System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting speech data during a call; means for converting the collected speech data into text data using a speech recognition engine; means for summarizing the converted text data using a summarization engine; means for storing the summarized text data; and means for allowing a user to access the stored text data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Unlike emails and chats, telephone conversations do not leave a text record of the conversation, which makes it difficult to review the content later. In particular, detailed notes must be taken to avoid losing important points during meetings or important consultations, which places a burden on users. The present invention aims to eliminate this hassle by automatically converting and summarizing the contents of phone conversations, making it easy to review even long conversations. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for saving the summarized text data, and an access means for allowing a user to access the saved text data. This system collects call content in real time, converts it into text using the voice recognition engine, and then uses the summarization engine to extract important points and create a summary. The generated summary is saved in a database so that the user can access it later, facilitating information review and sharing.

[0006] A "call" is the act of exchanging information with another person in real time via voice.

[0007] "Voice data" means data collected in digital form from the voice of a call.

[0008] The "collection means" is a means for acquiring voice data during a call using an input device such as a microphone.

[0009] A "speech recognition engine" is a software or hardware component that analyzes and converts voice data into corresponding text data.

[0010] "Text data" refers to data in which voice data has been converted into text information.

[0011] The "conversion means" is a means for transmitting collected voice data to a voice recognition engine and converting it into text data.

[0012] A "summary engine" is a software or hardware component that analyzes text data, extracts key points, and summarizes them.

[0013] The "summarization means" is a means for passing text data to a summarization engine to generate a summary.

[0014] "Storage means" refers to a means for storing summarized text data in a storage device such as a database.

[0015] "Access means" refers to the means by which a user accesses the stored text data.

[0016] A "system" is a collection of multiple elements that work together to achieve a specific function. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0039] System configuration

[0040] 1. Collection Method

[0041] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0042] 2. Conversion Method

[0043] The server receives the voice data sent from the device and passes it to a voice recognition engine. The voice recognition engine analyzes the voice data and converts it into corresponding text data. For example, voice data such as "We talked about the progress of the project" is converted into text data such as "We talked about the progress of the project."

[0044] 3. Summary tools

[0045] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into the summary "Confirmed the project progress and next steps."

[0046] 4. Preservation means

[0047] The server stores the generated summary in a database, along with metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0048] 5. Access

[0049] Users can access the saved summaries after the call via a web portal or mobile app, and can easily search through saved summaries to quickly review key points.

[0050] Program processing explanation

[0051] The program processing of this system will be explained in natural language below.

[0052] Audio data collection

[0053] 1. Users

[0054] Initiate a call, for example, call a colleague for a business meeting.

[0055] 2. Terminal

[0056] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0057] Voice data recognition and conversion

[0058] 3. Server

[0059] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0060] 4. Speech Recognition Engine

[0061] The collected voice data is analyzed and converted into appropriate text data. For example, a voice saying "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0062] Summarizing text data

[0063] 5. Server

[0064] Receives text data and passes it to a summarization engine.

[0065] 6. Summarization Engine

[0066] It analyzes text data and generates summaries, such as "a conversation with a client about the progress of a project."

[0067] Storing and Accessing Summary Data

[0068] 7. Server

[0069] The generated summary is stored in a database, and the stored summary data includes the call date and time, the call recipient, and the call duration.

[0070] 8. Users

[0071] After the call ends, users can access and review the saved summary data through the web portal or mobile app. Users can easily search the summary data and quickly review key points of the call.

[0072] Specific examples

[0073] For example, consider a scenario in which a salesperson is talking to a customer, explaining product details and discussing the purchase procedure. The conversation during the call is collected as voice data by the device and sent to a server. A speech recognition engine converts this into text data, and a summarization engine extracts important points and generates a summary. The server then stores the summarized data in a database, allowing the salesperson to easily check the summary later.

[0074] The above is a specific example of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, significantly improving business efficiency.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] A user initiates a call, for example, calling a colleague for a business meeting.

[0078] Step 2:

[0079] When a call starts, the device collects audio data through the microphone and transmits the collected audio data to the server in real time.

[0080] Step 3:

[0081] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0082] Step 4:

[0083] The speech recognition engine analyzes the voice data and converts the content into text. For example, the speech "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0084] Step 5:

[0085] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0086] Step 6:

[0087] The summarization engine analyzes the text data, extracts key points, and generates a summary, such as "a conversation about the progress of a project."

[0088] Step 7:

[0089] The server stores the generated summary in a database, along with metadata such as the date and time of the call, who the call was with, and the duration of the call.

[0090] Step 8:

[0091] After the call ends, the user accesses the stored summary data through a web portal or mobile app.

[0092] Step 9:

[0093] Users can easily search through the saved summary data to see key points from the call, such as "We reported on the progress of the project and discussed next steps."

[0094] Through this series of steps, the conversation is automatically transcribed, summarized, and saved, allowing users to quickly check the information they need later.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern business communications, it is important to efficiently understand and record the contents of phone calls. However, manually transcribing and summarizing phone call content is time-consuming and labor-intensive, and important points can often be overlooked. Furthermore, there are few systems that properly store this information and make it easily accessible later. This creates challenges in efficiently managing and utilizing call content.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for adding metadata including the call date and time, the call recipient, and the call duration to the generated summary and storing the resulting summary in a database, and an access means for allowing a user to access the stored text data via a web portal or a mobile app. This allows a user to automatically convert the contents of a call into text, efficiently obtain and store summaries, and easily search and view them later.

[0100] The "collection means" is a device or system that has the function of acquiring voice data during a call.

[0101] The "conversion means" is a device or system that includes a voice recognition engine for converting collected voice data into text data.

[0102] The "summarization means" is a device or system that includes a summarization engine for analyzing the converted text data, extracting important points, and generating a summary.

[0103] The "storage means" is a device or system that has the function of storing the generated summary in a database and adding metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0104] "Access means" means a device or system that allows users to access stored text data through a web portal or mobile app.

[0105] A "speech recognition engine" is software or algorithms for analyzing voice data and converting it into corresponding text data.

[0106] A "summary engine" is software or an algorithm that extracts important information from input text data and generates a summary.

[0107] "Metadata" is auxiliary information such as the date and time of the call, the call recipient, and the duration of the call, which is associated with the call data.

[0108] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0109] System configuration

[0110] 1. Collection Method

[0111] During a call, the device collects audio data through the microphone. This data is collected in real time using a calling application or call management software and sent to a server. Specifically, audio data is acquired using the microphone input of the calling application and sent to the server via an API using an HTTP POST request.

[0112] 2. Conversion Method

[0113] The server receives the voice data sent from the device and passes it to a voice recognition engine. Commercial voice recognition engines such as Google Cloud Speech-to-Text and IBM Watson Speech to Text can be used. The server saves the received voice data and calls the voice recognition engine's API to send a request to convert the voice data into text data.

[0114] 3. Summary tools

[0115] The server passes the converted text data to a summarization engine. For example, OpenAI's GPT-3 can be used as a summarization engine. To pass the received text data to the summarization engine, an API request is generated and a summary request is sent. The summarization engine receives the text data, generates a summary using its internal natural language processing algorithm, and returns the result to the server.

[0116] 4. Preservation means

[0117] The server stores the generated summary in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The generated summary data is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query.

[0118] 5. Access

[0119] After a call ends, users can access the saved summary data through a web portal or mobile app. Users can easily search the summary data to quickly check the key points of the call. Users submit a search query through the UI, and the server retrieves the required summary data from the database and displays it on the web portal or mobile app.

[0120] Specific examples

[0121] For example, consider a scenario where a salesperson is talking to a customer, explaining product details and discussing the purchase process. This conversation is collected as voice data by the device and sent to a server using Google Cloud Speech-to-Text. A speech recognition engine such as GPT-3 then converts this data into text data, and a summarization engine extracts key points and generates a summary. The server then stores the generated summary in a database, allowing the salesperson to easily review it later.

[0122] Prompt Sentence Examples

[0123] Here is an example prompt for using GPT-3 to generate a curated summary:

[0124] Prompt: "Summarize the following text: 'We discussed the progress of the project. We identified next steps.'"

[0125] Sample output: "Check project progress and next steps"

[0126] The above is an embodiment of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, greatly improving business efficiency.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1:

[0129] The user starts a call. Voice data (call content) is generated as input. The device starts collecting voice data in real time via the microphone as soon as the call starts. Specifically, the voice data is acquired using the microphone input of the call application. The voice data collected in real time is generated as output. This voice data is encrypted and sent to the server.

[0130] Step 2:

[0131] The server receives the voice data sent from the device. As input, encrypted voice data is sent to the server. The server prepares this voice data to be passed to the speech recognition engine. Specifically, the server decrypts the received data and formats it for the speech recognition engine's API request. As output, formatted data is generated to be passed to the speech recognition engine.

[0132] Step 3:

[0133] The speech recognition engine analyzes the speech data and converts it into corresponding text data. The speech data passed to the speech recognition engine is used as input. Specifically, it analyzes the speech input and runs an algorithm to convert the speech waveform into text. As output, converted text data is generated and returned to the server. For example, speech saying "Report on project progress" is converted into text data saying "Report on project progress."

[0134] Step 4:

[0135] The server receives the converted text data and passes it to the summarization engine. The text data returned by the speech recognition engine is used as input. Specifically, the server reformats the received data for the summarization engine's API request. As output, formatted text data is generated to be passed to the summarization engine.

[0136] Step 5:

[0137] The summarization engine analyzes the text data, extracts key points, and generates a summary. As input, it uses formatted text data received from the server. Specifically, it uses natural language processing algorithms to analyze the text data and generate a summary. As output, it generates summarized text data and returns it to the server. For example, a summary such as "Conversation with a client about the progress of a project" is generated.

[0138] Step 6:

[0139] The server receives the generated summaries and stores them in a database. The input is the summary data returned by the summarization engine. Specifically, metadata such as the call date and time, call recipient, and call duration are added to the generated summary data, and it is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query. The output is the summary data stored in the database.

[0140] Step 7:

[0141] After the call ends, the user accesses the stored summary data through a web portal or mobile app. As input, the user submits a search query. Specifically, the server retrieves the required summary data from the database and displays the specified summary data on the web portal or mobile app. As output, the summary data is generated in a format that can be viewed by the user.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] The current food delivery industry lacks a way to accurately record phone calls between delivery staff and customers and quickly confirm important points. This makes it difficult to accurately confirm order details and delivery details, resulting in lower customer satisfaction and a deterioration in work efficiency. Furthermore, the enormous amount of time required to confirm phone call details places a heavy burden on staff. A system that can solve these problems is needed.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for saving the summarized text data together with metadata, and an access means for allowing delivery staff or managers to access the saved summary text data via a smartphone application. This enables automatic recording of call content and summarization of important points, allowing for quick confirmation of the content of calls with customers. As a result, improved business efficiency and customer satisfaction can be expected.

[0147] The "collection means" is a means for collecting voice data during a call, and uses the terminal's microphone or a collection application.

[0148] The "conversion means" is a means for converting collected voice data into text data using a voice recognition engine.

[0149] A "voice recognition engine" is software or hardware that analyzes voice data and converts it into corresponding text data.

[0150] The "summarization means" is a means for generating a summary from the converted text data using a summarization engine.

[0151] A "summary engine" is software that analyzes text data, extracts important points, and generates summaries.

[0152] The "storage means" is a means for storing summarized text data together with metadata, and uses a storage system such as a database.

[0153] "Access means" refers to the means by which delivery staff and managers can access and check the stored summary text data through a smartphone application.

[0154] "Delivery staff" refers to staff in charge of food delivery services, who confirm the delivery address of orders and deliver them.

[0155] A "smartphone application" is software that runs on a smartphone and is a program designed to provide specific functions.

[0156] "Metadata" is data that includes additional information such as the date and time of a call and the person who called, and is information that makes it easier to manage and search the main data.

[0157] This invention is a system designed for the food delivery industry, which includes the following means for automatically transcribing and summarizing phone call content. The system's main components are a smartphone, a server, a speech recognition engine, a summarization engine, a database, and a mobile application.

[0158] Collection Method

[0159] The delivery staff starts a call with the customer using their smartphone. During the call, voice data is collected through the smartphone's microphone. The voice data is sent to the server in real time.

[0160] Conversion Method

[0161] The server sends the received voice data to a speech recognition engine, such as the Google Speech-to-Text API, which analyzes the voice data and converts it into corresponding text data.

[0162] Summary tools

[0163] The server then sends the converted text data to a summarization engine, which could be a generative AI model such as OpenAI GPT-4. The summarization engine analyzes the text data, extracts key points, and generates a summary.

[0164] Preservation means

[0165] The server stores the summarized text data in a database, along with metadata such as the call date and time and the call recipient. A database system such as SQLite can be used to store the data.

[0166] Access

[0167] Delivery staff and managers can access the saved summary text data through a smartphone application, which provides an interface that allows users to easily search and view the saved summary data.

[0168] Specific examples

[0169] For example, if a delivery staff member is making a delivery to "1-2-3, Chiyoda-ku, Tokyo," they will confirm the address over the phone with the customer. The contents of the call are collected by the smartphone and sent to a server. A voice recognition engine converts the text into "1-2-3, Chiyoda-ku, Tokyo," and a summarization engine summarizes it as "Please confirm the delivery address again." This data is stored in a database, and can be checked later by the delivery staff member.

[0170] Examples of prompts for generative AI models include:

[0171] "Please summarize the following text: 'Yamamoto-san, can you confirm the address again?' 'Yes, it's 1-2-3, Chiyoda-ku, Tokyo.'"

[0172] This system makes it possible to automatically record call content and summarize key points, which is expected to improve operational efficiency and customer satisfaction.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] A user initiates a call. Specifically, a delivery staff member uses a smartphone to call a customer and initiates a call. The input is the delivery staff member's call initiation action, and the output is the smartphone's microphone collecting voice data.

[0176] Step 2:

[0177] The device sends the collected voice data to the server in real time. The voice data obtained through the smartphone microphone is uploaded to the server in real time. The input is the collected voice data, and the output is the voice data being stored on the server.

[0178] Step 3:

[0179] The server sends the received voice data to a speech recognition engine. The server passes the voice data to a speech recognition engine such as the Google Speech-to-Text API. The input is the voice data stored on the server, and the output is the text data generated by the speech recognition engine.

[0180] Step 4:

[0181] The server sends the text data generated by the speech recognition engine to a summarization engine, such as OpenAI GPT-4, which creates a summary. The input is the text data obtained from the speech recognition engine, and the output is the summary data generated by the summarization engine.

[0182] Step 5:

[0183] The server stores the generated summary data together with metadata in a database, such as SQLite, along with metadata such as the call date and time, the call recipients, etc. The input is the summary data and associated metadata, and the output is the entries stored in the database.

[0184] Step 6:

[0185] Users access the stored summary data through a smartphone application. Delivery staff and managers can use the app's interface to retrieve and review the summary data from the database. The input is the user's search request, and the output is a display of the summary data for the search query.

[0186] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0187] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0188] System configuration

[0189] 1. Collection Method

[0190] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0191] 2. Conversion Method

[0192] The server receives the voice data sent from the device and passes it to a voice recognition engine, which analyzes the voice data and converts it into corresponding text data.

[0193] 3. Summary tools

[0194] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts key points, and generates a summary.

[0195] 4. Emotion recognition means

[0196] The server recognizes the user's emotion by passing the voice data to an emotion engine, which analyzes the tone and pitch of the voice data to identify the user's emotion.

[0197] 5. Preservation means

[0198] The server stores the summary data and the recognized emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration.

[0199] 6. Access

[0200] Users can access the saved summary data and sentiment information after the call ends through a web portal or mobile app. Users can easily search the saved summary and sentiment information and quickly check key points and changes in sentiment.

[0201] Program processing explanation

[0202] The program processing of this system will be explained in natural language below.

[0203] Audio data collection

[0204] 1. Users

[0205] A call begins, for example, a salesperson discusses product details with a customer.

[0206] 2. Terminal

[0207] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0208] Voice data recognition and conversion

[0209] 3. Server

[0210] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0211] 4. Speech Recognition Engine

[0212] The collected voice data is analyzed and the content is converted into text. For example, the speech "What functions does this product have?" is converted into text.

[0213] Text data summarization and emotion recognition

[0214] 5. Server

[0215] Receives text data and passes it to a summarization engine.

[0216] 6. Summarization Engine

[0217] Analyzes text data and generates summaries, such as "Question about product features."

[0218] 7. Server

[0219] Voice data is passed to the emotion engine to recognize emotions.

[0220] 8. Emotion Engine

[0221] It analyzes the tone and pitch of the voice to identify the user's emotions, generating emotional information such as "excited" or "calm."

[0222] Storing and accessing summary data and emotional information

[0223] 9. Server

[0224] The generated summary and sentiment information are stored in a database, along with metadata such as the call date and time, call recipient, and call duration.

[0225] 10. Users

[0226] After the call ends, users can access and review the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly review key points and sentiment at the time.

[0227] Specific examples

[0228] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. During the call, a microphone collects voice data in real time and sends it to a server. A speech recognition engine converts the voice data into text, and a summarization engine extracts key points and generates a summary. Furthermore, an emotion engine identifies the user's emotion from the voice, generating a summary and emotional information such as "Conversation about project progress, excited." The server then stores this data in a database, allowing users to easily review the summary and emotional information later. For example, a project manager can later understand the emotions expressed by team members when they speak, which can be used as a reference for making better decisions.

[0229] The above is a specific implementation of the "system for automatically converting phone call content into text, summarizing, and recognizing emotions." This system allows users to efficiently check and record phone call content and emotional information, significantly improving business efficiency and the quality of communication.

[0230] The processing flow will be explained below.

[0231] Step 1:

[0232] A user initiates a call, for example, a project manager calling a team member to request a project status update.

[0233] Step 2:

[0234] When a call starts, the device collects voice data through the microphone and transmits the collected voice data to the server in real time.

[0235] Step 3:

[0236] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0237] Step 4:

[0238] The speech recognition engine analyzes the voice data and converts the content into text. For example, a voice saying "Please tell me about the progress of the project" is converted into text data such as "Please tell me about the progress of the project."

[0239] Step 5:

[0240] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0241] Step 6:

[0242] The summarization engine analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into a summary called "Project progress and next steps."

[0243] Step 7:

[0244] The server passes the same voice data to the emotion engine, which analyzes the voice data and recognizes the user's emotion.

[0245] Step 8:

[0246] The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, for example, if the voice is upbeat it will be recognized as "excited."

[0247] Step 9:

[0248] The server stores the generated summary and the recognized emotion information in a database, including metadata such as the call date and time, call recipient, and call duration.

[0249] Step 10:

[0250] After the call ends, users can access the saved summary data and sentiment information through a web portal or mobile app. Users can easily search the saved summary and sentiment information to identify key points and changes in sentiment.

[0251] Step 11:

[0252] The user can then decide on the next action based on the stored summary and sentiment information. For example, a project manager can adjust the content and progress of the next meeting by taking into account the sentiment of team members.

[0253] Through this series of steps, the call content is automatically transcribed into text and a summary and emotional information are saved, allowing users to quickly check the necessary information and emotional situation later.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] In today's business environment, the speed of information exchange via telephone calls is important. However, manually recording and analyzing call content is time-consuming and labor-intensive. Therefore, there is a need for a system that can automatically convert call content into text, summarize it, and recognize and record user emotions. The existence of such a system can improve business efficiency and the quality of communication.

[0257] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0258] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary of the converted text data using a summarization engine, an emotion recognition means for analyzing the voice data using an emotion engine to generate emotion information, a storage means for saving the summarized text data and emotion information, and an access means for allowing a user to access the saved text data and emotion information. This allows the content of the call and emotion information to be efficiently checked and recorded, significantly improving business efficiency and the quality of communication.

[0259] The "collection means" refers to a device or function for collecting voice data during a call.

[0260] "Conversion means" refers to a process or device that converts collected voice data into text data using a voice recognition engine.

[0261] The "summarization means" refers to a process or device that generates a summary from the converted text data using a summarization engine.

[0262] "Emotion recognition means" refers to a process or device that analyzes voice data using an emotion engine and generates user emotion information.

[0263] "Storage means" refers to a process or device for storing summarized text data and emotion information.

[0264] "Access means" refers to the means or interface by which a user can access the stored text data and emotion information.

[0265] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0266] System configuration

[0267] 1. Collection Method

[0268] During a call, the device collects audio data through a microphone. This data is collected in real time using a phone application or call management software and sent to a server. For example, the device uses the microphone on a smartphone or PC.

[0269] 2. Conversion Method

[0270] The server receives the voice data sent from the device and passes it to a voice recognition engine, which uses a speech recognition API from, for example, Google or IBM, to analyze the voice data and convert it into corresponding text data.

[0271] 3. Summary tools

[0272] The server passes the converted text data to a summarization engine, which uses a generative AI model to analyze the text data, extract key points, and generate a summary.

[0273] 4. Emotion recognition means

[0274] The server passes the voice data to an emotion engine to recognize the user's emotion. The emotion engine uses an emotion analysis model to analyze the tone and pitch of the voice data and identify the user's emotion.

[0275] 5. Preservation means

[0276] The server stores the generated summary and emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The database can be, for example, MySQL or PostgreSQL.

[0277] 6. Access

[0278] After the call, users can access the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly check key points and sentiment changes. Frameworks such as React and Flutter are used to develop the web portal and mobile app.

[0279] Specific examples

[0280] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. The device collects voice data in real time through the microphone and sends it to a server. The server passes the voice data to a speech recognition engine, which converts it into text. The server then passes the text data to a summarization engine, which extracts key points and generates a summary. The server also passes the voice data to an emotion engine to identify the user's emotion. The generated summary and emotion information, such as "Conversation about the project's progress, excited," are then stored in a database by the server. Users can then access this data through a web portal or mobile app and easily review the summary and emotion information later. For example, a project manager can later understand the emotions expressed by team members and use this information to make better decisions.

[0281] An example of a specific prompt using a generative AI model might be: "Please summarize the contents of the call. I will provide the audio data. Please extract the key points and summarize. Also, please analyze the emotional information and indicate changes in emotion."

[0282] This system allows users to efficiently check and record call content and emotional information, significantly improving business efficiency and communication quality.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1:

[0285] The user initiates a call.

[0286] Specific operation: A user launches a calling application and starts a call with a caller. For example, a salesperson may be discussing product details with a customer.

[0287] Step 2:

[0288] The device collects the audio data.

[0289] Input: User's call audio

[0290] Specific operation: The device uses the built-in microphone to collect call audio in real time, and the collected audio data is stored in a buffer via call management software.

[0291] Output: Real-time collected audio data

[0292] Step 3:

[0293] The terminal transmits the voice data to the server.

[0294] Input: Collected audio data

[0295] Specific operation: The terminal transmits the collected voice data to the server via the network. During this transmission process, the voice data is divided into packets and streamed over the network in real time.

[0296] Output: Audio data sent to the server

[0297] Step 4:

[0298] The server receives the voice data and passes it to the voice recognition engine.

[0299] Input: Audio data sent from the device

[0300] Specific operation: The server checks the received voice data and converts it into the input format of the voice recognition engine. The converted voice data is then passed to the voice recognition engine.

[0301] Output: Voice data input to the voice recognition engine

[0302] Step 5:

[0303] A voice recognition engine converts the voice data into text data.

[0304] Input: Audio data passed to the speech recognition engine

[0305] How it works: The speech recognition engine analyzes the speech data and converts it into corresponding text using a language model. For example, it analyzes and converts the speech "What features does this product have?"

[0306] Output: Converted text data

[0307] Step 6:

[0308] The server passes the text data to the summarization engine.

[0309] Input: Text data converted by the speech recognition engine

[0310] Specific operation: The server converts the text data into a format suitable for the summarization engine and passes it to the summarization engine.

[0311] Output: Text data input to the summarization engine

[0312] Step 7:

[0313] A summarization engine summarizes the text data.

[0314] Input: Text data passed to the summarization engine

[0315] How it works: The summarization engine uses a generative AI model to analyze text data, extract key points, and generate summaries, such as "Question about product features."

[0316] Output: Generated summary data

[0317] Step 8:

[0318] The server passes the voice data to the emotion engine to recognize the emotion.

[0319] Input: Audio data sent to the server

[0320] Specific operation: The server converts the voice data into a format suitable for the emotion engine and passes it to the emotion engine.

[0321] Output: Voice data input to the emotion engine

[0322] Step 9:

[0323] The emotion engine analyzes the voice data and generates emotion information.

[0324] Input: Audio data passed to the emotion engine

[0325] Specific operation: The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, generating emotion information such as "excited" or "calm."

[0326] Output: Generated emotion information

[0327] Step 10:

[0328] The server stores the summary data and emotion information in a database.

[0329] Input: Generated summary data and sentiment information

[0330] Specific operation: The server stores the generated summary data and emotion information, as well as metadata such as the call date and time, call recipient, and call duration, in a database.

[0331] Output: Summary data and sentiment information stored in a database

[0332] Step 11:

[0333] Users access the stored summary data and emotion information through a web portal or mobile app.

[0334] Input: Summary data and emotion information stored in a database

[0335] What it does: Users use a web portal or mobile app to search and view the data they need, allowing them to see key points and associated sentiment information.

[0336] Output: Summary data and emotion information displayed on the user screen

[0337] (Application example 2)

[0338] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0339] Modern content distribution services require the ability to identify key points in each scene of a video being viewed by a user and recognize the emotions present in that scene. This information can improve the user's viewing experience and be useful for better content recommendations and individual viewing history management. However, current technology does not provide a system that can process this information automatically, requiring a significant amount of manual work and time. To solve this problem, a system is needed that can efficiently collect audio data during viewing and automate speech recognition, summary generation, and emotion recognition.

[0340] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting audio data being viewed, a conversion means for converting the collected audio data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, an emotion recognition means for recognizing and identifying emotions from the audio data, a storage means for saving the summarized text data and the identified emotion information, and an access means for allowing the user to access the saved text data and emotion information. This makes it possible for the user to grasp important scenes in the video work they are viewing and recognize the emotions they were feeling at the time.

[0341] The "collection means" is a device or program that has the function of collecting audio data during viewing.

[0342] The "conversion means" refers to a device or program that has the function of converting collected voice data into text data using a voice recognition engine.

[0343] The "summarization means" refers to a device or program that has the function of generating a summary from the converted text data using a summary engine.

[0344] "Emotion recognition means" refers to a device or program that has the function of recognizing and identifying emotions from voice data.

[0345] The "storage means" refers to a device or program that has the function of storing the summarized text data and the identified emotion information.

[0346] The "access means" refers to a device or program that has the function of allowing a user to access the stored text data and emotion information.

[0347] This invention is a system that provides an excellent viewing experience by collecting audio data during viewing and automating speech recognition, summary generation, and emotion recognition. To implement this system, collection means, conversion means, summarization means, emotion recognition means, storage means, and access means are required.

[0348] System configuration

[0349] 1. Collection Method

[0350] The device collects audio data through a microphone while listening to the content (this can be a smartphone, smart glasses, or other device capable of collecting audio data), and transmits the collected audio data to a server in real time.

[0351] 2. Conversion Method

[0352] The server receives the voice data sent from the device and passes it to a speech recognition engine (e.g., Google Cloud Speech-to-Text API), which analyzes the voice data and converts it into corresponding text data.

[0353] 3. Summary tools

[0354] The server passes the converted text data to a summarization engine (e.g., OpenAI GPT-3 model), which analyzes the text data, extracts key points, and generates a summary.

[0355] 4. Emotion recognition means

[0356] The server passes the voice data to an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion.

[0357] 5. Preservation means

[0358] The server stores the generated summary and emotion information in a database (e.g., Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information.

[0359] 6. Access

[0360] After watching, users can access the saved summary data and emotion information through a smartphone app or smart glasses. Users can easily search the saved summary and emotion information and quickly check important points and changes in emotion.

[0361] Specific examples

[0362] For example, consider a case where a user is watching a drama and a moving conversation takes place in the scene. Audio data from that scene is collected through a microphone and sent to a server. A speech recognition engine converts the audio data into text data, and a summarization engine extracts important points and generates a summary. Furthermore, an emotion engine recognizes the user's emotions from the voice and generates emotional information such as "I am moved." This data is then stored in a database by the server, allowing the user to later check the summary and emotional information.

[0363] Generative AI model and example prompts

[0364] For example, the following prompt can be used to generate a summary:

[0365] Summarize the following text:

[0366] "The time I spent with my family was truly precious. I couldn't have come this far without everyone's support over the past year. I want to express my heartfelt gratitude."

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] The user starts the content they are viewing. The device (such as a smartphone or smart glasses) collects audio data. The audio data is collected in real time via a microphone and sent to the server. The input data is the audio data, which is then sent to the server as audio data.

[0370] Step 2:

[0371] The server passes the voice data received from the device to the voice recognition engine (Google Cloud Speech-to-Text API). The voice recognition engine analyzes the voice data and converts it into corresponding text data. The input data is voice data, and the output data is text data.

[0372] Step 3:

[0373] The server passes the converted text data to a summarization engine (OpenAI GPT-3 model). The summarization engine analyzes the text data, extracts key points, and generates a summary. The input data is text data, and the output data is the summarized text. Specifically, the summary is generated by giving the prompt, "Please summarize the following text."

[0374] Step 4:

[0375] The server passes the voice data to the emotion engine (Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion. The input data is voice data, and the output data is emotional information.

[0376] Step 5:

[0377] The server stores the generated summary and emotion information in a database (Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information. The input data is the summarized text and emotion information, and the output data is the data stored in the database.

[0378] Step 6:

[0379] After watching, the user accesses the database using a smartphone app or smart glasses to check the saved summary data and emotional information. The input data is the user's request, and the output data is the displayed summary and emotional information.

[0380] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0383] [Second embodiment]

[0384] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0385] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0390] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0391] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0393] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0396] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0397] System configuration

[0398] 1. Collection Method

[0399] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0400] 2. Conversion Method

[0401] The server receives the voice data sent from the device and passes it to a voice recognition engine. The voice recognition engine analyzes the voice data and converts it into corresponding text data. For example, voice data such as "We talked about the progress of the project" is converted into text data such as "We talked about the progress of the project."

[0402] 3. Summary tools

[0403] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into the summary "Confirmed the project progress and next steps."

[0404] 4. Preservation means

[0405] The server stores the generated summary in a database, along with metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0406] 5. Access

[0407] Users can access the saved summaries after the call via a web portal or mobile app, and can easily search through saved summaries to quickly review key points.

[0408] Program processing explanation

[0409] The program processing of this system will be explained in natural language below.

[0410] Audio data collection

[0411] 1. Users

[0412] Initiate a call, for example, call a colleague for a business meeting.

[0413] 2. Terminal

[0414] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0415] Voice data recognition and conversion

[0416] 3. Server

[0417] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0418] 4. Speech Recognition Engine

[0419] The collected voice data is analyzed and converted into appropriate text data. For example, a voice saying "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0420] Summarizing text data

[0421] 5. Server

[0422] Receives text data and passes it to a summarization engine.

[0423] 6. Summarization Engine

[0424] It analyzes text data and generates summaries, such as "a conversation with a client about the progress of a project."

[0425] Storing and Accessing Summary Data

[0426] 7. Server

[0427] The generated summary is stored in a database, and the stored summary data includes the call date and time, the call recipient, and the call duration.

[0428] 8. Users

[0429] After the call ends, users can access and review the saved summary data through the web portal or mobile app. Users can easily search the summary data and quickly review key points of the call.

[0430] Specific examples

[0431] For example, consider a scenario in which a salesperson is talking to a customer, explaining product details and discussing the purchase procedure. The conversation during the call is collected as voice data by the device and sent to a server. A speech recognition engine converts this into text data, and a summarization engine extracts important points and generates a summary. The server then stores the summarized data in a database, allowing the salesperson to easily check the summary later.

[0432] The above is a specific example of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, significantly improving business efficiency.

[0433] The processing flow will be explained below.

[0434] Step 1:

[0435] A user initiates a call, for example, calling a colleague for a business meeting.

[0436] Step 2:

[0437] When a call starts, the device collects audio data through the microphone and transmits the collected audio data to the server in real time.

[0438] Step 3:

[0439] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0440] Step 4:

[0441] The speech recognition engine analyzes the voice data and converts the content into text. For example, the speech "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0442] Step 5:

[0443] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0444] Step 6:

[0445] The summarization engine analyzes the text data, extracts key points, and generates a summary, such as "a conversation about the progress of a project."

[0446] Step 7:

[0447] The server stores the generated summary in a database, along with metadata such as the date and time of the call, who the call was with, and the duration of the call.

[0448] Step 8:

[0449] After the call ends, the user accesses the stored summary data through a web portal or mobile app.

[0450] Step 9:

[0451] Users can easily search through the saved summary data to see key points from the call, such as "We reported on the progress of the project and discussed next steps."

[0452] Through this series of steps, the conversation is automatically transcribed, summarized, and saved, allowing users to quickly check the information they need later.

[0453] Example 1

[0454] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0455] In modern business communications, it is important to efficiently understand and record the contents of phone calls. However, manually transcribing and summarizing phone call content is time-consuming and labor-intensive, and important points can often be overlooked. Furthermore, there are few systems that properly store this information and make it easily accessible later. This creates challenges in efficiently managing and utilizing call content.

[0456] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0457] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for adding metadata including the call date and time, the call recipient, and the call duration to the generated summary and storing the resulting summary in a database, and an access means for allowing a user to access the stored text data via a web portal or a mobile app. This allows a user to automatically convert the contents of a call into text, efficiently obtain and store summaries, and easily search and view them later.

[0458] The "collection means" is a device or system that has the function of acquiring voice data during a call.

[0459] The "conversion means" is a device or system that includes a voice recognition engine for converting collected voice data into text data.

[0460] The "summarization means" is a device or system that includes a summarization engine for analyzing the converted text data, extracting important points, and generating a summary.

[0461] The "storage means" is a device or system that has the function of storing the generated summary in a database and adding metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0462] "Access means" means a device or system that allows users to access stored text data through a web portal or mobile app.

[0463] A "speech recognition engine" is software or algorithms for analyzing voice data and converting it into corresponding text data.

[0464] A "summary engine" is software or an algorithm that extracts important information from input text data and generates a summary.

[0465] "Metadata" is auxiliary information such as the date and time of the call, the call recipient, and the duration of the call, which is associated with the call data.

[0466] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0467] System configuration

[0468] 1. Collection Method

[0469] During a call, the device collects audio data through the microphone. This data is collected in real time using a calling application or call management software and sent to a server. Specifically, audio data is acquired using the microphone input of the calling application and sent to the server via an API using an HTTP POST request.

[0470] 2. Conversion Method

[0471] The server receives the voice data sent from the device and passes it to a voice recognition engine. Commercial voice recognition engines such as Google Cloud Speech-to-Text and IBM Watson Speech to Text can be used. The server saves the received voice data and calls the voice recognition engine's API to send a request to convert the voice data into text data.

[0472] 3. Summary tools

[0473] The server passes the converted text data to a summarization engine. For example, OpenAI's GPT-3 can be used as a summarization engine. To pass the received text data to the summarization engine, an API request is generated and a summary request is sent. The summarization engine receives the text data, generates a summary using its internal natural language processing algorithm, and returns the result to the server.

[0474] 4. Preservation means

[0475] The server stores the generated summary in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The generated summary data is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query.

[0476] 5. Access

[0477] After a call ends, users can access the saved summary data through a web portal or mobile app. Users can easily search the summary data to quickly check the key points of the call. Users submit a search query through the UI, and the server retrieves the required summary data from the database and displays it on the web portal or mobile app.

[0478] Specific examples

[0479] For example, consider a scenario where a salesperson is talking to a customer, explaining product details and discussing the purchase process. This conversation is collected as voice data by the device and sent to a server using Google Cloud Speech-to-Text. A speech recognition engine such as GPT-3 then converts this data into text data, and a summarization engine extracts key points and generates a summary. The server then stores the generated summary in a database, allowing the salesperson to easily review it later.

[0480] Prompt Sentence Examples

[0481] Here is an example prompt for using GPT-3 to generate a curated summary:

[0482] Prompt: "Summarize the following text: 'We discussed the progress of the project. We identified next steps.'"

[0483] Sample output: "Check project progress and next steps"

[0484] The above is an embodiment of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, greatly improving business efficiency.

[0485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0486] Step 1:

[0487] The user starts a call. Voice data (call content) is generated as input. The device starts collecting voice data in real time via the microphone as soon as the call starts. Specifically, the voice data is acquired using the microphone input of the call application. The voice data collected in real time is generated as output. This voice data is encrypted and sent to the server.

[0488] Step 2:

[0489] The server receives the voice data sent from the device. As input, encrypted voice data is sent to the server. The server prepares this voice data to be passed to the speech recognition engine. Specifically, the server decrypts the received data and formats it for the speech recognition engine's API request. As output, formatted data is generated to be passed to the speech recognition engine.

[0490] Step 3:

[0491] The speech recognition engine analyzes the speech data and converts it into corresponding text data. The speech data passed to the speech recognition engine is used as input. Specifically, it analyzes the speech input and runs an algorithm to convert the speech waveform into text. As output, converted text data is generated and returned to the server. For example, speech saying "Report on project progress" is converted into text data saying "Report on project progress."

[0492] Step 4:

[0493] The server receives the converted text data and passes it to the summarization engine. The text data returned by the speech recognition engine is used as input. Specifically, the server reformats the received data for the summarization engine's API request. As output, formatted text data is generated to be passed to the summarization engine.

[0494] Step 5:

[0495] The summarization engine analyzes the text data, extracts key points, and generates a summary. As input, it uses formatted text data received from the server. Specifically, it uses natural language processing algorithms to analyze the text data and generate a summary. As output, it generates summarized text data and returns it to the server. For example, a summary such as "Conversation with a client about the progress of a project" is generated.

[0496] Step 6:

[0497] The server receives the generated summaries and stores them in a database. The input is the summary data returned by the summarization engine. Specifically, metadata such as the call date and time, call recipient, and call duration are added to the generated summary data, and it is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query. The output is the summary data stored in the database.

[0498] Step 7:

[0499] After the call ends, the user accesses the stored summary data through a web portal or mobile app. As input, the user submits a search query. Specifically, the server retrieves the required summary data from the database and displays the specified summary data on the web portal or mobile app. As output, the summary data is generated in a format that can be viewed by the user.

[0500] (Application example 1)

[0501] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0502] The current food delivery industry lacks a way to accurately record phone calls between delivery staff and customers and quickly confirm important points. This makes it difficult to accurately confirm order details and delivery details, resulting in lower customer satisfaction and a deterioration in work efficiency. Furthermore, the enormous amount of time required to confirm phone call details places a heavy burden on staff. A system that can solve these problems is needed.

[0503] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0504] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for saving the summarized text data together with metadata, and an access means for allowing delivery staff or managers to access the saved summary text data via a smartphone application. This enables automatic recording of call content and summarization of important points, allowing for quick confirmation of the content of calls with customers. As a result, improved business efficiency and customer satisfaction can be expected.

[0505] The "collection means" is a means for collecting voice data during a call, and uses the terminal's microphone or a collection application.

[0506] The "conversion means" is a means for converting collected voice data into text data using a voice recognition engine.

[0507] A "voice recognition engine" is software or hardware that analyzes voice data and converts it into corresponding text data.

[0508] The "summarization means" is a means for generating a summary from the converted text data using a summarization engine.

[0509] A "summary engine" is software that analyzes text data, extracts important points, and generates summaries.

[0510] The "storage means" is a means for storing summarized text data together with metadata, and uses a storage system such as a database.

[0511] "Access means" refers to the means by which delivery staff and managers can access and check the stored summary text data through a smartphone application.

[0512] "Delivery staff" refers to staff in charge of food delivery services, who confirm the delivery address of orders and deliver them.

[0513] A "smartphone application" is software that runs on a smartphone and is a program designed to provide specific functions.

[0514] "Metadata" is data that includes additional information such as the date and time of a call and the person who called, and is information that makes it easier to manage and search the main data.

[0515] This invention is a system designed for the food delivery industry, which includes the following means for automatically transcribing and summarizing phone call content. The system's main components are a smartphone, a server, a speech recognition engine, a summarization engine, a database, and a mobile application.

[0516] Collection Method

[0517] The delivery staff starts a call with the customer using their smartphone. During the call, voice data is collected through the smartphone's microphone. The voice data is sent to the server in real time.

[0518] Conversion Method

[0519] The server sends the received voice data to a speech recognition engine, such as the Google Speech-to-Text API, which analyzes the voice data and converts it into corresponding text data.

[0520] Summary tools

[0521] The server then sends the converted text data to a summarization engine, which could be a generative AI model such as OpenAI GPT-4. The summarization engine analyzes the text data, extracts key points, and generates a summary.

[0522] Preservation means

[0523] The server stores the summarized text data in a database, along with metadata such as the call date and time and the call recipient. A database system such as SQLite can be used to store the data.

[0524] Access

[0525] Delivery staff and managers can access the saved summary text data through a smartphone application, which provides an interface that allows users to easily search and view the saved summary data.

[0526] Specific examples

[0527] For example, if a delivery staff member is making a delivery to "1-2-3, Chiyoda-ku, Tokyo," they will confirm the address over the phone with the customer. The contents of the call are collected by the smartphone and sent to a server. A voice recognition engine converts the text into "1-2-3, Chiyoda-ku, Tokyo," and a summarization engine summarizes it as "Please confirm the delivery address again." This data is stored in a database, and can be checked later by the delivery staff member.

[0528] Examples of prompts for generative AI models include:

[0529] "Please summarize the following text: 'Yamamoto-san, can you confirm the address again?' 'Yes, it's 1-2-3, Chiyoda-ku, Tokyo.'"

[0530] This system makes it possible to automatically record call content and summarize key points, which is expected to improve operational efficiency and customer satisfaction.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] A user initiates a call. Specifically, a delivery staff member uses a smartphone to call a customer and initiates a call. The input is the delivery staff member's call initiation action, and the output is the smartphone's microphone collecting voice data.

[0534] Step 2:

[0535] The device sends the collected voice data to the server in real time. The voice data obtained through the smartphone microphone is uploaded to the server in real time. The input is the collected voice data, and the output is the voice data being stored on the server.

[0536] Step 3:

[0537] The server sends the received voice data to a speech recognition engine. The server passes the voice data to a speech recognition engine such as the Google Speech-to-Text API. The input is the voice data stored on the server, and the output is the text data generated by the speech recognition engine.

[0538] Step 4:

[0539] The server sends the text data generated by the speech recognition engine to a summarization engine, such as OpenAI GPT-4, which creates a summary. The input is the text data obtained from the speech recognition engine, and the output is the summary data generated by the summarization engine.

[0540] Step 5:

[0541] The server stores the generated summary data together with metadata in a database, such as SQLite, along with metadata such as the call date and time, the call recipients, etc. The input is the summary data and associated metadata, and the output is the entries stored in the database.

[0542] Step 6:

[0543] Users access the stored summary data through a smartphone application. Delivery staff and managers can use the app's interface to retrieve and review the summary data from the database. The input is the user's search request, and the output is a display of the summary data for the search query.

[0544] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0545] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0546] System configuration

[0547] 1. Collection Method

[0548] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0549] 2. Conversion Method

[0550] The server receives the voice data sent from the device and passes it to a voice recognition engine, which analyzes the voice data and converts it into corresponding text data.

[0551] 3. Summary tools

[0552] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts key points, and generates a summary.

[0553] 4. Emotion recognition means

[0554] The server recognizes the user's emotion by passing the voice data to an emotion engine, which analyzes the tone and pitch of the voice data to identify the user's emotion.

[0555] 5. Preservation means

[0556] The server stores the summary data and the recognized emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration.

[0557] 6. Access

[0558] Users can access the saved summary data and sentiment information after the call ends through a web portal or mobile app. Users can easily search the saved summary and sentiment information and quickly check key points and changes in sentiment.

[0559] Program processing explanation

[0560] The program processing of this system will be explained in natural language below.

[0561] Audio data collection

[0562] 1. Users

[0563] A call begins, for example, a salesperson discusses product details with a customer.

[0564] 2. Terminal

[0565] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0566] Voice data recognition and conversion

[0567] 3. Server

[0568] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0569] 4. Speech Recognition Engine

[0570] The collected voice data is analyzed and the content is converted into text. For example, the speech "What functions does this product have?" is converted into text.

[0571] Text data summarization and emotion recognition

[0572] 5. Server

[0573] Receives text data and passes it to a summarization engine.

[0574] 6. Summarization Engine

[0575] Analyzes text data and generates summaries, such as "Question about product features."

[0576] 7. Server

[0577] Voice data is passed to the emotion engine to recognize emotions.

[0578] 8. Emotion Engine

[0579] It analyzes the tone and pitch of the voice to identify the user's emotions, generating emotional information such as "excited" or "calm."

[0580] Storing and accessing summary data and emotional information

[0581] 9. Server

[0582] The generated summary and sentiment information are stored in a database, along with metadata such as the call date and time, call recipient, and call duration.

[0583] 10. Users

[0584] After the call ends, users can access and review the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly review key points and sentiment at the time.

[0585] Specific examples

[0586] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. During the call, a microphone collects voice data in real time and sends it to a server. A speech recognition engine converts the voice data into text, and a summarization engine extracts key points and generates a summary. Furthermore, an emotion engine identifies the user's emotion from the voice, generating a summary and emotional information such as "Conversation about project progress, excited." The server then stores this data in a database, allowing users to easily review the summary and emotional information later. For example, a project manager can later understand the emotions expressed by team members when they speak, which can be used as a reference for making better decisions.

[0587] The above is a specific implementation of the "system for automatically converting phone call content into text, summarizing, and recognizing emotions." This system allows users to efficiently check and record phone call content and emotional information, significantly improving business efficiency and the quality of communication.

[0588] The processing flow will be explained below.

[0589] Step 1:

[0590] A user initiates a call, for example, a project manager calling a team member to request a project status update.

[0591] Step 2:

[0592] When a call starts, the device collects voice data through the microphone and transmits the collected voice data to the server in real time.

[0593] Step 3:

[0594] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0595] Step 4:

[0596] The speech recognition engine analyzes the voice data and converts the content into text. For example, a voice saying "Please tell me about the progress of the project" is converted into text data such as "Please tell me about the progress of the project."

[0597] Step 5:

[0598] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0599] Step 6:

[0600] The summarization engine analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into a summary called "Project progress and next steps."

[0601] Step 7:

[0602] The server passes the same voice data to the emotion engine, which analyzes the voice data and recognizes the user's emotion.

[0603] Step 8:

[0604] The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, for example, if the voice is upbeat it will be recognized as "excited."

[0605] Step 9:

[0606] The server stores the generated summary and the recognized emotion information in a database, including metadata such as the call date and time, call recipient, and call duration.

[0607] Step 10:

[0608] After the call ends, users can access the saved summary data and sentiment information through a web portal or mobile app. Users can easily search the saved summary and sentiment information to identify key points and changes in sentiment.

[0609] Step 11:

[0610] The user can then decide on the next action based on the stored summary and sentiment information. For example, a project manager can adjust the content and progress of the next meeting by taking into account the sentiment of team members.

[0611] Through this series of steps, the call content is automatically transcribed into text and a summary and emotional information are saved, allowing users to quickly check the necessary information and emotional situation later.

[0612] Example 2

[0613] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0614] In today's business environment, the speed of information exchange via telephone calls is important. However, manually recording and analyzing call content is time-consuming and labor-intensive. Therefore, there is a need for a system that can automatically convert call content into text, summarize it, and recognize and record user emotions. The existence of such a system can improve business efficiency and the quality of communication.

[0615] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0616] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary of the converted text data using a summarization engine, an emotion recognition means for analyzing the voice data using an emotion engine to generate emotion information, a storage means for saving the summarized text data and emotion information, and an access means for allowing a user to access the saved text data and emotion information. This allows the content of the call and emotion information to be efficiently checked and recorded, significantly improving business efficiency and the quality of communication.

[0617] The "collection means" refers to a device or function for collecting voice data during a call.

[0618] "Conversion means" refers to a process or device that converts collected voice data into text data using a voice recognition engine.

[0619] The "summarization means" refers to a process or device that generates a summary from the converted text data using a summarization engine.

[0620] "Emotion recognition means" refers to a process or device that analyzes voice data using an emotion engine and generates user emotion information.

[0621] "Storage means" refers to a process or device for storing summarized text data and emotion information.

[0622] "Access means" refers to the means or interface by which a user can access the stored text data and emotion information.

[0623] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0624] System configuration

[0625] 1. Collection Method

[0626] During a call, the device collects audio data through a microphone. This data is collected in real time using a phone application or call management software and sent to a server. For example, the device uses the microphone on a smartphone or PC.

[0627] 2. Conversion Method

[0628] The server receives the voice data sent from the device and passes it to a voice recognition engine, which uses a speech recognition API from, for example, Google or IBM, to analyze the voice data and convert it into corresponding text data.

[0629] 3. Summary tools

[0630] The server passes the converted text data to a summarization engine, which uses a generative AI model to analyze the text data, extract key points, and generate a summary.

[0631] 4. Emotion recognition means

[0632] The server passes the voice data to an emotion engine to recognize the user's emotion. The emotion engine uses an emotion analysis model to analyze the tone and pitch of the voice data and identify the user's emotion.

[0633] 5. Preservation means

[0634] The server stores the generated summary and emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The database can be, for example, MySQL or PostgreSQL.

[0635] 6. Access

[0636] After the call, users can access the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly check key points and sentiment changes. Frameworks such as React and Flutter are used to develop the web portal and mobile app.

[0637] Specific examples

[0638] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. The device collects voice data in real time through the microphone and sends it to a server. The server passes the voice data to a speech recognition engine, which converts it into text. The server then passes the text data to a summarization engine, which extracts key points and generates a summary. The server also passes the voice data to an emotion engine to identify the user's emotion. The generated summary and emotion information, such as "Conversation about the project's progress, excited," are then stored in a database by the server. Users can then access this data through a web portal or mobile app and easily review the summary and emotion information later. For example, a project manager can later understand the emotions expressed by team members and use this information to make better decisions.

[0639] An example of a specific prompt using a generative AI model might be: "Please summarize the contents of the call. I will provide the audio data. Please extract the key points and summarize. Also, please analyze the emotional information and indicate changes in emotion."

[0640] This system allows users to efficiently check and record call content and emotional information, significantly improving business efficiency and communication quality.

[0641] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0642] Step 1:

[0643] The user initiates a call.

[0644] Specific operation: A user launches a calling application and starts a call with a caller. For example, a salesperson may be discussing product details with a customer.

[0645] Step 2:

[0646] The device collects the audio data.

[0647] Input: User's call audio

[0648] Specific operation: The device uses the built-in microphone to collect call audio in real time, and the collected audio data is stored in a buffer via call management software.

[0649] Output: Real-time collected audio data

[0650] Step 3:

[0651] The terminal transmits the voice data to the server.

[0652] Input: Collected audio data

[0653] Specific operation: The terminal transmits the collected voice data to the server via the network. During this transmission process, the voice data is divided into packets and streamed over the network in real time.

[0654] Output: Audio data sent to the server

[0655] Step 4:

[0656] The server receives the voice data and passes it to the voice recognition engine.

[0657] Input: Audio data sent from the device

[0658] Specific operation: The server checks the received voice data and converts it into the input format of the voice recognition engine. The converted voice data is then passed to the voice recognition engine.

[0659] Output: Voice data input to the voice recognition engine

[0660] Step 5:

[0661] A voice recognition engine converts the voice data into text data.

[0662] Input: Audio data passed to the speech recognition engine

[0663] How it works: The speech recognition engine analyzes the speech data and converts it into corresponding text using a language model. For example, it analyzes and converts the speech "What features does this product have?"

[0664] Output: Converted text data

[0665] Step 6:

[0666] The server passes the text data to the summarization engine.

[0667] Input: Text data converted by the speech recognition engine

[0668] Specific operation: The server converts the text data into a format suitable for the summarization engine and passes it to the summarization engine.

[0669] Output: Text data input to the summarization engine

[0670] Step 7:

[0671] A summarization engine summarizes the text data.

[0672] Input: Text data passed to the summarization engine

[0673] How it works: The summarization engine uses a generative AI model to analyze text data, extract key points, and generate summaries, such as "Question about product features."

[0674] Output: Generated summary data

[0675] Step 8:

[0676] The server passes the voice data to the emotion engine to recognize the emotion.

[0677] Input: Audio data sent to the server

[0678] Specific operation: The server converts the voice data into a format suitable for the emotion engine and passes it to the emotion engine.

[0679] Output: Voice data input to the emotion engine

[0680] Step 9:

[0681] The emotion engine analyzes the voice data and generates emotion information.

[0682] Input: Audio data passed to the emotion engine

[0683] Specific operation: The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, generating emotion information such as "excited" or "calm."

[0684] Output: Generated emotion information

[0685] Step 10:

[0686] The server stores the summary data and emotion information in a database.

[0687] Input: Generated summary data and sentiment information

[0688] Specific operation: The server stores the generated summary data and emotion information, as well as metadata such as the call date and time, call recipient, and call duration, in a database.

[0689] Output: Summary data and sentiment information stored in a database

[0690] Step 11:

[0691] Users access the stored summary data and emotion information through a web portal or mobile app.

[0692] Input: Summary data and emotion information stored in a database

[0693] What it does: Users use a web portal or mobile app to search and view the data they need, allowing them to see key points and associated sentiment information.

[0694] Output: Summary data and emotion information displayed on the user screen

[0695] (Application example 2)

[0696] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0697] Modern content distribution services require the ability to identify key points in each scene of a video being viewed by a user and recognize the emotions present in that scene. This information can improve the user's viewing experience and be useful for better content recommendations and individual viewing history management. However, current technology does not provide a system that can process this information automatically, requiring a significant amount of manual work and time. To solve this problem, a system is needed that can efficiently collect audio data during viewing and automate speech recognition, summary generation, and emotion recognition.

[0698] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting audio data being viewed, a conversion means for converting the collected audio data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, an emotion recognition means for recognizing and identifying emotions from the audio data, a storage means for saving the summarized text data and the identified emotion information, and an access means for allowing the user to access the saved text data and emotion information. This makes it possible for the user to grasp important scenes in the video work they are viewing and recognize the emotions they were feeling at the time.

[0699] The "collection means" is a device or program that has the function of collecting audio data during viewing.

[0700] The "conversion means" refers to a device or program that has the function of converting collected voice data into text data using a voice recognition engine.

[0701] The "summarization means" refers to a device or program that has the function of generating a summary from the converted text data using a summary engine.

[0702] "Emotion recognition means" refers to a device or program that has the function of recognizing and identifying emotions from voice data.

[0703] The "storage means" refers to a device or program that has the function of storing the summarized text data and the identified emotion information.

[0704] The "access means" refers to a device or program that has the function of allowing a user to access the stored text data and emotion information.

[0705] This invention is a system that provides an excellent viewing experience by collecting audio data during viewing and automating speech recognition, summary generation, and emotion recognition. To implement this system, collection means, conversion means, summarization means, emotion recognition means, storage means, and access means are required.

[0706] System configuration

[0707] 1. Collection Method

[0708] The device collects audio data through a microphone while listening to the content (this can be a smartphone, smart glasses, or other device capable of collecting audio data), and transmits the collected audio data to a server in real time.

[0709] 2. Conversion Method

[0710] The server receives the voice data sent from the device and passes it to a speech recognition engine (e.g., Google Cloud Speech-to-Text API), which analyzes the voice data and converts it into corresponding text data.

[0711] 3. Summary tools

[0712] The server passes the converted text data to a summarization engine (e.g., OpenAI GPT-3 model), which analyzes the text data, extracts key points, and generates a summary.

[0713] 4. Emotion recognition means

[0714] The server passes the voice data to an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion.

[0715] 5. Preservation means

[0716] The server stores the generated summary and emotion information in a database (e.g., Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information.

[0717] 6. Access

[0718] After watching, users can access the saved summary data and emotion information through a smartphone app or smart glasses. Users can easily search the saved summary and emotion information and quickly check important points and changes in emotion.

[0719] Specific examples

[0720] For example, consider a case where a user is watching a drama and a moving conversation takes place in the scene. Audio data from that scene is collected through a microphone and sent to a server. A speech recognition engine converts the audio data into text data, and a summarization engine extracts important points and generates a summary. Furthermore, an emotion engine recognizes the user's emotions from the voice and generates emotional information such as "I am moved." This data is then stored in a database by the server, allowing the user to later check the summary and emotional information.

[0721] Generative AI model and example prompts

[0722] For example, the following prompt can be used to generate a summary:

[0723] Summarize the following text:

[0724] "The time I spent with my family was truly precious. I couldn't have come this far without everyone's support over the past year. I want to express my heartfelt gratitude."

[0725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0726] Step 1:

[0727] The user starts the content they are viewing. The device (such as a smartphone or smart glasses) collects audio data. The audio data is collected in real time via a microphone and sent to the server. The input data is the audio data, which is then sent to the server as audio data.

[0728] Step 2:

[0729] The server passes the voice data received from the device to the voice recognition engine (Google Cloud Speech-to-Text API). The voice recognition engine analyzes the voice data and converts it into corresponding text data. The input data is voice data, and the output data is text data.

[0730] Step 3:

[0731] The server passes the converted text data to a summarization engine (OpenAI GPT-3 model). The summarization engine analyzes the text data, extracts key points, and generates a summary. The input data is text data, and the output data is the summarized text. Specifically, the summary is generated by giving the prompt, "Please summarize the following text."

[0732] Step 4:

[0733] The server passes the voice data to the emotion engine (Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion. The input data is voice data, and the output data is emotional information.

[0734] Step 5:

[0735] The server stores the generated summary and emotion information in a database (Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information. The input data is the summarized text and emotion information, and the output data is the data stored in the database.

[0736] Step 6:

[0737] After watching, the user accesses the database using a smartphone app or smart glasses to check the saved summary data and emotional information. The input data is the user's request, and the output data is the displayed summary and emotional information.

[0738] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0739] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0740] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0741] [Third embodiment]

[0742] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0743] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0744] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0745] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0746] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0747] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0748] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0749] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0750] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0751] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0752] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0753] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0754] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0755] System configuration

[0756] 1. Collection Method

[0757] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0758] 2. Conversion Method

[0759] The server receives the voice data sent from the device and passes it to a voice recognition engine. The voice recognition engine analyzes the voice data and converts it into corresponding text data. For example, voice data such as "We talked about the progress of the project" is converted into text data such as "We talked about the progress of the project."

[0760] 3. Summary tools

[0761] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into the summary "Confirmed the project progress and next steps."

[0762] 4. Preservation means

[0763] The server stores the generated summary in a database, along with metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0764] 5. Access

[0765] Users can access the saved summaries after the call via a web portal or mobile app, and can easily search through saved summaries to quickly review key points.

[0766] Program processing explanation

[0767] The program processing of this system will be explained in natural language below.

[0768] Audio data collection

[0769] 1. Users

[0770] Initiate a call, for example, call a colleague for a business meeting.

[0771] 2. Terminal

[0772] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0773] Voice data recognition and conversion

[0774] 3. Server

[0775] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0776] 4. Speech Recognition Engine

[0777] The collected voice data is analyzed and converted into appropriate text data. For example, a voice saying "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0778] Summarizing text data

[0779] 5. Server

[0780] Receives text data and passes it to a summarization engine.

[0781] 6. Summarization Engine

[0782] It analyzes text data and generates summaries, such as "a conversation with a client about the progress of a project."

[0783] Storing and Accessing Summary Data

[0784] 7. Server

[0785] The generated summary is stored in a database, and the stored summary data includes the call date and time, the call recipient, and the call duration.

[0786] 8. Users

[0787] After the call ends, users can access and review the saved summary data through the web portal or mobile app. Users can easily search the summary data and quickly review key points of the call.

[0788] Specific examples

[0789] For example, consider a scenario in which a salesperson is talking to a customer, explaining product details and discussing the purchase procedure. The conversation during the call is collected as voice data by the device and sent to a server. A speech recognition engine converts this into text data, and a summarization engine extracts important points and generates a summary. The server then stores the summarized data in a database, allowing the salesperson to easily check the summary later.

[0790] The above is a specific example of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, significantly improving business efficiency.

[0791] The processing flow will be explained below.

[0792] Step 1:

[0793] A user initiates a call, for example, calling a colleague for a business meeting.

[0794] Step 2:

[0795] When a call starts, the device collects audio data through the microphone and transmits the collected audio data to the server in real time.

[0796] Step 3:

[0797] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0798] Step 4:

[0799] The speech recognition engine analyzes the voice data and converts the content into text. For example, the speech "Report on the progress of the project" is converted into text "Report on the progress of the project."

[0800] Step 5:

[0801] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0802] Step 6:

[0803] The summarization engine analyzes the text data, extracts key points, and generates a summary, such as "a conversation about the progress of a project."

[0804] Step 7:

[0805] The server stores the generated summary in a database, along with metadata such as the date and time of the call, who the call was with, and the duration of the call.

[0806] Step 8:

[0807] After the call ends, the user accesses the stored summary data through a web portal or mobile app.

[0808] Step 9:

[0809] Users can easily search through the saved summary data to see key points from the call, such as "We reported on the progress of the project and discussed next steps."

[0810] Through this series of steps, the conversation is automatically transcribed, summarized, and saved, allowing users to quickly check the information they need later.

[0811] Example 1

[0812] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0813] In modern business communications, it is important to efficiently understand and record the contents of phone calls. However, manually transcribing and summarizing phone call content is time-consuming and labor-intensive, and important points can often be overlooked. Furthermore, there are few systems that properly store this information and make it easily accessible later. This creates challenges in efficiently managing and utilizing call content.

[0814] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0815] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for adding metadata including the call date and time, the call recipient, and the call duration to the generated summary and storing the resulting summary in a database, and an access means for allowing a user to access the stored text data via a web portal or a mobile app. This allows a user to automatically convert the contents of a call into text, efficiently obtain and store summaries, and easily search and view them later.

[0816] The "collection means" is a device or system that has the function of acquiring voice data during a call.

[0817] The "conversion means" is a device or system that includes a voice recognition engine for converting collected voice data into text data.

[0818] The "summarization means" is a device or system that includes a summarization engine for analyzing the converted text data, extracting important points, and generating a summary.

[0819] The "storage means" is a device or system that has the function of storing the generated summary in a database and adding metadata such as the date and time of the call, the call recipient, and the duration of the call.

[0820] "Access means" means a device or system that allows users to access stored text data through a web portal or mobile app.

[0821] A "speech recognition engine" is software or algorithms for analyzing voice data and converting it into corresponding text data.

[0822] A "summary engine" is software or an algorithm that extracts important information from input text data and generates a summary.

[0823] "Metadata" is auxiliary information such as the date and time of the call, the call recipient, and the duration of the call, which is associated with the call data.

[0824] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[0825] System configuration

[0826] 1. Collection Method

[0827] During a call, the device collects audio data through the microphone. This data is collected in real time using a calling application or call management software and sent to a server. Specifically, audio data is acquired using the microphone input of the calling application and sent to the server via an API using an HTTP POST request.

[0828] 2. Conversion Method

[0829] The server receives the voice data sent from the device and passes it to a voice recognition engine. Commercial voice recognition engines such as Google Cloud Speech-to-Text and IBM Watson Speech to Text can be used. The server saves the received voice data and calls the voice recognition engine's API to send a request to convert the voice data into text data.

[0830] 3. Summary tools

[0831] The server passes the converted text data to a summarization engine. For example, OpenAI's GPT-3 can be used as a summarization engine. To pass the received text data to the summarization engine, an API request is generated and a summary request is sent. The summarization engine receives the text data, generates a summary using its internal natural language processing algorithm, and returns the result to the server.

[0832] 4. Preservation means

[0833] The server stores the generated summary in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The generated summary data is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query.

[0834] 5. Access

[0835] After a call ends, users can access the saved summary data through a web portal or mobile app. Users can easily search the summary data to quickly check the key points of the call. Users submit a search query through the UI, and the server retrieves the required summary data from the database and displays it on the web portal or mobile app.

[0836] Specific examples

[0837] For example, consider a scenario where a salesperson is talking to a customer, explaining product details and discussing the purchase process. This conversation is collected as voice data by the device and sent to a server using Google Cloud Speech-to-Text. A speech recognition engine such as GPT-3 then converts this data into text data, and a summarization engine extracts key points and generates a summary. The server then stores the generated summary in a database, allowing the salesperson to easily review it later.

[0838] Prompt Sentence Examples

[0839] Here is an example prompt for using GPT-3 to generate a curated summary:

[0840] Prompt: "Summarize the following text: 'We discussed the progress of the project. We identified next steps.'"

[0841] Sample output: "Check project progress and next steps"

[0842] The above is an embodiment of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, greatly improving business efficiency.

[0843] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0844] Step 1:

[0845] The user starts a call. Voice data (call content) is generated as input. The device starts collecting voice data in real time via the microphone as soon as the call starts. Specifically, the voice data is acquired using the microphone input of the call application. The voice data collected in real time is generated as output. This voice data is encrypted and sent to the server.

[0846] Step 2:

[0847] The server receives the voice data sent from the device. As input, encrypted voice data is sent to the server. The server prepares this voice data to be passed to the speech recognition engine. Specifically, the server decrypts the received data and formats it for the speech recognition engine's API request. As output, formatted data is generated to be passed to the speech recognition engine.

[0848] Step 3:

[0849] The speech recognition engine analyzes the speech data and converts it into corresponding text data. The speech data passed to the speech recognition engine is used as input. Specifically, it analyzes the speech input and runs an algorithm to convert the speech waveform into text. As output, converted text data is generated and returned to the server. For example, speech saying "Report on project progress" is converted into text data saying "Report on project progress."

[0850] Step 4:

[0851] The server receives the converted text data and passes it to the summarization engine. The text data returned by the speech recognition engine is used as input. Specifically, the server reformats the received data for the summarization engine's API request. As output, formatted text data is generated to be passed to the summarization engine.

[0852] Step 5:

[0853] The summarization engine analyzes the text data, extracts key points, and generates a summary. As input, it uses formatted text data received from the server. Specifically, it uses natural language processing algorithms to analyze the text data and generate a summary. As output, it generates summarized text data and returns it to the server. For example, a summary such as "Conversation with a client about the progress of a project" is generated.

[0854] Step 6:

[0855] The server receives the generated summaries and stores them in a database. The input is the summary data returned by the summarization engine. Specifically, metadata such as the call date and time, call recipient, and call duration are added to the generated summary data, and it is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query. The output is the summary data stored in the database.

[0856] Step 7:

[0857] After the call ends, the user accesses the stored summary data through a web portal or mobile app. As input, the user submits a search query. Specifically, the server retrieves the required summary data from the database and displays the specified summary data on the web portal or mobile app. As output, the summary data is generated in a format that can be viewed by the user.

[0858] (Application example 1)

[0859] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0860] The current food delivery industry lacks a way to accurately record phone calls between delivery staff and customers and quickly confirm important points. This makes it difficult to accurately confirm order details and delivery details, resulting in lower customer satisfaction and a deterioration in work efficiency. Furthermore, the enormous amount of time required to confirm phone call details places a heavy burden on staff. A system that can solve these problems is needed.

[0861] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0862] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for saving the summarized text data together with metadata, and an access means for allowing delivery staff or managers to access the saved summary text data via a smartphone application. This enables automatic recording of call content and summarization of important points, allowing for quick confirmation of the content of calls with customers. As a result, improved business efficiency and customer satisfaction can be expected.

[0863] The "collection means" is a means for collecting voice data during a call, and uses the terminal's microphone or a collection application.

[0864] The "conversion means" is a means for converting collected voice data into text data using a voice recognition engine.

[0865] A "voice recognition engine" is software or hardware that analyzes voice data and converts it into corresponding text data.

[0866] The "summarization means" is a means for generating a summary from the converted text data using a summarization engine.

[0867] A "summary engine" is software that analyzes text data, extracts important points, and generates summaries.

[0868] The "storage means" is a means for storing summarized text data together with metadata, and uses a storage system such as a database.

[0869] "Access means" refers to the means by which delivery staff and managers can access and check the stored summary text data through a smartphone application.

[0870] "Delivery staff" refers to staff in charge of food delivery services, who confirm the delivery address of orders and deliver them.

[0871] A "smartphone application" is software that runs on a smartphone and is a program designed to provide specific functions.

[0872] "Metadata" is data that includes additional information such as the date and time of a call and the person who called, and is information that makes it easier to manage and search the main data.

[0873] This invention is a system designed for the food delivery industry, which includes the following means for automatically transcribing and summarizing phone call content. The system's main components are a smartphone, a server, a speech recognition engine, a summarization engine, a database, and a mobile application.

[0874] Collection Method

[0875] The delivery staff starts a call with the customer using their smartphone. During the call, voice data is collected through the smartphone's microphone. The voice data is sent to the server in real time.

[0876] Conversion Method

[0877] The server sends the received voice data to a speech recognition engine, such as the Google Speech-to-Text API, which analyzes the voice data and converts it into corresponding text data.

[0878] Summary tools

[0879] The server then sends the converted text data to a summarization engine, which could be a generative AI model such as OpenAI GPT-4. The summarization engine analyzes the text data, extracts key points, and generates a summary.

[0880] Preservation means

[0881] The server stores the summarized text data in a database, along with metadata such as the call date and time and the call recipient. A database system such as SQLite can be used to store the data.

[0882] Access

[0883] Delivery staff and managers can access the saved summary text data through a smartphone application, which provides an interface that allows users to easily search and view the saved summary data.

[0884] Specific examples

[0885] For example, if a delivery staff member is making a delivery to "1-2-3, Chiyoda-ku, Tokyo," they will confirm the address over the phone with the customer. The contents of the call are collected by the smartphone and sent to a server. A voice recognition engine converts the text into "1-2-3, Chiyoda-ku, Tokyo," and a summarization engine summarizes it as "Please confirm the delivery address again." This data is stored in a database, and can be checked later by the delivery staff member.

[0886] Examples of prompts for generative AI models include:

[0887] "Please summarize the following text: 'Yamamoto-san, can you confirm the address again?' 'Yes, it's 1-2-3, Chiyoda-ku, Tokyo.'"

[0888] This system makes it possible to automatically record call content and summarize key points, which is expected to improve operational efficiency and customer satisfaction.

[0889] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0890] Step 1:

[0891] A user initiates a call. Specifically, a delivery staff member uses a smartphone to call a customer and initiates a call. The input is the delivery staff member's call initiation action, and the output is the smartphone's microphone collecting voice data.

[0892] Step 2:

[0893] The device sends the collected voice data to the server in real time. The voice data obtained through the smartphone microphone is uploaded to the server in real time. The input is the collected voice data, and the output is the voice data being stored on the server.

[0894] Step 3:

[0895] The server sends the received voice data to a speech recognition engine. The server passes the voice data to a speech recognition engine such as the Google Speech-to-Text API. The input is the voice data stored on the server, and the output is the text data generated by the speech recognition engine.

[0896] Step 4:

[0897] The server sends the text data generated by the speech recognition engine to a summarization engine, such as OpenAI GPT-4, which creates a summary. The input is the text data obtained from the speech recognition engine, and the output is the summary data generated by the summarization engine.

[0898] Step 5:

[0899] The server stores the generated summary data together with metadata in a database, such as SQLite, along with metadata such as the call date and time, the call recipients, etc. The input is the summary data and associated metadata, and the output is the entries stored in the database.

[0900] Step 6:

[0901] Users access the stored summary data through a smartphone application. Delivery staff and managers can use the app's interface to retrieve and review the summary data from the database. The input is the user's search request, and the output is a display of the summary data for the search query.

[0902] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0903] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0904] System configuration

[0905] 1. Collection Method

[0906] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[0907] 2. Conversion Method

[0908] The server receives the voice data sent from the device and passes it to a voice recognition engine, which analyzes the voice data and converts it into corresponding text data.

[0909] 3. Summary tools

[0910] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts key points, and generates a summary.

[0911] 4. Emotion recognition means

[0912] The server recognizes the user's emotion by passing the voice data to an emotion engine, which analyzes the tone and pitch of the voice data to identify the user's emotion.

[0913] 5. Preservation means

[0914] The server stores the summary data and the recognized emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration.

[0915] 6. Access

[0916] Users can access the saved summary data and sentiment information after the call ends through a web portal or mobile app. Users can easily search the saved summary and sentiment information and quickly check key points and changes in sentiment.

[0917] Program processing explanation

[0918] The program processing of this system will be explained in natural language below.

[0919] Audio data collection

[0920] 1. Users

[0921] A call begins, for example, a salesperson discusses product details with a customer.

[0922] 2. Terminal

[0923] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[0924] Voice data recognition and conversion

[0925] 3. Server

[0926] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[0927] 4. Speech Recognition Engine

[0928] The collected voice data is analyzed and the content is converted into text. For example, the speech "What functions does this product have?" is converted into text.

[0929] Text data summarization and emotion recognition

[0930] 5. Server

[0931] Receives text data and passes it to a summarization engine.

[0932] 6. Summarization Engine

[0933] Analyzes text data and generates summaries, such as "Question about product features."

[0934] 7. Server

[0935] Voice data is passed to the emotion engine to recognize emotions.

[0936] 8. Emotion Engine

[0937] It analyzes the tone and pitch of the voice to identify the user's emotions, generating emotional information such as "excited" or "calm."

[0938] Storing and accessing summary data and emotional information

[0939] 9. Server

[0940] The generated summary and sentiment information are stored in a database, along with metadata such as the call date and time, call recipient, and call duration.

[0941] 10. Users

[0942] After the call ends, users can access and review the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly review key points and sentiment at the time.

[0943] Specific examples

[0944] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. During the call, a microphone collects voice data in real time and sends it to a server. A speech recognition engine converts the voice data into text, and a summarization engine extracts key points and generates a summary. Furthermore, an emotion engine identifies the user's emotion from the voice, generating a summary and emotional information such as "Conversation about project progress, excited." The server then stores this data in a database, allowing users to easily review the summary and emotional information later. For example, a project manager can later understand the emotions expressed by team members when they speak, which can be used as a reference for making better decisions.

[0945] The above is a specific implementation of the "system for automatically converting phone call content into text, summarizing, and recognizing emotions." This system allows users to efficiently check and record phone call content and emotional information, significantly improving business efficiency and the quality of communication.

[0946] The processing flow will be explained below.

[0947] Step 1:

[0948] A user initiates a call, for example, a project manager calling a team member to request a project status update.

[0949] Step 2:

[0950] When a call starts, the device collects voice data through the microphone and transmits the collected voice data to the server in real time.

[0951] Step 3:

[0952] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[0953] Step 4:

[0954] The speech recognition engine analyzes the voice data and converts the content into text. For example, a voice saying "Please tell me about the progress of the project" is converted into text data such as "Please tell me about the progress of the project."

[0955] Step 5:

[0956] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[0957] Step 6:

[0958] The summarization engine analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into a summary called "Project progress and next steps."

[0959] Step 7:

[0960] The server passes the same voice data to the emotion engine, which analyzes the voice data and recognizes the user's emotion.

[0961] Step 8:

[0962] The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, for example, if the voice is upbeat it will be recognized as "excited."

[0963] Step 9:

[0964] The server stores the generated summary and the recognized emotion information in a database, including metadata such as the call date and time, call recipient, and call duration.

[0965] Step 10:

[0966] After the call ends, users can access the saved summary data and sentiment information through a web portal or mobile app. Users can easily search the saved summary and sentiment information to identify key points and changes in sentiment.

[0967] Step 11:

[0968] The user can then decide on the next action based on the stored summary and sentiment information. For example, a project manager can adjust the content and progress of the next meeting by taking into account the sentiment of team members.

[0969] Through this series of steps, the call content is automatically transcribed into text and a summary and emotional information are saved, allowing users to quickly check the necessary information and emotional situation later.

[0970] Example 2

[0971] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0972] In today's business environment, the speed of information exchange via telephone calls is important. However, manually recording and analyzing call content is time-consuming and labor-intensive. Therefore, there is a need for a system that can automatically convert call content into text, summarize it, and recognize and record user emotions. The existence of such a system can improve business efficiency and the quality of communication.

[0973] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0974] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary of the converted text data using a summarization engine, an emotion recognition means for analyzing the voice data using an emotion engine to generate emotion information, a storage means for saving the summarized text data and emotion information, and an access means for allowing a user to access the saved text data and emotion information. This allows the content of the call and emotion information to be efficiently checked and recorded, significantly improving business efficiency and the quality of communication.

[0975] The "collection means" refers to a device or function for collecting voice data during a call.

[0976] "Conversion means" refers to a process or device that converts collected voice data into text data using a voice recognition engine.

[0977] The "summarization means" refers to a process or device that generates a summary from the converted text data using a summarization engine.

[0978] "Emotion recognition means" refers to a process or device that analyzes voice data using an emotion engine and generates user emotion information.

[0979] "Storage means" refers to a process or device for storing summarized text data and emotion information.

[0980] "Access means" refers to the means or interface by which a user can access the stored text data and emotion information.

[0981] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[0982] System configuration

[0983] 1. Collection Method

[0984] During a call, the device collects audio data through a microphone. This data is collected in real time using a phone application or call management software and sent to a server. For example, the device uses the microphone on a smartphone or PC.

[0985] 2. Conversion Method

[0986] The server receives the voice data sent from the device and passes it to a voice recognition engine, which uses a speech recognition API from, for example, Google or IBM, to analyze the voice data and convert it into corresponding text data.

[0987] 3. Summary tools

[0988] The server passes the converted text data to a summarization engine, which uses a generative AI model to analyze the text data, extract key points, and generate a summary.

[0989] 4. Emotion recognition means

[0990] The server passes the voice data to an emotion engine to recognize the user's emotion. The emotion engine uses an emotion analysis model to analyze the tone and pitch of the voice data and identify the user's emotion.

[0991] 5. Preservation means

[0992] The server stores the generated summary and emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The database can be, for example, MySQL or PostgreSQL.

[0993] 6. Access

[0994] After the call, users can access the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly check key points and sentiment changes. Frameworks such as React and Flutter are used to develop the web portal and mobile app.

[0995] Specific examples

[0996] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. The device collects voice data in real time through the microphone and sends it to a server. The server passes the voice data to a speech recognition engine, which converts it into text. The server then passes the text data to a summarization engine, which extracts key points and generates a summary. The server also passes the voice data to an emotion engine to identify the user's emotion. The generated summary and emotion information, such as "Conversation about the project's progress, excited," are then stored in a database by the server. Users can then access this data through a web portal or mobile app and easily review the summary and emotion information later. For example, a project manager can later understand the emotions expressed by team members and use this information to make better decisions.

[0997] An example of a specific prompt using a generative AI model might be: "Please summarize the contents of the call. I will provide the audio data. Please extract the key points and summarize. Also, please analyze the emotional information and indicate changes in emotion."

[0998] This system allows users to efficiently check and record call content and emotional information, significantly improving business efficiency and communication quality.

[0999] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1000] Step 1:

[1001] The user initiates a call.

[1002] Specific operation: A user launches a calling application and starts a call with a caller. For example, a salesperson may be discussing product details with a customer.

[1003] Step 2:

[1004] The device collects the audio data.

[1005] Input: User's call audio

[1006] Specific operation: The device uses the built-in microphone to collect call audio in real time, and the collected audio data is stored in a buffer via call management software.

[1007] Output: Real-time collected audio data

[1008] Step 3:

[1009] The terminal transmits the voice data to the server.

[1010] Input: Collected audio data

[1011] Specific operation: The terminal transmits the collected voice data to the server via the network. During this transmission process, the voice data is divided into packets and streamed over the network in real time.

[1012] Output: Audio data sent to the server

[1013] Step 4:

[1014] The server receives the voice data and passes it to the voice recognition engine.

[1015] Input: Audio data sent from the device

[1016] Specific operation: The server checks the received voice data and converts it into the input format of the voice recognition engine. The converted voice data is then passed to the voice recognition engine.

[1017] Output: Voice data input to the voice recognition engine

[1018] Step 5:

[1019] A voice recognition engine converts the voice data into text data.

[1020] Input: Audio data passed to the speech recognition engine

[1021] How it works: The speech recognition engine analyzes the speech data and converts it into corresponding text using a language model. For example, it analyzes and converts the speech "What features does this product have?"

[1022] Output: Converted text data

[1023] Step 6:

[1024] The server passes the text data to the summarization engine.

[1025] Input: Text data converted by the speech recognition engine

[1026] Specific operation: The server converts the text data into a format suitable for the summarization engine and passes it to the summarization engine.

[1027] Output: Text data input to the summarization engine

[1028] Step 7:

[1029] A summarization engine summarizes the text data.

[1030] Input: Text data passed to the summarization engine

[1031] How it works: The summarization engine uses a generative AI model to analyze text data, extract key points, and generate summaries, such as "Question about product features."

[1032] Output: Generated summary data

[1033] Step 8:

[1034] The server passes the voice data to the emotion engine to recognize the emotion.

[1035] Input: Audio data sent to the server

[1036] Specific operation: The server converts the voice data into a format suitable for the emotion engine and passes it to the emotion engine.

[1037] Output: Voice data input to the emotion engine

[1038] Step 9:

[1039] The emotion engine analyzes the voice data and generates emotion information.

[1040] Input: Audio data passed to the emotion engine

[1041] Specific operation: The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, generating emotion information such as "excited" or "calm."

[1042] Output: Generated emotion information

[1043] Step 10:

[1044] The server stores the summary data and emotion information in a database.

[1045] Input: Generated summary data and sentiment information

[1046] Specific operation: The server stores the generated summary data and emotion information, as well as metadata such as the call date and time, call recipient, and call duration, in a database.

[1047] Output: Summary data and sentiment information stored in a database

[1048] Step 11:

[1049] Users access the stored summary data and emotion information through a web portal or mobile app.

[1050] Input: Summary data and emotion information stored in a database

[1051] What it does: Users use a web portal or mobile app to search and view the data they need, allowing them to see key points and associated sentiment information.

[1052] Output: Summary data and emotion information displayed on the user screen

[1053] (Application example 2)

[1054] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1055] Modern content distribution services require the ability to identify key points in each scene of a video being viewed by a user and recognize the emotions present in that scene. This information can improve the user's viewing experience and be useful for better content recommendations and individual viewing history management. However, current technology does not provide a system that can process this information automatically, requiring a significant amount of manual work and time. To solve this problem, a system is needed that can efficiently collect audio data during viewing and automate speech recognition, summary generation, and emotion recognition.

[1056] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting audio data being viewed, a conversion means for converting the collected audio data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, an emotion recognition means for recognizing and identifying emotions from the audio data, a storage means for saving the summarized text data and the identified emotion information, and an access means for allowing the user to access the saved text data and emotion information. This makes it possible for the user to grasp important scenes in the video work they are viewing and recognize the emotions they were feeling at the time.

[1057] The "collection means" is a device or program that has the function of collecting audio data during viewing.

[1058] The "conversion means" refers to a device or program that has the function of converting collected voice data into text data using a voice recognition engine.

[1059] The "summarization means" refers to a device or program that has the function of generating a summary from the converted text data using a summary engine.

[1060] "Emotion recognition means" refers to a device or program that has the function of recognizing and identifying emotions from voice data.

[1061] The "storage means" refers to a device or program that has the function of storing the summarized text data and the identified emotion information.

[1062] The "access means" refers to a device or program that has the function of allowing a user to access the stored text data and emotion information.

[1063] This invention is a system that provides an excellent viewing experience by collecting audio data during viewing and automating speech recognition, summary generation, and emotion recognition. To implement this system, collection means, conversion means, summarization means, emotion recognition means, storage means, and access means are required.

[1064] System configuration

[1065] 1. Collection Method

[1066] The device collects audio data through a microphone while listening to the content (this can be a smartphone, smart glasses, or other device capable of collecting audio data), and transmits the collected audio data to a server in real time.

[1067] 2. Conversion Method

[1068] The server receives the voice data sent from the device and passes it to a speech recognition engine (e.g., Google Cloud Speech-to-Text API), which analyzes the voice data and converts it into corresponding text data.

[1069] 3. Summary tools

[1070] The server passes the converted text data to a summarization engine (e.g., OpenAI GPT-3 model), which analyzes the text data, extracts key points, and generates a summary.

[1071] 4. Emotion recognition means

[1072] The server passes the voice data to an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion.

[1073] 5. Preservation means

[1074] The server stores the generated summary and emotion information in a database (e.g., Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information.

[1075] 6. Access

[1076] After watching, users can access the saved summary data and emotion information through a smartphone app or smart glasses. Users can easily search the saved summary and emotion information and quickly check important points and changes in emotion.

[1077] Specific examples

[1078] For example, consider a case where a user is watching a drama and a moving conversation takes place in the scene. Audio data from that scene is collected through a microphone and sent to a server. A speech recognition engine converts the audio data into text data, and a summarization engine extracts important points and generates a summary. Furthermore, an emotion engine recognizes the user's emotions from the voice and generates emotional information such as "I am moved." This data is then stored in a database by the server, allowing the user to later check the summary and emotional information.

[1079] Generative AI model and example prompts

[1080] For example, the following prompt can be used to generate a summary:

[1081] Summarize the following text:

[1082] "The time I spent with my family was truly precious. I couldn't have come this far without everyone's support over the past year. I want to express my heartfelt gratitude."

[1083] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1084] Step 1:

[1085] The user starts the content they are viewing. The device (such as a smartphone or smart glasses) collects audio data. The audio data is collected in real time via a microphone and sent to the server. The input data is the audio data, which is then sent to the server as audio data.

[1086] Step 2:

[1087] The server passes the voice data received from the device to the voice recognition engine (Google Cloud Speech-to-Text API). The voice recognition engine analyzes the voice data and converts it into corresponding text data. The input data is voice data, and the output data is text data.

[1088] Step 3:

[1089] The server passes the converted text data to a summarization engine (OpenAI GPT-3 model). The summarization engine analyzes the text data, extracts key points, and generates a summary. The input data is text data, and the output data is the summarized text. Specifically, the summary is generated by giving the prompt, "Please summarize the following text."

[1090] Step 4:

[1091] The server passes the voice data to the emotion engine (Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion. The input data is voice data, and the output data is emotional information.

[1092] Step 5:

[1093] The server stores the generated summary and emotion information in a database (Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information. The input data is the summarized text and emotion information, and the output data is the data stored in the database.

[1094] Step 6:

[1095] After watching, the user accesses the database using a smartphone app or smart glasses to check the saved summary data and emotional information. The input data is the user's request, and the output data is the displayed summary and emotional information.

[1096] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1097] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1098] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1099] [Fourth embodiment]

[1100] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1101] 7, a 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.

[1102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1103] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1104] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1107] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1108] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1109] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1111] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1112] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1113] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[1114] System configuration

[1115] 1. Collection Method

[1116] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[1117] 2. Conversion Method

[1118] The server receives the voice data sent from the device and passes it to a voice recognition engine. The voice recognition engine analyzes the voice data and converts it into corresponding text data. For example, voice data such as "We talked about the progress of the project" is converted into text data such as "We talked about the progress of the project."

[1119] 3. Summary tools

[1120] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into the summary "Confirmed the project progress and next steps."

[1121] 4. Preservation means

[1122] The server stores the generated summary in a database, along with metadata such as the date and time of the call, the call recipient, and the duration of the call.

[1123] 5. Access

[1124] Users can access the saved summaries after the call via a web portal or mobile app, and can easily search through saved summaries to quickly review key points.

[1125] Program processing explanation

[1126] The program processing of this system will be explained in natural language below.

[1127] Audio data collection

[1128] 1. Users

[1129] Initiate a call, for example, call a colleague for a business meeting.

[1130] 2. Terminal

[1131] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[1132] Voice data recognition and conversion

[1133] 3. Server

[1134] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[1135] 4. Speech Recognition Engine

[1136] The collected voice data is analyzed and converted into appropriate text data. For example, a voice saying "Report on the progress of the project" is converted into text "Report on the progress of the project."

[1137] Summarizing text data

[1138] 5. Server

[1139] Receives text data and passes it to a summarization engine.

[1140] 6. Summarization Engine

[1141] It analyzes text data and generates summaries, such as "a conversation with a client about the progress of a project."

[1142] Storing and Accessing Summary Data

[1143] 7. Server

[1144] The generated summary is stored in a database, and the stored summary data includes the call date and time, the call recipient, and the call duration.

[1145] 8. Users

[1146] After the call ends, users can access and review the saved summary data through the web portal or mobile app. Users can easily search the summary data and quickly review key points of the call.

[1147] Specific examples

[1148] For example, consider a scenario in which a salesperson is talking to a customer, explaining product details and discussing the purchase procedure. The conversation during the call is collected as voice data by the device and sent to a server. A speech recognition engine converts this into text data, and a summarization engine extracts important points and generates a summary. The server then stores the summarized data in a database, allowing the salesperson to easily check the summary later.

[1149] The above is a specific example of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, significantly improving business efficiency.

[1150] The processing flow will be explained below.

[1151] Step 1:

[1152] A user initiates a call, for example, calling a colleague for a business meeting.

[1153] Step 2:

[1154] When a call starts, the device collects audio data through the microphone and transmits the collected audio data to the server in real time.

[1155] Step 3:

[1156] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[1157] Step 4:

[1158] The speech recognition engine analyzes the voice data and converts the content into text. For example, the speech "Report on the progress of the project" is converted into text "Report on the progress of the project."

[1159] Step 5:

[1160] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[1161] Step 6:

[1162] The summarization engine analyzes the text data, extracts key points, and generates a summary, such as "a conversation about the progress of a project."

[1163] Step 7:

[1164] The server stores the generated summary in a database, along with metadata such as the date and time of the call, who the call was with, and the duration of the call.

[1165] Step 8:

[1166] After the call ends, the user accesses the stored summary data through a web portal or mobile app.

[1167] Step 9:

[1168] Users can easily search through the saved summary data to see key points from the call, such as "We reported on the progress of the project and discussed next steps."

[1169] Through this series of steps, the conversation is automatically transcribed, summarized, and saved, allowing users to quickly check the information they need later.

[1170] Example 1

[1171] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1172] In modern business communications, it is important to efficiently understand and record the contents of phone calls. However, manually transcribing and summarizing phone call content is time-consuming and labor-intensive, and important points can often be overlooked. Furthermore, there are few systems that properly store this information and make it easily accessible later. This creates challenges in efficiently managing and utilizing call content.

[1173] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1174] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for adding metadata including the call date and time, the call recipient, and the call duration to the generated summary and storing the resulting summary in a database, and an access means for allowing a user to access the stored text data via a web portal or a mobile app. This allows a user to automatically convert the contents of a call into text, efficiently obtain and store summaries, and easily search and view them later.

[1175] The "collection means" is a device or system that has the function of acquiring voice data during a call.

[1176] The "conversion means" is a device or system that includes a voice recognition engine for converting collected voice data into text data.

[1177] The "summarization means" is a device or system that includes a summarization engine for analyzing the converted text data, extracting important points, and generating a summary.

[1178] The "storage means" is a device or system that has the function of storing the generated summary in a database and adding metadata such as the date and time of the call, the call recipient, and the duration of the call.

[1179] "Access means" means a device or system that allows users to access stored text data through a web portal or mobile app.

[1180] A "speech recognition engine" is software or algorithms for analyzing voice data and converting it into corresponding text data.

[1181] A "summary engine" is software or an algorithm that extracts important information from input text data and generates a summary.

[1182] "Metadata" is auxiliary information such as the date and time of the call, the call recipient, and the duration of the call, which is associated with the call data.

[1183] The present invention relates to a system for automatically transcribing and summarizing telephone conversations. Implementing this system requires the collection of speech data during a call, conversion to text using a speech recognition engine, generation of summaries using a summarization engine, storage of the data, and a means for user access.

[1184] System configuration

[1185] 1. Collection Method

[1186] During a call, the device collects audio data through the microphone. This data is collected in real time using a calling application or call management software and sent to a server. Specifically, audio data is acquired using the microphone input of the calling application and sent to the server via an API using an HTTP POST request.

[1187] 2. Conversion Method

[1188] The server receives the voice data sent from the device and passes it to a voice recognition engine. Commercial voice recognition engines such as Google Cloud Speech-to-Text and IBM Watson Speech to Text can be used. The server saves the received voice data and calls the voice recognition engine's API to send a request to convert the voice data into text data.

[1189] 3. Summary tools

[1190] The server passes the converted text data to a summarization engine. For example, OpenAI's GPT-3 can be used as a summarization engine. To pass the received text data to the summarization engine, an API request is generated and a summary request is sent. The summarization engine receives the text data, generates a summary using its internal natural language processing algorithm, and returns the result to the server.

[1191] 4. Preservation means

[1192] The server stores the generated summary in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The generated summary data is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query.

[1193] 5. Access

[1194] After a call ends, users can access the saved summary data through a web portal or mobile app. Users can easily search the summary data to quickly check the key points of the call. Users submit a search query through the UI, and the server retrieves the required summary data from the database and displays it on the web portal or mobile app.

[1195] Specific examples

[1196] For example, consider a scenario where a salesperson is talking to a customer, explaining product details and discussing the purchase process. This conversation is collected as voice data by the device and sent to a server using Google Cloud Speech-to-Text. A speech recognition engine such as GPT-3 then converts this data into text data, and a summarization engine extracts key points and generates a summary. The server then stores the generated summary in a database, allowing the salesperson to easily review it later.

[1197] Prompt Sentence Examples

[1198] Here is an example prompt for using GPT-3 to generate a curated summary:

[1199] Prompt: "Summarize the following text: 'We discussed the progress of the project. We identified next steps.'"

[1200] Sample output: "Check project progress and next steps"

[1201] The above is an embodiment of the "system that automatically converts phone call content into text and summarizes it." This system allows users to efficiently check and record phone call content, greatly improving business efficiency.

[1202] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1203] Step 1:

[1204] The user starts a call. Voice data (call content) is generated as input. The device starts collecting voice data in real time via the microphone as soon as the call starts. Specifically, the voice data is acquired using the microphone input of the call application. The voice data collected in real time is generated as output. This voice data is encrypted and sent to the server.

[1205] Step 2:

[1206] The server receives the voice data sent from the device. As input, encrypted voice data is sent to the server. The server prepares this voice data to be passed to the speech recognition engine. Specifically, the server decrypts the received data and formats it for the speech recognition engine's API request. As output, formatted data is generated to be passed to the speech recognition engine.

[1207] Step 3:

[1208] The speech recognition engine analyzes the speech data and converts it into corresponding text data. The speech data passed to the speech recognition engine is used as input. Specifically, it analyzes the speech input and runs an algorithm to convert the speech waveform into text. As output, converted text data is generated and returned to the server. For example, speech saying "Report on project progress" is converted into text data saying "Report on project progress."

[1209] Step 4:

[1210] The server receives the converted text data and passes it to the summarization engine. The text data returned by the speech recognition engine is used as input. Specifically, the server reformats the received data for the summarization engine's API request. As output, formatted text data is generated to be passed to the summarization engine.

[1211] Step 5:

[1212] The summarization engine analyzes the text data, extracts key points, and generates a summary. As input, it uses formatted text data received from the server. Specifically, it uses natural language processing algorithms to analyze the text data and generate a summary. As output, it generates summarized text data and returns it to the server. For example, a summary such as "Conversation with a client about the progress of a project" is generated.

[1213] Step 6:

[1214] The server receives the generated summaries and stores them in a database. The input is the summary data returned by the summarization engine. Specifically, metadata such as the call date and time, call recipient, and call duration are added to the generated summary data, and it is saved in a database management system (e.g., MySQL or PostgreSQL) using an INSERT query. The output is the summary data stored in the database.

[1215] Step 7:

[1216] After the call ends, the user accesses the stored summary data through a web portal or mobile app. As input, the user submits a search query. Specifically, the server retrieves the required summary data from the database and displays the specified summary data on the web portal or mobile app. As output, the summary data is generated in a format that can be viewed by the user.

[1217] (Application example 1)

[1218] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1219] The current food delivery industry lacks a way to accurately record phone calls between delivery staff and customers and quickly confirm important points. This makes it difficult to accurately confirm order details and delivery details, resulting in lower customer satisfaction and a deterioration in work efficiency. Furthermore, the enormous amount of time required to confirm phone call details places a heavy burden on staff. A system that can solve these problems is needed.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1221] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, a storage means for saving the summarized text data together with metadata, and an access means for allowing delivery staff or managers to access the saved summary text data via a smartphone application. This enables automatic recording of call content and summarization of important points, allowing for quick confirmation of the content of calls with customers. As a result, improved business efficiency and customer satisfaction can be expected.

[1222] The "collection means" is a means for collecting voice data during a call, and uses the terminal's microphone or a collection application.

[1223] The "conversion means" is a means for converting collected voice data into text data using a voice recognition engine.

[1224] A "voice recognition engine" is software or hardware that analyzes voice data and converts it into corresponding text data.

[1225] The "summarization means" is a means for generating a summary from the converted text data using a summarization engine.

[1226] A "summary engine" is software that analyzes text data, extracts important points, and generates summaries.

[1227] The "storage means" is a means for storing summarized text data together with metadata, and uses a storage system such as a database.

[1228] "Access means" refers to the means by which delivery staff and managers can access and check the stored summary text data through a smartphone application.

[1229] "Delivery staff" refers to staff in charge of food delivery services, who confirm the delivery address of orders and deliver them.

[1230] A "smartphone application" is software that runs on a smartphone and is a program designed to provide specific functions.

[1231] "Metadata" is data that includes additional information such as the date and time of a call and the person who called, and is information that makes it easier to manage and search the main data.

[1232] This invention is a system designed for the food delivery industry, which includes the following means for automatically transcribing and summarizing phone call content. The system's main components are a smartphone, a server, a speech recognition engine, a summarization engine, a database, and a mobile application.

[1233] Collection Method

[1234] The delivery staff starts a call with the customer using their smartphone. During the call, voice data is collected through the smartphone's microphone. The voice data is sent to the server in real time.

[1235] Conversion Method

[1236] The server sends the received voice data to a speech recognition engine, such as the Google Speech-to-Text API, which analyzes the voice data and converts it into corresponding text data.

[1237] Summary tools

[1238] The server then sends the converted text data to a summarization engine, which could be a generative AI model such as OpenAI GPT-4. The summarization engine analyzes the text data, extracts key points, and generates a summary.

[1239] Preservation means

[1240] The server stores the summarized text data in a database, along with metadata such as the call date and time and the call recipient. A database system such as SQLite can be used to store the data.

[1241] Access

[1242] Delivery staff and managers can access the saved summary text data through a smartphone application, which provides an interface that allows users to easily search and view the saved summary data.

[1243] Specific examples

[1244] For example, if a delivery staff member is making a delivery to "1-2-3, Chiyoda-ku, Tokyo," they will confirm the address over the phone with the customer. The contents of the call are collected by the smartphone and sent to a server. A voice recognition engine converts the text into "1-2-3, Chiyoda-ku, Tokyo," and a summarization engine summarizes it as "Please confirm the delivery address again." This data is stored in a database, and can be checked later by the delivery staff member.

[1245] Examples of prompts for generative AI models include:

[1246] "Please summarize the following text: 'Yamamoto-san, can you confirm the address again?' 'Yes, it's 1-2-3, Chiyoda-ku, Tokyo.'"

[1247] This system makes it possible to automatically record call content and summarize key points, which is expected to improve operational efficiency and customer satisfaction.

[1248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1249] Step 1:

[1250] A user initiates a call. Specifically, a delivery staff member uses a smartphone to call a customer and initiates a call. The input is the delivery staff member's call initiation action, and the output is the smartphone's microphone collecting voice data.

[1251] Step 2:

[1252] The device sends the collected voice data to the server in real time. The voice data obtained through the smartphone microphone is uploaded to the server in real time. The input is the collected voice data, and the output is the voice data being stored on the server.

[1253] Step 3:

[1254] The server sends the received voice data to a speech recognition engine. The server passes the voice data to a speech recognition engine such as the Google Speech-to-Text API. The input is the voice data stored on the server, and the output is the text data generated by the speech recognition engine.

[1255] Step 4:

[1256] The server sends the text data generated by the speech recognition engine to a summarization engine, such as OpenAI GPT-4, which creates a summary. The input is the text data obtained from the speech recognition engine, and the output is the summary data generated by the summarization engine.

[1257] Step 5:

[1258] The server stores the generated summary data together with metadata in a database, such as SQLite, along with metadata such as the call date and time, the call recipients, etc. The input is the summary data and associated metadata, and the output is the entries stored in the database.

[1259] Step 6:

[1260] Users access the stored summary data through a smartphone application. Delivery staff and managers can use the app's interface to retrieve and review the summary data from the database. The input is the user's search request, and the output is a display of the summary data for the search query.

[1261] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1262] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[1263] System configuration

[1264] 1. Collection Method

[1265] The device collects audio data through a microphone during a call, and uses a phone application or call management software to collect this data in real time and send it to a server.

[1266] 2. Conversion Method

[1267] The server receives the voice data sent from the device and passes it to a voice recognition engine, which analyzes the voice data and converts it into corresponding text data.

[1268] 3. Summary tools

[1269] The server passes the converted text data to a summarization engine, which analyzes the text data, extracts key points, and generates a summary.

[1270] 4. Emotion recognition means

[1271] The server recognizes the user's emotion by passing the voice data to an emotion engine, which analyzes the tone and pitch of the voice data to identify the user's emotion.

[1272] 5. Preservation means

[1273] The server stores the summary data and the recognized emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration.

[1274] 6. Access

[1275] Users can access the saved summary data and sentiment information after the call ends through a web portal or mobile app. Users can easily search the saved summary and sentiment information and quickly check key points and changes in sentiment.

[1276] Program processing explanation

[1277] The program processing of this system will be explained in natural language below.

[1278] Audio data collection

[1279] 1. Users

[1280] A call begins, for example, a salesperson discusses product details with a customer.

[1281] 2. Terminal

[1282] As soon as the call starts, the device starts collecting voice data through the microphone, and transmits the collected voice data to the server in real time.

[1283] Voice data recognition and conversion

[1284] 3. Server

[1285] The received voice data is passed to the voice recognition engine, which converts the voice data into text data.

[1286] 4. Speech Recognition Engine

[1287] The collected voice data is analyzed and the content is converted into text. For example, the speech "What functions does this product have?" is converted into text.

[1288] Text data summarization and emotion recognition

[1289] 5. Server

[1290] Receives text data and passes it to a summarization engine.

[1291] 6. Summarization Engine

[1292] Analyzes text data and generates summaries, such as "Question about product features."

[1293] 7. Server

[1294] Voice data is passed to the emotion engine to recognize emotions.

[1295] 8. Emotion Engine

[1296] It analyzes the tone and pitch of the voice to identify the user's emotions, generating emotional information such as "excited" or "calm."

[1297] Storing and accessing summary data and emotional information

[1298] 9. Server

[1299] The generated summary and sentiment information are stored in a database, along with metadata such as the call date and time, call recipient, and call duration.

[1300] 10. Users

[1301] After the call ends, users can access and review the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly review key points and sentiment at the time.

[1302] Specific examples

[1303] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. During the call, a microphone collects voice data in real time and sends it to a server. A speech recognition engine converts the voice data into text, and a summarization engine extracts key points and generates a summary. Furthermore, an emotion engine identifies the user's emotion from the voice, generating a summary and emotional information such as "Conversation about project progress, excited." The server then stores this data in a database, allowing users to easily review the summary and emotional information later. For example, a project manager can later understand the emotions expressed by team members when they speak, which can be used as a reference for making better decisions.

[1304] The above is a specific implementation of the "system for automatically converting phone call content into text, summarizing, and recognizing emotions." This system allows users to efficiently check and record phone call content and emotional information, significantly improving business efficiency and the quality of communication.

[1305] The processing flow will be explained below.

[1306] Step 1:

[1307] A user initiates a call, for example, a project manager calling a team member to request a project status update.

[1308] Step 2:

[1309] When a call starts, the device collects voice data through the microphone and transmits the collected voice data to the server in real time.

[1310] Step 3:

[1311] The server sends the received voice data to a voice recognition engine, which converts the voice data into text data.

[1312] Step 4:

[1313] The speech recognition engine analyzes the voice data and converts the content into text. For example, a voice saying "Please tell me about the progress of the project" is converted into text data such as "Please tell me about the progress of the project."

[1314] Step 5:

[1315] The server receives the text data returned from the speech recognition engine and passes it to the summarization engine.

[1316] Step 6:

[1317] The summarization engine analyzes the text data, extracts important points, and generates a summary. For example, the text data "We discussed the progress of the project and confirmed the next steps" is converted into a summary called "Project progress and next steps."

[1318] Step 7:

[1319] The server passes the same voice data to the emotion engine, which analyzes the voice data and recognizes the user's emotion.

[1320] Step 8:

[1321] The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, for example, if the voice is upbeat it will be recognized as "excited."

[1322] Step 9:

[1323] The server stores the generated summary and the recognized emotion information in a database, including metadata such as the call date and time, call recipient, and call duration.

[1324] Step 10:

[1325] After the call ends, users can access the saved summary data and sentiment information through a web portal or mobile app. Users can easily search the saved summary and sentiment information to identify key points and changes in sentiment.

[1326] Step 11:

[1327] The user can then decide on the next action based on the stored summary and sentiment information. For example, a project manager can adjust the content and progress of the next meeting by taking into account the sentiment of team members.

[1328] Through this series of steps, the call content is automatically transcribed into text and a summary and emotional information are saved, allowing users to quickly check the necessary information and emotional situation later.

[1329] Example 2

[1330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1331] In today's business environment, the speed of information exchange via telephone calls is important. However, manually recording and analyzing call content is time-consuming and labor-intensive. Therefore, there is a need for a system that can automatically convert call content into text, summarize it, and recognize and record user emotions. The existence of such a system can improve business efficiency and the quality of communication.

[1332] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1333] In this invention, the server includes a collection means for collecting voice data during a call, a conversion means for converting the collected voice data into text data using a voice recognition engine, a summarization means for generating a summary of the converted text data using a summarization engine, an emotion recognition means for analyzing the voice data using an emotion engine to generate emotion information, a storage means for saving the summarized text data and emotion information, and an access means for allowing a user to access the saved text data and emotion information. This allows the content of the call and emotion information to be efficiently checked and recorded, significantly improving business efficiency and the quality of communication.

[1334] The "collection means" refers to a device or function for collecting voice data during a call.

[1335] "Conversion means" refers to a process or device that converts collected voice data into text data using a voice recognition engine.

[1336] The "summarization means" refers to a process or device that generates a summary from the converted text data using a summarization engine.

[1337] "Emotion recognition means" refers to a process or device that analyzes voice data using an emotion engine and generates user emotion information.

[1338] "Storage means" refers to a process or device for storing summarized text data and emotion information.

[1339] "Access means" refers to the means or interface by which a user can access the stored text data and emotion information.

[1340] This invention relates to a system that automatically converts telephone conversations into text, summarizes them, and recognizes and records user emotions. Implementing this system requires the collection of voice data during a call, text conversion using a speech recognition engine, summary generation using a summarization engine, emotion recognition using an emotion engine, data storage, and a means for user access.

[1341] System configuration

[1342] 1. Collection Method

[1343] During a call, the device collects audio data through a microphone. This data is collected in real time using a phone application or call management software and sent to a server. For example, the device uses the microphone on a smartphone or PC.

[1344] 2. Conversion Method

[1345] The server receives the voice data sent from the device and passes it to a voice recognition engine, which uses a speech recognition API from, for example, Google or IBM, to analyze the voice data and convert it into corresponding text data.

[1346] 3. Summary tools

[1347] The server passes the converted text data to a summarization engine, which uses a generative AI model to analyze the text data, extract key points, and generate a summary.

[1348] 4. Emotion recognition means

[1349] The server passes the voice data to an emotion engine to recognize the user's emotion. The emotion engine uses an emotion analysis model to analyze the tone and pitch of the voice data and identify the user's emotion.

[1350] 5. Preservation means

[1351] The server stores the generated summary and emotion information in a database, along with metadata such as the call date and time, the call recipient, and the call duration. The database can be, for example, MySQL or PostgreSQL.

[1352] 6. Access

[1353] After the call, users can access the saved summary data and sentiment information through a web portal or mobile app, allowing them to quickly check key points and sentiment changes. Frameworks such as React and Flutter are used to develop the web portal and mobile app.

[1354] Specific examples

[1355] For example, consider a scenario where a project manager is talking with a development team. During the call, they discuss the project's progress and next steps. The device collects voice data in real time through the microphone and sends it to a server. The server passes the voice data to a speech recognition engine, which converts it into text. The server then passes the text data to a summarization engine, which extracts key points and generates a summary. The server also passes the voice data to an emotion engine to identify the user's emotion. The generated summary and emotion information, such as "Conversation about the project's progress, excited," are then stored in a database by the server. Users can then access this data through a web portal or mobile app and easily review the summary and emotion information later. For example, a project manager can later understand the emotions expressed by team members and use this information to make better decisions.

[1356] An example of a specific prompt using a generative AI model might be: "Please summarize the contents of the call. I will provide the audio data. Please extract the key points and summarize. Also, please analyze the emotional information and indicate changes in emotion."

[1357] This system allows users to efficiently check and record call content and emotional information, significantly improving business efficiency and communication quality.

[1358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1359] Step 1:

[1360] The user initiates a call.

[1361] Specific operation: A user launches a calling application and starts a call with a caller. For example, a salesperson may be discussing product details with a customer.

[1362] Step 2:

[1363] The device collects the audio data.

[1364] Input: User's call audio

[1365] Specific operation: The device uses the built-in microphone to collect call audio in real time, and the collected audio data is stored in a buffer via call management software.

[1366] Output: Real-time collected audio data

[1367] Step 3:

[1368] The terminal transmits the voice data to the server.

[1369] Input: Collected audio data

[1370] Specific operation: The terminal transmits the collected voice data to the server via the network. During this transmission process, the voice data is divided into packets and streamed over the network in real time.

[1371] Output: Audio data sent to the server

[1372] Step 4:

[1373] The server receives the voice data and passes it to the voice recognition engine.

[1374] Input: Audio data sent from the device

[1375] Specific operation: The server checks the received voice data and converts it into the input format of the voice recognition engine. The converted voice data is then passed to the voice recognition engine.

[1376] Output: Voice data input to the voice recognition engine

[1377] Step 5:

[1378] A voice recognition engine converts the voice data into text data.

[1379] Input: Audio data passed to the speech recognition engine

[1380] How it works: The speech recognition engine analyzes the speech data and converts it into corresponding text using a language model. For example, it analyzes and converts the speech "What features does this product have?"

[1381] Output: Converted text data

[1382] Step 6:

[1383] The server passes the text data to the summarization engine.

[1384] Input: Text data converted by the speech recognition engine

[1385] Specific operation: The server converts the text data into a format suitable for the summarization engine and passes it to the summarization engine.

[1386] Output: Text data input to the summarization engine

[1387] Step 7:

[1388] A summarization engine summarizes the text data.

[1389] Input: Text data passed to the summarization engine

[1390] How it works: The summarization engine uses a generative AI model to analyze text data, extract key points, and generate summaries, such as "Question about product features."

[1391] Output: Generated summary data

[1392] Step 8:

[1393] The server passes the voice data to the emotion engine to recognize the emotion.

[1394] Input: Audio data sent to the server

[1395] Specific operation: The server converts the voice data into a format suitable for the emotion engine and passes it to the emotion engine.

[1396] Output: Voice data input to the emotion engine

[1397] Step 9:

[1398] The emotion engine analyzes the voice data and generates emotion information.

[1399] Input: Audio data passed to the emotion engine

[1400] Specific operation: The emotion engine analyzes the tone and pitch of the voice to identify the user's emotion, generating emotion information such as "excited" or "calm."

[1401] Output: Generated emotion information

[1402] Step 10:

[1403] The server stores the summary data and emotion information in a database.

[1404] Input: Generated summary data and sentiment information

[1405] Specific operation: The server stores the generated summary data and emotion information, as well as metadata such as the call date and time, call recipient, and call duration, in a database.

[1406] Output: Summary data and sentiment information stored in a database

[1407] Step 11:

[1408] Users access the stored summary data and emotion information through a web portal or mobile app.

[1409] Input: Summary data and emotion information stored in a database

[1410] What it does: Users use a web portal or mobile app to search and view the data they need, allowing them to see key points and associated sentiment information.

[1411] Output: Summary data and emotion information displayed on the user screen

[1412] (Application example 2)

[1413] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1414] Modern content distribution services require the ability to identify key points in each scene of a video being viewed by a user and recognize the emotions present in that scene. This information can improve the user's viewing experience and be useful for better content recommendations and individual viewing history management. However, current technology does not provide a system that can process this information automatically, requiring a significant amount of manual work and time. To solve this problem, a system is needed that can efficiently collect audio data during viewing and automate speech recognition, summary generation, and emotion recognition.

[1415] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting audio data being viewed, a conversion means for converting the collected audio data into text data using a voice recognition engine, a summarization means for generating a summary from the converted text data using a summarization engine, an emotion recognition means for recognizing and identifying emotions from the audio data, a storage means for saving the summarized text data and the identified emotion information, and an access means for allowing the user to access the saved text data and emotion information. This makes it possible for the user to grasp important scenes in the video work they are viewing and recognize the emotions they were feeling at the time.

[1416] The "collection means" is a device or program that has the function of collecting audio data during viewing.

[1417] The "conversion means" refers to a device or program that has the function of converting collected voice data into text data using a voice recognition engine.

[1418] The "summarization means" refers to a device or program that has the function of generating a summary from the converted text data using a summary engine.

[1419] "Emotion recognition means" refers to a device or program that has the function of recognizing and identifying emotions from voice data.

[1420] The "storage means" refers to a device or program that has the function of storing the summarized text data and the identified emotion information.

[1421] The "access means" refers to a device or program that has the function of allowing a user to access the stored text data and emotion information.

[1422] This invention is a system that provides an excellent viewing experience by collecting audio data during viewing and automating speech recognition, summary generation, and emotion recognition. To implement this system, collection means, conversion means, summarization means, emotion recognition means, storage means, and access means are required.

[1423] System configuration

[1424] 1. Collection Method

[1425] The device collects audio data through a microphone while listening to the content (this can be a smartphone, smart glasses, or other device capable of collecting audio data), and transmits the collected audio data to a server in real time.

[1426] 2. Conversion Method

[1427] The server receives the voice data sent from the device and passes it to a speech recognition engine (e.g., Google Cloud Speech-to-Text API), which analyzes the voice data and converts it into corresponding text data.

[1428] 3. Summary tools

[1429] The server passes the converted text data to a summarization engine (e.g., OpenAI GPT-3 model), which analyzes the text data, extracts key points, and generates a summary.

[1430] 4. Emotion recognition means

[1431] The server passes the voice data to an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion.

[1432] 5. Preservation means

[1433] The server stores the generated summary and emotion information in a database (e.g., Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information.

[1434] 6. Access

[1435] After watching, users can access the saved summary data and emotion information through a smartphone app or smart glasses. Users can easily search the saved summary and emotion information and quickly check important points and changes in emotion.

[1436] Specific examples

[1437] For example, consider a case where a user is watching a drama and a moving conversation takes place in the scene. Audio data from that scene is collected through a microphone and sent to a server. A speech recognition engine converts the audio data into text data, and a summarization engine extracts important points and generates a summary. Furthermore, an emotion engine recognizes the user's emotions from the voice and generates emotional information such as "I am moved." This data is then stored in a database by the server, allowing the user to later check the summary and emotional information.

[1438] Generative AI model and example prompts

[1439] For example, the following prompt can be used to generate a summary:

[1440] Summarize the following text:

[1441] "The time I spent with my family was truly precious. I couldn't have come this far without everyone's support over the past year. I want to express my heartfelt gratitude."

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] The user starts the content they are viewing. The device (such as a smartphone or smart glasses) collects audio data. The audio data is collected in real time via a microphone and sent to the server. The input data is the audio data, which is then sent to the server as audio data.

[1445] Step 2:

[1446] The server passes the voice data received from the device to the voice recognition engine (Google Cloud Speech-to-Text API). The voice recognition engine analyzes the voice data and converts it into corresponding text data. The input data is voice data, and the output data is text data.

[1447] Step 3:

[1448] The server passes the converted text data to a summarization engine (OpenAI GPT-3 model). The summarization engine analyzes the text data, extracts key points, and generates a summary. The input data is text data, and the output data is the summarized text. Specifically, the summary is generated by giving the prompt, "Please summarize the following text."

[1449] Step 4:

[1450] The server passes the voice data to the emotion engine (Microsoft Azure Emotion API) to recognize the user's emotion. The emotion engine analyzes the tone and pitch of the voice data to identify the user's emotion. The input data is voice data, and the output data is emotional information.

[1451] Step 5:

[1452] The server stores the generated summary and emotion information in a database (Firebase Firestore), along with metadata such as viewing date and time, content type, and scene information. The input data is the summarized text and emotion information, and the output data is the data stored in the database.

[1453] Step 6:

[1454] After watching, the user accesses the database using a smartphone app or smart glasses to check the saved summary data and emotional information. The input data is the user's request, and the output data is the displayed summary and emotional information.

[1455] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1456] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1457] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1458] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1459] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1460] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1461] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1462] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1463] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1464] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1465] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1466] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1467] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1468] 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.

[1469] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1470] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1471] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1472] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1473] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1474] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1475] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1476] The following is further disclosed regarding the above embodiment.

[1477] (Claim 1)

[1478] A collection means for collecting voice data during a call;

[1479] A conversion means for converting the collected voice data into text data using a voice recognition engine;

[1480] a summarization means for generating a summary of the converted text data using a summarization engine;

[1481] a storage means for storing the summarized text data;

[1482] an access means for allowing a user to access the stored text data;

[1483] A system including:

[1484] (Claim 2)

[1485] 10. The system of claim 1, wherein voice data during a call is collected in real time and transmitted to a voice recognition engine.

[1486] (Claim 3)

[1487] 2. The system according to claim 1, wherein the text data converted by the speech recognition engine is analyzed by a summarization engine, and important points are extracted and summarized.

[1488] "Example 1"

[1489] (Claim 1)

[1490] A collection means for collecting voice data during a call;

[1491] A conversion means for converting the collected voice data into text data using a voice recognition engine;

[1492] a summarization means for generating a summary of the converted text data using a summarization engine;

[1493] a storage means for adding metadata including the call date and time, the call recipient, and the call duration to the generated summary and storing the resulting summary in a database;

[1494] A means for users to access the stored text data through a web portal or a mobile app;

[1495] A system including:

[1496] (Claim 2)

[1497] 2. The system according to claim 1, wherein voice data during a call is collected in real time, encrypted, and transmitted to a voice recognition engine.

[1498] (Claim 3)

[1499] 2. The system according to claim 1, wherein the summarization engine analyzes the text data converted by the speech recognition engine using a natural language processing algorithm, extracts important points, and summarizes them.

[1500] "Application Example 1"

[1501] (Claim 1)

[1502] A collection means for collecting voice data during a call;

[1503] A conversion means for converting the collected voice data into text data using a voice recognition engine;

[1504] a summarization means for generating a summary of the converted text data using a summarization engine;

[1505] a storage means for storing the summarized text data together with metadata;

[1506] A means of access for delivery staff and managers to access the stored summary text data through a smartphone application;

[1507] A system including:

[1508] (Claim 2)

[1509] 10. The system of claim 1, wherein voice data during a call is collected in real time and transmitted to a voice recognition engine.

[1510] (Claim 3)

[1511] 2. The system according to claim 1, wherein the text data converted by the speech recognition engine is analyzed by a summarization engine, and important points are extracted and summarized.

[1512] "Example 2: Combining Emotion Engines"

[1513] (Claim 1)

[1514] A collection means for collecting voice data during a call;

[1515] A conversion means for converting the collected voice data into text data using a voice recognition engine;

[1516] a summarization means for generating a summary of the converted text data using a summarization engine;

[1517] emotion recognition means for analyzing voice data using an emotion engine and generating emotion information;

[1518] a storage means for storing the summarized text data and emotion information;

[1519] access means for allowing a user to access the stored text data and emotion information;

[1520] A system including:

[1521] (Claim 2)

[1522] 10. The system of claim 1, wherein voice data during a call is collected in real time and transmitted to a voice recognition engine.

[1523] (Claim 3)

[1524] 2. The system according to claim 1, wherein the text data converted by the speech recognition engine is analyzed by a summarization engine, and important points are extracted and summarized.

[1525] "Application example 2 when combining emotion engines"

[1526] (Claim 1)

[1527] A collection means for collecting voice data during a call;

[1528] A conversion means for converting the collected voice data into text data using a voice recognition engine;

[1529] a summarization means for generating a summary of the converted text data using a summarization engine;

[1530] emotion recognition means for recognizing and identifying emotions from voice data;

[1531] a storage means for storing the summarized text data and the identified emotion information;

[1532] access means for allowing a user to access the stored text data and emotion information;

[1533] A system including:

[1534] (Claim 2)

[1535] 10. The system of claim 1, wherein voice data during a call is collected in real time and transmitted to a voice recognition engine.

[1536] (Claim 3)

[1537] 2. The system according to claim 1, wherein the text data converted by the speech recognition engine is analyzed by a summarization engine, and important points are extracted and summarized. [Explanation of symbols]

[1538] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A collection means for collecting voice data during a call; A conversion means for converting the collected voice data into text data using a voice recognition engine; a summarization means for generating a summary of the converted text data using a summarization engine; a storage means for storing the summarized text data; an access means for allowing a user to access the stored text data; A system including:

2. 2. The system of claim 1, wherein voice data is collected in real time during a call and transmitted to a voice recognition engine.

3. 2. The system according to claim 1, wherein the text data converted by the speech recognition engine is analyzed by a summarization engine, and important points are extracted and summarized.

Images