System

Abstract

To provide a system.SOLUTION: A system includes: first means for acquiring the past approval history and the tendency of an approver from a database storing the past information; second means for generating a first prompt sentence for outputting a draft wording that is highly likely to be approved by the approver on the basis of the acquired past approval history and the acquired tendency of the approver; third means for generating a draft wording by entering the generated first prompt text into a generative AI model; and fourth means for displaying the generated draft wording on a terminal of a business operator.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] In the past, the internal approval drafting process carried out daily by corporate sales staff placed a heavy burden on sales staff and SCs, and it was difficult to create draft text that would satisfy each approver. [Means for solving the problem]

[0005] To solve this problem, we use AI to retrieve information from a database that stores past information and use machine learning to automatically generate draft proposals and contract wording. Furthermore, by presenting the generated draft proposals interactively, we reduce the burden on sales staff and create draft proposals that are satisfactory to each approver. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, there is a database that stores past information. This database includes, for example, information on contracts and proposals made by corporate sales in the past. There is an AI that acquires information from this database and automatically generates draft proposals for the proposal and contract portions using machine learning. This AI is trained using machine learning techniques such as deep learning and reinforcement learning. The generated draft proposals are presented to the salesperson through an interactive interface. This interface is realized in the form of, for example, a chatbot or a voice assistant. "Example 2"

[0029] In another embodiment of the present invention, AI generates draft wording to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform. For example, it significantly reduces the time and effort required for salespeople to draft proposals and contracts.

[0030] "Example 3"

[0031] In a further embodiment of the present invention, AI generates draft text that is expected to be acceptable to the approver. Specifically, AI learns the past approval history and the approver's tendencies, and generates draft text based on that. This makes it possible to provide draft text that is likely to be acceptable to the approver.

[0032] The processing flow of each embodiment will be described below.

[0033] "Example 1"

[0034] Step 1: Obtain the necessary information from a database that stores past information. This information may be information about past contracts or proposals, for example.

[0035] Step 2: Based on the acquired information, machine learning is used to automatically generate draft proposal and contract text. This AI is trained using machine learning techniques such as deep learning and reinforcement learning.

[0036] Step 3: The generated message draft is presented to the salesperson through a conversational interface, which can be realized in the form of a chatbot or voice assistant, for example.

[0037] "Example 2"

[0038] Step 1: AI generates draft message to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform.

[0039] Step 2: For example, it significantly reduces the time and effort required by salespeople to draft proposals and contracts.

[0040] "Example 3"

[0041] Step 1: The AI ​​generates draft text that is expected to be acceptable to the approver. Specifically, the AI ​​learns past approval history and approver tendencies.

[0042] Step 2: Based on this, a draft message is generated, which makes it possible to provide a draft message that is likely to be accepted by the approver.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form 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."

[0045] In traditional corporate sales, the problem was that creating proposals and contracts took a lot of time and effort. It was also difficult for salespeople to efficiently utilize information from past proposals and contracts, which resulted in a decline in the quality of proposals. Furthermore, creating documents that would convince approvers required experience and skill, which placed a significant burden on new salespeople.

[0046] 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.

[0047] In this invention, the server includes means for retrieving information from a database storing past information, means for training a machine learning model using the retrieved information, means for automatically generating draft proposal and contract wording using the trained machine learning model, and means for interactively presenting the generated draft wording. This reduces the burden on sales staff and enables the efficient creation of high-quality proposals and contracts. Furthermore, automatically generating draft wording that satisfies the approver can also expedite the approval process.

[0048] A "database" is a system for storing past information and retrieving that information as needed.

[0049] "Means of obtaining information" refers to the methods and techniques used to extract the necessary information from the database.

[0050] A "machine learning model" is an algorithm or framework that learns from data and performs specific tasks automatically.

[0051] A "training method" is a method or technique for training a machine learning model using data.

[0052] "Automatic proposal generation means" means a method or technology for automatically generating new proposal or contract language using a trained machine learning model.

[0053] The "interactive presentation means" refers to a method or technology for interactively displaying the generated draft text to the user.

[0054] "Salesperson" refers to the person in charge or staff who handles corporate sales.

[0055] "Approver" refers to a person who has the authority to review and approve the contents of a proposal or contract.

[0056] MODE FOR CARRYING OUT THE INVENTION

[0057] The present invention provides a system for improving the efficiency of creating proposals and contracts in corporate sales and reducing the burden on salespeople. A specific embodiment of this system will be described below.

[0058] Retrieving information from a database

[0059] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, dates, and customer information. The server extracts information from the database using an SQL query. For example, by executing the query "SELECT FROM contracts WHERE date > '2020-01-01'", it retrieves contract information from 2020 onwards.

[0060] Training a machine learning model

[0061] The server uses the acquired information to train a machine learning model. This model uses techniques such as deep learning and reinforcement learning. Specifically, it uses the TENSORFLOW (registered trademark) framework. The server cleans and normalizes the data, and trains the model using the preprocessed data. For example, it uses a Long Short-Term Memory (LSTM) network to train a text generation model.

[0062] Automatic generation of draft text

[0063] The server uses the trained LSTM model to automatically generate new proposal and contract wording. When a user enters a prompt such as "Please generate a new proposal," the server inputs this prompt into the model and obtains the generated wording. For example, the generated wording might be "This proposal provides the optimal solution to your company's needs."

[0064] Present to the salesperson

[0065] The generated proposal is presented to the salesperson through a conversational interface. This interface can take the form of a chatbot or voice assistant. The salesperson accesses the chatbot through their device and checks the generated proposal. For example, if the salesperson types into the chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[0066] Examples and prompts

[0067] Suppose a user needs to create a new proposal. The user accesses the system through their device and instructs it to generate a draft proposal based on information from past similar proposals. The server retrieves the past proposal information from the database and generates a new draft proposal using a machine learning model. The generated draft proposal is presented to the user through a chatbot.

[0068] Example prompt sentence:

[0069] "Please generate a draft proposal for a new proposal based on past corporate sales proposal information."

[0070] In this way, users can efficiently create new proposals.

[0071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0072] Step 1:

[0073] The server retrieves information about past contracts and proposals from the database. An SQL query is used as input. For example, execute the query "SELECT FROM contracts WHERE date > '2020-01-01'". This query outputs contract information from 2020 onwards. The server stores the retrieved data in memory.

[0074] Step 2:

[0075] The server preprocesses the acquired data. Raw data acquired from the database is used as input. Preprocessing includes cleaning the data (filling in missing values ​​and removing outliers) and normalizing it (scaling the data). This results in output data in a format suitable for training machine learning models.

[0076] Step 3:

[0077] The server uses the preprocessed data to train a machine learning model. The preprocessed data is used as input. Specifically, it uses the TensorFlow framework to train a Long Short-Term Memory (LSTM) network. The training results in a model that can be used to generate proposal and contract text.

[0078] Step 4:

[0079] The server uses the trained LSTM model to automatically generate draft text for new proposals and contracts. The prompt text entered by the user is used as input. For example, the prompt text may read, "Please generate a new proposal." The server inputs this prompt text into the model and outputs the generated draft text. For example, the generated text may read, "This proposal provides the optimal solution for your company's needs."

[0080] Step 5:

[0081] The server presents the generated proposal to the salesperson through a conversational interface. The generated proposal is used as input. The conversational interface can be realized in the form of a chatbot or a voice assistant. For example, if a salesperson inputs to a chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[0082] (Application example 1)

[0083] Next, a description will be given of Application Example 1 of Embodiment 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."

[0084] In traditional sales activities, salespeople have to manually refer to information on past contracts and proposals to create new proposals and contracts, which takes a lot of time and effort. Furthermore, since the quality of proposals and contracts depends on the experience and skills of the salesperson, it is difficult to maintain a consistent level of quality. Furthermore, there is a need for a way for salespeople to efficiently create proposals while on the go.

[0085] 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.

[0086] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, and means for presenting the generated draft wording to a sales representative via a smartphone. This enables sales representatives to quickly generate high-quality proposal and contract wording based on past data and conduct efficient sales activities even when they are out and about.

[0087] A "database storing past information" is a data storage system that stores information on contracts and proposals made by corporate sales in the past, allowing it to be searched and retrieved as needed.

[0088] "Machine learning" is a technology in which a computer learns patterns and rules from data and uses that knowledge to make predictions and judgments about new data.

[0089] "Artificial intelligence that automatically generates draft proposal and contract wording" is a program that uses machine learning to analyze past data and automatically generate new proposal and contract texts.

[0090] The "interactive presentation means" is an interface that interactively displays the generated draft text to the user, allowing the user to confirm and modify its content.

[0091] "Means of presenting to sales representatives via their smartphones" is a function that displays the generated draft text on the sales representative's smartphone, allowing them to conduct sales activities efficiently even when they are out and about.

[0092] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposals and contractual texts, a means for interactively presenting the generated draft proposals, and a means for presenting the generated draft proposals to sales representatives via their smartphones.

[0093] System configuration

[0094] 1. Database: The server has a database that stores information on contracts and proposals that have been made by the corporate sales department. This database is constructed using a known database management system.

[0095] 2. Artificial Intelligence: The server includes artificial intelligence (AI) that uses machine learning (e.g., OpenAI's GPT-3®) to automatically generate new proposals and contracts based on past data. This AI is implemented using a known programming language.

[0096] 3. Conversational Interface: The generated sales pitch is presented to the salesperson through a conversational interface, which can be in the form of a chatbot or voice assistant.

[0097] 4. Smartphone application: The generated sales pitch is displayed on the salesperson's smartphone. The smartphone application runs on the ANDROID platform, enabling salespeople to efficiently conduct sales activities even on the go.

[0098] Processing flow

[0099] 1. Data Acquisition: The server retrieves past proposals and contracts for a particular client from the database.

[0100] 2. Prompt generation: The server generates prompts to be input into the artificial intelligence based on the past suggestions it has obtained.

[0101] 3. Text generation: AI generates new proposals and contracts based on the generated prompts.

[0102] 4. Presentation of draft text: The draft text is presented to the sales representative through an interactive interface.

[0103] 5. Display on smartphone: The generated sales pitch is displayed on the sales representative's smartphone, allowing the sales representative to conduct sales activities efficiently even when on the go.

[0104] Hardware and software used

[0105] Hardware: Servers, smartphones

[0106] software

[0107] Specific examples

[0108] For example, if the previous recommendation for client ID 123 was "This product is of high quality and offers excellent value for money," the new recommendation generated might be "This product uses the latest technology and is highly reliable."

[0109] Prompt Sentence Examples

[0110] Previous proposal: This product is of high quality and offers excellent value for money. Generate a new proposal:

[0111] In this way, salespeople can easily generate new proposals using their smartphones and make effective proposals to their clients.

[0112] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0113] Step 1:

[0114] The server retrieves past offers and contracts for a specific client from a database. The input is a client ID, and the output is a list of past offers and contracts. Specifically, the server runs an SQL query to extract offers from the database that are associated with the given client ID.

[0115] Step 2:

[0116] The server generates a prompt to be input to the artificial intelligence based on the acquired past suggestions. The input is a list of past suggestions, and the output is a prompt. Specifically, the server combines the past suggestions into one text and creates a prompt with the prefix "Past suggestions: ".

[0117] Step 3:

[0118] The server sends the generated prompt to the AI ​​to generate new proposals or contracts. The input is the prompt, and the output is the generated proposal. Specifically, the server calls the OpenAI GPT-3 API, passing the prompt as input and receiving the generated text.

[0119] Step 4:

[0120] The server presents the generated proposal to the salesperson through a conversational interface. The input is the generated proposal, and the output is an interface that the salesperson can check and modify. Specifically, the server displays the generated proposal in chatbot format, allowing the salesperson to check and modify its contents.

[0121] Step 5:

[0122] The server displays the generated proposal on the sales representative's smartphone. The input is the generated proposal, and the output is the proposal displayed on the smartphone screen. Specifically, the server sends the generated proposal to a smartphone application, allowing the sales representative to check and use the proposal even when they are out and about.

[0123] Example 2

[0124] Next, a description will be given of Example 2 of Form 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."

[0125] Salespeople are required to reduce the time and effort required to draft proposals and contracts, and to work more efficiently. It is also important to maintain a consistent quality in drafts and quickly generate content that satisfies approvers. A system to solve these problems is needed.

[0126] 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.

[0127] In this invention, the server includes a generation AI model that acquires information from a database storing past information and automatically generates draft proposals for the proposal and contract portions using machine learning, a means for generating prompt text based on information entered by the user, and a means for interactively presenting the generated draft proposals, thereby reducing the burden on salespeople and enabling the efficient generation of high-quality draft proposals.

[0128] A "database" is a system for storing past information and retrieving that information as needed.

[0129] "Machine learning" is a technology that allows computers to learn patterns from data and make predictions and classifications.

[0130] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate draft proposals and contract wording.

[0131] A "prompt sentence" is a sentence that gives instructions to a generative AI model based on information entered by the user.

[0132] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[0133] A "salesperson" is a person in charge of the job of drafting proposals and contract texts.

[0134] A "draft" is a draft of the text of a proposal or contract.

[0135] An "approver" is a person who has the authority to review and approve the generated draft text.

[0136] This invention is a system that reduces the burden on salespeople and efficiently generates high-quality proposals and contract drafts. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0137] First, the server has a database that stores past information and retrieves it as needed. The database stores information about past proposals and contracts. The server uses a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) that uses machine learning to automatically generate draft proposal and contract wording.

[0138] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[0139] Customer name: XYZ Co., Ltd.

[0140] Proposal: Proposal for a new marketing strategy

[0141] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[0142] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. For example, it generates the following prompt:

[0143] "Please prepare a proposal for a new marketing strategy for XYZ Corporation. The proposal should include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[0144] The generative AI model receives prompts and generates proposals and contracts with the same quality as a salesperson would produce manually. For example, it generates proposals like this:

[0145] "XYZ Co., Ltd.

[0146] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[0147] Proposal details:

[0148] Introducing new marketing strategies

[0149] Initial cost: 1 million yen

[0150] Monthly fee: 100,000 yen

[0151] We appreciate your consideration.

[0152] Sincerely"

[0153] The generated draft message is sent from the server to the terminal and presented to the user interactively. The user can check the displayed draft message and make corrections as necessary. This reduces the burden on sales staff and enables the efficient generation of high-quality draft messages.

[0154] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0155] Step 1:

[0156] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[0157] Customer name: XYZ Co., Ltd.

[0158] Proposal: Proposal for a new marketing strategy

[0159] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[0160] Input: Customer name, proposal details, contract terms

[0161] Output: Basic information entered by the user

[0162] Step 2:

[0163] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. The server analyzes the entered information and creates an appropriate prompt. For example, the server might generate a prompt such as, "Please prepare a proposal for a new marketing strategy for XYZ Co., Ltd. The proposal must include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[0164] Input: Basic information entered by the user

[0165] Output: Generated prompt statement

[0166] Step 3:

[0167] The server sends the prompt to a generative AI model (e.g., OpenAI's GPT-4) to generate a draft. The generative AI model creates a draft proposal or contract based on the prompt. For example, it might generate a draft like this:

[0168] "XYZ Co., Ltd.

[0169] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[0170] Proposal details:

[0171] Introducing new marketing strategies

[0172] Initial cost: 1 million yen

[0173] Monthly fee: 100,000 yen

[0174] We appreciate your consideration.

[0175] Sincerely"

[0176] Input: Generated prompt text

[0177] Output: Generated text proposal

[0178] Step 4:

[0179] The server transmits the generated draft text to the terminal and presents it to the user interactively. The user can check the displayed draft text and make corrections as necessary. The user can check the draft text on the terminal screen, check for errors in the draft text, and make corrections as necessary.

[0180] Input: Generated text proposal

[0181] Output: Proposal of text presented to the user

[0182] In this way, the server, terminal, and user work in cooperation, reducing the burden on salespeople and enabling efficient generation of high-quality draft text.

[0183] (Application example 2)

[0184] Next, a description will be given of Application Example 2 of Form 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."

[0185] The problem is that salespeople spend a lot of time and effort creating proposals and contracts. Furthermore, communicating with customers and managing the progress of sales activities are also time-consuming, making it difficult to conduct efficient sales activities. There is a need to solve these problems, reduce the burden on salespeople, and realize efficient sales activities.

[0186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0187] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, means for automating communication with customers, means for automatically generating proposals and contracts, means for managing and analyzing customer information, and means for managing the progress of sales activities, which significantly reduces the burden on salespeople and enables more efficient sales activities.

[0188] "Historical information" refers to past data and records related to sales activities.

[0189] A "database" refers to an information management system that stores information systematically and allows it to be searched and retrieved as needed.

[0190] "Machine learning" refers to the technology that allows computers to learn patterns from data and make predictions and classifications.

[0191] "Draft proposal / contract text" refers to a draft proposal or contract that is presented to a customer in sales activities.

[0192] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[0193] "Interactive presentation means" refers to the way in which the user and the system interact with each other to exchange information.

[0194] "Means of automating communication with customers" refers to methods of automating communication with customers, such as email and chat.

[0195] "Means for automatically generating proposals and contracts" refers to a method for automatically creating proposals and contracts required for sales activities.

[0196] "Means for managing and analyzing customer information" refers to methods for organizing and analyzing data about customers.

[0197] "Means for managing the progress of sales activities" refers to methods for tracking and managing the progress of the sales process.

[0198] A system for implementing this invention is configured as follows: A server retrieves information from a database storing past information and uses machine learning to automatically generate draft proposal and contract wording. The generated draft wording is presented to the user interactively. The system also has the function of automating communication with customers and automatically generating proposals and contracts. It also includes the function of managing and analyzing customer information and managing the progress of sales activities.

[0199] Hardware and software used

[0200] Hardware: Servers, user devices (smartphones, PCs, etc.)

[0201] Software: API, database management system (e.g., MySQL (registered trademark))

[0202] Data processing and calculation

[0203] 1. Obtaining information from a database: The server obtains data on past sales activities from a database, including past proposals, contracts, and communication history with customers.

[0204] 2. Generating draft text using machine learning: Based on the acquired data, a machine learning model (e.g., OpenAI's GPT-3) is used to generate draft text for proposals and contracts.

[0205] 3. Interactive presentation: The generated draft text is interactively presented on the user's device, allowing the user to review the draft text and make corrections as necessary.

[0206] 4. Automating communication with customers: The server automates email and chat communication with customers based on the generated text suggestions.

[0207] 5. Automatic generation of proposals and contracts: The server automatically generates formal proposals and contracts based on the generated draft text.

[0208] 6. Management and analysis of customer information: The server organizes and analyzes customer information to improve the efficiency of sales activities.

[0209] 7. Sales Activity Progress Management: The server tracks and manages the progress of the sales process.

[0210] Specific examples

[0211] For example, if the customer name is "ABC Co., Ltd." and the product details are "the latest AI-enabled smartphone," the following prompt sentence would be sent to the generative AI model:

[0212] Prompt Sentence Examples

[0213] Customer Name: ABC Co., Ltd.

[0214] Product details: The latest AI-enabled smartphone

[0215] Please prepare your proposal based on the information below.

[0216] Based on this prompt, the generative AI model generates the text of the proposal, reducing the burden on the salesperson. The generated proposal is then presented interactively to the user's device, allowing the user to review the content and make any necessary revisions.

[0217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0218] Step 1:

[0219] The server retrieves data on past sales activities from a database. The input is past proposals, contracts, communication history with customers, etc. stored in the database. The output is a collection of the retrieved data. This data is used in subsequent processing.

[0220] Step 2:

[0221] The server uses a machine learning model (e.g., OpenAI's GPT-3) based on the acquired data to generate a draft proposal or contract. The input is the data acquired in step 1. The output is the generated draft. Specifically, the server converts the data into a prompt sentence and sends it to the generative AI model.

[0222] Step 3:

[0223] The server interactively presents the generated draft text to the user terminal. The input is the draft text generated in step 2. The output is the draft text displayed on the user terminal. Specifically, the draft text is displayed on the user interface so that the user can check and modify it.

[0224] Step 4:

[0225] The server automates email and chat communications with customers based on the generated message templates. The input is the message template generated in step 2. The output is the email or chat message to be sent to the customer. Specifically, the server converts the message template into email or chat format and automatically sends it.

[0226] Step 5:

[0227] The server automatically generates a formal proposal or contract based on the generated draft text. The input is the draft text generated in step 2. The output is a formal proposal or contract. Specifically, the server formats the draft text into a formal document format and converts it into a format that can be saved and printed.

[0228] Step 6:

[0229] The server organizes and analyzes customer information. The input is customer information stored in a database. The output is the analysis results and organized customer information. Specifically, it organizes customer information by category and applies analytical algorithms to extract useful insights.

[0230] Step 7:

[0231] The server tracks and manages the progress of the sales process. The input is data and progress information about sales activities. The output is a progress report. Specifically, it tracks each stage of sales activities and generates a dashboard to visualize the progress.

[0232] Example 3

[0233] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0234] Conventional message draft generation systems generate message drafts without sufficient consideration of past approval history or approver tendencies, making it difficult to efficiently create message drafts that approvers will agree with. Furthermore, they did not adequately generate message drafts to reduce the burden on sales staff. This resulted in delays in the approval process and reduced work efficiency.

[0235] The specification process by the specification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a means for the user to input a prompt sentence, a means for the terminal to send the prompt sentence to the server, a means for the server to acquire past approval history and approver tendencies from a database, a means for generating a draft text using a generative AI model, a means for sending the generated draft text to the terminal, a means for the terminal to display the draft text to the user, and a means for the user to check the draft text and modify it as necessary. This makes it possible to efficiently generate draft text that takes into account past approval history and approver tendencies, and to provide a draft text that is likely to be acceptable to the approver. Furthermore, it is possible to reduce the burden on sales personnel and improve work efficiency.

[0236] A "database" is a system for storing past information and retrieving that information as needed.

[0237] "Artificial intelligence" refers to a program or system that uses machine learning to automatically generate draft text.

[0238] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[0239] A "prompt sentence" is a text that includes instructions and conditions for generating a sentence proposal, which is input by the user.

[0240] A "terminal" is a device through which a user enters prompt sentences and communicates with a server.

[0241] A "server" is a computer system that retrieves information from a database, generates draft text using a generative AI model, and transmits it to a terminal.

[0242] A "generative AI model" is an artificial intelligence model that learns from past data and generates draft text.

[0243] "Approval history" is data that includes past approval statements and feedback from approvers.

[0244] The "approver tendency" is a pattern based on what kind of text the approver has approved in the past or what kind of feedback the approver has provided.

[0245] A "draft text" is a draft document generated by the generative AI model that is likely to be acceptable to the approver.

[0246] A "user" is a person who enters prompt text and reviews and modifies the generated text suggestions.

[0247] The present invention relates to a system for generating draft wording in consideration of past approval history and the tendencies of approvers. A specific embodiment of this system will be described below.

[0248] First, the user inputs a prompt using a terminal. A prompt is text that includes instructions and conditions for generating a draft. For example, the prompt might say, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to place importance on specific figures and clear objectives."

[0249] The terminal sends the input prompt to the server using a communication protocol such as an HTTP POST request.

[0250] The server accesses the database to retrieve the approval history and approver trends. The database stores past approval statements and approver feedback. For example, it executes a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[0251] Next, the server runs a generative AI model based on the acquired data to generate a draft message. For example, OpenAI's GPT-4 is used as the generative AI model. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[0252] The generated draft text is sent from the server to the device using a communication protocol such as an HTTP response.

[0253] The terminal displays the received draft to the user. The user interface includes a text area and a display widget. The user can check the displayed draft and make corrections as necessary. The corrected draft is used as the final approval request.

[0254] This system makes it possible to efficiently generate draft texts that take into account past approval history and approver tendencies, and provide draft texts that are likely to be accepted by the approver. It also reduces the burden on sales personnel and improves work efficiency. The flow of the identification process in the third embodiment will be described with reference to FIG. 15.

[0255] Step 1:

[0256] The user enters a prompt statement.

[0257] The user inputs a prompt into an input field on the terminal, for example, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to value specific figures and clear objectives."

[0258] Input: prompt statement

[0259] Output: The prompt text entered

[0260] Step 2:

[0261] The terminal sends the prompt to the server.

[0262] The terminal sends the entered prompt sentence to the server as an HTTP POST request.

[0263] Input: prompt statement

[0264] Output: The prompt sent to the server

[0265] Step 3:

[0266] The server retrieves the past approval history and approver tendencies from the database.

[0267] The server accesses the database to retrieve the approval history and approver trends, for example, by executing a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[0268] Input: prompt statement, database

[0269] Output: Past approval history and approver trends

[0270] Step 4:

[0271] The server generates draft text using a generative AI model.

[0272] The server runs a generative AI model (such as OpenAI's GPT-4) based on the acquired data to generate a draft message. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[0273] Input: Past approval history and approver trends

[0274] Output: Generated text proposal

[0275] Step 5:

[0276] The server transmits the generated draft text to the terminal.

[0277] The server sends the generated draft text to the terminal as an HTTP response.

[0278] Input: Generated text proposal

[0279] Output: Proposal sent to the terminal

[0280] Step 6:

[0281] The terminal displays the draft message to the user.

[0282] The terminal displays the received message in the text area, allowing the user to check the displayed message.

[0283] Input: Proposal sent to the terminal

[0284] Output: Proposed text displayed to the user

[0285] Step 7:

[0286] The user checks the draft and makes corrections as necessary.

[0287] The user checks the displayed draft and makes any necessary changes. For example, they can change "Personnel costs: 5 million yen" to "Personnel costs: 6 million yen." The revised draft is used as the final approval request.

[0288] Input: Proposed text displayed to the user

[0289] Output: Revised text

[0290] (Application example 3)

[0291] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0292] Conventional electronic payment systems have the problem of taking a great deal of time and effort to create approval documents that the approver will agree to. Furthermore, approval processes are often delayed because approval documents are created without taking into account the approver's preferences. This leads to inefficiencies in the approval process for expense settlements and large transactions within companies, resulting in a decline in overall business efficiency.

[0293] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0294] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for the proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, and means for learning the tendencies of approvers and generating draft proposals that are likely to be acceptable to the approvers. This makes it possible to quickly generate draft proposals that are easy for approvers to accept, and to streamline the approval process for electronic payments.

[0295] "Past information" refers to data and history that the system has collected in the past.

[0296] A "database" is a collection of information that systematically stores past information and allows it to be searched and retrieved as needed.

[0297] "Machine learning" is a technology that allows computers to analyze large amounts of data and automatically learn patterns and rules.

[0298] "Draft text of proposal / contract portion" refers to the draft text included in the proposal or contract.

[0299] "Artificial intelligence" refers to systems that use techniques such as machine learning to mimic human intelligence and automatically perform specific tasks.

[0300] "Interactive presentation means" refers to the interface that allows the user and the system to exchange information interactively.

[0301] "Approver trends" is data that indicates the criteria and patterns that a particular approver has used in approving in the past.

[0302] "Draft text that is likely to be accepted by the approver" refers to a draft of text that is likely to be approved, created taking into account the approver's past tendencies.

[0303] As an embodiment of the present invention, an electronic payment approval assistant system will be described as an example. This system operates in cooperation with three entities: a server, a terminal, and a user.

[0304] First, the server has a database that stores past information, including data on past approval history and approver tendencies. The server retrieves information from this database and uses machine learning to automatically generate draft proposal and contract wording. Specifically, the server uses APIs based on Python, Pandas, and OpenAI to analyze past approval history and learn approver tendencies.

[0305] The generated draft is then presented interactively to a terminal, which is a device used by the user, such as a smartphone or tablet, through which the user can review the draft and make any necessary corrections. The interactive interface is designed to be easy for users to operate.

[0306] Furthermore, the server learns the approver's tendencies and generates a message that is likely to be accepted by the approver. In this process, a generative AI model is used to generate message suggestions based on features extracted from past approval history. Specific examples of prompts include the following:

[0307] Example prompt sentence:

[0308] Generate the following wording suggestions based on the approver's tendencies:

[0309] This trip is an important meeting with a new client and requires prompt approval.

[0310] Approver tendency: {features extracted from the approver's past approval history}

[0311] This system can quickly generate draft text that is easy for the approver to understand, making it possible to streamline the approval process for electronic payments.As a specific example, consider the approval process for expense reimbursement within a company.When an employee applies for reimbursement for travel expenses and their supervisor's approval is required, by using this system, a draft text that is easy for the supervisor to understand can be automatically generated, allowing for quick approval.

[0312] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0313] Step 1:

[0314] The server obtains approval history data from a database that stores past information.

[0315] Input: Past approval history data stored in the database

[0316] Output: Acquired approval history data

[0317] Specific operation: The server uses an SQL query to extract past approval history data from the database.

[0318] Step 2:

[0319] The server inputs the acquired approval history data into a machine learning model to learn the approver's tendencies.

[0320] Input: Acquired approval history data

[0321] Output: Learning results about approver tendencies

[0322] How it works: The server preprocesses the data using publicly known libraries and inputs it into a machine learning model. The model learns past approval patterns and extracts approver tendencies.

[0323] Step 3:

[0324] Based on the learning results, the server inputs a prompt sentence into the generative AI model and generates a draft sentence.

[0325] Input: Learning results on approver tendencies, prompt text

[0326] Output: Generated text proposal

[0327] Specific operation: The server uses OpenAI's API to input the prompt sentence and learning results into the generative AI model to generate a draft sentence.

[0328] Step 4:

[0329] The server transmits the generated draft text to the terminal and presents it interactively.

[0330] Input: Generated text proposal

[0331] Output: Proposal displayed on the terminal

[0332] Specific operation: The server sends the generated draft text to the terminal via an HTTP request, and the terminal displays it on the user interface.

[0333] Step 5:

[0334] The user checks the draft text generated through the terminal and makes corrections as necessary.

[0335] Input: Proposal of text displayed on the terminal

[0336] Output: Revised text

[0337] Specific operation: The user uses the terminal interface to check the draft text and, if necessary, makes corrections in a text editor.

[0338] Step 6:

[0339] The server stores the revised draft as the final approved document.

[0340] Input: Revised draft text

[0341] Output: Final approval statement saved

[0342] Specific operation: The server saves the revised draft text in the database and completes the approval process.

[0343] 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.

[0344] "Example 1"

[0345] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes a user's emotions. The emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. Specifically, it generates positive suggestions when the user is happy, and apologetic suggestions when the user is angry.

[0346] "Example 2"

[0347] The emotion engine also adjusts the message suggestions based on the user's emotions. Specifically, it generates positive language when the user is happy, and apologetic language when the user is angry. For example, when the user is happy, it generates a message like "This proposal will lead to further success in your business," and when the user is angry, it generates a message like "We deeply apologize that our service did not meet your expectations."

[0348] "Example 3"

[0349] Furthermore, the emotion engine automatically generates proposals for the proposal and contract sections based on the user's emotions. Specifically, it generates positive proposals when the user is happy, and proposals that include words of apology when the user is angry. For example, when the user is happy, it generates a proposal such as "This proposal will lead to further success in your business," and when the user is angry, it generates a proposal such as "We deeply apologize that our service did not meet your expectations."

[0350] The processing flow of each embodiment will be described below.

[0351] "Example 1"

[0352] Step 1: The AI ​​activates an emotion engine that infers emotions from the user's tone of voice, facial expressions, and choice of words.

[0353] Step 2: The emotion engine recognizes the user's emotion and determines the content of the suggestion based on that emotion.

[0354] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and presents it to the user.

[0355] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[0356] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposed text based on the emotion.

[0357] Step 3: Based on the results of the emotion engine, the AI ​​generates a draft message and presents it to the user.

[0358] "Example 3"

[0359] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[0360] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposal and contract portion based on that emotion.

[0361] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and contract portion and presents it to the user.

[0362] Example 1

[0363] Next, a description will be given of Example 1 of Form 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."

[0364] In conventional sales activities, salespeople had to manually refer to information on past contracts and proposals to create new proposals. This work required time and effort, increasing the burden on salespeople. It was also difficult to make appropriate proposals based on the user's emotions, making it difficult to improve customer satisfaction.

[0365] 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.

[0366] In this invention, the server includes means for acquiring information from a database storing past information, means for training a machine learning model using the acquired information, means for automatically generating draft proposals for the proposal and contract portion using the trained machine learning model, means for presenting the generated draft proposals through an interactive interface, means including an emotion engine for recognizing user emotions, and means for adjusting the draft proposals based on information obtained from the emotion engine. This reduces the burden on sales staff and makes it possible to make optimal proposals based on the user's emotions.

[0367] A "database" is an information management system that stores past information and enables the efficient retrieval of necessary information.

[0368] A "machine learning model" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[0369] "Training" is the process of training a machine learning model using large amounts of data to learn and improve its performance.

[0370] A "draft" is a draft of a document that describes the contents of a proposal or contract.

[0371] An "interactive interface" is a user interface that allows two-way communication between a user and a system.

[0372] The "emotion engine" is a system that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[0373] "Adjustment" means changing content or settings to suit specific conditions or circumstances.

[0374] MODE FOR CARRYING OUT THE INVENTION

[0375] This invention is a system that acquires information from a database that stores past information and uses machine learning to automatically generate draft proposal and contract wording. Specific embodiments of this system are described below.

[0376] Retrieving information from a database

[0377] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, and customer responses. The server uses an SQL query to extract past contract information from the database. For example, it executes a query such as "SELECT FROM contracts WHERE date > '2020-01-01'".

[0378] Training a machine learning model

[0379] The server uses the acquired information to train a machine learning model. This model is capable of automatically generating draft proposal and contract wording using techniques such as deep learning and reinforcement learning. Specifically, it uses a framework such as TensorFlow. The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[0380] Generate draft text

[0381] The server uses a trained machine learning model to generate draft proposal and contract text. These draft proposals are designed to include optimal content based on past data. The server inputs a prompt text into the generative AI model to generate a draft proposal. For example, it executes code such as "generate_text('Generate a new proposal text')".

[0382] Proposal of text is presented through the interface

[0383] The terminal presents the generated message draft to the salesperson through a conversational interface. This interface can be implemented in the form of a chatbot or voice assistant. The terminal displays the generated message draft on the chatbot's UI. For example, it executes a code such as "chatbot.display_message(generated_text)".

[0384] Recognizing user emotions with an emotion engine

[0385] The device recognizes the user's emotions using an emotion engine. This emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. The device uses OpenCV to analyze the user's facial expressions and infer emotions. For example, it executes code such as "emotion = emotion_recognition.detect_face_expression(user_image)".

[0386] Adjusting message proposals according to emotions

[0387] The server generates text suggestions based on the information obtained from the emotion engine according to the user's emotions. If the user is happy, it generates a positive suggestion, and if the user is angry, it generates a suggestion including an apology. Based on the output of the emotion engine, the server inputs an appropriate prompt sentence into the generative AI model. For example, it executes code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[0388] Specific examples

[0389] Example 1: Proposal Generation

[0390] The following proposal is generated based on the user's past contract information.

[0391] Example prompt sentence:

[0392] "Generate new proposals based on past contract information."

[0393] An example of a generated suggestion:

[0394] "Customer, based on the terms of your previous contract, we would like to make you a new proposal with similar conditions. We appreciate your consideration."

[0395] Example 2: Adjusting message proposals based on emotions

[0396] If the user is angry, the emotion engine will recognize that emotion and generate a suggested message that includes an apology.

[0397] Example prompt sentence:

[0398] "Generate suggestion sentences for when the user is angry."

[0399] An example of a generated suggestion:

[0400] "Dear customer, we apologize for the inconvenience. With this proposal, we will improve the past issues and offer you better terms."

[0401] In this way, the system utilizes past data to automatically generate optimal suggestions based on the user's emotions.

[0402] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0403] Step 1:

[0404] The server retrieves the information from a database that stores past information.

[0405] Input: Database query (e.g., "SELECT FROM contracts WHERE date > '2020-01-01'")

[0406] Data processing: Execute SQL queries to extract past contract information.

[0407] Output: A dataset of retrieved contract information

[0408] Specific operation: The server extracts past contract information from the database using an SQL query, for example, "SELECT FROM contracts WHERE date > '2020-01-01'".

[0409] Step 2:

[0410] The server uses the acquired information to train a machine learning model.

[0411] Input: Dataset of retrieved contract information

[0412] Data processing: Preprocessing the dataset and converting it into a format suitable for machine learning models.

[0413] Output: A trained machine learning model

[0414] Specific operation: The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[0415] Step 3:

[0416] The server uses the trained machine learning model to generate draft proposal and contract text.

[0417] Input: A trained machine learning model, a prompt (e.g., "Generate a new suggestion")

[0418] Data processing: The prompt sentence is input into the model and a draft sentence is generated.

[0419] Output: Generated text proposal

[0420] Specific operation: The server inputs a prompt sentence into the generative AI model and generates a text suggestion. For example, it executes a code such as "generate_text('Generate a new suggested text')".

[0421] Step 4:

[0422] The terminal presents the generated draft message to the salesperson through an interactive interface.

[0423] Input: Generated text proposal

[0424] Data processing: Converting the draft text into a format suitable for the interactive interface.

[0425] Output: Proposal of text to be presented to the salesperson

[0426] Specific operation: The terminal displays the generated message on the chatbot's UI, for example, by executing code such as "chatbot.display_message(generated_text)".

[0427] Step 5:

[0428] The terminal uses an emotion engine to recognize the user's emotions.

[0429] Input: Your tone of voice, facial expressions, and word choice

[0430] Data processing: Analyze user emotions using an emotion engine.

[0431] Output: Estimated user emotion

[0432] Specific operation: The device uses OpenCV to analyze the user's facial expression and estimate their emotion. For example, it executes code like "emotion = emotion_recognition.detect_face_expression(user_image)".

[0433] Step 6:

[0434] The server generates a message proposal based on the user's emotions based on the information obtained from the emotion engine.

[0435] Input: Estimated user sentiment, trained machine learning model

[0436] Data processing: Generate prompt sentences according to the emotion, input them into the model, and generate draft sentences.

[0437] Output: Suggested text based on emotion

[0438] Specific operation: The server inputs an appropriate prompt sentence to the generative AI model based on the output of the emotion engine. For example, it executes a code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[0439] (Application example 1)

[0440] Next, a description will be given of Application Example 1 of Embodiment 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."

[0441] With conventional sales support systems, it was difficult for salespeople to quickly refer to past proposals and contract information and make optimal proposals when dealing with customers. It was also difficult to recognize customer emotions in real time and make proposals accordingly. Furthermore, in physical stores, when sales staff deal with customers, they are required to make optimal proposals based on past sales data and proposal content, but there was a lack of efficient means to do this. To solve these issues, a system that recognizes customer emotions and generates proposal text that corresponds to them is needed.

[0442] 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.

[0443] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating proposal and contract wording proposals using machine learning, means for interactively presenting the generated proposal wording proposals, an emotion engine for recognizing a user's emotions, means for generating proposal wording according to the user's emotions, and means installed in smart glasses to support customer service. This enables salespeople and store clerks to quickly make optimal proposals based on past proposal and contract information when serving customers, and further enables proposals according to the customer's emotions to be made in real time.

[0444] "Past information" refers to data that includes information on contracts and proposals that corporate sales have made in the past.

[0445] A "database" is a system that stores past information and can retrieve that information as needed.

[0446] "Artificial intelligence" is a technology that uses machine learning to automatically generate draft proposal and contract wording.

[0447] "Interactive presentation" refers to a method in which the generated draft text is presented to the salesperson via a chatbot, voice assistant, etc.

[0448] The "emotion engine" is a technology that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[0449] The "means for generating a suggested message according to the user's emotions" is a method for generating an appropriate suggested message based on the emotions estimated by the emotion engine.

[0450] "Smart glasses" are wearable devices equipped with a display and camera that can display information and capture images.

[0451] The "means for supporting customer service" is a method that uses smart glasses to display optimal suggestion text when a store clerk is interacting with a customer.

[0452] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposal and contract wording, a means for interactively presenting the generated draft proposals, an emotion engine that recognizes the user's emotions, a means for generating proposal wording in accordance with the user's emotions, and a means that is installed in smart glasses and supports customer service.

[0453] The server retrieves information from a database that stores past information and uses machine learning to automatically generate proposal and contract wording. Specifically, it uses deep learning and reinforcement learning models trained with TensorFlow. The generated wording is presented to the salesperson through a conversational interface such as a chatbot or voice assistant.

[0454] The device uses smart glasses to capture the customer's facial expressions and tone of voice, and recognizes the user's emotions using an emotion engine. The emotion engine uses an emotion recognition model based on TensorFlow to infer emotions from the user's tone of voice, facial expressions, and choice of words. Based on the inferred emotions, a generative AI model is used to generate optimal suggested text. The generative AI model uses natural language generation models such as GPT-2.

[0455] When a user wears the smart glasses and interacts with a customer, the smart glasses display shows the optimal proposal based on past sales data and the content of the proposal, allowing the user to make proposals in real time that reflect the customer's emotions.

[0456] For example, if a customer is looking at a product with a smile, the emotion recognition model will determine this as "joy" and generate a suggestion message such as, "This product is particularly popular. We're offering a special discount right now, so please give it a try." If the customer has a confused expression, the emotion recognition model will determine this as "confused" and generate a suggestion message such as, "If you need any help, we'd be happy to help you."

[0457] An example of a prompt is as follows:

[0458] "Optimal Proposal Text When Customers are Happy: Past Proposal Data"

[0459] "Optimal Proposal Text for Customers in a Confused State: Past Proposal Data"

[0460] This allows salespeople and store clerks to quickly make optimal proposals based on past proposals and contract information when dealing with customers, and also allows them to make proposals in real time that reflect the customer's emotions.

[0461] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0462] Step 1:

[0463] The server retrieves the information from a database that stores past information.

[0464] Input: Past proposals and contract information stored in a database

[0465] Output: Past proposal and contract information obtained

[0466] What happens: The server uses SQL queries to extract the necessary information from the database and loads it into memory.

[0467] Step 2:

[0468] The server uses machine learning to automatically generate draft proposal and contract wording based on the acquired information.

[0469] Input: Past proposals and contract information

[0470] Output: Generated proposal and contract draft

[0471] Specific operation: The server inputs data into deep learning models and reinforcement learning models trained using TensorFlow to generate optimal text suggestions.

[0472] Step 3:

[0473] The server presents the generated draft text to the salesperson through an interactive interface.

[0474] Input: Generated proposal and contract draft

[0475] Output: Proposal of text presented to the salesperson

[0476] Specific operation: The server sends the generated draft message to the salesperson's device via a chatbot or voice assistant and displays it.

[0477] Step 4:

[0478] The device uses smart glasses to capture the customer's facial expressions and tone of voice.

[0479] Input: Customer facial expressions and tone of voice

[0480] Output: Captured customer facial expressions and tone of voice data

[0481] How it works: The device uses a camera and microphone in its smart glasses to capture the customer's facial expressions and voice in real time.

[0482] Step 5:

[0483] The terminal inputs the captured data into an emotion engine to recognize the user's emotion.

[0484] Input: Captured customer facial and tone of voice data

[0485] Output: Estimated user emotion

[0486] Specific operation: The device inputs data into an emotion recognition model using TensorFlow to estimate the user's emotions.

[0487] Step 6:

[0488] The server uses a generative AI model to generate optimal suggested text based on the estimated emotions.

[0489] Input: Estimated user sentiment, past suggestion data

[0490] Output: Suggested text based on emotion

[0491] Specific operation: The server inputs the prompt sentence into a natural language generation model such as GPT-2 and generates the optimal suggested sentence.

[0492] Step 7:

[0493] The terminal displays the generated proposal text on the display of the smart glasses.

[0494] Input: Generated suggestion text

[0495] Output: Suggestion text displayed on the smart glasses display

[0496] Specific operation: The terminal sends the generated proposal text to the display of the smart glasses and displays it.

[0497] This allows the user to make suggestions in real time that correspond to the customer's emotions.

[0498] Example 2

[0499] Next, a description will be given of Example 2 of Form 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."

[0500] In conventional sales activities, salespeople spend a lot of time and effort creating proposals and contracts. In addition, it is difficult to generate appropriate wording that reflects the user's emotions, making it difficult to improve customer satisfaction.

[0501] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft wording for the proposal and contract portion using machine learning, means for interactively presenting the generated draft wording, an emotion engine for analyzing the user's emotions, and means for adjusting the draft wording based on the user's emotions. This reduces the burden on the salesperson and makes it possible to generate appropriate draft wording based on the user's emotions.

[0502] A "database" is a system for storing past information and retrieving that information as needed.

[0503] "Artificial intelligence" is a technology that uses machine learning to automatically generate draft proposals and contract wording.

[0504] The "means for interactive presentation" is a method for interactively displaying the generated draft text to the user.

[0505] An "emotion engine" is a technology for analyzing a user's emotions and identifying their emotional state.

[0506] The "means for adjusting the proposed text" is a method for appropriately correcting the proposed text generated based on the user's feelings.

[0507] MODE FOR CARRYING OUT THE INVENTION

[0508] The present invention relates to a system for reducing the burden on salespeople and generating appropriate message proposals in response to user emotions. Specific embodiments of this system will be described below.

[0509] System configuration

[0510] The system consists of the following main components:

[0511] 1. Database: A system for storing past information and retrieving it when needed.

[0512] 2. Artificial Intelligence (AI): This technology uses machine learning to automatically generate proposal and contract wording. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-4).

[0513] 3. Interactive presentation: The generated drafts are displayed interactively to the user, for example, via a web interface or a mobile application.

[0514] 4. Emotion Engine: This technology analyzes the user's emotions and identifies their emotional state. Specifically, it uses an emotion engine.

[0515] 5. Means for adjusting text suggestions: A method for appropriately modifying generated text suggestions based on the user's emotions.

[0516] System Operation

[0517] The server collects basic information such as the proposal details and contract terms entered by the user into the terminal. For example, if the user proposes a new marketing strategy, the proposal details "new marketing strategy" and the contract terms "annual contract" are entered.

[0518] Next, the server generates a prompt for the generative AI model based on the data entered by the user. For example, it generates the following prompt:

[0519] Proposal: New marketing strategy

[0520] Terms and conditions: Annual contract

[0521] Generate a draft of the text.

[0522] The server sends the generated prompt to the generative AI model, which then generates a suggested message based on the prompt, such as "This new marketing strategy will lead to greater success for your business."

[0523] The server then collects the user's emotion data and sends it to the emotion engine, which analyzes the user's emotions and identifies their emotional state, such as happy or angry.

[0524] The server adjusts the generated message proposals based on the analysis results of the emotion engine. For example, if the user is happy, the server adjusts the message proposal to include positive language. If the user is angry, the server adjusts the message proposal to include apologetic language.

[0525] Finally, the server transmits the adjusted final draft text to the terminal, and the user can check the final draft text on the terminal and modify it as necessary.

[0526] Specific examples

[0527] As a concrete example, consider the following scenario:

[0528] Scenario 1: Happy users

[0529] Input data: Proposal content "New marketing strategy", contract terms "Annual contract"

[0530] Output of the generative AI model: Proposed text: "This new marketing strategy will make your business even more successful."

[0531] Adjusting the emotion engine: Generate text suggestions containing positive words because the user is happy

[0532] Scenario 2: The user is angry

[0533] Input data: Proposal content "Service improvement proposal", contract terms "Monthly contract"

[0534] Output of generative AI model: Proposed text: "We deeply apologize that our service did not meet your expectations."

[0535] Adjusting the emotion engine: Generate a message containing an apology because the user is angry.

[0536] In this way, the system operates in which the server, terminal, and user work together to generate draft wording to reduce the burden on salespeople.

[0537] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0538] Step 1: Collecting User Input Data

[0539] The user inputs basic information such as the proposal content and contract terms into the terminal. For example, if the user is proposing a new marketing strategy, the proposal content is "New Marketing Strategy" and the contract terms are "Annual Contract." The input data is sent to the server.

[0540] Step 2: Generate prompts for the generative AI model

[0541] The server generates a prompt for the generative AI model based on the data entered by the user. For example, it generates the following prompt:

[0542] Proposal: New marketing strategy

[0543] Terms and conditions: Annual contract

[0544] Generate a draft of the text.

[0545] This prompt is sent to a generative AI model.

[0546] Step 3: Generate copy using a generative AI model

[0547] The server sends the generated prompt to a generative AI model (for example, OpenAI's GPT-4). The generative AI model generates a message based on the prompt. For example, it might generate a message like, "This new marketing strategy will lead to greater success for your business." The generated message is then returned to the server.

[0548] Step 4: Analyze user sentiment with the emotion engine

[0549] The server collects the user's emotion data and sends it to the emotion engine, which analyzes the user's emotion and identifies the user's emotional state, such as happy, angry, etc. The analysis result is returned to the server.

[0550] Step 5: Adjust the draft copy based on sentiment

[0551] The server adjusts the generated message proposals based on the analysis results of the emotion engine. For example, if the user is happy, the message proposal is adjusted to include more positive language. If the user is angry, the message proposal is adjusted to include more apologetic language. The adjusted message proposals are saved on the server.

[0552] Step 6: Output the final draft

[0553] The server sends the final draft text to the terminal, where the user can review it and make any necessary changes. After the user has confirmed it, the final draft text will be used as a formal proposal or contract document.

[0554] (Application example 2)

[0555] Next, a description will be given of Application Example 2 of Form 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."

[0556] In conventional sales activities, salespeople spend a great deal of time and effort creating proposal and contract drafts. They also need to respond appropriately to customer emotions, but this is difficult to do manually. This increases the salesperson's workload and can potentially lead to a decrease in customer satisfaction. Therefore, there is a need for a system that can reduce the salesperson's workload and automatically generate appropriate drafts based on customer emotions.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0558] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, means for analyzing user emotions, and means for adjusting the draft proposals based on the user emotions. This reduces the burden on sales staff and enables the automatic generation of appropriate draft proposals in accordance with customer emotions.

[0559] A "database" is a system for storing past information and retrieving that information as needed.

[0560] "Machine learning" is a technology that allows computers to learn patterns from data and make predictions and classifications.

[0561] "Draft proposal / contract text" refers to a draft document used when making proposals or contracts with customers in sales activities.

[0562] The "interactive presentation means" is an interface for displaying the generated draft text while interacting with the user.

[0563] "Means for analyzing user emotions" refers to technology for analyzing emotions from user input and behavior.

[0564] The "means for adjusting a proposed message based on the user's emotions" is a technique for appropriately changing a proposed message in accordance with the analyzed user's emotions.

[0565] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a database storing past information, a machine learning model, a sentiment analysis engine, and a generative AI model. The terminal is a device operated by the user, such as a smartphone or PC. The user is a salesperson or customer support representative.

[0566] The server first retrieves past information from a database. This information includes past proposals, contract texts, and customer feedback. Next, it uses a machine learning model to automatically generate proposal and contract texts from the retrieved information. These generated texts are then presented interactively on the terminal.

[0567] The user can review the draft text and make corrections if necessary. In addition, the server uses a sentiment analysis engine to analyze emotions from the user's input and behavior. The sentiment analysis engine can utilize existing sentiment analysis tools.

[0568] Once the user's emotions are analyzed, a generative AI model adjusts the suggested message based on that emotion. For example, if the user is happy, it will generate a positive message, and if the user is angry, it will generate a message containing an apology. This process uses generative AI models such as OpenAI's GPT-3.

[0569] For example, if the user is satisfied with the product, the prompt might read:

[0570] Prompt: Suggested prompt for a happy user: Thank you for your recent purchase. We hope you are satisfied with our service.

[0571] By inputting this prompt sentence into a generative AI model, it is possible to generate appropriate sentence suggestions that correspond to the user's emotions.

[0572] This system reduces the burden on sales staff and enables the automatic generation of appropriate message proposals based on customer emotions, which is expected to improve customer satisfaction and sales efficiency.

[0573] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0574] Step 1:

[0575] The server retrieves past information from a database. The input is data such as past proposals, contract documents, and customer feedback. The output is the retrieved past information. Specifically, the server executes SQL queries to extract the required information from the database.

[0576] Step 2:

[0577] The server uses a machine learning model to automatically generate draft proposals and contracts from the acquired information. The input is the past information acquired in step 1. The output is the generated draft proposals. Specifically, the server runs a machine learning algorithm to generate new draft proposals based on past information.

[0578] Step 3:

[0579] The server interactively presents the generated draft text on the terminal. The input is the draft text generated in step 2. The output is the draft text displayed on the terminal. Specifically, the server sends the draft text to the terminal in JSON format, and the terminal displays it on the user interface.

[0580] Step 4:

[0581] The user checks the draft text through the terminal and makes corrections as necessary. The input is the draft text presented in step 3. The output is the draft text corrected by the user. In concrete terms, the user edits the draft text using the input field on the terminal.

[0582] Step 5:

[0583] The server uses a sentiment analysis engine to analyze emotions from the user's input and behavior. The input is the draft text corrected in step 4 and the user's input data. The output is the user's sentiment score. Specifically, the server calls an API, analyzes the user's input data, and obtains the sentiment score.

[0584] Step 6:

[0585] The server uses a generative AI model to adjust the suggested sentences based on the user's emotions. The input is the emotion score obtained in step 5 and the suggested sentences modified in step 4. The output is the suggested sentences adjusted according to the emotions. Specifically, the server inputs the prompt sentence into OpenAI's GPT-3 model and generates suggested sentences according to the emotions.

[0586] Step 7:

[0587] The server presents the adjusted draft text again to the terminal. The input is the draft text adjusted in step 6. The output is the final draft text displayed on the terminal. Specifically, the server sends the adjusted draft text to the terminal in JSON format, and the terminal displays it on the user interface.

[0588] Example 3

[0589] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0590] Conventional systems could generate draft messages based on past information, but they were unable to generate draft messages that reflected the user's emotions. This made it difficult to automatically generate proposals, apologies, and other messages that matched the user's emotions. Furthermore, there was a lack of concrete means for generating draft messages that would satisfy the approver, which resulted in an inefficient approval process.

[0591] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0592] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, an emotion engine for detecting user emotions, and means for generating draft proposals based on emotion data acquired from the emotion engine. This makes it possible to automatically generate appropriate draft proposals according to the user's emotions and provide draft proposals that are likely to be acceptable to the approver.

[0593] A "database" is a system for storing past information and retrieving that information as needed.

[0594] "Artificial intelligence" is a technology that uses machine learning to analyze data and automatically generate draft proposals and contract wording.

[0595] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to confirm and modify the draft text.

[0596] An "emotion engine" is a technology that detects emotions from a user's facial expressions, voice, etc. and analyzes that emotional data.

[0597] "Emotion data" is data that indicates the user's emotional state detected by the emotion engine.

[0598] A "draft text" is a draft of a proposal or contract that is generated by artificial intelligence.

[0599] This invention is a system that combines a database that stores past information, artificial intelligence that generates text suggestions using machine learning, and an emotion engine that detects the user's emotions. Specific embodiments of this system are described below.

[0600] System configuration

[0601] Database

[0602] The server uses a database that stores past approval history and approver trends. This database can be a relational database management system (RDBMS) such as MySQL. The database stores approval history data and approver trend data.

[0603] artificial intelligence

[0604] The server uses a generative AI model (e.g., GPT-4) to generate draft text based on information retrieved from the database. The generative AI model learns past approval history and approver tendencies, and generates new draft text based on that information.

[0605] Emotion Engine

[0606] The device uses an emotion engine to detect the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[0607] System Operation

[0608] Data collection

[0609] The server retrieves the past approval history data and approver trend data from the database. For example, the server retrieves the data by executing an SQL query such as "SELECT FROM approval_history WHERE approver_id = 'X'".

[0610] Data Learning

[0611] The server inputs the acquired data into the generative AI model and trains it. During the training process, it analyzes past approval history and approver tendencies to extract patterns.

[0612] Text generation

[0613] The server inputs a prompt into the generative AI model that has completed training, generating a new draft message. The prompt message contains specific instructions based on the approver's tendencies. For example, the server inputs a prompt message such as, "Please generate a draft message that approver X will be satisfied with. Please include specific numerical values."

[0614] Emotion Detection

[0615] The device captures the user's facial expression with a camera, calls an API, and sends the analysis results to the server. For example, if the user is happy, the emotion engine detects that emotion and sends the data "the user is happy" to the server.

[0616] Emotion-based text generation

[0617] The server generates appropriate message suggestions based on the received emotion data. For example, if the user is happy, the server inputs a prompt message such as "Please generate a message suggestion for when the user is happy" into the generative AI model. The generative AI model then generates a message suggestion such as "This suggestion will lead to further success in your business."

[0618] Specific examples

[0619] Examples of data collection

[0620] The server executes the SQL query "SELECT FROM approval_history WHERE approver_id = 'X'" to retrieve data from the database.

[0621] Example of text generation

[0622] The server inputs the prompt "Please generate a draft wording that will satisfy Approver X. Please include specific numerical values" into the generative AI model and receives the generated draft wording.

[0623] Example of emotion-based text generation

[0624] The server inputs the prompt "Please generate suggested message suggestions for when the user is happy" into the generative AI model and presents the generated message suggestions to the user.

[0625] In this way, the system generates an optimal draft message according to the emotions of the approver and the user in cooperation with the server, the terminal, and the user. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0626] Step 1: Data collection

[0627] The server retrieves past approval history data and approver trend data from the database. As input, it executes an SQL query (e.g., "SELECT FROM approval_history WHERE approver_id = 'X'"), and as output, it loads the retrieved data into memory. Specifically, the server establishes a database connection, executes the SQL query, and retrieves the results.

[0628] Step 2: Data training

[0629] The server inputs the acquired data into a generative AI model (e.g., GPT-4) and trains the model. It uses past approval history data and approver tendency data as input, and obtains a trained generative AI model as output. Specifically, the server preprocesses the data and inputs it into the generative AI model to begin the learning process.

[0630] Step 3: Generate text suggestions

[0631] The server inputs a prompt sentence into the generative AI model that has completed training, generating a new draft text. The prompt sentence (e.g., "Please generate a draft text that approver X will be satisfied with. Please include specific numerical values.") is used as input, and the generated draft text is obtained as output. Specifically, the server inputs the prompt sentence into the generative AI model and receives the generated draft text.

[0632] Step 4: Emotion detection

[0633] The device captures the user's facial expression with a camera, calls the API, and sends the analysis results to the server. The user's facial expression data is used as input, and the analyzed emotion data is obtained as output. Specifically, the device captures the user's facial expression with a camera, sends the data to the API, and receives the analysis results.

[0634] Step 5: Emotion-based message generation

[0635] The server generates appropriate message suggestions based on the received emotion data. It uses emotion data (e.g., "The user is happy") as input and obtains message suggestions corresponding to the emotion as output. Specifically, the server analyzes the emotion data, inputs a prompt (e.g., "Please generate suggested message suggestions for when the user is happy") into the generative AI model, and receives the generated message suggestions.

[0636] In this way, the system works in cooperation with the server, terminal, and user to generate optimal draft text that reflects the emotions of the approver and user.

[0637] (Application example 3)

[0638] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0639] Conventional message draft generation systems had difficulty generating message drafts that took the user's emotions into account, and were unable to increase user satisfaction. Furthermore, there was a lack of appropriate means for generating message drafts that would satisfy the approver, which sometimes delayed the approval process. Furthermore, there was insufficient generation of message drafts to reduce the burden on sales staff.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: artificial intelligence that acquires information from a database storing past information and automatically generates draft proposals for the proposal and contract portions using machine learning; means for interactively presenting the generated draft proposals; an emotion engine that analyzes the user's emotions; and means for adjusting the draft proposals based on the emotion engine. This makes it possible to generate draft proposals that take the user's emotions into consideration, thereby increasing user satisfaction. Furthermore, by generating draft proposals that are satisfactory to the approver, delays in the approval process can be prevented. Furthermore, draft proposals can also be generated to reduce the burden on sales staff.

[0641] "Past information" refers to data such as the user's or approver's past behavioral history, transaction history, and approval history.

[0642] A "database" refers to an information accumulation system that systematically stores past information and allows it to be searched and retrieved as needed.

[0643] "Machine learning" refers to a technology that allows computers to analyze large amounts of data, find patterns and regularities, and then automatically perform specific tasks.

[0644] "Draft of proposal / contract portion" refers to a draft document that describes the proposal content and contract content to be presented to the user or approver.

[0645] "Artificial intelligence" refers to computer systems that use technologies such as machine learning and natural language processing to imitate and assist human intellectual tasks.

[0646] The "means for interactive presentation" refers to an interface for interactively displaying the generated draft text to the user or approver and receiving feedback.

[0647] An "emotion engine" refers to a software module that analyzes a user's emotions and takes appropriate action based on the results.

[0648] "Means for adjusting proposed text" refers to the function for appropriately correcting and adjusting the generated proposed text based on the analysis results of the emotion engine.

[0649] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposals for proposal and contract portions, a means for interactively presenting the generated draft proposals, an emotion engine that analyzes user emotions, and a means for adjusting the draft proposals based on the emotion engine.

[0650] The server first retrieves information from the database, such as the user's or approver's past behavioral history, transaction history, and approval history. Based on this information, a machine learning algorithm is used to generate draft proposals and contracts. The draft proposals are then presented interactively to the user or approver, who can then provide feedback.

[0651] Next, the emotion engine analyzes the user's emotions. The emotion engine analyzes emotions from the user's input and behavior and adjusts the message suggestions based on the results. For example, if the user is feeling anxious, it can add a reassuring message to the message suggestions.

[0652] This system requires software such as APIs, sentiment analysis modules, etc. Hardware such as a server and smartphones are required.

[0653] As a concrete example, consider the generation of a message when a user makes a large payment. If the user ID is 12345 and the payment amount is 10,000 yen, the following prompt sentence is generated based on the user's past payment history and the user's emotions.

[0654] Example prompt sentence:

[0655] User ID: 12345

[0656] Payment amount: 10,000 yen

[0657] Past payment history: Past payment history data

[0658] User Emotion: Anxiety

[0659] Generate an appropriate message.

[0660] By inputting this prompt sentence into a generative AI model, it is possible to generate an appropriate message that takes the user's emotions into consideration, thereby realizing a system that can increase user satisfaction.

[0661] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0662] Step 1:

[0663] The server retrieves information such as the user's and approver's past behavior history, transaction history, and approval history from the database. The input is the user ID and approver ID, and the output is data such as the user's and approver's past behavior history, transaction history, and approval history. This data is used in subsequent processing.

[0664] Step 2:

[0665] The server uses a machine learning algorithm based on the acquired past information to generate draft proposals and contracts. The input is the past information acquired in step 1, and the output is the generated draft proposal. Specifically, the server inputs past information into the machine learning model to generate the optimal draft proposal.

[0666] Step 3:

[0667] The server interactively presents the generated draft to the user or approver. The input is the draft generated in step 2, and the output is feedback from the user or approver. Specifically, the server displays the draft through the user interface and receives comments and revision requests from the user or approver.

[0668] Step 4:

[0669] The server analyzes emotions from user input and behavior using an emotion engine. The input is the user's feedback and behavior data, and the output is the user's emotional state. Specifically, the server analyzes the user's emotions using an emotion analysis module.

[0670] Step 5:

[0671] The server adjusts the proposed message based on the analysis results of the emotion engine. The input is the user's emotional state obtained in step 4 and the proposed message generated in step 2, and the output is the adjusted proposed message. Specifically, the server modifies the content of the proposed message according to the user's emotions, for example, adding a message that gives a sense of security to a user who is feeling anxious.

[0672] Step 6:

[0673] The server presents the adjusted draft to the user or approver again and receives final feedback. The input is the draft adjusted in step 5, and the output is the final approval or revision request. Specifically, the draft is displayed again through the user interface for final confirmation.

[0674] Step 7:

[0675] The server saves the final draft text in a database and uses it to generate draft text for future proposals and contracts as needed. The input is the final draft text, and the output is an updated database. Specifically, the final draft text is stored in the database and used as training data for future machine learning models.

[0676] 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.

[0677] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0678] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0679] 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.

[0680] [Second embodiment]

[0681] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0693] "Example 1"

[0694] In one embodiment of the present invention, there is a database that stores past information. This database includes, for example, information on contracts and proposals made by corporate sales in the past. There is an AI that acquires information from this database and automatically generates draft proposals for the proposal and contract portions using machine learning. This AI is trained using machine learning techniques such as deep learning and reinforcement learning. The generated draft proposals are presented to the salesperson through an interactive interface. This interface is realized in the form of, for example, a chatbot or a voice assistant. "Example 2"

[0695] In another embodiment of the present invention, AI generates draft wording to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform. For example, it significantly reduces the time and effort required for salespeople to draft proposals and contracts.

[0696] "Example 3"

[0697] In a further embodiment of the present invention, AI generates draft text that is expected to be acceptable to the approver. Specifically, AI learns the past approval history and the approver's tendencies, and generates draft text based on that. This makes it possible to provide draft text that is likely to be acceptable to the approver.

[0698] The processing flow of each embodiment will be described below.

[0699] "Example 1"

[0700] Step 1: Obtain the necessary information from a database that stores past information. This information may be information about past contracts or proposals, for example.

[0701] Step 2: Based on the acquired information, machine learning is used to automatically generate draft proposal and contract text. This AI is trained using machine learning techniques such as deep learning and reinforcement learning.

[0702] Step 3: The generated message draft is presented to the salesperson through a conversational interface, which can be realized in the form of a chatbot or voice assistant, for example.

[0703] "Example 2"

[0704] Step 1: AI generates draft message to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform.

[0705] Step 2: For example, it significantly reduces the time and effort required by salespeople to draft proposals and contracts.

[0706] "Example 3"

[0707] Step 1: The AI ​​generates draft text that is expected to be acceptable to the approver. Specifically, the AI ​​learns past approval history and approver tendencies.

[0708] Step 2: Based on this, a draft message is generated, which makes it possible to provide a draft message that is likely to be accepted by the approver.

[0709] Example 1

[0710] Next, a description will be given of Example 1 of Form 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."

[0711] In traditional corporate sales, the problem was that creating proposals and contracts took a lot of time and effort. It was also difficult for salespeople to efficiently utilize information from past proposals and contracts, which resulted in a decline in the quality of proposals. Furthermore, creating documents that would convince approvers required experience and skill, which placed a significant burden on new salespeople.

[0712] 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.

[0713] In this invention, the server includes means for retrieving information from a database storing past information, means for training a machine learning model using the retrieved information, means for automatically generating draft proposal and contract wording using the trained machine learning model, and means for interactively presenting the generated draft wording. This reduces the burden on sales staff and enables the efficient creation of high-quality proposals and contracts. Furthermore, automatically generating draft wording that satisfies the approver can also expedite the approval process.

[0714] A "database" is a system for storing past information and retrieving that information as needed.

[0715] "Means of obtaining information" refers to the methods and techniques used to extract the necessary information from the database.

[0716] A "machine learning model" is an algorithm or framework that learns from data and performs specific tasks automatically.

[0717] A "training method" is a method or technique for training a machine learning model using data.

[0718] "Automatic proposal generation means" means a method or technology for automatically generating new proposal or contract language using a trained machine learning model.

[0719] The "interactive presentation means" refers to a method or technique for interactively displaying the generated draft text to the user.

[0720] "Salesperson" refers to the person in charge or staff who handles corporate sales.

[0721] "Approver" refers to a person who has the authority to review and approve the contents of a proposal or contract.

[0722] MODE FOR CARRYING OUT THE INVENTION

[0723] The present invention provides a system for improving the efficiency of creating proposals and contracts in corporate sales and reducing the burden on salespeople. A specific embodiment of this system will be described below.

[0724] Retrieving information from a database

[0725] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, dates, and customer information. The server extracts information from the database using an SQL query. For example, by executing the query "SELECT FROM contracts WHERE date > '2020-01-01'", it retrieves contract information from 2020 onwards.

[0726] Training a machine learning model

[0727] The server uses the acquired information to train a machine learning model. This model uses techniques such as deep learning and reinforcement learning. Specifically, it uses the TensorFlow framework. The server cleans and normalizes the data, and then trains the model using the preprocessed data. For example, it uses a Long Short-Term Memory (LSTM) network to train a text generation model.

[0728] Automatic generation of draft text

[0729] The server uses the trained LSTM model to automatically generate new proposal and contract wording. When a user enters a prompt such as "Please generate a new proposal," the server inputs this prompt into the model and obtains the generated wording. For example, the generated wording might be "This proposal provides the optimal solution to your company's needs."

[0730] Present to the salesperson

[0731] The generated proposal is presented to the salesperson through a conversational interface. This interface can take the form of a chatbot or voice assistant. The salesperson accesses the chatbot through their device and checks the generated proposal. For example, if the salesperson types into the chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[0732] Examples and prompts

[0733] Suppose a user needs to create a new proposal. The user accesses the system through their device and instructs it to generate a draft proposal based on information from past similar proposals. The server retrieves the past proposal information from the database and generates a new draft proposal using a machine learning model. The generated draft proposal is presented to the user through a chatbot.

[0734] Example prompt sentence:

[0735] "Please generate a draft proposal for a new proposal based on past corporate sales proposal information."

[0736] In this way, users can efficiently create new proposals.

[0737] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0738] Step 1:

[0739] The server retrieves information about past contracts and proposals from the database. An SQL query is used as input. For example, execute the query "SELECT FROM contracts WHERE date > '2020-01-01'". This query outputs contract information from 2020 onwards. The server stores the retrieved data in memory.

[0740] Step 2:

[0741] The server preprocesses the acquired data. Raw data acquired from the database is used as input. Preprocessing includes cleaning the data (filling in missing values ​​and removing outliers) and normalizing it (scaling the data). This results in output data in a format suitable for training machine learning models.

[0742] Step 3:

[0743] The server uses the preprocessed data to train a machine learning model. The preprocessed data is used as input. Specifically, it uses the TensorFlow framework to train a Long Short-Term Memory (LSTM) network. The training results in a model that can be used to generate proposal and contract text.

[0744] Step 4:

[0745] The server uses the trained LSTM model to automatically generate draft text for new proposals and contracts. The prompt text entered by the user is used as input. For example, the prompt text may read, "Please generate a new proposal." The server inputs this prompt text into the model and outputs the generated draft text. For example, the generated text may read, "This proposal provides the optimal solution for your company's needs."

[0746] Step 5:

[0747] The server presents the generated proposal to the salesperson through a conversational interface. The generated proposal is used as input. The conversational interface can be realized in the form of a chatbot or a voice assistant. For example, if a salesperson inputs to a chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[0748] (Application example 1)

[0749] Next, a description will be given of Application Example 1 of Form 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."

[0750] In traditional sales activities, salespeople have to manually refer to information on past contracts and proposals to create new proposals and contracts, which takes a lot of time and effort. Furthermore, since the quality of proposals and contracts depends on the experience and skills of the salesperson, it is difficult to maintain a consistent level of quality. Furthermore, there is a need for a way for salespeople to efficiently create proposals while on the go.

[0751] 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.

[0752] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, and means for presenting the generated draft wording to a sales representative via a smartphone. This enables sales representatives to quickly generate high-quality proposal and contract wording based on past data and conduct efficient sales activities even when they are out and about.

[0753] A "database storing past information" is a data storage system that stores information on contracts and proposals made by corporate sales in the past, allowing it to be searched and retrieved as needed.

[0754] "Machine learning" is a technology in which a computer learns patterns and rules from data and uses that knowledge to make predictions and judgments about new data.

[0755] "Artificial intelligence that automatically generates draft proposal and contract wording" is a program that uses machine learning to analyze past data and automatically generate new proposal and contract texts.

[0756] The "interactive presentation means" is an interface that interactively displays the generated draft text to the user, allowing the user to confirm and modify its content.

[0757] "Means of presenting to sales representatives via their smartphones" is a function that displays the generated draft text on the sales representative's smartphone, allowing them to conduct sales activities efficiently even when they are out and about.

[0758] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposals and contractual texts, a means for interactively presenting the generated draft proposals, and a means for presenting the generated draft proposals to sales representatives via their smartphones.

[0759] System configuration

[0760] 1. Database: The server has a database that stores information on contracts and proposals that have been made by the corporate sales department. This database is constructed using a known database management system.

[0761] 2. Artificial Intelligence: The server includes an artificial intelligence (AI) that uses machine learning (e.g., OpenAI's GPT-3) to automatically generate new proposals and contracts based on past data. This AI is implemented using a known programming language.

[0762] 3. Conversational Interface: The generated sales pitch is presented to the salesperson through a conversational interface, which can be in the form of a chatbot or voice assistant.

[0763] 4. Smartphone application: The generated sales pitch is displayed on the salesperson's smartphone. The smartphone application runs on the Android platform, enabling salespeople to efficiently conduct sales activities on the go.

[0764] Processing flow

[0765] 1. Data Acquisition: The server retrieves past proposals and contracts for a particular client from the database.

[0766] 2. Prompt generation: The server generates prompts to be input into the artificial intelligence based on the past suggestions it has obtained.

[0767] 3. Text generation: AI generates new proposals and contracts based on the generated prompts.

[0768] 4. Presentation of draft text: The draft text is presented to the sales representative through an interactive interface.

[0769] 5. Display on smartphone: The generated sales pitch is displayed on the sales representative's smartphone, allowing the sales representative to conduct sales activities efficiently even when on the go.

[0770] Hardware and software used

[0771] Hardware: Servers, smartphones

[0772] software

[0773] Specific examples

[0774] For example, if the previous recommendation for client ID 123 was "This product is of high quality and offers excellent value for money," the new recommendation generated might be "This product uses the latest technology and is highly reliable."

[0775] Prompt Sentence Examples

[0776] Previous proposal: This product is of high quality and offers excellent value for money. Generate a new proposal:

[0777] In this way, salespeople can easily generate new proposals using their smartphones and make effective proposals to their clients.

[0778] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0779] Step 1:

[0780] The server retrieves past offers and contracts for a specific client from a database. The input is a client ID, and the output is a list of past offers and contracts. Specifically, the server runs an SQL query to extract offers from the database that are associated with the given client ID.

[0781] Step 2:

[0782] The server generates a prompt to be input to the artificial intelligence based on the acquired past suggestions. The input is a list of past suggestions, and the output is a prompt. Specifically, the server combines the past suggestions into one text and creates a prompt with the prefix "Past suggestions: ".

[0783] Step 3:

[0784] The server sends the generated prompt to the AI ​​to generate new proposals or contracts. The input is the prompt, and the output is the generated proposal. Specifically, the server calls the OpenAI GPT-3 API, passing the prompt as input and receiving the generated text.

[0785] Step 4:

[0786] The server presents the generated proposal to the salesperson through a conversational interface. The input is the generated proposal, and the output is an interface that the salesperson can check and modify. Specifically, the server displays the generated proposal in chatbot format, allowing the salesperson to check and modify its contents.

[0787] Step 5:

[0788] The server displays the generated proposal on the sales representative's smartphone. The input is the generated proposal, and the output is the proposal displayed on the smartphone screen. Specifically, the server sends the generated proposal to a smartphone application, allowing the sales representative to check and use the proposal even when they are out and about.

[0789] Example 2

[0790] Next, a description will be given of Example 2 of Form 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."

[0791] Salespeople are required to reduce the time and effort required to draft proposals and contracts, and to work more efficiently. It is also important to maintain a consistent quality in drafts and quickly generate content that satisfies approvers. A system to solve these problems is needed.

[0792] 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.

[0793] In this invention, the server includes a generation AI model that acquires information from a database storing past information and automatically generates draft proposals for the proposal and contract portions using machine learning, a means for generating prompt text based on information entered by the user, and a means for interactively presenting the generated draft proposals, thereby reducing the burden on salespeople and enabling the efficient generation of high-quality draft proposals.

[0794] A "database" is a system for storing past information and retrieving that information as needed.

[0795] "Machine learning" is a technology that allows computers to learn patterns from data and make predictions and classifications.

[0796] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate draft proposals and contract wording.

[0797] A "prompt sentence" is a sentence that gives instructions to a generative AI model based on information entered by the user.

[0798] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[0799] A "salesperson" is a person in charge of the job of drafting proposals and contract texts.

[0800] A "draft" is a draft of the text of a proposal or contract.

[0801] An "approver" is a person who has the authority to review and approve the generated draft text.

[0802] This invention is a system that reduces the burden on salespeople and efficiently generates high-quality proposals and contract drafts. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0803] First, the server has a database that stores past information and retrieves it as needed. The database stores information about past proposals and contracts. The server uses a generative AI model (e.g., OpenAI's GPT-4) that uses machine learning to automatically generate proposal and contract wording.

[0804] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[0805] Customer name: XYZ Co., Ltd.

[0806] Proposal: Proposal for a new marketing strategy

[0807] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[0808] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. For example, it generates the following prompt:

[0809] "Please prepare a proposal for a new marketing strategy for XYZ Corporation. The proposal should include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[0810] The generative AI model receives prompts and generates proposals and contracts with the same quality as a salesperson would produce manually. For example, it generates proposals like this:

[0811] "XYZ Co., Ltd.

[0812] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[0813] Proposal details:

[0814] Introducing new marketing strategies

[0815] Initial cost: 1 million yen

[0816] Monthly fee: 100,000 yen

[0817] We appreciate your consideration.

[0818] Sincerely"

[0819] The generated draft message is sent from the server to the terminal and presented to the user interactively. The user can check the displayed draft message and make corrections as necessary. This reduces the burden on sales staff and enables the efficient generation of high-quality draft messages.

[0820] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0821] Step 1:

[0822] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[0823] Customer name: XYZ Co., Ltd.

[0824] Proposal: Proposal for a new marketing strategy

[0825] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[0826] Input: Customer name, proposal details, contract terms

[0827] Output: Basic information entered by the user

[0828] Step 2:

[0829] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. The server analyzes the entered information and creates an appropriate prompt. For example, the server might generate a prompt such as, "Please prepare a proposal for a new marketing strategy for XYZ Co., Ltd. The proposal must include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[0830] Input: Basic information entered by the user

[0831] Output: Generated prompt statement

[0832] Step 3:

[0833] The server sends the prompt to a generative AI model (e.g., OpenAI's GPT-4) to generate a draft. The generative AI model creates a draft proposal or contract based on the prompt. For example, it might generate a draft like this:

[0834] "XYZ Co., Ltd.

[0835] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[0836] Proposal details:

[0837] Introducing new marketing strategies

[0838] Initial cost: 1 million yen

[0839] Monthly fee: 100,000 yen

[0840] We appreciate your consideration.

[0841] Sincerely"

[0842] Input: Generated prompt text

[0843] Output: Generated text proposal

[0844] Step 4:

[0845] The server transmits the generated draft text to the terminal and presents it to the user interactively. The user can check the displayed draft text and make corrections as necessary. The user can check the draft text on the terminal screen, check for errors in the draft text, and make corrections as necessary.

[0846] Input: Generated text proposal

[0847] Output: Proposal of text presented to the user

[0848] In this way, the server, terminal, and user work in cooperation, reducing the burden on salespeople and enabling efficient generation of high-quality draft text.

[0849] (Application example 2)

[0850] Next, a description will be given of Application Example 2 of Form 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."

[0851] The problem is that salespeople spend a lot of time and effort creating proposals and contracts. Furthermore, communicating with customers and managing the progress of sales activities are also time-consuming, making it difficult to conduct efficient sales activities. There is a need to solve these problems, reduce the burden on salespeople, and realize efficient sales activities.

[0852] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0853] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, means for automating communication with customers, means for automatically generating proposals and contracts, means for managing and analyzing customer information, and means for managing the progress of sales activities, which significantly reduces the burden on salespeople and enables more efficient sales activities.

[0854] "Historical information" refers to past data and records related to sales activities.

[0855] A "database" refers to an information management system that stores information systematically and allows it to be searched and retrieved as needed.

[0856] "Machine learning" refers to the technology that allows computers to learn patterns from data and make predictions and classifications.

[0857] "Draft proposal / contract text" refers to a draft proposal or contract that is presented to a customer in sales activities.

[0858] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[0859] "Interactive presentation means" refers to the way in which the user and the system interact with each other to exchange information.

[0860] "Means of automating communication with customers" refers to methods of automating communication with customers, such as email and chat.

[0861] "Means for automatically generating proposals and contracts" refers to a method for automatically creating proposals and contracts required for sales activities.

[0862] "Means for managing and analyzing customer information" refers to methods for organizing and analyzing data about customers.

[0863] "Means for managing the progress of sales activities" refers to methods for tracking and managing the progress of the sales process.

[0864] A system for implementing this invention is configured as follows: A server retrieves information from a database storing past information and uses machine learning to automatically generate draft proposal and contract wording. The generated draft wording is presented to the user interactively. The system also has the function of automating communication with customers and automatically generating proposals and contracts. It also includes the function of managing and analyzing customer information and managing the progress of sales activities.

[0865] Hardware and software used

[0866] Hardware: Servers, user devices (smartphones, PCs, etc.)

[0867] Software: API, database management system (e.g. MySQL)

[0868] Data processing and calculation

[0869] 1. Obtaining information from a database: The server obtains data on past sales activities from a database, including past proposals, contracts, and communication history with customers.

[0870] 2. Generating draft text using machine learning: Based on the acquired data, a machine learning model (e.g., OpenAI's GPT-3) is used to generate draft text for proposals and contracts.

[0871] 3. Interactive presentation: The generated draft text is interactively presented on the user's device, allowing the user to review the draft text and make corrections as necessary.

[0872] 4. Automating communication with customers: The server automates email and chat communication with customers based on the generated text suggestions.

[0873] 5. Automatic generation of proposals and contracts: The server automatically generates formal proposals and contracts based on the generated draft text.

[0874] 6. Management and analysis of customer information: The server organizes and analyzes customer information to improve the efficiency of sales activities.

[0875] 7. Sales Activity Progress Management: The server tracks and manages the progress of the sales process.

[0876] Specific examples

[0877] For example, if the customer name is "ABC Co., Ltd." and the product details are "the latest AI-enabled smartphone," the following prompt sentence would be sent to the generative AI model:

[0878] Prompt Sentence Examples

[0879] Customer Name: ABC Co., Ltd.

[0880] Product details: The latest AI-enabled smartphone

[0881] Please prepare your proposal based on the information below.

[0882] Based on this prompt, the generative AI model generates the text of the proposal, reducing the burden on the salesperson. The generated proposal is then presented interactively to the user's device, allowing the user to review the content and make any necessary revisions.

[0883] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0884] Step 1:

[0885] The server retrieves data on past sales activities from a database. The input is past proposals, contracts, communication history with customers, etc. stored in the database. The output is a collection of the retrieved data. This data is used in subsequent processing.

[0886] Step 2:

[0887] The server uses a machine learning model (e.g., OpenAI's GPT-3) based on the acquired data to generate a draft proposal or contract. The input is the data acquired in step 1. The output is the generated draft. Specifically, the server converts the data into a prompt sentence and sends it to the generative AI model.

[0888] Step 3:

[0889] The server interactively presents the generated draft text to the user terminal. The input is the draft text generated in step 2. The output is the draft text displayed on the user terminal. Specifically, the draft text is displayed on the user interface so that the user can check and modify it.

[0890] Step 4:

[0891] The server automates email and chat communications with customers based on the generated message templates. The input is the message template generated in step 2. The output is the email or chat message to be sent to the customer. Specifically, the server converts the message template into email or chat format and automatically sends it.

[0892] Step 5:

[0893] The server automatically generates a formal proposal or contract based on the generated draft text. The input is the draft text generated in step 2. The output is a formal proposal or contract. Specifically, the server formats the draft text into a formal document format and converts it into a format that can be saved and printed.

[0894] Step 6:

[0895] The server organizes and analyzes customer information. The input is customer information stored in a database. The output is the analysis results and organized customer information. Specifically, it organizes customer information by category and applies analytical algorithms to extract useful insights.

[0896] Step 7:

[0897] The server tracks and manages the progress of the sales process. The input is data and progress information about sales activities. The output is a progress report. Specifically, it tracks each stage of sales activities and generates a dashboard to visualize the progress.

[0898] Example 3

[0899] Next, a description will be given of Example 3 of Form Example 3. 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."

[0900] Conventional message draft generation systems generate message drafts without sufficient consideration of past approval history or approver tendencies, making it difficult to efficiently create message drafts that approvers will agree with. Furthermore, they did not adequately generate message drafts to reduce the burden on sales staff. This resulted in delays in the approval process and reduced work efficiency.

[0901] The specification process by the specification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a means for the user to input a prompt sentence, a means for the terminal to send the prompt sentence to the server, a means for the server to acquire past approval history and approver tendencies from a database, a means for generating a draft text using a generative AI model, a means for sending the generated draft text to the terminal, a means for the terminal to display the draft text to the user, and a means for the user to check the draft text and modify it as necessary. This makes it possible to efficiently generate draft text that takes into account past approval history and approver tendencies, and to provide a draft text that is likely to be acceptable to the approver. Furthermore, it is possible to reduce the burden on sales personnel and improve work efficiency.

[0902] A "database" is a system for storing past information and retrieving that information as needed.

[0903] "Artificial intelligence" refers to a program or system that uses machine learning to automatically generate draft text.

[0904] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[0905] A "prompt sentence" is a text that includes instructions and conditions for generating a sentence proposal, which is input by the user.

[0906] A "terminal" is a device through which a user enters prompt sentences and communicates with a server.

[0907] A "server" is a computer system that retrieves information from a database, generates draft text using a generative AI model, and transmits it to a terminal.

[0908] A "generative AI model" is an artificial intelligence model that learns from past data and generates draft text.

[0909] "Approval history" is data that includes past approval statements and feedback from approvers.

[0910] The "tendency of the approver" is a pattern based on what kind of text the approver has approved in the past or what kind of feedback the approver has provided.

[0911] A "draft text" is a draft document generated by the generative AI model that is likely to be acceptable to the approver.

[0912] A "user" is a person who enters prompt text and reviews and modifies the generated text suggestions.

[0913] The present invention relates to a system for generating draft wording in consideration of past approval history and the tendencies of approvers. A specific embodiment of this system will be described below.

[0914] First, the user inputs a prompt using a terminal. A prompt is text that includes instructions and conditions for generating a draft. For example, the prompt might say, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to place importance on specific figures and clear objectives."

[0915] The terminal sends the input prompt to the server using a communication protocol such as an HTTP POST request.

[0916] The server accesses the database to retrieve the approval history and approver trends. The database stores past approval statements and approver feedback. For example, it executes a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[0917] Next, the server runs a generative AI model based on the acquired data to generate a draft message. For example, OpenAI's GPT-4 is used as the generative AI model. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[0918] The generated draft text is sent from the server to the device using a communication protocol such as an HTTP response.

[0919] The terminal displays the received draft to the user. The user interface includes a text area and a display widget. The user can check the displayed draft and make corrections as necessary. The corrected draft is used as the final approval request.

[0920] This system makes it possible to efficiently generate draft texts that take into account past approval history and approver tendencies, and provide draft texts that are likely to be accepted by the approver. It also reduces the burden on sales personnel and improves work efficiency. The flow of the identification process in the third embodiment will be described with reference to FIG. 15.

[0921] Step 1:

[0922] The user enters a prompt statement.

[0923] The user inputs a prompt into an input field on the terminal, for example, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to value specific figures and clear objectives."

[0924] Input: prompt statement

[0925] Output: The prompt text entered

[0926] Step 2:

[0927] The terminal sends the prompt to the server.

[0928] The terminal sends the entered prompt sentence to the server as an HTTP POST request.

[0929] Input: prompt statement

[0930] Output: The prompt sent to the server

[0931] Step 3:

[0932] The server retrieves the past approval history and approver tendencies from the database.

[0933] The server accesses the database to retrieve the approval history and approver trends, for example, by executing a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[0934] Input: prompt statement, database

[0935] Output: Past approval history and approver trends

[0936] Step 4:

[0937] The server generates draft text using a generative AI model.

[0938] The server runs a generative AI model (such as OpenAI's GPT-4) based on the acquired data to generate a draft message. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[0939] Input: Past approval history and approver trends

[0940] Output: Generated text proposal

[0941] Step 5:

[0942] The server transmits the generated draft text to the terminal.

[0943] The server sends the generated draft text to the terminal as an HTTP response.

[0944] Input: Generated text proposal

[0945] Output: Proposal sent to the terminal

[0946] Step 6:

[0947] The terminal displays the draft message to the user.

[0948] The terminal displays the received message in the text area, allowing the user to check the displayed message.

[0949] Input: Proposal sent to the terminal

[0950] Output: Proposed text displayed to the user

[0951] Step 7:

[0952] The user checks the draft and makes corrections as necessary.

[0953] The user checks the displayed draft and makes any necessary changes. For example, they can change "Personnel costs: 5 million yen" to "Personnel costs: 6 million yen." The revised draft is used as the final approval request.

[0954] Input: Proposed text displayed to the user

[0955] Output: Revised text

[0956] (Application example 3)

[0957] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0958] Conventional electronic payment systems have the problem of taking a great deal of time and effort to create approval documents that the approver will agree to. Furthermore, approval processes are often delayed because approval documents are created without taking into account the approver's preferences. This leads to inefficiencies in the approval process for expense settlements and large transactions within companies, resulting in a decline in overall business efficiency.

[0959] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0960] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for the proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, and means for learning the tendencies of approvers and generating draft proposals that are likely to be acceptable to the approvers. This makes it possible to quickly generate draft proposals that are easy for approvers to accept, and to streamline the approval process for electronic payments.

[0961] "Past information" refers to data and history that the system has collected in the past.

[0962] A "database" is a collection of information that systematically stores past information and allows it to be searched and retrieved as needed.

[0963] "Machine learning" is a technology that allows computers to analyze large amounts of data and automatically learn patterns and rules.

[0964] "Draft text of proposal / contract portion" refers to the draft text included in the proposal or contract.

[0965] "Artificial intelligence" refers to systems that use techniques such as machine learning to mimic human intelligence and automatically perform specific tasks.

[0966] "Interactive presentation means" refers to the interface that allows the user and the system to exchange information interactively.

[0967] "Approver trends" is data that indicates the standards and patterns that a particular approver has used in approving in the past.

[0968] "Draft text that is likely to be accepted by the approver" refers to a draft of text that is likely to be approved, created taking into account the approver's past tendencies.

[0969] As an embodiment of the present invention, an electronic payment approval assistant system will be described as an example. This system operates in cooperation with three entities: a server, a terminal, and a user.

[0970] First, the server has a database that stores past information, including data on past approval history and approver tendencies. The server retrieves information from this database and uses machine learning to automatically generate draft proposal and contract wording. Specifically, the server uses APIs based on Python, Pandas, and OpenAI to analyze past approval history and learn approver tendencies.

[0971] The generated draft is then presented interactively to a terminal, which is a device used by the user, such as a smartphone or tablet, through which the user can review the draft and make any necessary corrections. The interactive interface is designed to be easy for users to operate.

[0972] Furthermore, the server learns the approver's tendencies and generates a message that is likely to be accepted by the approver. In this process, a generative AI model is used to generate message suggestions based on features extracted from past approval history. Specific examples of prompts include the following:

[0973] Example prompt sentence:

[0974] Generate the following wording suggestions based on the approver's tendencies:

[0975] This trip is an important meeting with a new client and requires prompt approval.

[0976] Approver tendency: {features extracted from the approver's past approval history}

[0977] This system can quickly generate draft text that is easy for the approver to understand, making it possible to streamline the approval process for electronic payments.As a specific example, consider the approval process for expense reimbursement within a company.When an employee applies for reimbursement for travel expenses and their supervisor's approval is required, by using this system, a draft text that is easy for the supervisor to understand can be automatically generated, allowing for quick approval.

[0978] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0979] Step 1:

[0980] The server obtains approval history data from a database that stores past information.

[0981] Input: Past approval history data stored in the database

[0982] Output: Acquired approval history data

[0983] Specific operation: The server uses an SQL query to extract past approval history data from the database.

[0984] Step 2:

[0985] The server inputs the acquired approval history data into a machine learning model to learn the approver's tendencies.

[0986] Input: Acquired approval history data

[0987] Output: Learning results about approver tendencies

[0988] How it works: The server preprocesses the data using publicly known libraries and inputs it into a machine learning model. The model learns past approval patterns and extracts approver tendencies.

[0989] Step 3:

[0990] Based on the learning results, the server inputs a prompt sentence into the generative AI model and generates a draft sentence.

[0991] Input: Learning results on approver tendencies, prompt text

[0992] Output: Generated text proposal

[0993] Specific operation: The server uses OpenAI's API to input the prompt sentence and learning results into the generative AI model to generate a draft sentence.

[0994] Step 4:

[0995] The server transmits the generated draft text to the terminal and presents it interactively.

[0996] Input: Generated text proposal

[0997] Output: Proposal displayed on the terminal

[0998] Specific operation: The server sends the generated draft text to the terminal via an HTTP request, and the terminal displays it on the user interface.

[0999] Step 5:

[1000] The user checks the draft text generated through the terminal and makes corrections as necessary.

[1001] Input: Proposal of text displayed on the terminal

[1002] Output: Revised text

[1003] Specific operation: The user uses the terminal interface to check the draft text and, if necessary, makes corrections in a text editor.

[1004] Step 6:

[1005] The server stores the revised draft as the final approved document.

[1006] Input: Revised draft text

[1007] Output: Final approval statement saved

[1008] Specific operation: The server saves the revised draft text in the database and completes the approval process.

[1009] 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.

[1010] "Example 1"

[1011] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes a user's emotions. The emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. Specifically, it generates positive suggestions when the user is happy, and apologetic suggestions when the user is angry.

[1012] "Example 2"

[1013] The emotion engine also adjusts the message suggestions based on the user's emotions. Specifically, it generates positive language when the user is happy, and apologetic language when the user is angry. For example, when the user is happy, it generates a message like "This proposal will lead to further success in your business," and when the user is angry, it generates a message like "We deeply apologize that our service did not meet your expectations."

[1014] "Example 3"

[1015] Furthermore, the emotion engine automatically generates proposals for the proposal and contract sections based on the user's emotions. Specifically, it generates positive proposals when the user is happy, and proposals that include words of apology when the user is angry. For example, when the user is happy, it generates a proposal such as "This proposal will lead to further success in your business," and when the user is angry, it generates a proposal such as "We deeply apologize that our service did not meet your expectations."

[1016] The processing flow of each embodiment will be described below.

[1017] "Example 1"

[1018] Step 1: The AI ​​activates an emotion engine that infers emotions from the user's tone of voice, facial expressions, and choice of words.

[1019] Step 2: The emotion engine recognizes the user's emotion and determines the content of the suggestion based on that emotion.

[1020] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and presents it to the user.

[1021] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[1022] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposed text based on the emotion.

[1023] Step 3: Based on the results of the emotion engine, the AI ​​generates a draft message and presents it to the user.

[1024] "Example 3"

[1025] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[1026] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposal and contract portion based on that emotion.

[1027] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and contract portion and presents it to the user.

[1028] Example 1

[1029] Next, a description will be given of Example 1 of Form 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."

[1030] In conventional sales activities, salespeople had to manually refer to information on past contracts and proposals to create new proposals. This work required time and effort, increasing the burden on salespeople. It was also difficult to make appropriate proposals based on the user's emotions, making it difficult to improve customer satisfaction.

[1031] 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.

[1032] In this invention, the server includes means for acquiring information from a database storing past information, means for training a machine learning model using the acquired information, means for automatically generating draft proposals for the proposal and contract portion using the trained machine learning model, means for presenting the generated draft proposals through an interactive interface, means including an emotion engine for recognizing user emotions, and means for adjusting the draft proposals based on information obtained from the emotion engine. This reduces the burden on sales staff and makes it possible to make optimal proposals based on the user's emotions.

[1033] A "database" is an information management system that stores past information and enables the efficient retrieval of necessary information.

[1034] A "machine learning model" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[1035] "Training" is the process of training a machine learning model using large amounts of data to learn and improve its performance.

[1036] A "draft" is a draft of a document that describes the contents of a proposal or contract.

[1037] An "interactive interface" is a user interface that allows two-way communication between a user and a system.

[1038] The "emotion engine" is a system that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[1039] "Adjustment" means changing content or settings to suit specific conditions or circumstances.

[1040] MODE FOR CARRYING OUT THE INVENTION

[1041] This invention is a system that acquires information from a database that stores past information and uses machine learning to automatically generate draft proposal and contract wording. Specific embodiments of this system are described below.

[1042] Retrieving information from a database

[1043] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, and customer responses. The server uses an SQL query to extract past contract information from the database. For example, it executes a query such as "SELECT FROM contracts WHERE date > '2020-01-01'".

[1044] Training a machine learning model

[1045] The server uses the acquired information to train a machine learning model. This model is capable of automatically generating draft proposal and contract wording using techniques such as deep learning and reinforcement learning. Specifically, it uses a framework such as TensorFlow. The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[1046] Generate draft text

[1047] The server uses a trained machine learning model to generate draft proposal and contract text. These draft proposals are designed to include optimal content based on past data. The server inputs a prompt text into the generative AI model to generate a draft proposal. For example, it executes code such as "generate_text('Generate a new proposal text')".

[1048] Proposal of text is presented through the interface

[1049] The terminal presents the generated message draft to the salesperson through a conversational interface. This interface can be implemented in the form of a chatbot or voice assistant. The terminal displays the generated message draft on the chatbot's UI. For example, it executes a code such as "chatbot.display_message(generated_text)".

[1050] Recognizing user emotions with an emotion engine

[1051] The device recognizes the user's emotions using an emotion engine. This emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. The device uses OpenCV to analyze the user's facial expressions and infer emotions. For example, it executes code such as "emotion = emotion_recognition.detect_face_expression(user_image)".

[1052] Adjusting message proposals according to emotions

[1053] The server generates text suggestions based on the information obtained from the emotion engine according to the user's emotions. If the user is happy, it generates a positive suggestion, and if the user is angry, it generates a suggestion including an apology. Based on the output of the emotion engine, the server inputs an appropriate prompt sentence into the generative AI model. For example, it executes code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[1054] Specific examples

[1055] Example 1: Proposal Generation

[1056] The following proposal is generated based on the user's past contract information.

[1057] Example prompt sentence:

[1058] "Generate new proposals based on past contract information."

[1059] An example of a generated suggestion:

[1060] "Customer, based on the terms of your previous contract, we would like to make you a new proposal with similar conditions. We appreciate your consideration."

[1061] Example 2: Adjusting message proposals based on emotions

[1062] If the user is angry, the emotion engine will recognize that emotion and generate a suggested message that includes an apology.

[1063] Example prompt sentence:

[1064] "Generate suggestion sentences for when the user is angry."

[1065] An example of a generated suggestion:

[1066] "Dear customer, we apologize for the inconvenience. With this proposal, we will improve the past issues and offer you better terms."

[1067] In this way, the system utilizes past data to automatically generate optimal suggestions based on the user's emotions.

[1068] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] The server retrieves the information from a database that stores past information.

[1071] Input: Database query (e.g., "SELECT FROM contracts WHERE date > '2020-01-01'")

[1072] Data processing: Execute SQL queries to extract past contract information.

[1073] Output: A dataset of retrieved contract information

[1074] Specific operation: The server extracts past contract information from the database using an SQL query, for example, "SELECT FROM contracts WHERE date > '2020-01-01'".

[1075] Step 2:

[1076] The server uses the acquired information to train a machine learning model.

[1077] Input: Dataset of retrieved contract information

[1078] Data processing: Preprocessing the dataset and converting it into a format suitable for machine learning models.

[1079] Output: A trained machine learning model

[1080] Specific operation: The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[1081] Step 3:

[1082] The server uses the trained machine learning model to generate draft proposal and contract text.

[1083] Input: A trained machine learning model, a prompt (e.g., "Generate a new suggestion")

[1084] Data processing: The prompt sentence is input into the model and a draft sentence is generated.

[1085] Output: Generated text proposal

[1086] Specific operation: The server inputs a prompt sentence into the generative AI model and generates a text suggestion. For example, it executes a code such as "generate_text('Generate a new suggested text')".

[1087] Step 4:

[1088] The terminal presents the generated draft message to the salesperson through an interactive interface.

[1089] Input: Generated text proposal

[1090] Data processing: Converting the draft text into a format suitable for the interactive interface.

[1091] Output: Proposal of text to be presented to the salesperson

[1092] Specific operation: The terminal displays the generated message on the chatbot's UI, for example, by executing code such as "chatbot.display_message(generated_text)".

[1093] Step 5:

[1094] The terminal uses an emotion engine to recognize the user's emotions.

[1095] Input: Your tone of voice, facial expressions, and word choice

[1096] Data processing: Analyze user emotions using an emotion engine.

[1097] Output: Estimated user emotion

[1098] Specific operation: The device uses OpenCV to analyze the user's facial expression and estimate their emotion. For example, it executes code like "emotion = emotion_recognition.detect_face_expression(user_image)".

[1099] Step 6:

[1100] The server generates a message proposal based on the user's emotions based on the information obtained from the emotion engine.

[1101] Input: Estimated user sentiment, trained machine learning model

[1102] Data processing: Generate prompt sentences according to the emotion, input them into the model, and generate draft sentences.

[1103] Output: Suggested text based on emotion

[1104] Specific operation: The server inputs an appropriate prompt sentence to the generative AI model based on the output of the emotion engine. For example, it executes a code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[1105] (Application example 1)

[1106] Next, a description will be given of Application Example 1 of Form 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."

[1107] With conventional sales support systems, it was difficult for salespeople to quickly refer to past proposals and contract information and make optimal proposals when dealing with customers. It was also difficult to recognize customer emotions in real time and make proposals accordingly. Furthermore, in physical stores, when sales staff deal with customers, they are required to make optimal proposals based on past sales data and proposal content, but there was a lack of efficient means to do this. To solve these issues, a system that recognizes customer emotions and generates proposal text that corresponds to them is needed.

[1108] 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.

[1109] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating proposal and contract wording proposals using machine learning, means for interactively presenting the generated proposal wording proposals, an emotion engine for recognizing a user's emotions, means for generating proposal wording according to the user's emotions, and means installed in smart glasses to support customer service. This enables salespeople and store clerks to quickly make optimal proposals based on past proposal and contract information when serving customers, and further enables proposals according to the customer's emotions to be made in real time.

[1110] "Past information" refers to data that includes information on contracts and proposals that corporate sales have made in the past.

[1111] A "database" is a system that stores past information and can retrieve that information as needed.

[1112] "Artificial intelligence" is a technology that uses machine learning to automatically generate draft proposal and contract wording.

[1113] "Interactive presentation" refers to a method in which the generated draft text is presented to the salesperson via a chatbot, voice assistant, etc.

[1114] The "emotion engine" is a technology that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[1115] The "means for generating a suggested message according to the user's emotions" is a method for generating an appropriate suggested message based on the emotions estimated by the emotion engine.

[1116] "Smart glasses" are wearable devices equipped with a display and camera that can display information and capture images.

[1117] The "means for supporting customer service" is a method that uses smart glasses to display optimal suggestion text when a store clerk is interacting with a customer.

[1118] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposal and contract wording, a means for interactively presenting the generated draft proposals, an emotion engine that recognizes the user's emotions, a means for generating proposal wording in accordance with the user's emotions, and a means that is installed in smart glasses and supports customer service.

[1119] The server retrieves information from a database that stores past information and uses machine learning to automatically generate proposal and contract wording. Specifically, it uses deep learning and reinforcement learning models trained with TensorFlow. The generated wording is presented to the salesperson through a conversational interface such as a chatbot or voice assistant.

[1120] The device uses smart glasses to capture the customer's facial expressions and tone of voice, and recognizes the user's emotions using an emotion engine. The emotion engine uses an emotion recognition model based on TensorFlow to infer emotions from the user's tone of voice, facial expressions, and choice of words. Based on the inferred emotions, a generative AI model is used to generate optimal suggested text. The generative AI model uses natural language generation models such as GPT-2.

[1121] When a user wears the smart glasses and interacts with a customer, the smart glasses display shows the optimal proposal based on past sales data and the content of the proposal, allowing the user to make proposals in real time that reflect the customer's emotions.

[1122] For example, if a customer is looking at a product with a smile, the emotion recognition model will determine this as "joy" and generate a suggestion message such as, "This product is particularly popular. We're offering a special discount right now, so please give it a try." If the customer has a confused expression, the emotion recognition model will determine this as "confused" and generate a suggestion message such as, "If you need any help, we'd be happy to help you."

[1123] An example of a prompt is as follows:

[1124] "Optimal Proposal Text When Customers are Happy: Past Proposal Data"

[1125] "Optimal Proposal Text for Customers in a Confused State: Past Proposal Data"

[1126] This allows salespeople and store clerks to quickly make optimal proposals based on past proposals and contract information when dealing with customers, and also allows them to make proposals in real time that reflect the customer's emotions.

[1127] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1128] Step 1:

[1129] The server retrieves the information from a database that stores past information.

[1130] Input: Past proposals and contract information stored in a database

[1131] Output: Past proposal and contract information obtained

[1132] What happens: The server uses SQL queries to extract the necessary information from the database and loads it into memory.

[1133] Step 2:

[1134] The server uses machine learning to automatically generate draft proposal and contract wording based on the acquired information.

[1135] Input: Past proposals and contract information

[1136] Output: Generated proposal and contract draft

[1137] Specific operation: The server inputs data into deep learning models and reinforcement learning models trained using TensorFlow to generate optimal text suggestions.

[1138] Step 3:

[1139] The server presents the generated draft text to the salesperson through an interactive interface.

[1140] Input: Generated proposal and contract draft

[1141] Output: Proposal of text presented to the salesperson

[1142] Specific operation: The server sends the generated draft message to the salesperson's device via a chatbot or voice assistant and displays it.

[1143] Step 4:

[1144] The device uses smart glasses to capture the customer's facial expressions and tone of voice.

[1145] Input: Customer facial expressions and tone of voice

[1146] Output: Captured customer facial expressions and tone of voice data

[1147] How it works: The device uses a camera and microphone in its smart glasses to capture the customer's facial expressions and voice in real time.

[1148] Step 5:

[1149] The terminal inputs the captured data into an emotion engine to recognize the user's emotion.

[1150] Input: Captured customer facial and tone of voice data

[1151] Output: Estimated user emotion

[1152] Specific operation: The device inputs data into an emotion recognition model using TensorFlow to estimate the user's emotions.

[1153] Step 6:

[1154] The server uses a generative AI model to generate optimal suggested text based on the estimated emotions.

[1155] Input: Estimated user sentiment, past suggestion data

[1156] Output: Suggested text based on emotion

[1157] Specific operation: The server inputs the prompt sentence into a natural language generation model such as GPT-2 and generates the optimal suggested sentence.

[1158] Step 7:

[1159] The terminal displays the generated proposal text on the display of the smart glasses.

[1160] Input: Generated suggestion text

[1161] Output: Suggestion text displayed on the smart glasses display

[1162] Specific operation: The terminal sends the generated proposal text to the display of the smart glasses and displays it.

[1163] This allows the user to make suggestions in real time that correspond to the customer's emotions.

[1164] Example 2

[1165] Next, a description will be given of Example 2 of Form 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."

[1166] In conventional sales activities, salespeople spend a lot of time and effort creating proposals and contracts. In addition, it is difficult to generate appropriate wording that reflects the user's emotions, making it difficult to improve customer satisfaction.

[1167] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft wording for the proposal and contract portion using machine learning, means for interactively presenting the generated draft wording, an emotion engine for analyzing the user's emotions, and means for adjusting the draft wording based on the user's emotions. This reduces the burden on the salesperson and makes it possible to generate appropriate draft wording based on the user's emotions.

[1168] A "database" is a system for storing past information and retrieving that information as needed.

[1169] "Artificial intelligence" is a technology that uses machine learning to automatically generate draft proposals and contract wording.

[1170] The "means for interactive presentation" is a method for interactively displaying the generated draft text to the user.

[1171] An "emotion engine" is a technology for analyzing a user's emotions and identifying their emotional state.

[1172] The "means for adjusting the proposed text" is a method for appropriately correcting the proposed text generated based on the user's feelings.

[1173] MODE FOR CARRYING OUT THE INVENTION

[1174] The present invention relates to a system for reducing the burden on salespeople and generating appropriate message proposals in response to user emotions. Specific embodiments of this system will be described below.

[1175] System configuration

[1176] The system consists of the following main components:

[1177] 1. Database: A system for storing past information and retrieving it when needed.

[1178] 2. Artificial Intelligence (AI): This technology uses machine learning to automatically generate proposal and contract wording. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-4).

[1179] 3. Interactive presentation: The generated draft text is displayed interactively to the user, for example, using a web interface or a mobile application.

[1180] 4. Emotion Engine: This technology analyzes the user's emotions and identifies their emotional state. Specifically, it uses an emotion engine.

[1181] 5. Means for adjusting text suggestions: A method for appropriately modifying generated text suggestions based on the user's emotions.

[1182] System Operation

[1183] The server collects basic information such as the proposal details and contract terms entered by the user into the terminal. For example, if the user proposes a new marketing strategy, the proposal details "new marketing strategy" and the contract terms "annual contract" are entered.

[1184] Next, the server generates a prompt for the generative AI model based on the data entered by the user. For example, it generates the following prompt:

[1185] Proposal: New marketing strategy

[1186] Terms and conditions: Annual contract

[1187] Generate a draft of the text.

[1188] The server sends the generated prompt to the generative AI model, which then generates a suggested message based on the prompt, such as "This new marketing strategy will lead to greater success for your business."

[1189] The server then collects the user's emotion data and sends it to the emotion engine, which analyzes the user's emotions and identifies their emotional state, such as happy or angry.

[1190] The server adjusts the generated message proposals based on the analysis results of the emotion engine. For example, if the user is happy, the server adjusts the message proposal to include positive language. If the user is angry, the server adjusts the message proposal to include apologetic language.

[1191] Finally, the server transmits the adjusted final draft text to the terminal, and the user can check the final draft text on the terminal and modify it as necessary.

[1192] Specific examples

[1193] As a concrete example, consider the following scenario:

[1194] Scenario 1: Happy users

[1195] Input data: Proposal content "New marketing strategy", contract terms "Annual contract"

[1196] Output of the generative AI model: Proposed text: "This new marketing strategy will make your business even more successful."

[1197] Adjusting the emotion engine: Generate text suggestions containing positive words because the user is happy

[1198] Scenario 2: The user is angry

[1199] Input data: Proposal content "Service improvement proposal", contract terms "Monthly contract"

[1200] Output of generative AI model: Proposed text: "We deeply apologize that our service did not meet your expectations."

[1201] Adjusting the emotion engine: Generate a message containing an apology because the user is angry.

[1202] In this way, the system operates in which the server, terminal, and user work together to generate draft wording to reduce the burden on salespeople.

[1203] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1204] Step 1: Collecting User Input Data

[1205] The user inputs basic information such as the proposal content and contract terms into the terminal. For example, if the user is proposing a new marketing strategy, the proposal content is "New Marketing Strategy" and the contract terms are "Annual Contract." The input data is sent to the server.

[1206] Step 2: Generate prompts for the generative AI model

[1207] The server generates a prompt for the generative AI model based on the data entered by the user. For example, it generates the following prompt:

[1208] Proposal: New marketing strategy

[1209] Terms and conditions: Annual contract

[1210] Generate a draft of the text.

[1211] This prompt is sent to a generative AI model.

[1212] Step 3: Generate copy using a generative AI model

[1213] The server sends the generated prompt to a generative AI model (for example, OpenAI's GPT-4). The generative AI model generates a message based on the prompt. For example, it might generate a message like, "This new marketing strategy will lead to greater success for your business." The generated message is then returned to the server.

[1214] Step 4: Analyze user sentiment with the emotion engine

[1215] The server collects the user's emotion data and sends it to the emotion engine, which analyzes the user's emotion and identifies the user's emotional state, such as happy, angry, etc. The analysis result is returned to the server.

[1216] Step 5: Adjust the draft copy based on sentiment

[1217] The server adjusts the generated message proposals based on the analysis results of the emotion engine. For example, if the user is happy, the message proposal is adjusted to include more positive language. If the user is angry, the message proposal is adjusted to include more apologetic language. The adjusted message proposals are saved on the server.

[1218] Step 6: Output the final draft

[1219] The server sends the final draft text to the terminal, where the user can review it and make any necessary changes. After the user has confirmed it, the final draft text will be used as a formal proposal or contract document.

[1220] (Application example 2)

[1221] Next, a description will be given of Application Example 2 of Form 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."

[1222] In conventional sales activities, salespeople spend a great deal of time and effort creating proposal and contract drafts. They also need to respond appropriately to customer emotions, but this is difficult to do manually. This increases the salesperson's workload and can potentially lead to a decrease in customer satisfaction. Therefore, there is a need for a system that can reduce the salesperson's workload and automatically generate appropriate drafts based on customer emotions.

[1223] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1224] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, means for analyzing user emotions, and means for adjusting the draft proposals based on the user emotions. This reduces the burden on sales staff and enables the automatic generation of appropriate draft proposals in accordance with customer emotions.

[1225] A "database" is a system for storing past information and retrieving that information as needed.

[1226] "Machine learning" is a technology that allows computers to learn patterns from data and make predictions and classifications.

[1227] "Draft proposal / contract text" refers to a draft document used when making proposals or contracts with customers in sales activities.

[1228] The "interactive presentation means" is an interface for displaying the generated draft text while interacting with the user.

[1229] "Means for analyzing user emotions" refers to technology for analyzing emotions from user input and behavior.

[1230] The "means for adjusting a proposed message based on the user's emotions" is a technique for appropriately changing a proposed message in accordance with the analyzed user's emotions.

[1231] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a database storing past information, a machine learning model, a sentiment analysis engine, and a generative AI model. The terminal is a device operated by the user, such as a smartphone or PC. The user is a salesperson or customer support representative.

[1232] The server first retrieves past information from a database. This information includes past proposals, contract texts, and customer feedback. Next, it uses a machine learning model to automatically generate proposal and contract texts from the retrieved information. These generated texts are then presented interactively on the terminal.

[1233] The user can review the draft text and make corrections if necessary. In addition, the server uses a sentiment analysis engine to analyze emotions from the user's input and behavior. The sentiment analysis engine can utilize existing sentiment analysis tools.

[1234] Once the user's emotions are analyzed, a generative AI model adjusts the suggested message based on that emotion. For example, if the user is happy, it will generate a positive message, and if the user is angry, it will generate a message containing an apology. This process uses generative AI models such as OpenAI's GPT-3.

[1235] For example, if the user is satisfied with the product, the prompt might read:

[1236] Prompt: Suggested prompt for a happy user: Thank you for your recent purchase. We hope you are satisfied with our service.

[1237] By inputting this prompt sentence into a generative AI model, it is possible to generate appropriate sentence suggestions that correspond to the user's emotions.

[1238] This system reduces the burden on sales staff and enables the automatic generation of appropriate message proposals based on customer emotions, which is expected to improve customer satisfaction and sales efficiency.

[1239] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1240] Step 1:

[1241] The server retrieves past information from a database. The input is data such as past proposals, contract documents, and customer feedback. The output is the retrieved past information. Specifically, the server executes SQL queries to extract the required information from the database.

[1242] Step 2:

[1243] The server uses a machine learning model to automatically generate draft proposals and contracts from the acquired information. The input is the past information acquired in step 1. The output is the generated draft proposals. Specifically, the server runs a machine learning algorithm to generate new draft proposals based on past information.

[1244] Step 3:

[1245] The server interactively presents the generated draft text on the terminal. The input is the draft text generated in step 2. The output is the draft text displayed on the terminal. Specifically, the server sends the draft text to the terminal in JSON format, and the terminal displays it on the user interface.

[1246] Step 4:

[1247] The user checks the draft text through the terminal and makes corrections as necessary. The input is the draft text presented in step 3. The output is the draft text corrected by the user. In concrete terms, the user edits the draft text using the input field on the terminal.

[1248] Step 5:

[1249] The server uses a sentiment analysis engine to analyze emotions from the user's input and behavior. The input is the draft text corrected in step 4 and the user's input data. The output is the user's sentiment score. Specifically, the server calls an API, analyzes the user's input data, and obtains the sentiment score.

[1250] Step 6:

[1251] The server uses a generative AI model to adjust the suggested sentences based on the user's emotions. The input is the emotion score obtained in step 5 and the suggested sentences modified in step 4. The output is the suggested sentences adjusted according to the emotions. Specifically, the server inputs the prompt sentence into OpenAI's GPT-3 model and generates suggested sentences according to the emotions.

[1252] Step 7:

[1253] The server presents the adjusted draft text again to the terminal. The input is the draft text adjusted in step 6. The output is the final draft text displayed on the terminal. Specifically, the server sends the adjusted draft text to the terminal in JSON format, and the terminal displays it on the user interface.

[1254] Example 3

[1255] Next, a description will be given of Example 3 of Form Example 3. 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."

[1256] Conventional systems could generate draft messages based on past information, but they were unable to generate draft messages that reflected the user's emotions. This made it difficult to automatically generate proposals, apologies, and other messages that matched the user's emotions. Furthermore, there was a lack of concrete means for generating draft messages that would satisfy the approver, which resulted in an inefficient approval process.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1258] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, an emotion engine for detecting user emotions, and means for generating draft proposals based on emotion data acquired from the emotion engine. This makes it possible to automatically generate appropriate draft proposals according to the user's emotions and provide draft proposals that are likely to be acceptable to the approver.

[1259] A "database" is a system for storing past information and retrieving that information as needed.

[1260] "Artificial intelligence" is a technology that uses machine learning to analyze data and automatically generate draft proposals and contract wording.

[1261] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to confirm and modify the draft text.

[1262] An "emotion engine" is a technology that detects emotions from a user's facial expressions, voice, etc. and analyzes that emotional data.

[1263] "Emotion data" is data that indicates the user's emotional state detected by the emotion engine.

[1264] A "draft text" is a draft of a proposal or contract that is generated by artificial intelligence.

[1265] This invention is a system that combines a database that stores past information, artificial intelligence that generates text suggestions using machine learning, and an emotion engine that detects the user's emotions. Specific embodiments of this system are described below.

[1266] System configuration

[1267] Database

[1268] The server uses a database that stores past approval history and approver trends. This database can be a relational database management system (RDBMS) such as MySQL. The database stores approval history data and approver trend data.

[1269] artificial intelligence

[1270] The server uses a generative AI model (e.g., GPT-4) to generate draft text based on information retrieved from the database. The generative AI model learns past approval history and approver tendencies, and generates new draft text based on that information.

[1271] Emotion Engine

[1272] The device uses an emotion engine to detect the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[1273] System Operation

[1274] Data collection

[1275] The server retrieves the past approval history data and approver trend data from the database. For example, the server retrieves the data by executing an SQL query such as "SELECT FROM approval_history WHERE approver_id = 'X'".

[1276] Data Learning

[1277] The server inputs the acquired data into the generative AI model and trains it. During the training process, it analyzes past approval history and approver tendencies to extract patterns.

[1278] Text generation

[1279] The server inputs a prompt into the generative AI model that has completed training, generating a new draft message. The prompt message contains specific instructions based on the approver's tendencies. For example, the server inputs a prompt message such as, "Please generate a draft message that approver X will be satisfied with. Please include specific numerical values."

[1280] Emotion Detection

[1281] The device captures the user's facial expression with a camera, calls an API, and sends the analysis results to the server. For example, if the user is happy, the emotion engine detects that emotion and sends the data "the user is happy" to the server.

[1282] Emotion-based text generation

[1283] The server generates appropriate message suggestions based on the received emotion data. For example, if the user is happy, the server inputs a prompt message such as "Please generate a message suggestion for when the user is happy" into the generative AI model. The generative AI model then generates a message suggestion such as "This suggestion will lead to further success in your business."

[1284] Specific examples

[1285] Examples of data collection

[1286] The server executes the SQL query "SELECT FROM approval_history WHERE approver_id = 'X'" to retrieve data from the database.

[1287] Example of text generation

[1288] The server inputs the prompt "Please generate a draft wording that will satisfy Approver X. Please include specific numerical values" into the generative AI model and receives the generated draft wording.

[1289] Example of emotion-based text generation

[1290] The server inputs the prompt "Please generate suggested message suggestions for when the user is happy" into the generative AI model and presents the generated message suggestions to the user.

[1291] In this way, the system generates an optimal draft message according to the emotions of the approver and the user in cooperation with the server, the terminal, and the user. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1292] Step 1: Data collection

[1293] The server retrieves past approval history data and approver trend data from the database. As input, it executes an SQL query (e.g., "SELECT FROM approval_history WHERE approver_id = 'X'"), and as output, it loads the retrieved data into memory. Specifically, the server establishes a database connection, executes the SQL query, and retrieves the results.

[1294] Step 2: Data training

[1295] The server inputs the acquired data into a generative AI model (e.g., GPT-4) and trains the model. It uses past approval history data and approver tendency data as input, and obtains a trained generative AI model as output. Specifically, the server preprocesses the data and inputs it into the generative AI model to begin the learning process.

[1296] Step 3: Generate text suggestions

[1297] The server inputs a prompt sentence into the generative AI model that has completed training, generating a new draft text. The prompt sentence (e.g., "Please generate a draft text that approver X will be satisfied with. Please include specific numerical values.") is used as input, and the generated draft text is obtained as output. Specifically, the server inputs the prompt sentence into the generative AI model and receives the generated draft text.

[1298] Step 4: Emotion detection

[1299] The device captures the user's facial expression with a camera, calls the API, and sends the analysis results to the server. The user's facial expression data is used as input, and the analyzed emotion data is obtained as output. Specifically, the device captures the user's facial expression with a camera, sends the data to the API, and receives the analysis results.

[1300] Step 5: Generate text suggestions based on emotions

[1301] The server generates appropriate message suggestions based on the received emotion data. It uses emotion data (e.g., "The user is happy") as input and obtains message suggestions corresponding to the emotion as output. Specifically, the server analyzes the emotion data, inputs a prompt (e.g., "Please generate suggested message suggestions for when the user is happy") into the generative AI model, and receives the generated message suggestions.

[1302] In this way, the system works in cooperation with the server, terminal, and user to generate optimal draft text that reflects the emotions of the approver and user.

[1303] (Application example 3)

[1304] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1305] Conventional message draft generation systems had difficulty generating message drafts that took the user's emotions into account, and were unable to increase user satisfaction. Furthermore, there was a lack of appropriate means for generating message drafts that would satisfy the approver, which sometimes delayed the approval process. Furthermore, there was insufficient generation of message drafts to reduce the burden on sales staff.

[1306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes: artificial intelligence that acquires information from a database storing past information and automatically generates draft proposals for the proposal and contract portions using machine learning; means for interactively presenting the generated draft proposals; an emotion engine that analyzes the user's emotions; and means for adjusting the draft proposals based on the emotion engine. This makes it possible to generate draft proposals that take the user's emotions into consideration, thereby increasing user satisfaction. Furthermore, by generating draft proposals that are satisfactory to the approver, delays in the approval process can be prevented. Furthermore, draft proposals can also be generated to reduce the burden on sales staff.

[1307] "Past information" refers to data such as the user's or approver's past behavioral history, transaction history, and approval history.

[1308] A "database" refers to an information accumulation system that systematically stores past information and allows it to be searched and retrieved as needed.

[1309] "Machine learning" refers to a technology that allows computers to analyze large amounts of data, find patterns and regularities, and then automatically perform specific tasks.

[1310] "Draft of proposal / contract portion" refers to a draft document that describes the proposal content and contract content to be presented to the user or approver.

[1311] "Artificial intelligence" refers to computer systems that use technologies such as machine learning and natural language processing to imitate and assist human intellectual tasks.

[1312] The "means for interactive presentation" refers to an interface for interactively displaying the generated draft text to the user or approver and receiving feedback.

[1313] An "emotion engine" refers to a software module that analyzes a user's emotions and takes appropriate action based on the results.

[1314] "Means for adjusting proposed text" refers to the function for appropriately correcting and adjusting the generated proposed text based on the analysis results of the emotion engine.

[1315] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposals for proposal and contract portions, a means for interactively presenting the generated draft proposals, an emotion engine that analyzes user emotions, and a means for adjusting the draft proposals based on the emotion engine.

[1316] The server first retrieves information from the database, such as the user's or approver's past behavioral history, transaction history, and approval history. Based on this information, a machine learning algorithm is used to generate draft proposals and contracts. The draft proposals are then presented interactively to the user or approver, who can then provide feedback.

[1317] Next, the emotion engine analyzes the user's emotions. The emotion engine analyzes emotions from the user's input and behavior and adjusts the message suggestions based on the results. For example, if the user is feeling anxious, it can add a reassuring message to the message suggestions.

[1318] This system requires software such as APIs, sentiment analysis modules, etc. Hardware such as a server and smartphones are required.

[1319] As a concrete example, consider the generation of a message when a user makes a large payment. If the user ID is 12345 and the payment amount is 10,000 yen, the following prompt sentence is generated based on the user's past payment history and the user's emotions.

[1320] Example prompt sentence:

[1321] User ID: 12345

[1322] Payment amount: 10,000 yen

[1323] Past payment history: Past payment history data

[1324] User Emotion: Anxiety

[1325] Generate an appropriate message.

[1326] By inputting this prompt sentence into a generative AI model, it is possible to generate an appropriate message that takes the user's emotions into consideration, thereby realizing a system that can increase user satisfaction.

[1327] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1328] Step 1:

[1329] The server retrieves information such as the user's and approver's past behavior history, transaction history, and approval history from the database. The input is the user ID and approver ID, and the output is data such as the user's and approver's past behavior history, transaction history, and approval history. This data is used in subsequent processing.

[1330] Step 2:

[1331] The server uses a machine learning algorithm based on the acquired past information to generate draft proposals and contracts. The input is the past information acquired in step 1, and the output is the generated draft proposal. Specifically, the server inputs past information into the machine learning model and generates the optimal draft proposal.

[1332] Step 3:

[1333] The server interactively presents the generated draft to the user or approver. The input is the draft generated in step 2, and the output is feedback from the user or approver. Specifically, the server displays the draft through the user interface and receives comments and revision requests from the user or approver.

[1334] Step 4:

[1335] The server analyzes emotions from user input and behavior using an emotion engine. The input is the user's feedback and behavior data, and the output is the user's emotional state. Specifically, the server analyzes the user's emotions using an emotion analysis module.

[1336] Step 5:

[1337] The server adjusts the proposed message based on the analysis results of the emotion engine. The input is the user's emotional state obtained in step 4 and the proposed message generated in step 2, and the output is the adjusted proposed message. Specifically, the server modifies the content of the proposed message according to the user's emotions, for example, adding a message that gives a sense of security to a user who is feeling anxious.

[1338] Step 6:

[1339] The server presents the adjusted draft to the user or approver again and receives final feedback. The input is the draft adjusted in step 5, and the output is the final approval or revision request. Specifically, the draft is displayed again through the user interface for final confirmation.

[1340] Step 7:

[1341] The server saves the final draft text in a database and uses it to generate draft text for future proposals and contracts as needed. The input is the final draft text, and the output is an updated database. Specifically, the final draft text is stored in the database and used as training data for future machine learning models.

[1342] 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.

[1343] 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> ) 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.

[1344] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1345] 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.

[1346] [Third embodiment]

[1347] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1348] 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.

[1349] 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).

[1350] 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.

[1351] 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.

[1352] 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).

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1359] "Example 1"

[1360] In one embodiment of the present invention, there is a database that stores past information. This database includes, for example, information on contracts and proposals made by corporate sales in the past. There is an AI that acquires information from this database and automatically generates draft proposals for the proposal and contract portions using machine learning. This AI is trained using machine learning techniques such as deep learning and reinforcement learning. The generated draft proposals are presented to the salesperson through an interactive interface. This interface is realized in the form of, for example, a chatbot or a voice assistant. "Example 2"

[1361] In another embodiment of the present invention, AI generates draft wording to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform. For example, it significantly reduces the time and effort required for salespeople to draft proposals and contracts.

[1362] "Example 3"

[1363] In a further embodiment of the present invention, AI generates draft text that is expected to be acceptable to the approver. Specifically, AI learns the past approval history and the approver's tendencies, and generates draft text based on that. This makes it possible to provide draft text that is likely to be acceptable to the approver.

[1364] The processing flow of each embodiment will be described below.

[1365] "Example 1"

[1366] Step 1: Obtain the necessary information from a database that stores past information. This information may be information about past contracts or proposals, for example.

[1367] Step 2: Based on the acquired information, machine learning is used to automatically generate draft proposal and contract text. This AI is trained using machine learning techniques such as deep learning and reinforcement learning.

[1368] Step 3: The generated message draft is presented to the salesperson through a conversational interface, which can be implemented in the form of a chatbot or voice assistant, for example.

[1369] "Example 2"

[1370] Step 1: AI generates draft message to reduce the burden on salespeople. Specifically, AI automates some of the tasks that salespeople normally perform.

[1371] Step 2: For example, it significantly reduces the time and effort required by salespeople to draft proposals and contracts.

[1372] "Example 3"

[1373] Step 1: The AI ​​generates draft text that is expected to be acceptable to the approver. Specifically, the AI ​​learns past approval history and approver tendencies.

[1374] Step 2: Based on this, a draft message is generated, which makes it possible to provide a draft message that is likely to be accepted by the approver.

[1375] Example 1

[1376] Next, a description will be given of Example 1 of Form 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."

[1377] In traditional corporate sales, the problem was that creating proposals and contracts took a lot of time and effort. It was also difficult for salespeople to efficiently utilize information from past proposals and contracts, which resulted in a decline in the quality of proposals. Furthermore, creating documents that would convince approvers required experience and skill, which placed a significant burden on new salespeople.

[1378] 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.

[1379] In this invention, the server includes means for retrieving information from a database storing past information, means for training a machine learning model using the retrieved information, means for automatically generating draft proposal and contract wording using the trained machine learning model, and means for interactively presenting the generated draft wording. This reduces the burden on sales staff and enables the efficient creation of high-quality proposals and contracts. Furthermore, automatically generating draft wording that satisfies the approver can also expedite the approval process.

[1380] A "database" is a system for storing past information and retrieving that information as needed.

[1381] "Means of obtaining information" refers to the methods and techniques used to extract the necessary information from the database.

[1382] A "machine learning model" is an algorithm or framework that learns from data and performs specific tasks automatically.

[1383] A "training method" is a method or technique for training a machine learning model using data.

[1384] "Automatic proposal generation means" means a method or technology for automatically generating new proposal or contract text using a trained machine learning model.

[1385] The "interactive presentation means" refers to a method or technique for interactively displaying the generated draft text to the user.

[1386] "Salesperson" refers to the person in charge or staff who handles corporate sales.

[1387] "Approver" refers to a person who has the authority to review and approve the contents of a proposal or contract.

[1388] MODE FOR CARRYING OUT THE INVENTION

[1389] The present invention is a system for improving the efficiency of creating proposals and contracts in corporate sales and reducing the burden on salespeople. A specific embodiment of this system will be described below.

[1390] Retrieving information from a database

[1391] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, dates, and customer information. The server extracts information from the database using an SQL query. For example, by executing the query "SELECT FROM contracts WHERE date > '2020-01-01'", it retrieves contract information from 2020 onwards.

[1392] Training a machine learning model

[1393] The server uses the acquired information to train a machine learning model. This model uses techniques such as deep learning and reinforcement learning. Specifically, it uses the TensorFlow framework. The server cleans and normalizes the data, and then trains the model using the preprocessed data. For example, it uses a Long Short-Term Memory (LSTM) network to train a text generation model.

[1394] Automatic generation of draft text

[1395] The server uses the trained LSTM model to automatically generate new proposal and contract wording. When a user enters a prompt such as "Please generate a new proposal," the server inputs this prompt into the model and obtains the generated wording. For example, the generated wording might be "This proposal provides the optimal solution to your company's needs."

[1396] Present to the salesperson

[1397] The generated proposal is presented to the salesperson through a conversational interface. This interface can take the form of a chatbot or voice assistant. The salesperson accesses the chatbot through their device and checks the generated proposal. For example, if the salesperson types into the chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[1398] Examples and prompts

[1399] Suppose a user needs to create a new proposal. The user accesses the system through their device and instructs it to generate a draft proposal based on information from past similar proposals. The server retrieves the past proposal information from the database and generates a new draft proposal using a machine learning model. The generated draft proposal is presented to the user through a chatbot.

[1400] Example prompt sentence:

[1401] "Please generate a draft proposal for a new proposal based on past corporate sales proposal information."

[1402] In this way, users can efficiently create new proposals.

[1403] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1404] Step 1:

[1405] The server retrieves information about past contracts and proposals from the database. An SQL query is used as input. For example, execute the query "SELECT FROM contracts WHERE date > '2020-01-01'". This query outputs contract information from 2020 onwards. The server stores the retrieved data in memory.

[1406] Step 2:

[1407] The server preprocesses the acquired data. Raw data acquired from the database is used as input. Preprocessing includes cleaning the data (filling in missing values ​​and removing outliers) and normalizing it (scaling the data). This results in output data in a format suitable for training machine learning models.

[1408] Step 3:

[1409] The server uses the preprocessed data to train a machine learning model. The preprocessed data is used as input. Specifically, it uses the TensorFlow framework to train a Long Short-Term Memory (LSTM) network. The training results in a model that can be used to generate proposal and contract text.

[1410] Step 4:

[1411] The server uses the trained LSTM model to automatically generate draft text for new proposals and contracts. The prompt text entered by the user is used as input. For example, the prompt text may read, "Please generate a new proposal." The server inputs this prompt text into the model and outputs the generated draft text. For example, the generated text may read, "This proposal provides the optimal solution for your company's needs."

[1412] Step 5:

[1413] The server presents the generated proposal to the salesperson through a conversational interface. The generated proposal is used as input. The conversational interface can be realized in the form of a chatbot or a voice assistant. For example, if a salesperson inputs to a chatbot, "Show me the proposal proposal," the chatbot will display the message, "This proposal provides the best solution to your company's needs."

[1414] (Application example 1)

[1415] Next, a description will be given of Application Example 1 of Form 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."

[1416] In traditional sales activities, salespeople have to manually refer to information on past contracts and proposals to create new proposals and contracts, which takes a lot of time and effort. Furthermore, since the quality of proposals and contracts depends on the experience and skills of the salesperson, it is difficult to maintain a consistent level of quality. Furthermore, there is a need for a way for salespeople to efficiently create proposals while on the go.

[1417] 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.

[1418] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, and means for presenting the generated draft wording to a sales representative via a smartphone. This enables sales representatives to quickly generate high-quality proposal and contract wording based on past data and conduct efficient sales activities even when they are out and about.

[1419] A "database storing past information" is a data storage system that stores information on contracts and proposals made by corporate sales in the past, allowing it to be searched and retrieved as needed.

[1420] "Machine learning" is a technology in which a computer learns patterns and rules from data and uses that knowledge to make predictions and judgments about new data.

[1421] "Artificial intelligence that automatically generates draft proposal and contract wording" is a program that uses machine learning to analyze past data and automatically generate new proposal and contract texts.

[1422] The "interactive presentation means" is an interface that interactively displays the generated draft text to the user, allowing the user to confirm and modify its content.

[1423] "Means of presenting to sales representatives via smartphones" is a function that displays the generated draft text on the sales representative's smartphone, allowing them to conduct sales activities efficiently even when they are out and about.

[1424] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposals and contractual texts, a means for interactively presenting the generated draft proposals, and a means for presenting the generated draft proposals to sales representatives via their smartphones.

[1425] System configuration

[1426] 1. Database: The server has a database that stores information on contracts and proposals that have been made by the corporate sales department. This database is constructed using a known database management system.

[1427] 2. Artificial Intelligence: The server includes an artificial intelligence (AI) that uses machine learning (e.g., OpenAI's GPT-3) to automatically generate new proposals and contracts based on past data. This AI is implemented using a known programming language.

[1428] 3. Conversational Interface: The generated sales pitch is presented to the salesperson through a conversational interface, which can be in the form of a chatbot or voice assistant.

[1429] 4. Smartphone application: The generated sales pitch is displayed on the salesperson's smartphone. The smartphone application runs on the Android platform, enabling salespeople to efficiently conduct sales activities on the go.

[1430] Processing flow

[1431] 1. Data Acquisition: The server retrieves past proposals and contracts for a particular client from the database.

[1432] 2. Prompt generation: The server generates prompts to be input into the artificial intelligence based on the past suggestions it has obtained.

[1433] 3. Text generation: AI generates new proposals and contracts based on the generated prompts.

[1434] 4. Presentation of draft text: The draft text is presented to the sales representative through an interactive interface.

[1435] 5. Display on smartphone: The generated draft sales text is displayed on the sales representative's smartphone, allowing the sales representative to conduct sales activities efficiently even when on the go.

[1436] Hardware and software used

[1437] Hardware: Servers, smartphones

[1438] software

[1439] Specific examples

[1440] For example, if the previous recommendation for client ID 123 was "This product is of high quality and offers excellent value for money," the new recommendation generated might be "This product uses the latest technology and is highly reliable."

[1441] Prompt Sentence Examples

[1442] Previous proposal: This product is of high quality and offers excellent value for money. Generate a new proposal:

[1443] In this way, salespeople can easily generate new proposals using their smartphones and make effective proposals to their clients.

[1444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1445] Step 1:

[1446] The server retrieves past offers and contracts for a specific client from a database. The input is a client ID, and the output is a list of past offers and contracts. Specifically, the server runs an SQL query to extract offers associated with the client ID from the database.

[1447] Step 2:

[1448] The server generates a prompt to be input to the artificial intelligence based on the past suggestions it has acquired. The input is a list of past suggestions, and the output is a prompt. Specifically, the server combines the past suggestions into one text and creates a prompt with the prefix "Past suggestions: ".

[1449] Step 3:

[1450] The server sends the generated prompt to the AI ​​to generate new proposals or contracts. The input is the prompt, and the output is the generated proposal. Specifically, the server calls the OpenAI GPT-3 API, passing the prompt as input and receiving the generated text.

[1451] Step 4:

[1452] The server presents the generated proposal to the salesperson through a conversational interface. The input is the generated proposal, and the output is an interface that the salesperson can check and modify. Specifically, the server displays the generated proposal in chatbot format, allowing the salesperson to check and modify its contents.

[1453] Step 5:

[1454] The server displays the generated proposal on the sales representative's smartphone. The input is the generated proposal, and the output is the proposal displayed on the smartphone screen. Specifically, the server sends the generated proposal to a smartphone application, allowing the sales representative to check and use the proposal even when they are out and about.

[1455] Example 2

[1456] Next, a description will be given of Example 2 of Form 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."

[1457] Salespeople are required to reduce the time and effort required to draft proposals and contracts, and to work more efficiently. It is also important to maintain a consistent quality in drafts and quickly generate content that satisfies approvers. A system to solve these problems is needed.

[1458] 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.

[1459] In this invention, the server includes a generation AI model that acquires information from a database storing past information and automatically generates draft proposals for the proposal and contract portions using machine learning, a means for generating prompt text based on information entered by the user, and a means for interactively presenting the generated draft proposals, thereby reducing the burden on salespeople and enabling the efficient generation of high-quality draft proposals.

[1460] A "database" is a system for storing past information and retrieving that information as needed.

[1461] "Machine learning" is a technology that allows computers to learn patterns from data and make predictions and classifications.

[1462] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate draft proposals and contract wording.

[1463] A "prompt sentence" is a sentence that gives instructions to a generative AI model based on information entered by the user.

[1464] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[1465] A "salesperson" is a person in charge of the job of drafting proposals and contract texts.

[1466] A "draft" is a draft of the text of a proposal or contract.

[1467] An "approver" is a person who has the authority to review and approve the generated draft text.

[1468] This invention is a system that reduces the burden on salespeople and efficiently generates high-quality proposals and contract drafts. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1469] First, the server has a database that stores past information and retrieves it as needed. The database stores information about past proposals and contracts. The server uses a generative AI model (e.g., OpenAI's GPT-4) that uses machine learning to automatically generate proposal and contract wording.

[1470] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[1471] Customer name: XYZ Co., Ltd.

[1472] Proposal: Proposal for a new marketing strategy

[1473] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[1474] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. For example, it generates the following prompt:

[1475] "Please prepare a proposal for a new marketing strategy for XYZ Corporation. The proposal should include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[1476] The generative AI model receives prompts and generates proposals and contracts with the same quality as a salesperson would produce manually. For example, it generates proposals like this:

[1477] "XYZ Co., Ltd.

[1478] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[1479] Proposal details:

[1480] Introducing new marketing strategies

[1481] Initial cost: 1 million yen

[1482] Monthly fee: 100,000 yen

[1483] We appreciate your consideration.

[1484] Sincerely"

[1485] The generated draft message is sent from the server to the terminal and presented to the user interactively. The user can check the displayed draft message and make corrections as necessary. This reduces the burden on sales staff and enables the efficient generation of high-quality draft messages.

[1486] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1487] Step 1:

[1488] The user inputs basic information about the proposal or contract from the terminal. Specifically, the user inputs information such as the customer name, proposal content, and contract terms (e.g., initial fee, monthly fee). For example, when a user creates a proposal for a new customer, the user inputs the following information into the terminal:

[1489] Customer name: XYZ Co., Ltd.

[1490] Proposal: Proposal for a new marketing strategy

[1491] Contract terms: Initial fee 1 million yen, monthly fee 100,000 yen

[1492] Input: Customer name, proposal details, contract terms

[1493] Output: Basic information entered by the user

[1494] Step 2:

[1495] The server generates a prompt based on the information entered by the user. This prompt contains instructions for the generative AI model. The server analyzes the entered information and creates an appropriate prompt. For example, the server might generate a prompt such as, "Please prepare a proposal for a new marketing strategy for XYZ Co., Ltd. The proposal must include contract terms of an initial fee of 1 million yen and a monthly fee of 100,000 yen."

[1496] Input: Basic information entered by the user

[1497] Output: Generated prompt statement

[1498] Step 3:

[1499] The server sends the prompt to a generative AI model (e.g., OpenAI's GPT-4) to generate a draft. The generative AI model creates a draft proposal or contract based on the prompt. For example, it might generate a draft like this:

[1500] "XYZ Co., Ltd.

[1501] Thank you for reading our proposal for a new marketing strategy. Below are the proposal details and terms of the contract.

[1502] Proposal details:

[1503] Introducing new marketing strategies

[1504] Initial cost: 1 million yen

[1505] Monthly fee: 100,000 yen

[1506] We appreciate your consideration.

[1507] Sincerely"

[1508] Input: Generated prompt text

[1509] Output: Generated text proposal

[1510] Step 4:

[1511] The server transmits the generated draft text to the terminal and presents it to the user interactively. The user can check the displayed draft text and make corrections as necessary. The user can check the draft text on the terminal screen, check for errors in the draft text, and make corrections as necessary.

[1512] Input: Generated text proposal

[1513] Output: Proposal of text presented to the user

[1514] In this way, the server, terminal, and user work in cooperation, reducing the burden on salespeople and enabling efficient generation of high-quality draft text.

[1515] (Application example 2)

[1516] Next, a description will be given of Application Example 2 of Form 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."

[1517] The problem is that salespeople spend a lot of time and effort creating proposals and contracts. Furthermore, communicating with customers and managing the progress of sales activities are also time-consuming, making it difficult to conduct efficient sales activities. There is a need to solve these problems, reduce the burden on salespeople, and realize efficient sales activities.

[1518] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1519] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposal and contract wording using machine learning, means for interactively presenting the generated draft wording, means for automating communication with customers, means for automatically generating proposals and contracts, means for managing and analyzing customer information, and means for managing the progress of sales activities, which significantly reduces the burden on salespeople and enables more efficient sales activities.

[1520] "Historical information" refers to past data and records related to sales activities.

[1521] A "database" refers to an information management system that stores information systematically and allows it to be searched and retrieved as needed.

[1522] "Machine learning" refers to the technology that allows computers to learn patterns from data and make predictions and classifications.

[1523] "Draft proposal / contract text" refers to a draft proposal or contract that is presented to a customer in sales activities.

[1524] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[1525] "Interactive presentation means" refers to the way in which the user and the system interact with each other to exchange information.

[1526] "Means of automating communication with customers" refers to methods of automating communication with customers, such as email and chat.

[1527] "Means for automatically generating proposals and contracts" refers to a method for automatically creating proposals and contracts required for sales activities.

[1528] "Means for managing and analyzing customer information" refers to methods for organizing and analyzing data about customers.

[1529] "Means for managing the progress of sales activities" refers to methods for tracking and managing the progress of the sales process.

[1530] A system for implementing this invention is configured as follows: A server retrieves information from a database storing past information and uses machine learning to automatically generate draft proposal and contract wording. The generated draft wording is presented to the user interactively. The system also has the function of automating communication with customers and automatically generating proposals and contracts. It also includes the function of managing and analyzing customer information and managing the progress of sales activities.

[1531] Hardware and software used

[1532] Hardware: Servers, user devices (smartphones, PCs, etc.)

[1533] Software: API, database management system (e.g. MySQL)

[1534] Data processing and calculation

[1535] 1. Obtaining information from a database: The server obtains data on past sales activities from a database, including past proposals, contracts, and communication history with customers.

[1536] 2. Generating draft text using machine learning: Based on the acquired data, a machine learning model (e.g., OpenAI's GPT-3) is used to generate draft text for proposals and contracts.

[1537] 3. Interactive presentation: The generated draft text is interactively presented on the user's device, allowing the user to review the draft text and make corrections as necessary.

[1538] 4. Automating communication with customers: The server automates email and chat communication with customers based on the generated text suggestions.

[1539] 5. Automatic generation of proposals and contracts: The server automatically generates formal proposals and contracts based on the generated draft text.

[1540] 6. Management and analysis of customer information: The server organizes and analyzes customer information to improve the efficiency of sales activities.

[1541] 7. Sales Activity Progress Management: The server tracks and manages the progress of the sales process.

[1542] Specific examples

[1543] For example, if the customer name is "ABC Co., Ltd." and the product details are "the latest AI-enabled smartphone," the following prompt sentence would be sent to the generative AI model:

[1544] Prompt Sentence Examples

[1545] Customer Name: ABC Co., Ltd.

[1546] Product details: The latest AI-enabled smartphone

[1547] Please prepare your proposal based on the information below.

[1548] Based on this prompt, the generative AI model generates the text of the proposal, reducing the burden on the salesperson. The generated proposal is then presented interactively to the user's device, allowing the user to review the content and make any necessary revisions.

[1549] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1550] Step 1:

[1551] The server retrieves data on past sales activities from a database. The input is past proposals, contracts, and communication history with customers stored in the database. The output is a collection of the retrieved data. This data is used in subsequent processing.

[1552] Step 2:

[1553] The server uses a machine learning model (e.g., OpenAI's GPT-3) based on the acquired data to generate a draft proposal or contract. The input is the data acquired in step 1. The output is the generated draft. Specifically, the server converts the data into a prompt sentence and sends it to the generative AI model.

[1554] Step 3:

[1555] The server interactively presents the generated draft text to the user terminal. The input is the draft text generated in step 2. The output is the draft text displayed on the user terminal. Specifically, the draft text is displayed on the user interface so that the user can check and modify it.

[1556] Step 4:

[1557] The server automates email and chat communications with customers based on the generated message templates. The input is the message template generated in step 2. The output is the email or chat message to be sent to the customer. Specifically, the server converts the message template into email or chat format and automatically sends it.

[1558] Step 5:

[1559] The server automatically generates a formal proposal or contract based on the generated draft text. The input is the draft text generated in step 2. The output is a formal proposal or contract. Specifically, the server formats the draft text into a formal document format and converts it into a format that can be saved and printed.

[1560] Step 6:

[1561] The server organizes and analyzes customer information. The input is customer information stored in a database. The output is the analysis results and organized customer information. Specifically, it organizes customer information by category and applies analytical algorithms to extract useful insights.

[1562] Step 7:

[1563] The server tracks and manages the progress of the sales process. The input is data and progress information about sales activities. The output is a progress report. Specifically, it tracks each stage of sales activities and generates a dashboard to visualize the progress.

[1564] Example 3

[1565] Next, a third embodiment of the third embodiment will be described. 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."

[1566] Conventional message draft generation systems generate message drafts without sufficient consideration of past approval history or approver tendencies, making it difficult to efficiently create message drafts that approvers will agree with. Furthermore, they did not adequately generate message drafts to reduce the burden on sales staff. This resulted in delays in the approval process and reduced work efficiency.

[1567] The specification process by the specification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a means for the user to input a prompt sentence, a means for the terminal to send the prompt sentence to the server, a means for the server to acquire past approval history and approver tendencies from a database, a means for generating a draft text using a generative AI model, a means for sending the generated draft text to the terminal, a means for the terminal to display the draft text to the user, and a means for the user to check the draft text and modify it as necessary. This makes it possible to efficiently generate draft text that takes into account past approval history and approver tendencies, and to provide a draft text that is likely to be acceptable to the approver. Furthermore, it is possible to reduce the burden on sales personnel and improve work efficiency.

[1568] A "database" is a system for storing past information and retrieving that information as needed.

[1569] "Artificial intelligence" refers to a program or system that uses machine learning to automatically generate draft text.

[1570] The "interactive presentation means" is an interface that displays the generated draft text to the user in an interactive format, allowing the user to check and correct it.

[1571] A "prompt sentence" is a text that includes instructions and conditions for generating a sentence proposal, which is input by the user.

[1572] A "terminal" is a device through which a user enters prompt sentences and communicates with a server.

[1573] A "server" is a computer system that retrieves information from a database, generates draft text using a generative AI model, and transmits it to a terminal.

[1574] A "generative AI model" is an artificial intelligence model that learns from past data and generates draft text.

[1575] "Approval history" is data that includes past approval statements and feedback from approvers.

[1576] The "approver tendency" is a pattern based on what kind of text the approver has approved in the past or what kind of feedback the approver has provided.

[1577] A "draft text" is a draft document generated by the generative AI model that is likely to be acceptable to the approver.

[1578] A "user" is a person who enters prompt text and reviews and modifies the generated text suggestions.

[1579] The present invention relates to a system for generating draft wording in consideration of past approval history and the tendencies of approvers. A specific embodiment of this system will be described below.

[1580] First, the user inputs a prompt using a terminal. A prompt is text that includes instructions and conditions for generating a draft. For example, the prompt might say, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to place importance on specific figures and clear objectives."

[1581] The terminal sends the input prompt to the server using a communication protocol such as an HTTP POST request.

[1582] The server accesses the database to retrieve the approval history and approver trends. The database stores past approval statements and approver feedback. For example, it executes a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[1583] Next, the server runs a generative AI model based on the acquired data to generate a draft message. For example, OpenAI's GPT-4 is used as the generative AI model. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[1584] The generated draft text is sent from the server to the device using a communication protocol such as an HTTP response.

[1585] The terminal displays the received draft to the user. The user interface includes a text area and a display widget. The user can check the displayed draft and make corrections as necessary. The corrected draft is used as the final approval request.

[1586] This system makes it possible to efficiently generate draft texts that take into account past approval history and approver tendencies, and provide draft texts that are likely to be accepted by the approver. It also reduces the burden on sales personnel and improves work efficiency. The flow of the identification process in the third embodiment will be described with reference to FIG. 15.

[1587] Step 1:

[1588] The user enters a prompt statement.

[1589] The user inputs a prompt into an input field on the terminal, for example, "Please write a statement requesting budget approval for a new project. Based on past approval history, approvers tend to value specific figures and clear objectives."

[1590] Input: prompt statement

[1591] Output: The prompt text entered

[1592] Step 2:

[1593] The terminal sends the prompt to the server.

[1594] The terminal sends the entered prompt sentence to the server as an HTTP POST request.

[1595] Input: prompt statement

[1596] Output: The prompt sent to the server

[1597] Step 3:

[1598] The server retrieves the past approval history and approver tendencies from the database.

[1599] The server accesses the database to retrieve the approval history and approver trends, for example, by executing a SQL query such as "SELECT FROM approval_history WHERE approver_id = '12345'".

[1600] Input: prompt statement, database

[1601] Output: Past approval history and approver trends

[1602] Step 4:

[1603] The server generates draft text using a generative AI model.

[1604] The server runs a generative AI model (such as OpenAI's GPT-4) based on the acquired data to generate a draft message. The generative AI model learns from past data and generates a message that is likely to be accepted by the approver.

[1605] Input: Past approval history and approver trends

[1606] Output: Generated text proposal

[1607] Step 5:

[1608] The server transmits the generated draft text to the terminal.

[1609] The server sends the generated draft text to the terminal as an HTTP response.

[1610] Input: Generated text proposal

[1611] Output: Proposal sent to the terminal

[1612] Step 6:

[1613] The terminal displays the draft message to the user.

[1614] The terminal displays the received message in the text area, allowing the user to check the displayed message.

[1615] Input: Proposal sent to the terminal

[1616] Output: Proposed text displayed to the user

[1617] Step 7:

[1618] The user checks the draft and makes corrections as necessary.

[1619] The user checks the displayed draft and makes any necessary changes. For example, they can change "Personnel costs: 5 million yen" to "Personnel costs: 6 million yen." The revised draft is used as the final approval request.

[1620] Input: Proposed text displayed to the user

[1621] Output: Revised text

[1622] (Application example 3)

[1623] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1624] Conventional electronic payment systems have the problem of taking a great deal of time and effort to create approval documents that the approver will agree to. Furthermore, approval processes are often delayed because approval documents are created without taking into account the approver's preferences. This leads to inefficiencies in the approval process for expense settlements and large transactions within companies, resulting in a decline in overall business efficiency.

[1625] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1626] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating draft proposals for the proposal and contract portions using machine learning, means for interactively presenting the generated draft proposals, and means for learning the tendencies of approvers and generating draft proposals that are likely to be acceptable to the approvers. This makes it possible to quickly generate draft proposals that are easy for approvers to accept, and to streamline the approval process for electronic payments.

[1627] "Past information" refers to data and history that the system has collected in the past.

[1628] A "database" is a collection of information that systematically stores past information and allows it to be searched and retrieved as needed.

[1629] "Machine learning" is a technology that allows computers to analyze large amounts of data and automatically learn patterns and rules.

[1630] "Draft text of proposal / contract portion" refers to the draft text included in the proposal or contract.

[1631] "Artificial intelligence" refers to systems that use techniques such as machine learning to mimic human intelligence and automatically perform specific tasks.

[1632] "Interactive presentation means" refers to the interface that allows the user and the system to exchange information interactively.

[1633] "Approver trends" is data that indicates the criteria and patterns that a particular approver has used in approving in the past.

[1634] "Draft text that is likely to be accepted by the approver" refers to a draft of text that is likely to be approved, created taking into account the approver's past tendencies.

[1635] As an embodiment of the present invention, an electronic payment approval assistant system will be described as an example. This system operates in cooperation with three entities: a server, a terminal, and a user.

[1636] First, the server has a database that stores past information, including data on past approval history and approver tendencies. The server retrieves information from this database and uses machine learning to automatically generate draft proposal and contract wording. Specifically, the server uses APIs based on Python, Pandas, and OpenAI to analyze past approval history and learn approver tendencies.

[1637] The generated draft is then presented interactively to a terminal, which is a device used by the user, such as a smartphone or tablet, through which the user can review the draft and make any necessary corrections. The interactive interface is designed to be easy for users to operate.

[1638] Furthermore, the server learns the approver's tendencies and generates a message that is likely to be accepted by the approver. In this process, a generative AI model is used to generate message suggestions based on features extracted from past approval history. Specific examples of prompts include the following:

[1639] Example prompt sentence:

[1640] Generate the following wording suggestions based on the approver's tendencies:

[1641] This trip is an important meeting with a new client and requires prompt approval.

[1642] Approver tendency: {features extracted from the approver's past approval history}

[1643] This system can quickly generate draft text that is easy for the approver to understand, making it possible to streamline the approval process for electronic payments.As a specific example, consider the approval process for expense reimbursement within a company.When an employee applies for reimbursement for travel expenses and their supervisor's approval is required, by using this system, a draft text that is easy for the supervisor to understand can be automatically generated, allowing for quick approval.

[1644] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1645] Step 1:

[1646] The server obtains approval history data from a database that stores past information.

[1647] Input: Past approval history data stored in the database

[1648] Output: Acquired approval history data

[1649] Specific operation: The server uses an SQL query to extract past approval history data from the database.

[1650] Step 2:

[1651] The server inputs the acquired approval history data into a machine learning model to learn the approver's tendencies.

[1652] Input: Acquired approval history data

[1653] Output: Learning results about approver tendencies

[1654] How it works: The server preprocesses the data using publicly known libraries and inputs it into a machine learning model. The model learns past approval patterns and extracts approver tendencies.

[1655] Step 3:

[1656] Based on the learning results, the server inputs a prompt sentence into the generative AI model and generates a draft sentence.

[1657] Input: Learning results on approver tendencies, prompt text

[1658] Output: Generated text proposal

[1659] Specific operation: The server uses OpenAI's API to input the prompt sentence and learning results into the generative AI model to generate a draft sentence.

[1660] Step 4:

[1661] The server transmits the generated draft text to the terminal and presents it interactively.

[1662] Input: Generated text proposal

[1663] Output: Proposal displayed on the terminal

[1664] Specific operation: The server sends the generated draft text to the terminal via an HTTP request, and the terminal displays it on the user interface.

[1665] Step 5:

[1666] The user checks the draft text generated through the terminal and makes corrections as necessary.

[1667] Input: Proposal of text displayed on the terminal

[1668] Output: Revised text

[1669] Specific operation: The user uses the terminal interface to check the draft text and, if necessary, makes corrections in a text editor.

[1670] Step 6:

[1671] The server stores the revised draft as the final approved document.

[1672] Input: Revised draft text

[1673] Output: Final approval statement saved

[1674] Specific operation: The server saves the revised draft text in the database and completes the approval process.

[1675] 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.

[1676] "Example 1"

[1677] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes a user's emotions. The emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. Specifically, it generates positive suggestions when the user is happy, and apologetic suggestions when the user is angry.

[1678] "Example 2"

[1679] The emotion engine also adjusts the message suggestions based on the user's emotions. Specifically, it generates positive language when the user is happy, and apologetic language when the user is angry. For example, when the user is happy, it generates a message like "This proposal will lead to further success in your business," and when the user is angry, it generates a message like "We deeply apologize that our service did not meet your expectations."

[1680] "Example 3"

[1681] Furthermore, the emotion engine automatically generates proposals for the proposal and contract sections based on the user's emotions. Specifically, it generates positive proposals when the user is happy, and proposals that include words of apology when the user is angry. For example, when the user is happy, it generates a proposal such as "This proposal will lead to further success in your business," and when the user is angry, it generates a proposal such as "We deeply apologize that our service did not meet your expectations."

[1682] The processing flow of each embodiment will be described below.

[1683] "Example 1"

[1684] Step 1: The AI ​​activates an emotion engine that infers emotions from the user's tone of voice, facial expressions, and choice of words.

[1685] Step 2: The emotion engine recognizes the user's emotion and determines the content of the suggestion based on that emotion.

[1686] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and presents it to the user.

[1687] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[1688] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposed text based on the emotion.

[1689] Step 3: Based on the results of the emotion engine, the AI ​​generates a draft message and presents it to the user.

[1690] "Example 3"

[1691] Step 1: The AI ​​activates the emotion engine to recognize the user's emotions.

[1692] Step 2: The emotion engine recognizes the user's emotion and determines the content of the proposal and contract portion based on that emotion.

[1693] Step 3: Based on the results of the emotion engine, the AI ​​generates a proposal and contract portion and presents it to the user.

[1694] Example 1

[1695] Next, a description will be given of Example 1 of Form 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."

[1696] In conventional sales activities, salespeople had to manually refer to information on past contracts and proposals to create new proposals. This work required time and effort, increasing the burden on salespeople. It was also difficult to make appropriate proposals based on the user's emotions, making it difficult to improve customer satisfaction.

[1697] 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.

[1698] In this invention, the server includes means for acquiring information from a database storing past information, means for training a machine learning model using the acquired information, means for automatically generating draft proposals for the proposal and contract portion using the trained machine learning model, means for presenting the generated draft proposals through an interactive interface, means including an emotion engine for recognizing user emotions, and means for adjusting the draft proposals based on information obtained from the emotion engine. This reduces the burden on sales staff and makes it possible to make optimal proposals based on the user's emotions.

[1699] A "database" is an information management system that stores past information and enables the efficient retrieval of necessary information.

[1700] A "machine learning model" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[1701] "Training" is the process of training a machine learning model using large amounts of data to learn and improve its performance.

[1702] A "draft" is a draft of a document that describes the contents of a proposal or contract.

[1703] An "interactive interface" is a user interface that allows two-way communication between a user and a system.

[1704] The "emotion engine" is a system that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[1705] "Adjustment" means changing content or settings to suit specific conditions or circumstances.

[1706] MODE FOR CARRYING OUT THE INVENTION

[1707] This invention is a system that acquires information from a database that stores past information and uses machine learning to automatically generate draft proposal and contract wording. Specific embodiments of this system are described below.

[1708] Retrieving information from a database

[1709] The server retrieves the necessary information from a database that stores information on past contracts and proposals made by corporate sales. This database includes information such as contract details, proposal details, and customer responses. The server uses an SQL query to extract past contract information from the database. For example, it executes a query such as "SELECT FROM contracts WHERE date > '2020-01-01'".

[1710] Training a machine learning model

[1711] The server uses the acquired information to train a machine learning model. This model is capable of automatically generating draft proposal and contract wording using techniques such as deep learning and reinforcement learning. Specifically, it uses a framework such as TensorFlow. The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[1712] Generate draft text

[1713] The server uses a trained machine learning model to generate draft proposal and contract text. These draft proposals are designed to include optimal content based on past data. The server inputs a prompt text into the generative AI model to generate a draft proposal. For example, it executes code such as "generate_text('Generate a new proposal text')".

[1714] Proposal of text is presented through the interface

[1715] The terminal presents the generated message draft to the salesperson through a conversational interface. This interface can be implemented in the form of a chatbot or voice assistant. The terminal displays the generated message draft on the chatbot's UI. For example, it executes a code such as "chatbot.display_message(generated_text)".

[1716] Recognizing user emotions with an emotion engine

[1717] The device recognizes the user's emotions using an emotion engine. This emotion engine infers emotions from the user's tone of voice, facial expressions, and choice of words. The device uses OpenCV to analyze the user's facial expressions and infer emotions. For example, it executes code such as "emotion = emotion_recognition.detect_face_expression(user_image)".

[1718] Adjusting message proposals according to emotions

[1719] The server generates text suggestions based on the information obtained from the emotion engine according to the user's emotions. If the user is happy, it generates a positive suggestion, and if the user is angry, it generates a suggestion including an apology. Based on the output of the emotion engine, the server inputs an appropriate prompt sentence into the generative AI model. For example, it executes code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[1720] Specific examples

[1721] Example 1: Proposal Generation

[1722] The following proposal is generated based on the user's past contract information.

[1723] Example prompt sentence:

[1724] "Generate new proposals based on past contract information."

[1725] An example of a generated suggestion:

[1726] "Customer, based on the terms of your previous contract, we would like to make you a new proposal with similar conditions. We appreciate your consideration."

[1727] Example 2: Adjusting message proposals based on emotions

[1728] If the user is angry, the emotion engine will recognize that emotion and generate a suggested message that includes an apology.

[1729] Example prompt sentence:

[1730] "Generate suggestion sentences for when the user is angry."

[1731] An example of a generated suggestion:

[1732] "Dear customer, we apologize for the inconvenience. With this proposal, we will improve the past issues and offer you better terms."

[1733] In this way, the system utilizes past data to automatically generate optimal suggestions based on the user's emotions.

[1734] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1735] Step 1:

[1736] The server retrieves the information from a database that stores past information.

[1737] Input: Database query (e.g., "SELECT FROM contracts WHERE date > '2020-01-01'")

[1738] Data processing: Execute SQL queries to extract past contract information.

[1739] Output: A dataset of retrieved contract information

[1740] Specific operation: The server extracts past contract information from the database using an SQL query, for example, "SELECT FROM contracts WHERE date > '2020-01-01'".

[1741] Step 2:

[1742] The server uses the acquired information to train a machine learning model.

[1743] Input: Dataset of retrieved contract information

[1744] Data processing: Preprocessing the dataset and converting it into a format suitable for machine learning models.

[1745] Output: A trained machine learning model

[1746] Specific operation: The server uses TensorFlow to build a deep learning model and trains it using past contract data. For example, it executes code such as "model.fit(training_data, epochs=50)".

[1747] Step 3:

[1748] The server uses the trained machine learning model to generate draft proposal and contract text.

[1749] Input: A trained machine learning model, a prompt (e.g., "Generate a new suggestion")

[1750] Data processing: The prompt sentence is input into the model and a draft sentence is generated.

[1751] Output: Generated text proposal

[1752] Specific operation: The server inputs a prompt sentence into the generative AI model and generates a text suggestion. For example, it executes a code such as "generate_text('Generate a new suggested text')".

[1753] Step 4:

[1754] The terminal presents the generated draft message to the salesperson through an interactive interface.

[1755] Input: Generated text proposal

[1756] Data processing: Converting the draft text into a format suitable for the interactive interface.

[1757] Output: Proposal of text to be presented to the salesperson

[1758] Specific operation: The terminal displays the generated message on the chatbot's UI, for example, by executing code such as "chatbot.display_message(generated_text)".

[1759] Step 5:

[1760] The terminal uses an emotion engine to recognize the user's emotions.

[1761] Input: Your tone of voice, facial expressions, and word choice

[1762] Data processing: Analyze user emotions using an emotion engine.

[1763] Output: Estimated user emotion

[1764] Specific operation: The device uses OpenCV to analyze the user's facial expression and estimate their emotion. For example, it executes code like "emotion = emotion_recognition.detect_face_expression(user_image)".

[1765] Step 6:

[1766] The server generates a message proposal based on the user's emotions based on the information obtained from the emotion engine.

[1767] Input: Estimated user sentiment, trained machine learning model

[1768] Data processing: Generate prompt sentences according to the emotion, input them into the model, and generate draft sentences.

[1769] Output: Suggested text based on emotions

[1770] Specific operation: The server inputs an appropriate prompt sentence to the generative AI model based on the output of the emotion engine. For example, it executes a code such as "generate_text('Generate a suggestion sentence when the user is angry')".

[1771] (Application example 1)

[1772] Next, a description will be given of Application Example 1 of Form 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."

[1773] With conventional sales support systems, it was difficult for salespeople to quickly refer to past proposals and contract information and make optimal proposals when dealing with customers. It was also difficult to recognize customer emotions in real time and make proposals accordingly. Furthermore, in physical stores, when sales staff deal with customers, they are required to make optimal proposals based on past sales data and proposal content, but there was a lack of efficient means to do this. To solve these issues, a system that recognizes customer emotions and generates proposal text that corresponds to them is needed.

[1774] 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.

[1775] In this invention, the server includes means for acquiring information from a database storing past information and automatically generating proposal and contract wording proposals using machine learning, means for interactively presenting the generated proposal wording proposals, an emotion engine for recognizing a user's emotions, means for generating proposal wording according to the user's emotions, and means installed in smart glasses to support customer service. This enables salespeople and store clerks to quickly make optimal proposals based on past proposal and contract information when serving customers, and further enables proposals according to the customer's emotions to be made in real time.

[1776] "Past information" refers to data that includes information on contracts and proposals that corporate sales have made in the past.

[1777] A "database" is a system that stores past information and can retrieve that information as needed.

[1778] "Artificial intelligence" is a technology that uses machine learning to automatically generate draft proposal and contract wording.

[1779] "Interactive presentation" refers to a method in which the generated draft text is presented to the salesperson via a chatbot, voice assistant, etc.

[1780] The "emotion engine" is a technology that estimates emotions from the user's tone of voice, facial expressions, choice of words, etc.

[1781] The "means for generating a suggested message according to the user's emotions" is a method for generating an appropriate suggested message based on the emotions estimated by the emotion engine.

[1782] "Smart glasses" are wearable devices equipped with a display and camera that can display information and capture images.

[1783] The "means for supporting customer service" is a method that uses smart glasses to display optimal suggestion text when a store clerk is interacting with a customer.

[1784] A system for implementing this invention includes a database storing past information, artificial intelligence that uses machine learning to automatically generate draft proposal and contract wording, a means for interactively presenting the generated draft proposals, an emotion engine that recognizes the user's emotions, a means for generating proposal wording in accordance with the user's emotions, and a means that is installed in smart glasses and supports customer service.

[1785] The server retrieves information from a database that stores past information and uses machine learning to automatically generate proposal and contract wording. Specifically, it uses deep learning and reinforcement learning models trained with TensorFlow. The generated wording is presented to the salesperson through a conversational interface such as a chatbot or voice assistant.

[1786] The device uses smart glasses to capture the customer's facial expressions and tone of voice, and recognizes the user's emotions using an emotion engine. The emotion engine uses an emotion recognition model based on TensorFlow to infer emotions from the user's tone of voice, facial expressions, and choice of words. Based on the inferred emotions, a generative AI model is used to generate optimal suggested text. The generative AI model uses natural language generation models such as GPT-2.

[1787] When a user wears the smart glasses and interacts with a customer, the smart glasses display shows the optimal proposal based on past sales data and the content of the proposal, allowing the user to make proposals in real time that reflect the customer's emotions.

[1788] For example, if a customer is looking at a product with a smile, the emotion recognition model will determine this as "joy" and generate a suggestion message such as, "This product is particularly popular. We're offering a special discount right now, so please give it a try." If the customer has a confused expression, the emotion recognition model will determine this as "confused" and generate a suggestion message such as, "If you need any help, we'd be happy to help you."

[1789] An example of a prompt is as follows:

[1790] "Optimal Proposal Text When Customers are Happy: Past Proposal Data"

[1791] "Optimal Proposal Text for Customers in a Confused State: Past Proposal Data"

[1792] This allows salespeople and store clerks to quickly make optimal proposals based on past proposals and contract information when dealing with customers, and also allows them to make proposals in real time that reflect the customer's emotions.

[1793] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1794] Step 1:

[1795] The server retrieves the information from a database that stores past information.

[1796] Input: Past proposals and contract information stored in a database

[1797] Output: Past proposal and contract information obtained

[1798] What happens: The server uses SQL queries to extract the necessary information from the database and loads it into memory.

[1799] Step 2:

[1800] The server uses machine learning to automatically generate draft proposal and contract wording based on the acquired information.

[1801] Input: Past proposals and contract information

[1802] Output: Generated proposal and contract draft

[1803] Specific operation: The server inputs data into deep learning models and reinforcement learning models trained using TensorFlow to generate optimal text suggestions.

[1804] Step 3:

[1805] The server presents the generated draft text to the salesperson through an interactive interface.

[1806] Input: Generated proposal and contract draft

[1807] Output: Proposal of text presented to the salesperson

[1808] Specific operation: The server sends the generated draft message to the salesperson's device via a chatbot or voice assistant and displays it.

[1809] Step 4:

[1810] The device uses smart glasses to capture the customer's facial expressions and tone of voice.

[1811] Input: Customer facial expressions and tone of voice

[1812] Output: Captured customer facial expressions and tone of voice data

[1813] How it works: The device uses a camera and microphone in its smart glasses to capture the customer's facial expressions and voice in real time.

[1814] Step 5:

[1815] The terminal inputs the captured data into an emotion engine to recognize the user's emotion.

[1816] Input: Captured customer facial and tone of voice data

[1817] Output: Estimated user emotion

[1818] Specific operation: The device inputs data into an emotion recognition model using TensorFlow to estimate the user's emotions.

[1819] Step 6:

[1820] The server uses a generative AI model to generate optimal suggested text based on the estimated emotions.

[1821] Input: Estimated user sentiment, past suggestion data

[1822] Output: Suggested text based on emotion

[1823] Specific operation: The server inputs the prompt sentence into a natural language generation model such as GPT-2 and generates the optimal suggested sentence.

[1824] Step 7:

[1825] The terminal displays the generated proposal text on the display of the smart glasses.

[1826] Input: Generated suggestion text

[1827] Output: Suggestion text displayed on the smart glasses display

[1828] Specific operation: The terminal sends the generated proposal text to the display of the smart glasses and displays it.

[1829] This allows the user to make suggestions in real time that correspond to the customer's emotions.

[1830] Example 2

[1831] Next, a description will be given of Example 2 of Form 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."

[1832] In conventional sales activities, salespeople spend a lot of time and effort creating proposals and contracts. In addition, it is difficult to generate appropriate wording that reflects the user's emotions, making it difficult to improve cu...

Claims

1. A first means for acquiring a past approval history and a tendency of an approver from a database storing past information; a second means for generating a first prompt sentence for outputting a draft sentence that is likely to be accepted by the approver based on the acquired past approval history and the tendency of the approver; A third means for inputting the generated first prompt sentence into a generative AI model to generate the draft sentence; A fourth means for displaying the generated draft message on a terminal of a salesperson; A system including:

2. The first means acquires data including information on contracts and proposals made by the salesperson in the past from the database, a fifth means for estimating, by an emotion engine, an emotion of the customer based on the customer's tone of voice, facial expression, and word choice; The second means generates a second prompt sentence for outputting a suggested sentence according to the customer's emotion based on the data and the customer's emotion, The third means inputs the generated second prompt sentence into a generative AI model to generate the suggested sentence; The fourth means displays the generated proposal text on a display of smart glasses serving as the terminal of the salesperson. The system of claim 1 .

3. The second means adjusts the second prompt sentence so that a suggested sentence including positive words is output when the emotion of the customer indicates joy, and adjusts the second prompt sentence so that a suggested sentence including words of apology is output when the emotion of the customer indicates anger. The system of claim 2.

Images