0717] Step 3:

[0718] The emotion engine within the device receives text data and analyzes the emotions of the user and customer. The input is text data, and the emotion analysis algorithm analyzes it and outputs an emotional state (e.g., joy, anxiety, anger). Specifically, natural language processing techniques are used to score the emotions within the text.

[0719] Step 4:

[0720] The server integrates sentiment data and conversation content and generates optimal suggestions through a suggestion generator. The input for this step is sentiment data and text data, and the output is suggestion information. Specifically, the process involves a generation AI model constructing suggestion content based on past data.

[0721] Step 5:

[0722] The generated proposals are displayed on the terminal's display device. Output from the server is passed to the terminal as input, and the user can review it during the business negotiation. Specifically, the generated proposals are visualized and presented to the user in an easy-to-understand UI.

[0723] Step 6:

[0724] After a business negotiation concludes, the server collects the negotiation results and user feedback, and records this information in a database. The input consists of negotiation results data and feedback, while the output is saving the data to the database. This specific operation includes data format conversion and saving.

[0725] Step 7:

[0726] The recorded data is used to retrain the AI ​​model on the server. The input is the recorded data, and the output is the updated generative AI model. Specifically, retraining is performed using machine learning algorithms to improve the model's accuracy.

[0727] (Application Example 2)

[0728] 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".

[0729] In modern face-to-face sales and customer service, employees are required to instantly grasp the emotions of individual customers and respond flexibly and effectively based on that understanding. Especially in the busy environment of a physical store, maintaining high-quality service for multiple customers requires quick decision-making within limited timeframes. However, there are limitations to employees' subjective emotional judgment, and there is a lack of technical support to improve the accuracy and consistency of these judgments.

[0730] 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.

[0731] In this invention, the server includes means for converting voice input into text, means for analyzing the transcribed conversation and identifying the customer's emotional state, means for generating suggestions based on the analysis results and the customer's emotional state, means for displaying the generated suggestions on a display device, and means for capturing the customer's facial expressions and complementing the emotional analysis. This makes it possible to grasp the customer's emotions in real time and immediately provide optimal suggestions tailored to their individual needs.

[0732] "Methods for converting voice input to text" refer to technologies that convert voice data into textual information through digital processing.

[0733] "Methods for analyzing transcribed conversations and identifying emotional states" refers to technologies that infer emotions from text data based on vocabulary and context, and then explicitly represent those emotions as data.

[0734] "Means for generating suggestions based on analysis results and customer emotional states" refers to technologies that utilize analyzed emotional data to recommend actions and products optimized for customer needs.

[0735] "Means for presenting generated proposals on a display device" refers to a technology that displays the proposed information on a display in a format that allows for visual confirmation.

[0736] "A means of capturing customer facial expressions and complementing emotion analysis" refers to a technology that analyzes customer facial expression data to make emotion analysis of voice data more accurate.

[0737] The system program for implementing this invention realizes the conversion of voice data into text, sentiment analysis, suggestion generation, and result display as a series of steps. The system is operated as follows:

[0738] First, software is run on the device to acquire voice input and convert it to text. Specifically, the Google Cloud Speech-to-Text API is used to analyze customer-staff conversations in real time.

[0739] Next, the server analyzes this transcribed conversation to identify the emotional state. Sentiment analysis utilizes Microsoft Azure Text Analytics to determine the user's and customer's emotions based on words and context.

[0740] Based on the analyzed sentiment data, the server generates suggestions. This generation process utilizes a generative AI model, enabling the suggestion of products and services optimized to the customer's needs and emotions. At this stage, the suggestions are refined through prompt messages to obtain customized output.

[0741] The generated proposals are ultimately displayed on the terminal's display. This allows users to utilize real-time proposals during business negotiations and respond in a way that aligns with the customer's intentions.

[0742] For example, if a customer in a physical store says, "I'm interested in the new product, but I'm concerned about the price," and the analyzed emotion is determined to be "anxiety," the system can use this information to automatically display a suggestion such as, "We have discount options available to put your mind at ease regarding the price."

[0743] An example of a prompt message would be, "Suggest accessories that would suit a customer wearing a casual jacket." In this way, a system that strongly supports customer service in physical stores is realized.

[0744] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0745] Step 1:

[0746] The device collects audio of customer and staff conversations using a microphone. The input is real-time audio data, which is converted into text data using the Google Cloud Speech-to-Text API. The output is this text data.

[0747] Step 2:

[0748] The server receives transcribed conversation data and analyzes the emotional state using Microsoft Azure Text Analytics. The input is the text data from Step 1, and through this data, words and context are analyzed to identify emotions (e.g., interest, anxiety, satisfaction, etc.). The output is the emotional analysis data.

[0749] Step 3:

[0750] The server uses sentiment analysis data as input to generate customer suggestions using a generative AI model. In this step, prompts are used to provide appropriate instructions to the generative AI model, resulting in customized suggestions. The output is the suggested content.

[0751] Step 4:

[0752] The terminal displays the generated proposal content on its screen. The input is the proposal content from step 3, which is provided to the user as visual information in real time. The output is the visualized proposal.

[0753] This process allows the system to analyze customer emotions in real time, generate and display optimized suggestions, and help users respond immediately during business negotiations.

[0754] 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.

[0755] 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.

[0756] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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."

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] The following is further disclosed regarding the embodiments described above.

[0776] (Claim 1)

[0777] A device that converts voice input into text,

[0778] An analysis device that analyzes transcribed conversations,

[0779] A generation device that generates proposals based on analysis results,

[0780] A display device for displaying the generated suggestions,

[0781] A sales support system that includes this.

[0782] (Claim 2)

[0783] A means of collecting past customer data and storing it in a database,

[0784] A method for analyzing accumulated data to make sales forecasts,

[0785] The sales support system according to claim 1, further comprising means for proposing a strategy based on the prediction results.

[0786] (Claim 3)

[0787] A means of receiving sales negotiation results and user feedback and recording them in a database,

[0788] The sales support system according to claim 1, further comprising means for retraining an AI model based on recorded data.

[0789] "Example 1"

[0790] (Claim 1)

[0791] A means of converting audio data into text information,

[0792] A means of analyzing text information to identify customer interests and needs,

[0793] A generation means for generating proposed information based on the analyzed information,

[0794] A means for displaying the generated proposal information on the user device,

[0795] An information processing system that includes this.

[0796] (Claim 2)

[0797] A means of collecting past customer information and storing it in a memory device,

[0798] A means of analyzing accumulated information to make sales forecasts,

[0799] The information processing system according to claim 1, further comprising a means for proposing a sales strategy based on the prediction.

[0800] (Claim 3)

[0801] A means of receiving information on the results of business negotiations and user feedback, and recording this information in a storage device,

[0802] The information processing system according to claim 1, further comprising means for retraining a machine learning model based on recorded information.

[0803] "Application Example 1"

[0804] (Claim 1)

[0805] Methods for converting voice input to text,

[0806] A means of analyzing transcribed dialogue,

[0807] A means for generating product proposals based on analysis results,

[0808] A means of displaying the generated product suggestions,

[0809] An information processing system that includes this.

[0810] (Claim 2)

[0811] A means of collecting past user data and storing it in an information collection,

[0812] A means of analyzing accumulated information to forecast demand,

[0813] The information processing system according to claim 1, further comprising means for proposing a strategy based on the prediction results.

[0814] (Claim 3)

[0815] A means of receiving the results of the dialogue and user feedback and recording them in an information collection,

[0816] The information processing system according to claim 1, further comprising means for retraining a generated AI model based on recorded information.

[0817] "Example 2 of combining an emotion engine"

[0818] (Claim 1)

[0819] A means of acquiring and digitizing audio information,

[0820] A means of analyzing digitized content to identify emotions,

[0821] Means for generating suggestions based on identified sentiment data and content,

[0822] Means for presenting the generated proposals,

[0823] A means to enable flexible responses that adapt to the emotions of users and customers,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] A means of collecting and recording results and feedback after the conclusion of a business negotiation,

[0827] The system according to claim 1, further comprising means for retraining a model based on recorded data to improve performance.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising means for providing information that responds immediately to the customer's emotions when generating suggestions.

[0830] "Application example 2 when combining with an emotional engine"

[0831] (Claim 1)

[0832] Methods for converting voice input to text,

[0833] A means of analyzing transcribed conversations and identifying emotional states,

[0834] A means for generating suggestions based on analysis results and the customer's emotional state,

[0835] A means for displaying the generated proposal on a display device,

[0836] A means to capture customer facial expressions and complement emotion analysis,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] Equipped with means to collect past customer data and store it in a database,

[0840] A method for analyzing accumulated data to make sales forecasts,

[0841] The system according to claim 1, further comprising means for proposing a strategy based on the prediction results and real-time customer sentiment.

[0842] (Claim 3)

[0843] A means of receiving sales negotiation results and user feedback and recording them in a database,

[0844] The system according to claim 1, further comprising means for retraining a generative AI model based on recorded data and generating optimized suggestions using prompt sentences. [Explanation of Symbols]

[0845] 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. Methods for converting voice input to text, A means of analyzing transcribed dialogue, A means for generating product proposals based on analysis results, A means of displaying the generated product suggestions, An information processing system that includes this.

2. A means of collecting past user data and storing it in an information collection, A means of analyzing accumulated information to forecast demand, The information processing system according to claim 1, further comprising means for proposing a strategy based on the prediction results.

3. A means of receiving the results of the dialogue and user feedback and recording them in an information collection, The information processing system according to claim 1, further comprising means for retraining a generated AI model based on recorded information.

Images