system

Abstract

Provide a system. [Solution] A means of collecting past business negotiation data, event history, and company characteristic data; A means for preprocessing the collected data and constructing a model for predicting the probability of success using a machine learning algorithm; A means for prompting a user to input basic information about a new business negotiation and predicting the most suitable partner company based on the information; means for automatically generating business negotiation materials based on the predicted cooperating companies; The system includes means for following up on the results of the sales negotiations and continuously optimizing said model.

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] Currently, sales representatives select partner companies based on their experience, intuition, and market information, and manually create sales negotiation materials, which requires a significant amount of time and effort. This prevents sales representatives from concentrating on the actual sales negotiations. Furthermore, variations in the quality of sales negotiation materials can lead to a decrease in the consistency and effectiveness of proposals to customers. Therefore, it is necessary to provide a system that can improve the efficiency of sales activities and the success rate of sales negotiations. [Means for solving the problem]

[0005] The present invention provides a system for collecting past sales negotiation data, event history, and company characteristic data, preprocessing the data, and building a model for predicting the success rate using a machine learning algorithm. The system includes a means for having a user input basic information about new sales negotiations and predicting the most suitable partner companies based on the information. The system further includes a means for automatically generating sales negotiation materials based on the predicted partner companies and for following up on the results of the sales negotiations to continuously optimize the model, thereby improving sales efficiency and the success rate of sales negotiations. The system also includes a user interface for inputting basic sales negotiation information and a means for using APIs or database queries as a data collection method, thereby improving system usability and data accuracy.

[0006] "Business negotiation data" is data containing information related to business negotiations, including the content, results, transaction amounts, and periods of past business negotiations.

[0007] "Event history" is historical data that includes records of events that a company has participated in or events related to business negotiations.

[0008] "Company characteristic data" refers to data containing basic information and characteristics of a company, including information such as the industry, sales volume, past collaboration records, and number of employees.

[0009] "Preprocessing" is the process of removing noise and unnecessary parts from raw data and converting it into an analyzable format.

[0010] A "machine learning algorithm" is an algorithm that learns from data, finds patterns and rules, and makes predictions and classifications.

[0011] A "model for predicting the probability of success" is a mathematical and statistical model that calculates and predicts the likelihood of a business negotiation being successful based on past data.

[0012] "Business negotiation materials" are documents that compile proposals, company introductions, success stories, etc. used during business negotiations.

[0013] "Follow-up" is the process of tracking and recording the progress and results of a business negotiation.

[0014] "API" stands for Application Programming Interface, an interface for exchanging data and functions between different software.

[0015] A "database query" is a command or request to search for or retrieve information from a database. [Brief explanation of the drawings]

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

[0017] 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.

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

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

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

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

[0037] The system of the present invention is a system for improving the efficiency of sales negotiation activities by sales representatives and increasing the success rate of sales negotiations. The system is composed of entities, namely, a server, terminals, and users, and each entity operates as follows.

[0038] First, the server collects past sales negotiation data, event history, and company characteristic data. The collected data is retrieved via APIs and database queries. The details of sales negotiations, results, event details, and company characteristic information are then stored in a database.

[0039] Next, the server preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past examples of successful and unsuccessful sales negotiations are used as training data to build a model that predicts the probability of success for a sales negotiation. This model is created using algorithms such as regression analysis and random forests.

[0040] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0041] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0042] As the negotiation progresses, the user inputs the progress and results into the device. This negotiation result data is then sent back to the server and stored in a database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0043] As a concrete example, consider the case of planning the nationwide rollout of a new product. When the user inputs basic business negotiation information into the terminal, the server proposes three companies as the most suitable partners based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. As a result, the user can make an effective presentation using high-quality business negotiation materials, increasing the chances of success in the business negotiation.

[0044] This system allows sales representatives to significantly reduce the time and effort required to create sales documents and select partner companies, allowing them to focus on the content of the sales negotiations, resulting in more efficient sales activities and improved results.

[0045] The above is a specific embodiment for carrying out the present invention.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The server collects past sales data, event history, and company characteristic data using APIs and database queries, including transaction history, company disclosure information, and sales activity logs.

[0049] Step 2:

[0050] The server preprocesses the collected data, specifically cleaning the data, filling in missing data, removing outliers, and converting it into an analyzable format.

[0051] Step 3:

[0052] The server uses the preprocessed data to train machine learning algorithms, using techniques such as regression analysis and random forests to build models of deal success.

[0053] Step 4:

[0054] The user uses the terminal to input basic information about a new business deal, such as "nationwide expansion of a new product" or "target market."

[0055] Step 5:

[0056] The terminal sends the entered business negotiation information to the server, which then structures the input information in an appropriate format and passes it to the server.

[0057] Step 6:

[0058] Based on the business negotiation information received by the server, the server predicts the most suitable partner companies using the business negotiation success model it has built, and calculates the predicted list of candidate companies and the success probability.

[0059] Step 7:

[0060] The server sends the terminal a list of predicted partner companies, including the success probability of each partner company and related success stories.

[0061] Step 8:

[0062] The server automatically generates business documents based on the selected partner companies, including company introductions, success stories, and proposal details.

[0063] Step 9:

[0064] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections.

[0065] Step 10:

[0066] The user periodically inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0067] Step 11:

[0068] The terminal sends the entered negotiation result data to the server, which stores it in a database.

[0069] Step 12:

[0070] The server uses the sales negotiation result data to retrain and optimize the partner company success model, thereby improving the model's prediction accuracy.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] With conventional sales systems, collecting and analyzing data to improve the success rate of sales negotiations, selecting partner companies, and preparing sales negotiation materials required a lot of time and effort. As a result, sales representatives had to spend a lot of time collecting information necessary for sales negotiations and preparing materials, which meant they were unable to concentrate on the sales negotiations themselves. Furthermore, continuous optimization of the model based on sales negotiation results was not performed, making it difficult to improve prediction accuracy.

[0074] 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.

[0075] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the probability of success of the negotiation using a machine learning algorithm, means for having a user input basic information about a new negotiation and predicting the most suitable cooperating company based on the information, means for generating a candidate list of the predicted cooperating companies and sending it to a terminal, means for automatically generating negotiation materials based on the predicted cooperating companies, means for having a user input the progress and results of the negotiation and storing the result data on the server, and means for continuously optimizing the model using negotiation result data. This allows sales representatives to create high-quality negotiation materials in a short amount of time, allowing them to concentrate on the negotiation and continuously improving the accuracy of the predictive model.

[0076] "Business negotiation data" refers to data relating to the content and results of commercial transactions recorded in sales activities.

[0077] "Event history" is historical information about events and activities related to past business negotiations.

[0078] "Company characteristic data" is information on the characteristics of a company, such as its industry, size, performance, and geographic location.

[0079] A "means of collection" is a method or device for obtaining the required data using a database query or API.

[0080] "Preprocessing" is the process of preparing data for analysis and model building through processes such as data cleaning, filling in missing data, and removing outliers.

[0081] A "machine learning algorithm" is a set of mathematical and statistical methods for training predictive models based on data.

[0082] "Probability of success" is a numerical representation of the likelihood that a particular business deal will be successful.

[0083] The "optimal partner" is a partner company selected to increase the probability of success in business negotiations.

[0084] "Business negotiation materials" are documents that include the purpose of the business negotiation, introductions to collaborating companies, past success stories, proposal details, etc.

[0085] "Progress" is information that indicates the stage at which the negotiation is taking place and how it is progressing.

[0086] "Result data" is data indicating whether or not a deal was concluded, or other final results.

[0087] A "continuous optimization means" is a method or apparatus for periodically updating a predictive model using sales outcome data to improve its accuracy.

[0088] A "user interface" is software that provides the input and display screens for a user to interact with a system.

[0089] MODE FOR CARRYING OUT THE INVENTION

[0090] The system of the present invention is designed to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. This system is mainly composed of a server, terminals, and users. The role of each will be explained in detail below.

[0091] Server Features

[0092] The server first collects past negotiation data, event history, and company characteristics data. This collection is done using APIs and database queries. The specific hardware and software used are a database management system (DBMS) and an HTTP client library. The data collected at this stage includes detailed logs and information, which are necessary for subsequent processing.

[0093] The server then preprocesses the collected data. Specifically, it uses Python's Pandas library to clean the data, impute missing data, and remove outliers. The preprocessed data is then formatted and used to train a model using machine learning algorithms. For this training, it applies Sci-Kit Learn's random forest and regression analysis algorithms.

[0094] Once the model training is complete, the server receives basic information about new business deals sent by the user and uses this information to predict the most suitable partner companies. In this process, the trained machine learning model is applied to generate prediction results. The predicted partner companies are generated as a candidate list and returned to the terminal along with the success rate and past success stories.

[0095] The server also has the function of automatically generating business negotiation materials. These materials include introductions to partner companies, past success stories, and proposals tailored to the purpose of the business negotiations, and are created using template generation software. These generated materials are also sent to the terminal and made available for the user to review and edit.

[0096] Device Features

[0097] Users interface with the system via a terminal. First, when starting a new business negotiation, they use the terminal's input interface to enter basic information such as "nationwide expansion of new products" and "target market." This information is then sent from the terminal to the server.

[0098] The terminal displays the forecast results and business negotiation materials of partner companies generated by the server. The user can proceed with business negotiations based on this information. Specifically, by making a presentation using the materials displayed on the terminal, the probability of success in business negotiations can be increased.

[0099] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal, and this information is sent to the server and stored in a database.

[0100] User Roles

[0101] The users are primarily salespeople who use this system to conduct sales negotiations. They input basic information about new sales negotiations through their terminals and act based on the information provided by the system at each step of the negotiation.

[0102] Specific examples

[0103] Consider the case of planning a nationwide rollout of a new product. The user inputs information about "nationwide rollout of new product" and "target market" into the terminal. The server proposes "Company A, Company B, and Company C" as the most suitable collaborating companies based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. The user can use high-quality business negotiation materials to make an effective presentation and increase the chances of success in the business negotiation.

[0104] Prompt Sentence Examples

[0105] "We have started a business negotiation regarding the nationwide rollout of a new product. Please generate a list of partner companies and automatically create business negotiation materials. Basic information for the business negotiation: new product features, target market."

[0106] The above is a specific embodiment for carrying out the present invention. This system allows salespeople to significantly reduce the time and effort required to create sales materials and select partner companies, allowing them to focus on the content of the sales negotiations. This improves the efficiency of sales activities and the success rate.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Program processing flow

[0109] Step 1:

[0110] Data collection

[0111] The server uses APIs and database queries to collect past deal data, event history, and company characteristics data.

[0112] Input: API endpoints for databases and external systems

[0113] Output: The collected raw dataset

[0114] What happens: The server connects to the database and sends SQL queries to retrieve opportunity data. It also makes HTTP requests to external APIs to retrieve additional company information, thereby gathering additional information not stored in the database.

[0115] Step 2:

[0116] Data Preprocessing

[0117] The server uses Python's Pandas library to clean the collected data, completing missing data and removing outliers.

[0118] Input: Collected raw dataset

[0119] Output: Preprocessed clean dataset

[0120] Specific operations: Impute missing values ​​in the data with the mean or median, filter outliers based on conditions, and standardize the data into a consistent format.

[0121] Step 3:

[0122] Training a machine learning model

[0123] The server uses Sci-kit Learn to train machine learning models such as random forests and regression analysis using preprocessed datasets.

[0124] Input: Preprocessed clean dataset

[0125] Output: A trained machine learning model

[0126] How it works: The server splits the clean dataset into training and testing data, and then applies random forest and regression analysis algorithms to train the model. During this process, it adjusts the model's hyperparameters to maximize predictive performance.

[0127] Step 4:

[0128] Entering new business information

[0129] The user inputs basic information about the new business negotiation (e.g., nationwide expansion of a new product, target market) via the user interface of the terminal.

[0130] Input: Basic information about the opportunity

[0131] Output: Negotiation information sent from the device to the server

[0132] Specific operation: The user enters basic information about the business deal into the input field on the terminal and clicks the "Send" button, which sends the entered information to the server.

[0133] Step 5:

[0134] Prediction of optimal partner companies

[0135] The server preprocesses the received business negotiation information and then uses the trained machine learning model to predict the most suitable partner companies.

[0136] Input: Entered business information

[0137] Output: Predicted list of collaborating companies

[0138] How it works: The server preprocesses the sales negotiation information and inputs it into a trained machine learning model. The model predicts which partners have a high probability of success and generates a list of the results.

[0139] Step 6:

[0140] Generate a list of potential partner companies

[0141] The server generates a list of candidate collaborating companies based on the prediction results and sends it to the terminal.

[0142] Input: Predicted list of collaborating companies

[0143] Output: Candidate list sent to terminal

[0144] Specific operation: A list including the probability of success and past success cases for each predicted partner company is generated and sent to the terminal.

[0145] Step 7:

[0146] Automatic generation of sales documents

[0147] The server automatically generates business negotiation materials based on the predicted partner company information and sends them to the terminal.

[0148] Input: Predicted partner company information

[0149] Output: Automatically generated business documents (PDF, etc.)

[0150] Specific operation: Generate sales documents using templates that include introductions to partner companies, past success stories, and proposal details, and send them to the terminal in PDF format or other formats.

[0151] Step 8:

[0152] Entering the progress and results of sales negotiations

[0153] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal.

[0154] Input: Opportunity status and results

[0155] Output: Entered negotiation result data (sent to server)

[0156] Specific operation: The user enters the progress and results into the progress input screen on the device, clicks the "Save" button and sends the data to the server.

[0157] Step 9:

[0158] Continuously training the model

[0159] The server uses the input sales outcome data to continuously train and optimize the machine learning model.

[0160] Input: Updated Opportunity Outcome Data

[0161] Output: An optimized machine learning model

[0162] Specific operation: Retrain using saved sales outcome data to improve the model's predictive accuracy.

[0163] The above is the specific processing flow of this system.

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] Traditional sales negotiations require a lot of time and effort to collect data, select partners with a high probability of success, and create sales negotiation materials. Furthermore, efficient operation of robots and optimization of production plans within factories have been issues. An integrated system is needed to streamline these processes and improve sales negotiation and production efficiency.

[0167] 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.

[0168] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for new negotiations and predicting the most suitable partner company based on the information, means for automatically generating negotiation materials based on the predicted partner company, means for following up on the results of negotiations and continuously optimizing the model, means for collecting past production data and maintenance records and analyzing the operating status and production success rate of each work robot, means for proposing an optimal production schedule and robot placement, and means for automatically generating operation instructions and maintenance procedures, thereby enabling efficient negotiation activities and production line operations.

[0169] "Past business negotiation data" refers to all detailed information relating to business negotiations that have taken place in the past, including the performance and results of specific business negotiations.

[0170] "Event history" refers to information that records a series of events in a business meeting or other related activity, and includes, for example, meeting dates and attendee lists.

[0171] "Corporate characteristic data" refers to information about the characteristics and attributes of a specific company, including, for example, the size and performance of the company, its position within the industry, and so on.

[0172] A "machine learning algorithm" is a computational method that extracts patterns and rules based on past data and makes predictions and classifications for new data.

[0173] "Success probability" refers to the probability that a particular business negotiation will be successful, and is a value calculated based on analysis of past data.

[0174] The "best-fit collaborating company" refers to the company that is predicted to be able to provide the most advantageous and effective cooperation in a particular business negotiation.

[0175] "Business negotiation materials" refers to documents and presentation materials necessary to support the progress of business negotiations, including proposals and explanatory materials.

[0176] "Production data" refers to all data related to the production process at a factory or manufacturing site, including, for example, production volume, operating hours, and quality data.

[0177] "Maintenance records" refer to a series of records relating to the maintenance, inspection, and repair of equipment and machinery, and include, for example, the date and time of maintenance and the specific work carried out.

[0178] "Operating status" refers to the status of a robot or machine that indicates whether it is operating normally, and is data that includes operating time, error status, etc.

[0179] The "production success probability" is the probability that a specific production schedule or task will be successful, and is also a value calculated based on an analysis of past data.

[0180] An "operation instruction manual" refers to a document that lists specific instructions and procedures for production work, including the order of work and the materials to be used.

[0181] A "maintenance procedure manual" refers to a document that describes the procedures and methods for performing maintenance, inspection, and repairs on equipment and machinery, and includes specific work procedures.

[0182] The system of the present invention is designed to improve the efficiency of business negotiation activities and the success rate of business negotiations. This system is composed of entities such as a server, terminals, and users.

[0183] The server collects past deal data, event history, and company characteristic data. The collected data is retrieved using APIs or database queries and stored in a database. The server then preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past successful and unsuccessful deals are used as training data to build a model that predicts the probability of deal success. This model is created using algorithms such as regression analysis and random forests.

[0184] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, this information includes "nationwide expansion of a new product" and "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0185] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include introductions to partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and modify.

[0186] As the negotiation progresses, the user inputs the progress into the terminal. This negotiation result data is sent back to the server and stored in the database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0187] Furthermore, it also improves the efficiency of production lines within factories. The server collects past production data and maintenance records, and analyzes the operating status and production success rate of each work robot. It proposes optimal production schedules and robot placement, and automatically generates operation instructions and maintenance procedures. This enables efficient operation of robots within factories.

[0188] As a concrete example, the following prompt statements can be used to optimize the design of a new production line:

[0189] "In order to optimize the design of a new production line, please propose the optimal robot placement and maintenance schedule using past production data. The past data includes the operating status and maintenance records of each robot. Please predict the optimal operating time and maintenance timing for each robot on the new production line, and generate the optimal production schedule based on the results."

[0190] The hardware used includes a robot control unit and a server for data analysis, and the software uses Python, Scikit-learn, Pandas, etc. This will improve the efficiency of sales activities and production activities within the factory.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The server collects past deal data, event history, and company characteristic data using APIs or database queries. The input is raw deal data, event data, and company data obtained from the database, and the output is a collection of these raw data. Specific operations include executing database queries and reading the results.

[0194] Step 2:

[0195] The server preprocesses the collected raw data. The input is raw data, and the output is cleaned data. Specific data processing includes data cleaning, imputing missing data, and removing outliers. Pandas is used for this processing.

[0196] Step 3:

[0197] The server trains a machine learning model using the preprocessed data. The input is the cleaned sales opportunity data, event data, and company data, and the output is a trained model for predicting the probability of success. Specifically, the model is built using algorithms such as random forests and Scikit-learn.

[0198] Step 4:

[0199] The user inputs basic information for a new business negotiation via a terminal. The input is basic information for the business negotiation, such as "nationwide expansion of a new product" or "target market," and the output is the business negotiation information entered by the user. Specific operations include data input via a user interface.

[0200] Step 5:

[0201] The terminal sends the entered business negotiation information to the server. The input is the business negotiation information entered by the user, and the output is the transfer of this information to the server. A specific operation is the sending of an HTTP request.

[0202] Step 6:

[0203] The server uses a trained machine learning model to predict the optimal partner based on the received business negotiation information. The input is the business negotiation information sent to the server, and the output is a list of candidate partner companies and their success rate. Specific data operations include applying the model and calculating the predicted value.

[0204] Step 7:

[0205] The server automatically generates sales negotiation materials based on the predicted partner companies. The input is a list of candidate partner companies and the success probability, and the output is the sales negotiation materials. In operation, the sales negotiation materials are created using a text generation model, etc.

[0206] Step 8:

[0207] The terminal presents the generated sales negotiation materials to the user, allowing the user to review and modify them. The input is the sales negotiation materials, and the output is the sales negotiation materials reviewed and modified by the user. Operation includes providing display and editing functions via a user interface.

[0208] Step 9:

[0209] As the negotiation progresses, the user inputs the progress status into the terminal. The input is negotiation progress information, and the output is the progress data entered by the user. The operation includes recording the progress information and inputting it into the terminal.

[0210] Step 10:

[0211] The terminal sends the entered progress data to the server. The input is the negotiation progress data, and the output is the transfer of this data to the server. The operation is the sending of an HTTP request.

[0212] Step 11:

[0213] The server stores the received progress data in a database and continuously trains and optimizes the machine learning model. The input is the sales negotiation result data, and the output is the optimized machine learning model. Specific operations include data accumulation, model retraining, and evaluation.

[0214] 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.

[0215] The system of the present invention aims to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. Furthermore, by combining it with an emotion engine that recognizes the user's emotions and utilizes them in sales negotiations, it aims to improve the quality of sales negotiations. The system is composed of entities: a server, a terminal, and a user, and each entity operates as follows.

[0216] First, the server collects past business negotiation data, event history, and company characteristic data. The collected data is retrieved via API or database query, and the contents and results of business negotiations, event details, and company characteristic information are stored in the database.

[0217] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Using past examples of successful and unsuccessful deals as training data, a model is built to predict the probability of a deal being successful. This model is created using algorithms such as regression analysis and random forests.

[0218] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0219] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0220] In addition, the system of the present invention includes an emotion engine that recognizes the user's emotions. The emotion engine has the function of extracting and analyzing emotional data from voice, facial expressions, input speed, etc. while the user is operating the terminal. For example, if the user is feeling stressed, the system can detect this and present advice to help the user relax or simpler operating procedures.

[0221] As a concrete example, when planning the nationwide rollout of a new product, the user inputs basic business negotiation information into the device, and the server suggests three optimal partner companies: Company A, Company B, and Company C. Furthermore, the device's emotion engine analyzes the user's emotions, and if tension is detected, the server provides simple operating procedures to relax the user. The server then automatically generates business negotiation materials, allowing the user to proceed with the negotiation based on high-quality materials.

[0222] As the negotiation progresses, the user periodically enters the progress and results into the device. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0223] The system of this invention not only enables salespeople to significantly reduce the time and effort required to create sales documents and select partner companies, but also improves the quality of sales negotiations by using an emotion engine, resulting in more efficient sales activities and improved results.

[0224] The above is a specific embodiment for carrying out the present invention.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] The server collects past sales data, event history, and company characteristics data using APIs and database queries. This data includes transaction history, sales activity logs, and public company information.

[0228] Step 2:

[0229] The server preprocesses the collected data. Specifically, it cleans the data, removes noise, fills in missing data, and removes outliers. It also standardizes and normalizes the data format to convert it into an analyzable format.

[0230] Step 3:

[0231] The server uses the preprocessed data to train a machine learning algorithm. It uses algorithms such as regression analysis and random forests to build a model that predicts the probability of a deal being successful. This model uses examples of successful and unsuccessful deals as training data.

[0232] Step 4:

[0233] The user uses the terminal to input basic information about a new business. For example, the user enters details of the business, such as "nationwide expansion of a new product" or "target market," into an input form.

[0234] Step 5:

[0235] The terminal sends the business negotiation information entered by the user to the server, which automatically converts the input information into the required format and passes it on to the server.

[0236] Step 6:

[0237] Based on the business negotiation information received by the server, the machine learning model it has built is used to predict the most suitable partner company. The model calculates the probability of success of the business negotiation and generates a list of candidate partner companies.

[0238] Step 7:

[0239] The server sends a list of predicted partner companies to the device, which displays the success rate of each partner company and related success stories.

[0240] Step 8:

[0241] The server automatically generates business documents based on the selected partner companies. The documents include company introductions, success stories, proposals, etc. The documents are automatically created according to a format.

[0242] Step 9:

[0243] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections. The materials are also updated in accordance with the progress of the sales negotiation.

[0244] Step 10:

[0245] The server uses an emotion engine to recognize the user's emotions, and extracts the user's emotional data by analyzing facial expressions and voice using data from the device's camera and microphone.

[0246] Step 11:

[0247] The server provides advice tailored to the progress of the business negotiation based on the user's emotional data analyzed by the emotion engine. If the user is feeling stressed, it will suggest appropriate relief measures, such as suggestions for relaxing.

[0248] Step 12:

[0249] The user inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0250] Step 13:

[0251] The terminal sends the entered negotiation result data to the server, which stores it in a database and manages the negotiation results.

[0252] Step 14:

[0253] The server uses the sales negotiation result data to retrain and optimize the partner company success model. The collected new sales negotiation result data is reflected in the model to improve prediction accuracy.

[0254] Through the above steps, the system of the present invention improves the efficiency of sales negotiation activities by sales representatives, increases the success rate of negotiations, and improves the quality of negotiations by utilizing user emotion data, thereby realizing more efficient sales activities and improved results.

[0255] Example 2

[0256] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0257] While conventional sales negotiation support systems can perform basic procedures such as preprocessing sales negotiation data and selecting partner companies, they lack comprehensive functionality to improve the quality of sales negotiations. Furthermore, because they lack advice or operational support that takes users' emotions into consideration, users often feel stressed or find it difficult to operate the system. Therefore, there is a need to improve the efficiency of overall sales negotiation activities and the success rate of sales negotiations.

[0258] 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.

[0259] In this invention, the server includes means for collecting past business negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for a new business negotiation and predicting the most suitable partner company based on the information, means for automatically generating business negotiation materials based on the predicted partner company, means for following up on the results of the business negotiation and continuously optimizing the model, emotion recognition means for extracting and analyzing emotion data from voice, facial expression, input speed, etc., and means for presenting relaxation advice and simple operating procedures to the user using the emotion data. This makes it possible to improve the quality of the entire business negotiation and provide an environment in which the user can proceed with the business negotiation without stress.

[0260] "Business negotiation data" is data containing information about business negotiations that have taken place in the past, including the dates of the business negotiations, participating companies, business negotiation content, and results.

[0261] "Event history" is a record of past events and activities, including not only business meetings but also exhibitions, seminars, networking events, etc.

[0262] "Company characteristic data" refers to data that indicates basic information and characteristics of a company, including the company's size, industry, capital, location, etc.

[0263] "Preprocessing" refers to a series of operations to convert collected data into a format that is easier to analyze, such as cleaning the data, filling in missing data, and removing outliers.

[0264] A "machine learning algorithm" is an algorithm that uses large amounts of data to learn patterns and perform predictions, classification, and optimization. Examples include regression models and random forests.

[0265] A "model for predicting success probability" is a mathematical model for predicting the success probability of a sales negotiation based on past sales negotiation data. It is constructed using a machine learning algorithm.

[0266] "Cooperating companies" are companies selected to cooperate and collaborate in business negotiations and projects.

[0267] "Business materials" are documents, slides, and a set of materials prepared to support the progress of business negotiations, including proposal details, past success stories, company introductions, etc.

[0268] "Emotion recognition means" is a technology for detecting and analyzing a user's emotional state. It infers the user's emotions from voice, facial expressions, input speed, etc.

[0269] "Relaxation advice" is a suggestion or instruction to encourage the user to relax when they are feeling stressed.

[0270] A "user interface" is a screen or input device that allows a user to interact with a system. This includes terminal screens and input forms.

[0271] "API" stands for Application Program Interface, an interface for exchanging data and functions between software programs.

[0272] A "database query" is a set of instructions used to retrieve, insert, update, or delete data from a database.

[0273] The system of the present invention is configured so that a server, a terminal, and a user work together to improve the efficiency of business negotiation activities and increase the success rate of business negotiations. In particular, a specific embodiment of a business negotiation support system including an emotion recognition function will be described.

[0274] First, the server collects past sales negotiation data, event history, and company characteristics data. This is done using APIs and database queries. Specifically, it uses Amazon Athena to execute database queries and saves the data in an Amazon S3 bucket. This data includes sales negotiation dates, participating companies, sales negotiation content, and results.

[0275] The server then preprocesses the collected data using data manipulation libraries such as Pandas and NumPy to clean the data, impute missing data, remove outliers, and convert it into an analyzable format, such as by imputing NULL values ​​and removing outliers.

[0276] Based on the preprocessed data, the server uses machine learning algorithms to build a model that predicts the probability of a deal being successful. For this, it uses Scikit-learn to train a random forest model or a regression analysis model. The trained model is saved in Pickle format and later used for prediction.

[0277] When a user starts a new business negotiation, they input basic information about the negotiation via their terminal. The user uses the terminal's input form to enter information such as "nationwide expansion of new products" and "target market" and presses the send button. The terminal then sends this information to the server.

[0278] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format. The terminal displays the results on the screen so that the user can confirm and modify them.

[0279] Furthermore, the server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. LaTeX templates are used to generate the documents, and they are output in PDF format. The generated documents are sent to the terminal and made available for the user to review and edit.

[0280] The system of the present invention includes an emotion recognition means for recognizing the user's emotions. The device uses a camera and microphone to collect the user's facial expressions, voice, input speed, etc., and transmits them to a server. The server then analyzes the user's emotion data using an emotion recognition API (for example, the emotion recognition API of Microsoft® Azure®). If the user is feeling stressed, the server presents relaxation advice and simple operating instructions.

[0281] As the negotiation progresses, the user periodically enters the progress and results of the negotiation into the device. This data is then sent back to the server and stored in a database. The server then uses the new data to retrain the machine learning model, optimizing it and improving its prediction accuracy.

[0282] Example prompt sentence:

[0283] 1. Please suggest the best partner company for the nationwide rollout of our new product.

[0284] 2. Please predict the probability of success for a business negotiation that sets "men in their 20s" as the target market.

[0285] 3. Provide relaxation advice if the user is feeling tense.

[0286] In this way, the system of the present invention comprehensively supports business negotiation activities and aims to improve efficiency in order to increase the success rate of business negotiations. In addition, by using emotion recognition means, it reduces the mental burden on the user and provides a more comfortable and effective business negotiation environment.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1: Data collection

[0289] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs and database queries. Specifically, the server uses Amazon Athena to execute database queries to retrieve deal data. The retrieved data is stored in Amazon S3.

[0290] Input: API request, database query

[0291] Output: Opportunity data, event history, and company characteristics data stored in Amazon S3

[0292] What happens: The server sends an API request and runs a query in Amazon Athena to collect data.

[0293] Step 2: Data Preprocessing

[0294] The server preprocesses the collected data by cleaning it, filling in missing data, and removing outliers. The server uses Pandas and NumPy to perform these operations and convert it into an analyzable format.

[0295] Input: Raw data retrieved from S3

[0296] Output: Preprocessed data (NumPy array format)

[0297] Specific operation: The server uses Pandas to interpolate NULL values ​​and remove outliers. The preprocessed data is converted into a NumPy array.

[0298] Step 3: Model Building

[0299] The server uses the preprocessed data to train a machine learning algorithm. Specifically, it uses Scikit-learn to train a random forest model. The trained model is saved in Pickle format.

[0300] Input: Preprocessed data

[0301] Output: Trained machine learning model (in Pickle format)

[0302] What it does: The server uses Scikit-learn to train and save the model.

[0303] Step 4: Enter business information

[0304] When starting a new business negotiation, the user inputs basic information about the business via the terminal. The user enters information such as "nationwide expansion of new products" and "target market" into the input form on the terminal and presses the send button.

[0305] Input: Basic information about the deal (nationwide launch of new products, target market, etc.)

[0306] Output: The basic information of the opportunity sent to the server

[0307] Specific behavior: A user enters information into a form on a device and presses the submit button.

[0308] Step 5: Opportunity forecasting and results presentation

[0309] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format.

[0310] Input: Opportunity information submitted by the user

[0311] Output: Prediction results (list of collaborating companies, success probability)

[0312] Specific operation: The server inputs sales information into the model, generates prediction results, and sends them back to the device.

[0313] Step 6: Generate sales documents

[0314] The server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. The generated documents are sent to the terminal in PDF format.

[0315] Input: Predicted partner information

[0316] Output: Negotiation materials (PDF format)

[0317] Specific operation: The server generates business documents using a LaTeX template and sends them to the terminal.

[0318] Step 7: Emotion Recognition

[0319] The server extracts and analyzes emotional data from voice, facial expressions, input speed, etc. when the user operates the device. The server analyzes the user's emotions using an emotion recognition API.

[0320] Input: Data sent from your device, such as voice, facial expressions, and typing speed

[0321] Output: Analysis results of emotion data

[0322] Specific operation: The server uses the emotion recognition API to analyze the emotion data and determine the user's emotional state.

[0323] Step 8: Offer relaxation advice

[0324] The server provides relaxation advice and simple operation procedures based on the results of emotion recognition. If the user is feeling stressed, corresponding advice will be displayed on the screen.

[0325] Input: Emotion data analysis results

[0326] Output: Relaxation advice and simple operating instructions

[0327] Specific operation: The server generates advice based on the results of emotion analysis and sends it to the device.

[0328] Step 9: Enter opportunity progress and retrain the model

[0329] Users periodically enter the progress and results of sales negotiations into their devices. This data is sent to the server and stored in a database. The server then retrains the machine learning model using the new data, optimizing the model and improving its prediction accuracy.

[0330] Input: Negotiation status and results

[0331] Output: An updated machine learning model

[0332] Specific operation: The user inputs the progress data of the sales negotiations on the device and sends it to the server, which then retrains the model based on this data.

[0333] (Application example 2)

[0334] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0335] Current sales negotiation systems and sales activities are unable to properly grasp customer emotions and reactions, making it difficult to optimize the progress of sales negotiations. In particular, in brick-and-mortar stores, sales staff are required to discern customer emotions and respond appropriately, but this is difficult in practice, affecting sales negotiations and sales results. Efficiently generating appropriate sales negotiation materials and making proposals to customers is also a major challenge.

[0336] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting past negotiation data, event history, and company characteristic data; means for preprocessing the collected data and constructing a model for predicting the success probability using a machine learning algorithm; means for having a user input basic information about a new negotiation and predicting the optimal partner company based on the information; means for automatically generating negotiation materials based on the predicted partner company; means for following up on the results of the negotiation and continuously optimizing the model; means for acquiring the customer's facial expressions and voice from a terminal device in real time and analyzing their emotions; means for providing advice on the progress of the negotiation based on the analyzed emotion data; and means for sending the automatically generated negotiation materials to the customer as electronic data. This makes it possible to appropriately understand the customer's emotions and reactions, optimize the progress of the negotiation, and improve sales results.

[0337] "Sales negotiation data" refers to the content and results of sales negotiations, customer information, and all data related to sales negotiations.

[0338] "Event history" refers to records of past business negotiations and related events.

[0339] "Company characteristic data" refers to characteristic information such as a company's industry, size, business model, etc.

[0340] A "machine learning algorithm" refers to a computational method for analyzing data and performing pattern recognition and prediction.

[0341] "Cooperating companies" refer to companies with which we have cooperative relationships in business negotiations and projects.

[0342] "Business negotiation materials" refers to documents and data that summarize the information and proposals necessary to advance business negotiations.

[0343] "Follow-up" refers to the activity of tracking and checking the progress and results of a business negotiation and taking action as necessary.

[0344] "Terminal device" refers to an electronic device operated by a user, such as smart glasses or a smartphone.

[0345] "Emotion analysis" refers to the process of determining a person's emotional state based on facial expressions and voice data.

[0346] "Providing advice" means that the system presents the user with next actions or suggestions.

[0347] "Electronic data" refers to information or documents stored in digital form.

[0348]

[0349] This invention is a system that aims to support sales in brick-and-mortar stores, improving the efficiency of sales negotiations when sales staff use smart glasses to deal with customers, thereby increasing the success rate.

[0350] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs or database queries. The collected data is stored in a database.

[0351] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Past examples of successful and unsuccessful deals are used as training data to build a model that predicts the probability of a deal being successful. Algorithms such as regression analysis and random forests are used.

[0352] The user (sales staff) wears the smart glasses and inputs basic information about the business negotiation when a customer visits the store. For example, they input information about the products the customer is interested in and their past purchase history. This input information is sent from the smart glasses to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The prediction results are generated as a list of candidate partner companies and are displayed on the smart glasses along with the predicted success rate and past success stories.

[0353] The terminal device (smart glasses) equipped with an emotion engine captures the customer's facial expressions and voice in real time and analyzes their emotions. For example, the smart glasses' camera and microphone can analyze the customer's facial expressions and tone of voice to determine their emotional state. The system detects this and provides the sales staff with advice on how to relax or appropriate operating procedures for the progress of the sales negotiation.

[0354] For example, when a salesperson is negotiating with a customer who is interested in a new product, the system can calculate the customer's level of interest from facial expression analysis and instruct them to provide a detailed product explanation.If the customer expresses concern about the price, the system can advise them to present a special discount offer.

[0355] Furthermore, the server automatically generates sales documents based on the predicted partner companies. The sales documents include information about the partner companies, past success stories, and proposals that match the purpose of the sales negotiation. The generated sales documents are sent to the smart glasses and made available for review and modification by the sales staff.

[0356] As the negotiation progresses, the user periodically enters progress and results. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0357] Examples of prompts for generative AI models include:

[0358] "A customer is interested in a new product. Please create a document detailing the product and offering a price discount."

[0359] Such a system provides sales staff with highly accurate information on how to create sales materials and conduct sales negotiations appropriately, thereby significantly improving the optimization of sales negotiations and the success rate of sales negotiations.

[0360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0361] Step 1:

[0362] The server collects past deal data, event history, and company characteristic data. This data is retrieved using APIs or database queries and stored in a database. The input is deal data, event history, and company characteristic data, and the output is stored in the database as collected data.

[0363] Step 2:

[0364] The server preprocesses the collected data by cleaning it, filling in missing data, removing outliers, and converting it into an analyzable format. The input is the collected raw data, and the output is preprocessed, analyzable data. This prepares the data in a format suitable for analysis.

[0365] Step 3:

[0366] The server uses the preprocessed data to train a machine learning algorithm. Using examples of past successful and unsuccessful deals as training data, it builds a model that predicts the probability of a deal's success. This model is created using algorithms such as regression analysis and random forests. The input is the preprocessed, analyzable data, and the output is a predictive model.

[0367] Step 4:

[0368] The user inputs basic information about the business negotiation using the smart glasses. The input information is sent from the smart glasses to the server. The input is the basic information about the business negotiation, and the output is the basic information about the business negotiation sent to the server.

[0369] Step 5:

[0370] The server receives basic information about the business negotiation and predicts the most suitable partner companies based on a machine learning model. The prediction results are generated as a list of candidate partner companies and displayed on the smart glasses along with the probability of success of the business negotiation and past success stories. The input is the basic information about the business negotiation, and the output is a list of candidate partner companies.

[0371] Step 6:

[0372] The terminal device (smart glasses) captures the customer's facial expressions and voice in real time and analyzes their emotions. Based on the analysis results, it provides advice to the sales staff. The input is the customer's facial expressions and voice data, and the output is the emotion analysis results and advice. This makes it possible to determine the customer's emotional state in real time.

[0373] Step 7:

[0374] The server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiations, and are provided to the smart glasses. The input is a list of potential partner companies, and the output is the automatically generated business negotiation materials.

[0375] Step 8:

[0376] Users periodically input the progress and results of sales negotiations and send this to the server. The sales negotiation result data is stored in the server's database. The input is the sales negotiation progress and result data, and the output is the sales negotiation result data stored on the server. This allows the system to continuously retrain and optimize the model.

[0377] Step 9:

[0378] The server uses the sales outcome data to retrain and optimize the predictive model, improving the model's predictive accuracy and further increasing the success rate of future sales. The input is the sales outcome data, and the output is the optimized predictive model.

[0379]

[0380] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

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

[0383] [Second embodiment]

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

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

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

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

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

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

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

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

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0396] The system of the present invention is a system for improving the efficiency of sales negotiation activities by sales representatives and increasing the success rate of sales negotiations. The system is composed of entities, namely, a server, terminals, and users, and each entity operates as follows.

[0397] First, the server collects past sales negotiation data, event history, and company characteristic data. The collected data is retrieved via APIs and database queries. The details of sales negotiations, results, event details, and company characteristic information are then stored in a database.

[0398] Next, the server preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past examples of successful and unsuccessful sales negotiations are used as training data to build a model that predicts the probability of success for a sales negotiation. This model is created using algorithms such as regression analysis and random forests.

[0399] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0400] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0401] As the negotiation progresses, the user inputs the progress and results into the device. This negotiation result data is then sent back to the server and stored in a database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0402] As a concrete example, consider the case of planning the nationwide rollout of a new product. When the user inputs basic business negotiation information into the terminal, the server proposes three companies as the most suitable partners based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. As a result, the user can make an effective presentation using high-quality business negotiation materials, increasing the chances of success in the business negotiation.

[0403] This system allows sales representatives to significantly reduce the time and effort required to create sales documents and select partner companies, allowing them to focus on the content of the sales negotiations, resulting in more efficient sales activities and improved results.

[0404] The above is a specific embodiment for carrying out the present invention.

[0405] The processing flow will be explained below.

[0406] Step 1:

[0407] The server collects past sales data, event history, and company characteristic data using APIs and database queries, including transaction history, company disclosure information, and sales activity logs.

[0408] Step 2:

[0409] The server preprocesses the collected data, specifically cleaning the data, filling in missing data, removing outliers, and converting it into an analyzable format.

[0410] Step 3:

[0411] The server uses the preprocessed data to train machine learning algorithms, using techniques such as regression analysis and random forests to build models of deal success.

[0412] Step 4:

[0413] The user uses the terminal to input basic information about a new business deal, such as "nationwide expansion of a new product" or "target market."

[0414] Step 5:

[0415] The terminal sends the entered business negotiation information to the server, which then structures the input information in an appropriate format and passes it to the server.

[0416] Step 6:

[0417] Based on the business negotiation information received by the server, the server predicts the most suitable partner companies using the business negotiation success model it has built, and calculates the predicted list of candidate companies and the success probability.

[0418] Step 7:

[0419] The server sends the terminal a list of predicted partner companies, including the success probability of each partner company and related success stories.

[0420] Step 8:

[0421] The server automatically generates business documents based on the selected partner companies, including company introductions, success stories, and proposal details.

[0422] Step 9:

[0423] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections.

[0424] Step 10:

[0425] The user periodically inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0426] Step 11:

[0427] The terminal sends the entered negotiation result data to the server, which stores it in a database.

[0428] Step 12:

[0429] The server uses the sales negotiation result data to retrain and optimize the partner company success model, thereby improving the model's prediction accuracy.

[0430] Example 1

[0431] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0432] With conventional sales systems, collecting and analyzing data to improve the success rate of sales negotiations, selecting partner companies, and preparing sales negotiation materials required a lot of time and effort. As a result, sales representatives had to spend a lot of time collecting information necessary for sales negotiations and preparing materials, which meant they were unable to concentrate on the sales negotiations themselves. Furthermore, continuous optimization of the model based on sales negotiation results was not performed, making it difficult to improve prediction accuracy.

[0433] 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.

[0434] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the probability of success of the negotiation using a machine learning algorithm, means for having a user input basic information about a new negotiation and predicting the most suitable cooperating company based on the information, means for generating a candidate list of the predicted cooperating companies and sending it to a terminal, means for automatically generating negotiation materials based on the predicted cooperating companies, means for having a user input the progress and results of the negotiation and storing the result data on the server, and means for continuously optimizing the model using negotiation result data. This allows sales representatives to create high-quality negotiation materials in a short amount of time, allowing them to concentrate on the negotiation and continuously improving the accuracy of the predictive model.

[0435] "Business negotiation data" refers to data relating to the content and results of commercial transactions recorded in sales activities.

[0436] "Event history" is historical information about events and activities related to past business negotiations.

[0437] "Company characteristic data" is information on the characteristics of a company, such as its industry, size, performance, and geographic location.

[0438] A "means of collection" is a method or device for obtaining the required data using a database query or API.

[0439] "Preprocessing" is the process of preparing data for analysis and model building through processes such as data cleaning, filling in missing data, and removing outliers.

[0440] A "machine learning algorithm" is a set of mathematical and statistical methods for training predictive models based on data.

[0441] "Probability of success" is a numerical representation of the likelihood that a particular business deal will be successful.

[0442] The "optimal partner" is a partner company selected to increase the probability of success in business negotiations.

[0443] "Business negotiation materials" are documents that include the purpose of the business negotiation, introductions to collaborating companies, past success stories, proposal details, etc.

[0444] "Progress" is information that indicates the stage at which the negotiation is taking place and how it is progressing.

[0445] "Result data" is data indicating whether or not a deal was concluded, or other final results.

[0446] A "continuous optimization means" is a method or apparatus for periodically updating a predictive model using sales outcome data to improve its accuracy.

[0447] A "user interface" is software that provides the input and display screens for a user to interact with a system.

[0448] MODE FOR CARRYING OUT THE INVENTION

[0449] The system of the present invention is designed to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. This system is mainly composed of a server, terminals, and users. The role of each will be explained in detail below.

[0450] Server Features

[0451] The server first collects past negotiation data, event history, and company characteristics data. This collection is done using APIs and database queries. The specific hardware and software used are a database management system (DBMS) and an HTTP client library. The data collected at this stage includes detailed logs and information, which are necessary for subsequent processing.

[0452] The server then preprocesses the collected data. Specifically, it uses Python's Pandas library to clean the data, impute missing data, and remove outliers. The preprocessed data is then formatted and used to train a model using machine learning algorithms. For this training, it applies Sci-Kit Learn's random forest and regression analysis algorithms.

[0453] Once the model training is complete, the server receives basic information about new business deals sent by the user and uses this information to predict the most suitable partner companies. In this process, the trained machine learning model is applied to generate prediction results. The predicted partner companies are generated as a candidate list and returned to the terminal along with the success rate and past success stories.

[0454] The server also has the function of automatically generating business negotiation materials. These materials include introductions to partner companies, past success stories, and proposals tailored to the purpose of the business negotiations, and are created using template generation software. These generated materials are also sent to the terminal and made available for the user to review and edit.

[0455] Device Features

[0456] Users interface with the system via a terminal. First, when starting a new business negotiation, they use the terminal's input interface to enter basic information such as "nationwide expansion of new products" and "target market." This information is then sent from the terminal to the server.

[0457] The terminal displays the forecast results and business negotiation materials of partner companies generated by the server. The user can proceed with business negotiations based on this information. Specifically, by making a presentation using the materials displayed on the terminal, the probability of success in business negotiations can be increased.

[0458] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal, and this information is sent to the server and stored in a database.

[0459] User Roles

[0460] The users are primarily salespeople who use this system to conduct sales negotiations. They input basic information about new sales negotiations through their terminals and act based on the information provided by the system at each step of the negotiation.

[0461] Specific examples

[0462] Consider the case of planning a nationwide rollout of a new product. The user inputs information about "nationwide rollout of new product" and "target market" into the terminal. The server proposes "Company A, Company B, and Company C" as the most suitable collaborating companies based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. The user can use high-quality business negotiation materials to make an effective presentation and increase the chances of success in the business negotiation.

[0463] Prompt Sentence Examples

[0464] "We have started a business negotiation regarding the nationwide rollout of a new product. Please generate a list of partner companies and automatically create business negotiation materials. Basic information for the business negotiation: new product features, target market."

[0465] The above is a specific embodiment for carrying out the present invention. This system allows salespeople to significantly reduce the time and effort required to create sales materials and select partner companies, allowing them to focus on the content of the sales negotiations. This improves the efficiency of sales activities and the success rate.

[0466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0467] Program processing flow

[0468] Step 1:

[0469] Data collection

[0470] The server uses APIs and database queries to collect past deal data, event history, and company characteristics data.

[0471] Input: API endpoints for databases and external systems

[0472] Output: The collected raw dataset

[0473] What happens: The server connects to the database and sends SQL queries to retrieve opportunity data. It also makes HTTP requests to external APIs to retrieve additional company information, thereby gathering additional information not stored in the database.

[0474] Step 2:

[0475] Data Preprocessing

[0476] The server uses Python's Pandas library to clean the collected data, completing missing data and removing outliers.

[0477] Input: Collected raw dataset

[0478] Output: Preprocessed clean dataset

[0479] Specific operations: Impute missing values ​​in the data with the mean or median, filter outliers based on conditions, and standardize the data into a consistent format.

[0480] Step 3:

[0481] Training a machine learning model

[0482] The server uses Sci-kit Learn to train machine learning models such as random forests and regression analysis using preprocessed datasets.

[0483] Input: Preprocessed clean dataset

[0484] Output: A trained machine learning model

[0485] How it works: The server splits the clean dataset into training and testing data, and then applies random forest and regression analysis algorithms to train the model. During this process, it adjusts the model's hyperparameters to maximize predictive performance.

[0486] Step 4:

[0487] Entering new business information

[0488] The user inputs basic information about the new business negotiation (e.g., nationwide expansion of a new product, target market) via the user interface of the terminal.

[0489] Input: Basic information about the opportunity

[0490] Output: Negotiation information sent from the device to the server

[0491] Specific operation: The user enters basic information about the business deal into the input field on the terminal and clicks the "Send" button, which sends the entered information to the server.

[0492] Step 5:

[0493] Prediction of optimal partner companies

[0494] The server preprocesses the received business negotiation information and then uses the trained machine learning model to predict the most suitable partner companies.

[0495] Input: Entered business information

[0496] Output: Predicted list of collaborating companies

[0497] How it works: The server preprocesses the sales negotiation information and inputs it into a trained machine learning model. The model predicts which partners have a high probability of success and generates a list of the results.

[0498] Step 6:

[0499] Generate a list of potential partner companies

[0500] The server generates a list of candidate collaborating companies based on the prediction results and sends it to the terminal.

[0501] Input: Predicted list of collaborating companies

[0502] Output: Candidate list sent to terminal

[0503] Specific operation: A list including the probability of success and past success cases for each predicted partner company is generated and sent to the terminal.

[0504] Step 7:

[0505] Automatic generation of sales documents

[0506] The server automatically generates business negotiation materials based on the predicted partner company information and sends them to the terminal.

[0507] Input: Predicted partner company information

[0508] Output: Automatically generated business documents (PDF, etc.)

[0509] Specific operation: Generate sales documents using templates that include introductions to partner companies, past success stories, and proposal details, and send them to the terminal in PDF format or other formats.

[0510] Step 8:

[0511] Entering the progress and results of sales negotiations

[0512] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal.

[0513] Input: Opportunity status and results

[0514] Output: Entered negotiation result data (sent to server)

[0515] Specific operation: The user enters the progress and results into the progress input screen on the device, clicks the "Save" button and sends the data to the server.

[0516] Step 9:

[0517] Continuously training the model

[0518] The server uses the input sales outcome data to continuously train and optimize the machine learning model.

[0519] Input: Updated Opportunity Outcome Data

[0520] Output: An optimized machine learning model

[0521] Specific operation: Retrain using saved sales outcome data to improve the model's predictive accuracy.

[0522] The above is the specific processing flow of this system.

[0523] (Application example 1)

[0524] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0525] Traditional sales negotiations require a lot of time and effort to collect data, select partners with a high probability of success, and create sales negotiation materials. Furthermore, efficient operation of robots and optimization of production plans within factories have been issues. An integrated system is needed to streamline these processes and improve sales negotiation and production efficiency.

[0526] 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.

[0527] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for new negotiations and predicting the most suitable partner company based on the information, means for automatically generating negotiation materials based on the predicted partner company, means for following up on the results of negotiations and continuously optimizing the model, means for collecting past production data and maintenance records and analyzing the operating status and production success rate of each work robot, means for proposing an optimal production schedule and robot placement, and means for automatically generating operation instructions and maintenance procedures, thereby enabling efficient negotiation activities and production line operations.

[0528] "Past business negotiation data" refers to all detailed information relating to business negotiations that have taken place in the past, including the performance and results of specific business negotiations.

[0529] "Event history" refers to information that records a series of events in a business meeting or other related activity, and includes, for example, meeting dates and attendee lists.

[0530] "Corporate characteristic data" refers to information about the characteristics and attributes of a specific company, including, for example, the size and performance of the company, its position within the industry, and so on.

[0531] A "machine learning algorithm" is a computational method that extracts patterns and rules based on past data and makes predictions and classifications for new data.

[0532] "Success probability" refers to the probability that a particular business negotiation will be successful, and is a value calculated based on analysis of past data.

[0533] The "best-fit collaborating company" refers to the company that is predicted to be able to provide the most advantageous and effective cooperation in a particular business negotiation.

[0534] "Business negotiation materials" refers to documents and presentation materials necessary to support the progress of business negotiations, including proposals and explanatory materials.

[0535] "Production data" refers to all data related to the production process at a factory or manufacturing site, including, for example, production volume, operating hours, and quality data.

[0536] "Maintenance records" refer to a series of records relating to the maintenance, inspection, and repair of equipment and machinery, and include, for example, the date and time of maintenance and the specific work carried out.

[0537] "Operating status" refers to the status of a robot or machine that indicates whether it is operating normally, and is data that includes operating time, error status, etc.

[0538] The "production success probability" is the probability that a specific production schedule or task will be successful, and is also a value calculated based on an analysis of past data.

[0539] An "operation instruction manual" refers to a document that lists specific instructions and procedures for production work, including the order of work and the materials to be used.

[0540] A "maintenance procedure manual" refers to a document that describes the procedures and methods for performing maintenance, inspection, and repairs on equipment and machinery, and includes specific work procedures.

[0541] The system of the present invention is designed to improve the efficiency of business negotiation activities and the success rate of business negotiations. This system is composed of entities such as a server, terminals, and users.

[0542] The server collects past deal data, event history, and company characteristic data. The collected data is retrieved using APIs or database queries and stored in a database. The server then preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past successful and unsuccessful deals are used as training data to build a model that predicts the probability of deal success. This model is created using algorithms such as regression analysis and random forests.

[0543] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, this information includes "nationwide expansion of a new product" and "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0544] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include introductions to partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and modify.

[0545] As the negotiation progresses, the user inputs the progress into the terminal. This negotiation result data is sent back to the server and stored in the database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0546] Furthermore, it also improves the efficiency of production lines within factories. The server collects past production data and maintenance records, and analyzes the operating status and production success rate of each work robot. It proposes optimal production schedules and robot placement, and automatically generates operation instructions and maintenance procedures. This enables efficient operation of robots within factories.

[0547] As a concrete example, the following prompt statements can be used to optimize the design of a new production line:

[0548] "In order to optimize the design of a new production line, please propose the optimal robot placement and maintenance schedule using past production data. The past data includes the operating status and maintenance records of each robot. Please predict the optimal operating time and maintenance timing for each robot on the new production line, and generate the optimal production schedule based on the results."

[0549] The hardware used includes a robot control unit and a server for data analysis, and the software uses Python, Scikit-learn, Pandas, etc. This will improve the efficiency of sales activities and production activities within the factory.

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The server collects past deal data, event history, and company characteristic data using APIs or database queries. The input is raw deal data, event data, and company data obtained from the database, and the output is a collection of these raw data. Specific operations include executing database queries and reading the results.

[0553] Step 2:

[0554] The server preprocesses the collected raw data. The input is raw data, and the output is cleaned data. Specific data processing includes data cleaning, imputing missing data, and removing outliers. Pandas is used for this processing.

[0555] Step 3:

[0556] The server trains a machine learning model using the preprocessed data. The input is the cleaned sales opportunity data, event data, and company data, and the output is a trained model for predicting the probability of success. Specifically, the model is built using algorithms such as random forests and Scikit-learn.

[0557] Step 4:

[0558] The user inputs basic information for a new business negotiation via a terminal. The input is basic information for the business negotiation, such as "nationwide expansion of a new product" or "target market," and the output is the business negotiation information entered by the user. Specific operations include data input via a user interface.

[0559] Step 5:

[0560] The terminal sends the entered business negotiation information to the server. The input is the business negotiation information entered by the user, and the output is the transfer of this information to the server. A specific operation is the sending of an HTTP request.

[0561] Step 6:

[0562] The server uses a trained machine learning model to predict the optimal partner based on the received business negotiation information. The input is the business negotiation information sent to the server, and the output is a list of candidate partner companies and their success rate. Specific data operations include applying the model and calculating the predicted value.

[0563] Step 7:

[0564] The server automatically generates sales negotiation materials based on the predicted partner companies. The input is a list of candidate partner companies and the success probability, and the output is the sales negotiation materials. In operation, the sales negotiation materials are created using a text generation model, etc.

[0565] Step 8:

[0566] The terminal presents the generated sales negotiation materials to the user, allowing the user to review and modify them. The input is the sales negotiation materials, and the output is the sales negotiation materials reviewed and modified by the user. Operation includes providing display and editing functions via a user interface.

[0567] Step 9:

[0568] As the negotiation progresses, the user inputs the progress status into the terminal. The input is negotiation progress information, and the output is the progress data entered by the user. The operation includes recording the progress information and inputting it into the terminal.

[0569] Step 10:

[0570] The terminal sends the entered progress data to the server. The input is the negotiation progress data, and the output is the transfer of this data to the server. The operation is the sending of an HTTP request.

[0571] Step 11:

[0572] The server stores the received progress data in a database and continuously trains and optimizes the machine learning model. The input is the sales negotiation result data, and the output is the optimized machine learning model. Specific operations include data accumulation, model retraining, and evaluation.

[0573] 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.

[0574] The system of the present invention aims to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. Furthermore, by combining it with an emotion engine that recognizes the user's emotions and utilizes them in sales negotiations, it aims to improve the quality of sales negotiations. The system is composed of entities: a server, a terminal, and a user, and each entity operates as follows.

[0575] First, the server collects past business negotiation data, event history, and company characteristic data. The collected data is retrieved via API or database query, and the contents and results of business negotiations, event details, and company characteristic information are stored in the database.

[0576] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Using past examples of successful and unsuccessful deals as training data, a model is built to predict the probability of a deal being successful. This model is created using algorithms such as regression analysis and random forests.

[0577] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0578] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0579] In addition, the system of the present invention includes an emotion engine that recognizes the user's emotions. The emotion engine has the function of extracting and analyzing emotional data from voice, facial expressions, input speed, etc. while the user is operating the terminal. For example, if the user is feeling stressed, the system can detect this and present advice to help the user relax or simpler operating procedures.

[0580] As a concrete example, when planning the nationwide rollout of a new product, the user inputs basic business negotiation information into the device, and the server suggests three optimal partner companies: Company A, Company B, and Company C. Furthermore, the device's emotion engine analyzes the user's emotions, and if tension is detected, the server provides simple operating procedures to relax the user. The server then automatically generates business negotiation materials, allowing the user to proceed with the negotiation based on high-quality materials.

[0581] As the negotiation progresses, the user periodically enters the progress and results into the device. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0582] The system of this invention not only enables salespeople to significantly reduce the time and effort required to create sales documents and select partner companies, but also improves the quality of sales negotiations by using an emotion engine, resulting in more efficient sales activities and improved results.

[0583] The above is a specific embodiment for carrying out the present invention.

[0584] The processing flow will be explained below.

[0585] Step 1:

[0586] The server collects past sales data, event history, and company characteristics data using APIs and database queries. This data includes transaction history, sales activity logs, and public company information.

[0587] Step 2:

[0588] The server preprocesses the collected data. Specifically, it cleans the data, removes noise, fills in missing data, and removes outliers. It also standardizes and normalizes the data format to convert it into an analyzable format.

[0589] Step 3:

[0590] The server uses the preprocessed data to train a machine learning algorithm. It uses algorithms such as regression analysis and random forests to build a model that predicts the probability of a deal being successful. This model uses examples of successful and unsuccessful deals as training data.

[0591] Step 4:

[0592] The user uses the terminal to input basic information about a new business. For example, the user enters details of the business, such as "nationwide expansion of a new product" or "target market," into an input form.

[0593] Step 5:

[0594] The terminal sends the business negotiation information entered by the user to the server, which automatically converts the input information into the required format and passes it on to the server.

[0595] Step 6:

[0596] Based on the business negotiation information received by the server, the machine learning model it has built is used to predict the most suitable partner company. The model calculates the probability of success of the business negotiation and generates a list of candidate partner companies.

[0597] Step 7:

[0598] The server sends a list of predicted partner companies to the device, which displays the success rate of each partner company and related success stories.

[0599] Step 8:

[0600] The server automatically generates business documents based on the selected partner companies. The documents include company introductions, success stories, proposals, etc. The documents are automatically created according to a format.

[0601] Step 9:

[0602] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections. The materials are also updated in accordance with the progress of the sales negotiation.

[0603] Step 10:

[0604] The server uses an emotion engine to recognize the user's emotions, and extracts the user's emotional data by analyzing facial expressions and voice using data from the device's camera and microphone.

[0605] Step 11:

[0606] The server provides advice tailored to the progress of the business negotiation based on the user's emotional data analyzed by the emotion engine. If the user is feeling stressed, it will suggest appropriate relief measures, such as suggestions for relaxing.

[0607] Step 12:

[0608] The user inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0609] Step 13:

[0610] The terminal sends the entered negotiation result data to the server, which stores it in a database and manages the negotiation results.

[0611] Step 14:

[0612] The server uses the sales negotiation result data to retrain and optimize the partner company success model. The collected new sales negotiation result data is reflected in the model to improve prediction accuracy.

[0613] Through the above steps, the system of the present invention improves the efficiency of sales negotiation activities by sales representatives, increases the success rate of negotiations, and improves the quality of negotiations by utilizing user emotion data, thereby realizing more efficient sales activities and improved results.

[0614] Example 2

[0615] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0616] While conventional sales negotiation support systems can perform basic procedures such as preprocessing sales negotiation data and selecting partner companies, they lack comprehensive functionality to improve the quality of sales negotiations. Furthermore, because they lack advice or operational support that takes users' emotions into consideration, users often feel stressed or find it difficult to operate the system. Therefore, there is a need to improve the efficiency of overall sales negotiation activities and the success rate of sales negotiations.

[0617] 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.

[0618] In this invention, the server includes means for collecting past business negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for a new business negotiation and predicting the most suitable partner company based on the information, means for automatically generating business negotiation materials based on the predicted partner company, means for following up on the results of the business negotiation and continuously optimizing the model, emotion recognition means for extracting and analyzing emotion data from voice, facial expression, input speed, etc., and means for presenting relaxation advice and simple operating procedures to the user using the emotion data. This makes it possible to improve the quality of the entire business negotiation and provide an environment in which the user can proceed with the business negotiation without stress.

[0619] "Business negotiation data" is data containing information about business negotiations that have taken place in the past, including the dates of the business negotiations, participating companies, business negotiation content, and results.

[0620] "Event history" is a record of past events and activities, including not only business meetings but also exhibitions, seminars, networking events, etc.

[0621] "Company characteristic data" refers to data that indicates basic information and characteristics of a company, including the company's size, industry, capital, location, etc.

[0622] "Preprocessing" refers to a series of operations to convert collected data into a format that is easier to analyze, such as cleaning the data, filling in missing data, and removing outliers.

[0623] A "machine learning algorithm" is an algorithm that uses large amounts of data to learn patterns and perform predictions, classification, and optimization. Examples include regression models and random forests.

[0624] A "model for predicting success probability" is a mathematical model for predicting the success probability of a sales negotiation based on past sales negotiation data. It is constructed using a machine learning algorithm.

[0625] "Cooperating companies" are companies selected to cooperate and collaborate in business negotiations and projects.

[0626] "Business materials" are documents, slides, and a set of materials prepared to support the progress of business negotiations, including proposal details, past success stories, company introductions, etc.

[0627] "Emotion recognition means" is a technology for detecting and analyzing a user's emotional state. It infers the user's emotions from voice, facial expressions, input speed, etc.

[0628] "Relaxation advice" is a suggestion or instruction to encourage the user to relax when they are feeling stressed.

[0629] A "user interface" is a screen or input device that allows a user to interact with a system. This includes terminal screens and input forms.

[0630] "API" stands for Application Program Interface, an interface for exchanging data and functions between software programs.

[0631] A "database query" is a set of instructions used to retrieve, insert, update, or delete data from a database.

[0632] The system of the present invention is configured so that a server, a terminal, and a user work together to improve the efficiency of business negotiation activities and increase the success rate of business negotiations. In particular, a specific embodiment of a business negotiation support system including an emotion recognition function will be described.

[0633] First, the server collects past sales negotiation data, event history, and company characteristics data. This is done using APIs and database queries. Specifically, it uses Amazon Athena to execute database queries and saves the data in an Amazon S3 bucket. This data includes sales negotiation dates, participating companies, sales negotiation content, and results.

[0634] The server then preprocesses the collected data using data manipulation libraries such as Pandas and NumPy to clean the data, impute missing data, remove outliers, and convert it into an analyzable format, such as by imputing NULL values ​​and removing outliers.

[0635] Based on the preprocessed data, the server uses machine learning algorithms to build a model that predicts the probability of a deal being successful. For this, it uses Scikit-learn to train a random forest model or a regression analysis model. The trained model is saved in Pickle format and later used for prediction.

[0636] When a user starts a new business negotiation, they input basic information about the negotiation via their terminal. The user uses the terminal's input form to enter information such as "nationwide expansion of new products" and "target market" and presses the send button. The terminal then sends this information to the server.

[0637] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format. The terminal displays the results on the screen so that the user can confirm and modify them.

[0638] Furthermore, the server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. LaTeX templates are used to generate the documents, and they are output in PDF format. The generated documents are sent to the terminal and made available for the user to review and edit.

[0639] The system of the present invention includes an emotion recognition means for recognizing the user's emotions. The device uses a camera and microphone to collect the user's facial expressions, voice, input speed, etc., and transmits them to a server. The server then analyzes the user's emotion data using an emotion recognition API (e.g., Microsoft Azure's emotion recognition API). If the user is feeling stressed, the server presents relaxation advice and simple operating instructions.

[0640] As the negotiation progresses, the user periodically enters the progress and results of the negotiation into the device. This data is then sent back to the server and stored in a database. The server then uses the new data to retrain the machine learning model, optimizing it and improving its prediction accuracy.

[0641] Example prompt sentence:

[0642] 1. Please suggest the best partner company for the nationwide rollout of our new product.

[0643] 2. Please predict the probability of success for a business negotiation that sets "men in their 20s" as the target market.

[0644] 3. Provide relaxation advice if the user is feeling tense.

[0645] In this way, the system of the present invention comprehensively supports business negotiation activities and aims to improve efficiency in order to increase the success rate of business negotiations. In addition, by using emotion recognition means, it reduces the mental burden on the user and provides a more comfortable and effective business negotiation environment.

[0646] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0647] Step 1: Data collection

[0648] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs and database queries. Specifically, the server uses Amazon Athena to execute database queries to retrieve deal data. The retrieved data is stored in Amazon S3.

[0649] Input: API request, database query

[0650] Output: Opportunity data, event history, and company characteristics data stored in Amazon S3

[0651] What happens: The server sends an API request and runs a query in Amazon Athena to collect data.

[0652] Step 2: Data Preprocessing

[0653] The server preprocesses the collected data by cleaning it, filling in missing data, and removing outliers. The server uses Pandas and NumPy to perform these operations and convert it into an analyzable format.

[0654] Input: Raw data retrieved from S3

[0655] Output: Preprocessed data (NumPy array format)

[0656] Specific operation: The server uses Pandas to interpolate NULL values ​​and remove outliers. The preprocessed data is converted into a NumPy array.

[0657] Step 3: Model Building

[0658] The server uses the preprocessed data to train a machine learning algorithm. Specifically, it uses Scikit-learn to train a random forest model. The trained model is saved in Pickle format.

[0659] Input: Preprocessed data

[0660] Output: Trained machine learning model (in Pickle format)

[0661] What it does: The server uses Scikit-learn to train and save the model.

[0662] Step 4: Enter business information

[0663] When starting a new business negotiation, the user inputs basic information about the business via the terminal. The user enters information such as "nationwide expansion of new products" and "target market" into the input form on the terminal and presses the send button.

[0664] Input: Basic information about the deal (nationwide launch of new products, target market, etc.)

[0665] Output: The basic information of the opportunity sent to the server

[0666] Specific behavior: A user enters information into a form on a device and presses the submit button.

[0667] Step 5: Opportunity forecasting and results presentation

[0668] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format.

[0669] Input: Opportunity information submitted by the user

[0670] Output: Prediction results (list of collaborating companies, success probability)

[0671] Specific operation: The server inputs sales information into the model, generates prediction results, and sends them back to the device.

[0672] Step 6: Generate sales documents

[0673] The server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. The generated documents are sent to the terminal in PDF format.

[0674] Input: Predicted partner information

[0675] Output: Negotiation materials (PDF format)

[0676] Specific operation: The server generates business documents using a LaTeX template and sends them to the terminal.

[0677] Step 7: Emotion Recognition

[0678] The server extracts and analyzes emotional data from voice, facial expressions, input speed, etc. when the user operates the device. The server analyzes the user's emotions using an emotion recognition API.

[0679] Input: Data sent from your device, such as voice, facial expressions, and typing speed

[0680] Output: Analysis results of emotion data

[0681] Specific operation: The server uses the emotion recognition API to analyze the emotion data and determine the user's emotional state.

[0682] Step 8: Offer relaxation advice

[0683] The server provides relaxation advice and simple operation procedures based on the results of emotion recognition. If the user is feeling stressed, corresponding advice will be displayed on the screen.

[0684] Input: Emotion data analysis results

[0685] Output: Relaxation advice and simple operating instructions

[0686] Specific operation: The server generates advice based on the results of emotion analysis and sends it to the device.

[0687] Step 9: Enter opportunity progress and retrain the model

[0688] Users periodically enter the progress and results of sales negotiations into their devices. This data is sent to the server and stored in a database. The server then retrains the machine learning model using the new data, optimizing the model and improving its prediction accuracy.

[0689] Input: Negotiation status and results

[0690] Output: An updated machine learning model

[0691] Specific operation: The user inputs the progress data of the sales negotiations on the device and sends it to the server, which then retrains the model based on this data.

[0692] (Application example 2)

[0693] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0694] Current sales negotiation systems and sales activities are unable to properly grasp customer emotions and reactions, making it difficult to optimize the progress of sales negotiations. In particular, in brick-and-mortar stores, sales staff are required to discern customer emotions and respond appropriately, but this is difficult in practice, affecting sales negotiations and sales results. Efficiently generating appropriate sales negotiation materials and making proposals to customers is also a major challenge.

[0695] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting past negotiation data, event history, and company characteristic data; means for preprocessing the collected data and constructing a model for predicting the success probability using a machine learning algorithm; means for having a user input basic information about a new negotiation and predicting the optimal partner company based on the information; means for automatically generating negotiation materials based on the predicted partner company; means for following up on the results of the negotiation and continuously optimizing the model; means for acquiring the customer's facial expressions and voice from a terminal device in real time and analyzing their emotions; means for providing advice on the progress of the negotiation based on the analyzed emotion data; and means for sending the automatically generated negotiation materials to the customer as electronic data. This makes it possible to appropriately understand the customer's emotions and reactions, optimize the progress of the negotiation, and improve sales results.

[0696] "Sales negotiation data" refers to the content and results of sales negotiations, customer information, and all data related to sales negotiations.

[0697] "Event history" refers to records of past business negotiations and related events.

[0698] "Company characteristic data" refers to characteristic information such as a company's industry, size, business model, etc.

[0699] A "machine learning algorithm" refers to a computational method for analyzing data and performing pattern recognition and prediction.

[0700] "Cooperating companies" refer to companies with which we have cooperative relationships in business negotiations and projects.

[0701] "Business negotiation materials" refers to documents and data that summarize the information and proposals necessary to advance business negotiations.

[0702] "Follow-up" refers to the activity of tracking and checking the progress and results of a business negotiation and taking action as necessary.

[0703] "Terminal device" refers to an electronic device operated by a user, such as smart glasses or a smartphone.

[0704] "Emotion analysis" refers to the process of determining a person's emotional state based on facial expressions and voice data.

[0705] "Providing advice" means that the system presents the user with next actions or suggestions.

[0706] "Electronic data" refers to information or documents stored in digital form.

[0707]

[0708] This invention is a system that aims to support sales in brick-and-mortar stores, improving the efficiency of sales negotiations when sales staff use smart glasses to deal with customers, thereby increasing the success rate.

[0709] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs or database queries. The collected data is stored in a database.

[0710] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Past examples of successful and unsuccessful deals are used as training data to build a model that predicts the probability of a deal being successful. Algorithms such as regression analysis and random forests are used.

[0711] The user (sales staff) wears the smart glasses and inputs basic information about the business negotiation when a customer visits the store. For example, they input information about the products the customer is interested in and their past purchase history. This input information is sent from the smart glasses to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The prediction results are generated as a list of candidate partner companies and are displayed on the smart glasses along with the predicted success rate and past success stories.

[0712] The terminal device (smart glasses) equipped with an emotion engine captures the customer's facial expressions and voice in real time and analyzes their emotions. For example, the smart glasses' camera and microphone can analyze the customer's facial expressions and tone of voice to determine their emotional state. The system detects this and provides the sales staff with advice on how to relax or appropriate operating procedures for the progress of the sales negotiation.

[0713] For example, when a salesperson is negotiating with a customer who is interested in a new product, the system can calculate the customer's level of interest from facial expression analysis and instruct them to provide a detailed product explanation.If the customer expresses concern about the price, the system can advise them to present a special discount offer.

[0714] Furthermore, the server automatically generates sales documents based on the predicted partner companies. The sales documents include information about the partner companies, past success stories, and proposals that match the purpose of the sales negotiation. The generated sales documents are sent to the smart glasses and made available for review and modification by the sales staff.

[0715] As the negotiation progresses, the user periodically enters progress and results. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0716] Examples of prompts for generative AI models include:

[0717] "A customer is interested in a new product. Please create a document detailing the product and offering a price discount."

[0718] Such a system provides sales staff with highly accurate information on how to create sales materials and conduct sales negotiations appropriately, thereby significantly improving the optimization of sales negotiations and the success rate of sales negotiations.

[0719] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0720] Step 1:

[0721] The server collects past deal data, event history, and company characteristic data. This data is retrieved using APIs or database queries and stored in a database. The input is deal data, event history, and company characteristic data, and the output is stored in the database as collected data.

[0722] Step 2:

[0723] The server preprocesses the collected data by cleaning it, filling in missing data, removing outliers, and converting it into an analyzable format. The input is the collected raw data, and the output is preprocessed, analyzable data. This prepares the data in a format suitable for analysis.

[0724] Step 3:

[0725] The server uses the preprocessed data to train a machine learning algorithm. Using examples of past successful and unsuccessful deals as training data, it builds a model that predicts the probability of a deal's success. This model is created using algorithms such as regression analysis and random forests. The input is the preprocessed, analyzable data, and the output is a predictive model.

[0726] Step 4:

[0727] The user inputs basic information about the business negotiation using the smart glasses. The input information is sent from the smart glasses to the server. The input is the basic information about the business negotiation, and the output is the basic information about the business negotiation sent to the server.

[0728] Step 5:

[0729] The server receives basic information about the business negotiation and predicts the most suitable partner companies based on a machine learning model. The prediction results are generated as a list of candidate partner companies and displayed on the smart glasses along with the probability of success of the business negotiation and past success stories. The input is the basic information about the business negotiation, and the output is a list of candidate partner companies.

[0730] Step 6:

[0731] The terminal device (smart glasses) captures the customer's facial expressions and voice in real time and analyzes their emotions. Based on the analysis results, it provides advice to the sales staff. The input is the customer's facial expressions and voice data, and the output is the emotion analysis results and advice. This makes it possible to determine the customer's emotional state in real time.

[0732] Step 7:

[0733] The server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiations, and are provided to the smart glasses. The input is a list of potential partner companies, and the output is the automatically generated business negotiation materials.

[0734] Step 8:

[0735] Users periodically input the progress and results of sales negotiations and send this to the server. The sales negotiation result data is stored in the server's database. The input is the sales negotiation progress and result data, and the output is the sales negotiation result data stored on the server. This allows the system to continuously retrain and optimize the model.

[0736] Step 9:

[0737] The server uses the sales outcome data to retrain and optimize the predictive model, improving the model's predictive accuracy and further increasing the success rate of future sales. The input is the sales outcome data, and the output is the optimized predictive model.

[0738]

[0739] 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.

[0740] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0741] 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.

[0742] [Third embodiment]

[0743] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0744] 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.

[0745] 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).

[0746] 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.

[0747] 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.

[0748] 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).

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0755] The system of the present invention is a system for improving the efficiency of sales negotiation activities by sales representatives and increasing the success rate of sales negotiations. The system is composed of entities, namely, a server, terminals, and users, and each entity operates as follows.

[0756] First, the server collects past sales negotiation data, event history, and company characteristic data. The collected data is retrieved via APIs and database queries. The details of sales negotiations, results, event details, and company characteristic information are then stored in a database.

[0757] Next, the server preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past examples of successful and unsuccessful sales negotiations are used as training data to build a model that predicts the probability of success for a sales negotiation. This model is created using algorithms such as regression analysis and random forests.

[0758] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0759] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0760] As the negotiation progresses, the user inputs the progress and results into the device. This negotiation result data is then sent back to the server and stored in a database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0761] As a concrete example, consider the case of planning the nationwide rollout of a new product. When the user inputs basic business negotiation information into the terminal, the server proposes three companies as the most suitable partners based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. As a result, the user can make an effective presentation using high-quality business negotiation materials, increasing the chances of success in the business negotiation.

[0762] This system allows sales representatives to significantly reduce the time and effort required to create sales documents and select partner companies, allowing them to focus on the content of the sales negotiations, resulting in more efficient sales activities and improved results.

[0763] The above is a specific embodiment for carrying out the present invention.

[0764] The processing flow will be explained below.

[0765] Step 1:

[0766] The server collects past sales data, event history, and company characteristic data using APIs and database queries, including transaction history, company disclosure information, and sales activity logs.

[0767] Step 2:

[0768] The server preprocesses the collected data, specifically cleaning the data, filling in missing data, removing outliers, and converting it into an analyzable format.

[0769] Step 3:

[0770] The server uses the preprocessed data to train machine learning algorithms, using techniques such as regression analysis and random forests to build models of deal success.

[0771] Step 4:

[0772] The user uses the terminal to input basic information about a new business deal, such as "nationwide expansion of a new product" or "target market."

[0773] Step 5:

[0774] The terminal sends the entered business negotiation information to the server, which then structures the input information in an appropriate format and passes it to the server.

[0775] Step 6:

[0776] Based on the business negotiation information received by the server, the server predicts the most suitable partner companies using the business negotiation success model it has built, and calculates the predicted list of candidate companies and the success probability.

[0777] Step 7:

[0778] The server sends the terminal a list of predicted partner companies, including the success probability of each partner company and related success stories.

[0779] Step 8:

[0780] The server automatically generates business documents based on the selected partner companies, including company introductions, success stories, and proposal details.

[0781] Step 9:

[0782] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections.

[0783] Step 10:

[0784] The user periodically inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0785] Step 11:

[0786] The terminal sends the entered negotiation result data to the server, which stores it in a database.

[0787] Step 12:

[0788] The server uses the sales negotiation result data to retrain and optimize the partner company success model, thereby improving the model's prediction accuracy.

[0789] Example 1

[0790] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0791] With conventional sales systems, collecting and analyzing data to improve the success rate of sales negotiations, selecting partner companies, and preparing sales negotiation materials required a lot of time and effort. As a result, sales representatives had to spend a lot of time collecting information necessary for sales negotiations and preparing materials, which meant they were unable to concentrate on the sales negotiations themselves. Furthermore, continuous optimization of the model based on sales negotiation results was not performed, making it difficult to improve prediction accuracy.

[0792] 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.

[0793] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the probability of success of the negotiation using a machine learning algorithm, means for having a user input basic information about a new negotiation and predicting the most suitable cooperating company based on the information, means for generating a candidate list of the predicted cooperating companies and sending it to a terminal, means for automatically generating negotiation materials based on the predicted cooperating companies, means for having a user input the progress and results of the negotiation and storing the result data on the server, and means for continuously optimizing the model using negotiation result data. This allows sales representatives to create high-quality negotiation materials in a short amount of time, allowing them to concentrate on the negotiation and continuously improving the accuracy of the predictive model.

[0794] "Business negotiation data" refers to data relating to the content and results of commercial transactions recorded in sales activities.

[0795] "Event history" is historical information about events and activities related to past business negotiations.

[0796] "Company characteristic data" is information on the characteristics of a company, such as its industry, size, performance, and geographic location.

[0797] A "means of collection" is a method or device for obtaining the required data using a database query or API.

[0798] "Preprocessing" is the process of preparing data for analysis and model building through processes such as data cleaning, filling in missing data, and removing outliers.

[0799] A "machine learning algorithm" is a set of mathematical and statistical methods for training predictive models based on data.

[0800] "Probability of success" is a numerical representation of the likelihood that a particular business deal will be successful.

[0801] The "optimal partner" is a partner company selected to increase the probability of success in business negotiations.

[0802] "Business negotiation materials" are documents that include the purpose of the business negotiation, introductions to collaborating companies, past success stories, proposal details, etc.

[0803] "Progress" is information that indicates the stage at which the negotiation is taking place and how it is progressing.

[0804] "Result data" is data indicating whether or not a deal was concluded, or other final results.

[0805] A "continuous optimization means" is a method or apparatus for periodically updating a predictive model using sales outcome data to improve its accuracy.

[0806] A "user interface" is software that provides the input and display screens for a user to interact with a system.

[0807] MODE FOR CARRYING OUT THE INVENTION

[0808] The system of the present invention is designed to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. This system is mainly composed of a server, terminals, and users. The role of each will be explained in detail below.

[0809] Server Features

[0810] The server first collects past negotiation data, event history, and company characteristics data. This collection is done using APIs and database queries. The specific hardware and software used are a database management system (DBMS) and an HTTP client library. The data collected at this stage includes detailed logs and information, which are necessary for subsequent processing.

[0811] The server then preprocesses the collected data. Specifically, it uses Python's Pandas library to clean the data, impute missing data, and remove outliers. The preprocessed data is then formatted and used to train a model using machine learning algorithms. For this training, it applies Sci-Kit Learn's random forest and regression analysis algorithms.

[0812] Once the model training is complete, the server receives basic information about new business deals sent by the user and uses this information to predict the most suitable partner companies. In this process, the trained machine learning model is applied to generate prediction results. The predicted partner companies are generated as a candidate list and returned to the terminal along with the success rate and past success stories.

[0813] The server also has the function of automatically generating business negotiation materials. These materials include introductions to partner companies, past success stories, and proposals tailored to the purpose of the business negotiations, and are created using template generation software. These generated materials are also sent to the terminal and made available for the user to review and edit.

[0814] Device Features

[0815] Users interface with the system via a terminal. First, when starting a new business negotiation, they use the terminal's input interface to enter basic information such as "nationwide expansion of new products" and "target market." This information is then sent from the terminal to the server.

[0816] The terminal displays the forecast results and business negotiation materials of partner companies generated by the server. The user can proceed with business negotiations based on this information. Specifically, by making a presentation using the materials displayed on the terminal, the probability of success in business negotiations can be increased.

[0817] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal, and this information is sent to the server and stored in a database.

[0818] User Roles

[0819] The users are primarily salespeople who use this system to conduct sales negotiations. They input basic information about new sales negotiations through their terminals and act based on the information provided by the system at each step of the negotiation.

[0820] Specific examples

[0821] Consider the case of planning a nationwide rollout of a new product. The user inputs information about "nationwide rollout of new product" and "target market" into the terminal. The server proposes "Company A, Company B, and Company C" as the most suitable collaborating companies based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. The user can use high-quality business negotiation materials to make an effective presentation and increase the chances of success in the business negotiation.

[0822] Prompt Sentence Examples

[0823] "We have started a business negotiation regarding the nationwide rollout of a new product. Please generate a list of partner companies and automatically create business negotiation materials. Basic information for the business negotiation: new product features, target market."

[0824] The above is a specific embodiment for carrying out the present invention. This system allows salespeople to significantly reduce the time and effort required to create sales materials and select partner companies, allowing them to focus on the content of the sales negotiations. This improves the efficiency of sales activities and the success rate.

[0825] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0826] Program processing flow

[0827] Step 1:

[0828] Data collection

[0829] The server uses APIs and database queries to collect past deal data, event history, and company characteristics data.

[0830] Input: API endpoints for databases and external systems

[0831] Output: The collected raw dataset

[0832] What happens: The server connects to the database and sends SQL queries to retrieve opportunity data. It also makes HTTP requests to external APIs to retrieve additional company information, thereby gathering additional information not stored in the database.

[0833] Step 2:

[0834] Data Preprocessing

[0835] The server uses Python's Pandas library to clean the collected data, completing missing data and removing outliers.

[0836] Input: Collected raw dataset

[0837] Output: Preprocessed clean dataset

[0838] Specific operations: Impute missing values ​​in the data with the mean or median, filter outliers based on conditions, and standardize the data into a consistent format.

[0839] Step 3:

[0840] Training a machine learning model

[0841] The server uses Sci-kit Learn to train machine learning models such as random forests and regression analysis using preprocessed datasets.

[0842] Input: Preprocessed clean dataset

[0843] Output: A trained machine learning model

[0844] How it works: The server splits the clean dataset into training and testing data, and then applies random forest and regression analysis algorithms to train the model. During this process, it adjusts the model's hyperparameters to maximize predictive performance.

[0845] Step 4:

[0846] Entering new business information

[0847] The user inputs basic information about the new business negotiation (e.g., nationwide expansion of a new product, target market) via the user interface of the terminal.

[0848] Input: Basic information about the opportunity

[0849] Output: Negotiation information sent from the device to the server

[0850] Specific operation: The user enters basic information about the business deal into the input field on the terminal and clicks the "Send" button, which sends the entered information to the server.

[0851] Step 5:

[0852] Prediction of optimal partner companies

[0853] The server preprocesses the received business negotiation information and then uses the trained machine learning model to predict the most suitable partner companies.

[0854] Input: Entered business information

[0855] Output: Predicted list of collaborating companies

[0856] How it works: The server preprocesses the sales negotiation information and inputs it into a trained machine learning model. The model predicts which partners have a high probability of success and generates a list of the results.

[0857] Step 6:

[0858] Generate a list of potential partner companies

[0859] The server generates a list of candidate collaborating companies based on the prediction results and sends it to the terminal.

[0860] Input: Predicted list of collaborating companies

[0861] Output: Candidate list sent to terminal

[0862] Specific operation: A list including the probability of success and past success cases for each predicted partner company is generated and sent to the terminal.

[0863] Step 7:

[0864] Automatic generation of sales documents

[0865] The server automatically generates business negotiation materials based on the predicted partner company information and sends them to the terminal.

[0866] Input: Predicted partner company information

[0867] Output: Automatically generated business documents (PDF, etc.)

[0868] Specific operation: Generate sales documents using templates that include introductions to partner companies, past success stories, and proposal details, and send them to the terminal in PDF format or other formats.

[0869] Step 8:

[0870] Entering the progress and results of sales negotiations

[0871] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal.

[0872] Input: Opportunity status and results

[0873] Output: Entered negotiation result data (sent to server)

[0874] Specific operation: The user enters the progress and results into the progress input screen on the device, clicks the "Save" button and sends the data to the server.

[0875] Step 9:

[0876] Continuously training the model

[0877] The server uses the input sales outcome data to continuously train and optimize the machine learning model.

[0878] Input: Updated Opportunity Outcome Data

[0879] Output: An optimized machine learning model

[0880] Specific operation: Retrain using saved sales outcome data to improve the model's predictive accuracy.

[0881] The above is the specific processing flow of this system.

[0882] (Application example 1)

[0883] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0884] Traditional sales negotiations require a lot of time and effort to collect data, select partners with a high probability of success, and create sales negotiation materials. Furthermore, efficient operation of robots and optimization of production plans within factories have been issues. An integrated system is needed to streamline these processes and improve sales negotiation and production efficiency.

[0885] 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.

[0886] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for new negotiations and predicting the most suitable partner company based on the information, means for automatically generating negotiation materials based on the predicted partner company, means for following up on the results of negotiations and continuously optimizing the model, means for collecting past production data and maintenance records and analyzing the operating status and production success rate of each work robot, means for proposing an optimal production schedule and robot placement, and means for automatically generating operation instructions and maintenance procedures, thereby enabling efficient negotiation activities and production line operations.

[0887] "Past business negotiation data" refers to all detailed information relating to business negotiations that have taken place in the past, including the performance and results of specific business negotiations.

[0888] "Event history" refers to information that records a series of events in a business meeting or other related activity, and includes, for example, meeting dates and attendee lists.

[0889] "Corporate characteristic data" refers to information about the characteristics and attributes of a specific company, including, for example, the size and performance of the company, its position within the industry, and so on.

[0890] A "machine learning algorithm" is a computational method that extracts patterns and rules based on past data and makes predictions and classifications for new data.

[0891] "Success probability" refers to the probability that a particular business negotiation will be successful, and is a value calculated based on analysis of past data.

[0892] The "best-fit collaborating company" refers to the company that is predicted to be able to provide the most advantageous and effective cooperation in a particular business negotiation.

[0893] "Business negotiation materials" refers to documents and presentation materials necessary to support the progress of business negotiations, including proposals and explanatory materials.

[0894] "Production data" refers to all data related to the production process at a factory or manufacturing site, including, for example, production volume, operating hours, and quality data.

[0895] "Maintenance records" refer to a series of records relating to the maintenance, inspection, and repair of equipment and machinery, and include, for example, the date and time of maintenance and the specific work carried out.

[0896] "Operating status" refers to the status of a robot or machine that indicates whether it is operating normally, and is data that includes operating time, error status, etc.

[0897] The "production success probability" is the probability that a specific production schedule or task will be successful, and is also a value calculated based on an analysis of past data.

[0898] An "operation instruction manual" refers to a document that lists specific instructions and procedures for production work, including the order of work and the materials to be used.

[0899] A "maintenance procedure manual" refers to a document that describes the procedures and methods for performing maintenance, inspection, and repairs on equipment and machinery, and includes specific work procedures.

[0900] The system of the present invention is designed to improve the efficiency of business negotiation activities and the success rate of business negotiations. This system is composed of entities such as a server, terminals, and users.

[0901] The server collects past deal data, event history, and company characteristic data. The collected data is retrieved using APIs or database queries and stored in a database. The server then preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past successful and unsuccessful deals are used as training data to build a model that predicts the probability of deal success. This model is created using algorithms such as regression analysis and random forests.

[0902] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, this information includes "nationwide expansion of a new product" and "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0903] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include introductions to partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and modify.

[0904] As the negotiation progresses, the user inputs the progress into the terminal. This negotiation result data is sent back to the server and stored in the database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0905] Furthermore, it also improves the efficiency of production lines within factories. The server collects past production data and maintenance records, and analyzes the operating status and production success rate of each work robot. It proposes optimal production schedules and robot placement, and automatically generates operation instructions and maintenance procedures. This enables efficient operation of robots within factories.

[0906] As a concrete example, the following prompt statements can be used to optimize the design of a new production line:

[0907] "In order to optimize the design of a new production line, please propose the optimal robot placement and maintenance schedule using past production data. The past data includes the operating status and maintenance records of each robot. Please predict the optimal operating time and maintenance timing for each robot on the new production line, and generate the optimal production schedule based on the results."

[0908] The hardware used includes a robot control unit and a server for data analysis, and the software uses Python, Scikit-learn, Pandas, etc. This will improve the efficiency of sales activities and production activities within the factory.

[0909] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0910] Step 1:

[0911] The server collects past deal data, event history, and company characteristic data using APIs or database queries. The input is raw deal data, event data, and company data obtained from the database, and the output is a collection of these raw data. Specific operations include executing database queries and reading the results.

[0912] Step 2:

[0913] The server preprocesses the collected raw data. The input is raw data, and the output is cleaned data. Specific data processing includes data cleaning, imputing missing data, and removing outliers. Pandas is used for this processing.

[0914] Step 3:

[0915] The server trains a machine learning model using the preprocessed data. The input is the cleaned sales opportunity data, event data, and company data, and the output is a trained model for predicting the probability of success. Specifically, the model is built using algorithms such as random forests and Scikit-learn.

[0916] Step 4:

[0917] The user inputs basic information for a new business negotiation via a terminal. The input is basic information for the business negotiation, such as "nationwide expansion of a new product" or "target market," and the output is the business negotiation information entered by the user. Specific operations include data input via a user interface.

[0918] Step 5:

[0919] The terminal sends the entered business negotiation information to the server. The input is the business negotiation information entered by the user, and the output is the transfer of this information to the server. A specific operation is the sending of an HTTP request.

[0920] Step 6:

[0921] The server uses a trained machine learning model to predict the optimal partner based on the received business negotiation information. The input is the business negotiation information sent to the server, and the output is a list of candidate partner companies and their success rate. Specific data operations include applying the model and calculating the predicted value.

[0922] Step 7:

[0923] The server automatically generates sales negotiation materials based on the predicted partner companies. The input is a list of candidate partner companies and the success probability, and the output is the sales negotiation materials. In operation, the sales negotiation materials are created using a text generation model, etc.

[0924] Step 8:

[0925] The terminal presents the generated sales negotiation materials to the user, allowing the user to review and modify them. The input is the sales negotiation materials, and the output is the sales negotiation materials reviewed and modified by the user. Operation includes providing display and editing functions via a user interface.

[0926] Step 9:

[0927] As the negotiation progresses, the user inputs the progress status into the terminal. The input is negotiation progress information, and the output is the progress data entered by the user. The operation includes recording the progress information and inputting it into the terminal.

[0928] Step 10:

[0929] The terminal sends the entered progress data to the server. The input is the negotiation progress data, and the output is the transfer of this data to the server. The operation is the sending of an HTTP request.

[0930] Step 11:

[0931] The server stores the received progress data in a database and continuously trains and optimizes the machine learning model. The input is the sales negotiation result data, and the output is the optimized machine learning model. Specific operations include data accumulation, model retraining, and evaluation.

[0932] 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.

[0933] The system of the present invention aims to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. Furthermore, by combining it with an emotion engine that recognizes the user's emotions and utilizes them in sales negotiations, it aims to improve the quality of sales negotiations. The system is composed of entities: a server, a terminal, and a user, and each entity operates as follows.

[0934] First, the server collects past business negotiation data, event history, and company characteristic data. The collected data is retrieved via API or database query, and the contents and results of business negotiations, event details, and company characteristic information are stored in the database.

[0935] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Using past examples of successful and unsuccessful deals as training data, a model is built to predict the probability of a deal being successful. This model is created using algorithms such as regression analysis and random forests.

[0936] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[0937] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[0938] In addition, the system of the present invention includes an emotion engine that recognizes the user's emotions. The emotion engine has the function of extracting and analyzing emotional data from voice, facial expressions, input speed, etc. while the user is operating the terminal. For example, if the user is feeling stressed, the system can detect this and present advice to help the user relax or simpler operating procedures.

[0939] As a concrete example, when planning the nationwide rollout of a new product, the user inputs basic business negotiation information into the device, and the server suggests three optimal partner companies: Company A, Company B, and Company C. Furthermore, the device's emotion engine analyzes the user's emotions, and if tension is detected, the server provides simple operating procedures to relax the user. The server then automatically generates business negotiation materials, allowing the user to proceed with the negotiation based on high-quality materials.

[0940] As the negotiation progresses, the user periodically enters the progress and results into the device. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[0941] The system of this invention not only enables salespeople to significantly reduce the time and effort required to create sales documents and select partner companies, but also improves the quality of sales negotiations by using an emotion engine, resulting in more efficient sales activities and improved results.

[0942] The above is a specific embodiment for carrying out the present invention.

[0943] The processing flow will be explained below.

[0944] Step 1:

[0945] The server collects past sales data, event history, and company characteristics data using APIs and database queries. This data includes transaction history, sales activity logs, and public company information.

[0946] Step 2:

[0947] The server preprocesses the collected data. Specifically, it cleans the data, removes noise, fills in missing data, and removes outliers. It also standardizes and normalizes the data format to convert it into an analyzable format.

[0948] Step 3:

[0949] The server uses the preprocessed data to train a machine learning algorithm. It uses algorithms such as regression analysis and random forests to build a model that predicts the probability of a deal being successful. This model uses examples of successful and unsuccessful deals as training data.

[0950] Step 4:

[0951] The user uses the terminal to input basic information about a new business. For example, the user enters details of the business, such as "nationwide expansion of a new product" or "target market," into an input form.

[0952] Step 5:

[0953] The terminal sends the business negotiation information entered by the user to the server, which automatically converts the input information into the required format and passes it on to the server.

[0954] Step 6:

[0955] Based on the business negotiation information received by the server, the machine learning model it has built is used to predict the most suitable partner company. The model calculates the probability of success of the business negotiation and generates a list of candidate partner companies.

[0956] Step 7:

[0957] The server sends a list of predicted partner companies to the device, which displays the success rate of each partner company and related success stories.

[0958] Step 8:

[0959] The server automatically generates business documents based on the selected partner companies. The documents include company introductions, success stories, proposals, etc. The documents are automatically created according to a format.

[0960] Step 9:

[0961] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections. The materials are also updated in accordance with the progress of the sales negotiation.

[0962] Step 10:

[0963] The server uses an emotion engine to recognize the user's emotions, and extracts the user's emotional data by analyzing facial expressions and voice using data from the device's camera and microphone.

[0964] Step 11:

[0965] The server provides advice tailored to the progress of the business negotiation based on the user's emotional data analyzed by the emotion engine. If the user is feeling stressed, it will suggest appropriate relief measures, such as suggestions for relaxing.

[0966] Step 12:

[0967] The user inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[0968] Step 13:

[0969] The terminal sends the entered negotiation result data to the server, which stores it in a database and manages the negotiation results.

[0970] Step 14:

[0971] The server uses the sales negotiation result data to retrain and optimize the partner company success model. The collected new sales negotiation result data is reflected in the model to improve prediction accuracy.

[0972] Through the above steps, the system of the present invention improves the efficiency of sales negotiation activities by sales representatives, increases the success rate of negotiations, and improves the quality of negotiations by utilizing user emotion data, thereby realizing more efficient sales activities and improved results.

[0973] Example 2

[0974] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0975] While conventional sales negotiation support systems can perform basic procedures such as preprocessing sales negotiation data and selecting partner companies, they lack comprehensive functionality to improve the quality of sales negotiations. Furthermore, because they lack advice or operational support that takes users' emotions into consideration, users often feel stressed or find it difficult to operate the system. Therefore, there is a need to improve the efficiency of overall sales negotiation activities and the success rate of sales negotiations.

[0976] 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.

[0977] In this invention, the server includes means for collecting past business negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for a new business negotiation and predicting the most suitable partner company based on the information, means for automatically generating business negotiation materials based on the predicted partner company, means for following up on the results of the business negotiation and continuously optimizing the model, emotion recognition means for extracting and analyzing emotion data from voice, facial expression, input speed, etc., and means for presenting relaxation advice and simple operating procedures to the user using the emotion data. This makes it possible to improve the quality of the entire business negotiation and provide an environment in which the user can proceed with the business negotiation without stress.

[0978] "Business negotiation data" is data containing information about business negotiations that have taken place in the past, including the dates of the business negotiations, participating companies, business negotiation content, and results.

[0979] "Event history" is a record of past events and activities, including not only business meetings but also exhibitions, seminars, networking events, etc.

[0980] "Company characteristic data" refers to data that indicates basic information and characteristics of a company, including the company's size, industry, capital, location, etc.

[0981] "Preprocessing" refers to a series of operations to convert collected data into a format that is easier to analyze, such as cleaning the data, filling in missing data, and removing outliers.

[0982] A "machine learning algorithm" is an algorithm that uses large amounts of data to learn patterns and perform predictions, classification, and optimization. Examples include regression models and random forests.

[0983] A "model for predicting success probability" is a mathematical model for predicting the success probability of a sales negotiation based on past sales negotiation data. It is constructed using a machine learning algorithm.

[0984] "Cooperating companies" are companies selected to cooperate and collaborate in business negotiations and projects.

[0985] "Business materials" are documents, slides, and a set of materials prepared to support the progress of business negotiations, including proposal details, past success stories, company introductions, etc.

[0986] "Emotion recognition means" is a technology for detecting and analyzing a user's emotional state. It infers the user's emotions from voice, facial expressions, input speed, etc.

[0987] "Relaxation advice" is a suggestion or instruction to encourage the user to relax when they are feeling stressed.

[0988] A "user interface" is a screen or input device that allows a user to interact with a system. This includes terminal screens and input forms.

[0989] "API" stands for Application Program Interface, an interface for exchanging data and functions between software programs.

[0990] A "database query" is a set of instructions used to retrieve, insert, update, or delete data from a database.

[0991] The system of the present invention is configured so that a server, a terminal, and a user work together to improve the efficiency of business negotiation activities and increase the success rate of business negotiations. In particular, a specific embodiment of a business negotiation support system including an emotion recognition function will be described.

[0992] First, the server collects past sales negotiation data, event history, and company characteristics data. This is done using APIs and database queries. Specifically, it uses Amazon Athena to execute database queries and saves the data in an Amazon S3 bucket. This data includes sales negotiation dates, participating companies, sales negotiation content, and results.

[0993] The server then preprocesses the collected data using data manipulation libraries such as Pandas and NumPy to clean the data, impute missing data, remove outliers, and convert it into an analyzable format, such as by imputing NULL values ​​and removing outliers.

[0994] Based on the preprocessed data, the server uses machine learning algorithms to build a model that predicts the probability of a deal being successful. For this, it uses Scikit-learn to train a random forest model or a regression analysis model. The trained model is saved in Pickle format and later used for prediction.

[0995] When a user starts a new business negotiation, they input basic information about the negotiation via their terminal. The user uses the terminal's input form to enter information such as "nationwide expansion of new products" and "target market" and presses the send button. The terminal then sends this information to the server.

[0996] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format. The terminal displays the results on the screen so that the user can confirm and modify them.

[0997] Furthermore, the server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. LaTeX templates are used to generate the documents, and they are output in PDF format. The generated documents are sent to the terminal and made available for the user to review and edit.

[0998] The system of the present invention includes an emotion recognition means for recognizing the user's emotions. The device uses a camera and microphone to collect the user's facial expressions, voice, input speed, etc., and transmits them to a server. The server then analyzes the user's emotion data using an emotion recognition API (e.g., Microsoft Azure's emotion recognition API). If the user is feeling stressed, the server presents relaxation advice and simple operating instructions.

[0999] As the negotiation progresses, the user periodically enters the progress and results of the negotiation into the device. This data is then sent back to the server and stored in a database. The server then uses the new data to retrain the machine learning model, optimizing it and improving its prediction accuracy.

[1000] Example prompt sentence:

[1001] 1. Please suggest the best partner company for the nationwide rollout of our new product.

[1002] 2. Please predict the probability of success for a business negotiation that sets "men in their 20s" as the target market.

[1003] 3. Provide relaxation advice if the user is feeling tense.

[1004] In this way, the system of the present invention comprehensively supports business negotiation activities and aims to improve efficiency in order to increase the success rate of business negotiations. In addition, by using emotion recognition means, it reduces the mental burden on the user and provides a more comfortable and effective business negotiation environment.

[1005] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1006] Step 1: Data collection

[1007] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs and database queries. Specifically, the server uses Amazon Athena to execute database queries to retrieve deal data. The retrieved data is stored in Amazon S3.

[1008] Input: API request, database query

[1009] Output: Opportunity data, event history, and company characteristics data stored in Amazon S3

[1010] What happens: The server sends an API request and runs a query in Amazon Athena to collect data.

[1011] Step 2: Data Preprocessing

[1012] The server preprocesses the collected data by cleaning it, filling in missing data, and removing outliers. The server uses Pandas and NumPy to perform these operations and convert it into an analyzable format.

[1013] Input: Raw data retrieved from S3

[1014] Output: Preprocessed data (NumPy array format)

[1015] Specific operation: The server uses Pandas to interpolate NULL values ​​and remove outliers. The preprocessed data is converted into a NumPy array.

[1016] Step 3: Model Building

[1017] The server uses the preprocessed data to train a machine learning algorithm. Specifically, it uses Scikit-learn to train a random forest model. The trained model is saved in Pickle format.

[1018] Input: Preprocessed data

[1019] Output: Trained machine learning model (in Pickle format)

[1020] What it does: The server uses Scikit-learn to train and save the model.

[1021] Step 4: Enter business information

[1022] When starting a new business negotiation, the user inputs basic information about the business via the terminal. The user enters information such as "nationwide expansion of new products" and "target market" into the input form on the terminal and presses the send button.

[1023] Input: Basic information about the deal (nationwide launch of new products, target market, etc.)

[1024] Output: The basic information of the opportunity sent to the server

[1025] Specific behavior: A user enters information into a form on a device and presses the submit button.

[1026] Step 5: Opportunity forecasting and results presentation

[1027] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format.

[1028] Input: Opportunity information submitted by the user

[1029] Output: Prediction results (list of collaborating companies, success probability)

[1030] Specific operation: The server inputs sales information into the model, generates prediction results, and sends them back to the device.

[1031] Step 6: Generate sales documents

[1032] The server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. The generated documents are sent to the terminal in PDF format.

[1033] Input: Predicted partner information

[1034] Output: Negotiation materials (PDF format)

[1035] Specific operation: The server generates business documents using a LaTeX template and sends them to the terminal.

[1036] Step 7: Emotion Recognition

[1037] The server extracts and analyzes emotional data from voice, facial expressions, input speed, etc. when the user operates the device. The server analyzes the user's emotions using an emotion recognition API.

[1038] Input: Data sent from your device, such as voice, facial expressions, and typing speed

[1039] Output: Analysis results of emotion data

[1040] Specific operation: The server uses the emotion recognition API to analyze the emotion data and determine the user's emotional state.

[1041] Step 8: Offer relaxation advice

[1042] The server provides relaxation advice and simple operation procedures based on the results of emotion recognition. If the user is feeling stressed, corresponding advice will be displayed on the screen.

[1043] Input: Emotion data analysis results

[1044] Output: Relaxation advice and simple operating instructions

[1045] Specific operation: The server generates advice based on the results of emotion analysis and sends it to the device.

[1046] Step 9: Enter opportunity progress and retrain the model

[1047] Users periodically enter the progress and results of sales negotiations into their devices. This data is sent to the server and stored in a database. The server then retrains the machine learning model using the new data, optimizing the model and improving its prediction accuracy.

[1048] Input: Negotiation status and results

[1049] Output: An updated machine learning model

[1050] Specific operation: The user inputs the progress data of the sales negotiations on the device and sends it to the server, which then retrains the model based on this data.

[1051] (Application example 2)

[1052] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1053] Current sales negotiation systems and sales activities are unable to properly grasp customer emotions and reactions, making it difficult to optimize the progress of sales negotiations. In particular, in brick-and-mortar stores, sales staff are required to discern customer emotions and respond appropriately, but this is difficult in practice, affecting sales negotiations and sales results. Efficiently generating appropriate sales negotiation materials and making proposals to customers is also a major challenge.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting past negotiation data, event history, and company characteristic data; means for preprocessing the collected data and constructing a model for predicting the success probability using a machine learning algorithm; means for having a user input basic information about a new negotiation and predicting the optimal partner company based on the information; means for automatically generating negotiation materials based on the predicted partner company; means for following up on the results of the negotiation and continuously optimizing the model; means for acquiring the customer's facial expressions and voice from a terminal device in real time and analyzing their emotions; means for providing advice on the progress of the negotiation based on the analyzed emotion data; and means for sending the automatically generated negotiation materials to the customer as electronic data. This makes it possible to appropriately understand the customer's emotions and reactions, optimize the progress of the negotiation, and improve sales results.

[1055] "Sales negotiation data" refers to the content and results of sales negotiations, customer information, and all data related to sales negotiations.

[1056] "Event history" refers to records of past business negotiations and related events.

[1057] "Company characteristic data" refers to characteristic information such as a company's industry, size, business model, etc.

[1058] A "machine learning algorithm" refers to a computational method for analyzing data and performing pattern recognition and prediction.

[1059] "Cooperating companies" refer to companies with which we have cooperative relationships in business negotiations and projects.

[1060] "Business negotiation materials" refers to documents and data that summarize the information and proposals necessary to advance business negotiations.

[1061] "Follow-up" refers to the activity of tracking and checking the progress and results of a business negotiation and taking action as necessary.

[1062] "Terminal device" refers to an electronic device operated by a user, such as smart glasses or a smartphone.

[1063] "Emotion analysis" refers to the process of determining a person's emotional state based on facial expressions and voice data.

[1064] "Providing advice" means that the system presents the user with next actions or suggestions.

[1065] "Electronic data" refers to information or documents stored in digital form.

[1066]

[1067] This invention is a system that aims to support sales in brick-and-mortar stores, improving the efficiency of sales negotiations when sales staff use smart glasses to deal with customers, thereby increasing the success rate.

[1068] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs or database queries. The collected data is stored in a database.

[1069] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Past examples of successful and unsuccessful deals are used as training data to build a model that predicts the probability of a deal being successful. Algorithms such as regression analysis and random forests are used.

[1070] The user (sales staff) wears the smart glasses and inputs basic information about the business negotiation when a customer visits the store. For example, they input information about the products the customer is interested in and their past purchase history. This input information is sent from the smart glasses to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The prediction results are generated as a list of candidate partner companies and are displayed on the smart glasses along with the predicted success rate and past success stories.

[1071] The terminal device (smart glasses) equipped with an emotion engine captures the customer's facial expressions and voice in real time and analyzes their emotions. For example, the smart glasses' camera and microphone can analyze the customer's facial expressions and tone of voice to determine their emotional state. The system detects this and provides the sales staff with advice on how to relax or appropriate operating procedures for the progress of the sales negotiation.

[1072] For example, when a salesperson is negotiating with a customer who is interested in a new product, the system can calculate the customer's level of interest from facial expression analysis and instruct them to provide a detailed product explanation.If the customer expresses concern about the price, the system can advise them to present a special discount offer.

[1073] Furthermore, the server automatically generates sales documents based on the predicted partner companies. The sales documents include information about the partner companies, past success stories, and proposals that match the purpose of the sales negotiation. The generated sales documents are sent to the smart glasses and made available for review and modification by the sales staff.

[1074] As the negotiation progresses, the user periodically enters progress and results. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[1075] Examples of prompts for generative AI models include:

[1076] "A customer is interested in a new product. Please create a document detailing the product and offering a price discount."

[1077] Such a system provides sales staff with highly accurate information on how to create sales materials and conduct sales negotiations appropriately, thereby significantly improving the optimization of sales negotiations and the success rate of sales negotiations.

[1078] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1079] Step 1:

[1080] The server collects past deal data, event history, and company characteristic data. This data is retrieved using APIs or database queries and stored in a database. The input is deal data, event history, and company characteristic data, and the output is stored in the database as collected data.

[1081] Step 2:

[1082] The server preprocesses the collected data by cleaning it, filling in missing data, removing outliers, and converting it into an analyzable format. The input is the collected raw data, and the output is preprocessed, analyzable data. This prepares the data in a format suitable for analysis.

[1083] Step 3:

[1084] The server uses the preprocessed data to train a machine learning algorithm. Using examples of past successful and unsuccessful deals as training data, it builds a model that predicts the probability of a deal's success. This model is created using algorithms such as regression analysis and random forests. The input is the preprocessed, analyzable data, and the output is a predictive model.

[1085] Step 4:

[1086] The user inputs basic information about the business negotiation using the smart glasses. The input information is sent from the smart glasses to the server. The input is the basic information about the business negotiation, and the output is the basic information about the business negotiation sent to the server.

[1087] Step 5:

[1088] The server receives basic information about the business negotiation and predicts the most suitable partner companies based on a machine learning model. The prediction results are generated as a list of candidate partner companies and displayed on the smart glasses along with the probability of success of the business negotiation and past success stories. The input is the basic information about the business negotiation, and the output is a list of candidate partner companies.

[1089] Step 6:

[1090] The terminal device (smart glasses) captures the customer's facial expressions and voice in real time and analyzes their emotions. Based on the analysis results, it provides advice to the sales staff. The input is the customer's facial expressions and voice data, and the output is the emotion analysis results and advice. This makes it possible to determine the customer's emotional state in real time.

[1091] Step 7:

[1092] The server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiations, and are provided to the smart glasses. The input is a list of potential partner companies, and the output is the automatically generated business negotiation materials.

[1093] Step 8:

[1094] Users periodically input the progress and results of sales negotiations and send this to the server. The sales negotiation result data is stored in the server's database. The input is the sales negotiation progress and result data, and the output is the sales negotiation result data stored on the server. This allows the system to continuously retrain and optimize the model.

[1095] Step 9:

[1096] The server uses the sales outcome data to retrain and optimize the predictive model, improving the model's predictive accuracy and further increasing the success rate of future sales. The input is the sales outcome data, and the output is the optimized predictive model.

[1097]

[1098] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1100] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1101] [Fourth embodiment]

[1102] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1103] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1104] 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).

[1105] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1106] 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.

[1107] 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).

[1108] 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.

[1109] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1110] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1111] 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.

[1112] 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.

[1113] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1114] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1115] The system of the present invention is a system for improving the efficiency of sales negotiation activities by sales representatives and increasing the success rate of sales negotiations. The system is composed of entities, namely, a server, terminals, and users, and each entity operates as follows.

[1116] First, the server collects past sales negotiation data, event history, and company characteristic data. The collected data is retrieved via APIs and database queries. The details of sales negotiations, results, event details, and company characteristic information are then stored in a database.

[1117] Next, the server preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past examples of successful and unsuccessful sales negotiations are used as training data to build a model that predicts the probability of success for a sales negotiation. This model is created using algorithms such as regression analysis and random forests.

[1118] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[1119] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[1120] As the negotiation progresses, the user inputs the progress and results into the device. This negotiation result data is then sent back to the server and stored in a database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[1121] As a concrete example, consider the case of planning the nationwide rollout of a new product. When the user inputs basic business negotiation information into the terminal, the server proposes three companies as the most suitable partners based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. As a result, the user can make an effective presentation using high-quality business negotiation materials, increasing the chances of success in the business negotiation.

[1122] This system allows sales representatives to significantly reduce the time and effort required to create sales documents and select partner companies, allowing them to focus on the content of the sales negotiations, resulting in more efficient sales activities and improved results.

[1123] The above is a specific embodiment for carrying out the present invention.

[1124] The processing flow will be explained below.

[1125] Step 1:

[1126] The server collects past sales data, event history, and company characteristic data using APIs and database queries, including transaction history, company disclosure information, and sales activity logs.

[1127] Step 2:

[1128] The server preprocesses the collected data, specifically cleaning the data, filling in missing data, removing outliers, and converting it into an analyzable format.

[1129] Step 3:

[1130] The server uses the preprocessed data to train machine learning algorithms, using techniques such as regression analysis and random forests to build models of deal success.

[1131] Step 4:

[1132] The user uses the terminal to input basic information about a new business deal, such as "nationwide expansion of a new product" or "target market."

[1133] Step 5:

[1134] The terminal sends the entered business negotiation information to the server, which then structures the input information in an appropriate format and passes it to the server.

[1135] Step 6:

[1136] Based on the business negotiation information received by the server, the server predicts the most suitable partner companies using the business negotiation success model it has built, and calculates the predicted list of candidate companies and the success probability.

[1137] Step 7:

[1138] The server sends the terminal a list of predicted partner companies, including the success probability of each partner company and related success stories.

[1139] Step 8:

[1140] The server automatically generates business documents based on the selected partner companies, including company introductions, success stories, and proposal details.

[1141] Step 9:

[1142] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections.

[1143] Step 10:

[1144] The user periodically inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[1145] Step 11:

[1146] The terminal sends the entered negotiation result data to the server, which stores it in a database.

[1147] Step 12:

[1148] The server uses the sales negotiation result data to retrain and optimize the partner company success model, thereby improving the model's prediction accuracy.

[1149] Example 1

[1150] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1151] With conventional sales systems, collecting and analyzing data to improve the success rate of sales negotiations, selecting partner companies, and preparing sales negotiation materials required a lot of time and effort. As a result, sales representatives had to spend a lot of time collecting information necessary for sales negotiations and preparing materials, which meant they were unable to concentrate on the sales negotiations themselves. Furthermore, continuous optimization of the model based on sales negotiation results was not performed, making it difficult to improve prediction accuracy.

[1152] 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.

[1153] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the probability of success of the negotiation using a machine learning algorithm, means for having a user input basic information about a new negotiation and predicting the most suitable cooperating company based on the information, means for generating a candidate list of the predicted cooperating companies and sending it to a terminal, means for automatically generating negotiation materials based on the predicted cooperating companies, means for having a user input the progress and results of the negotiation and storing the result data on the server, and means for continuously optimizing the model using negotiation result data. This allows sales representatives to create high-quality negotiation materials in a short amount of time, allowing them to concentrate on the negotiation and continuously improving the accuracy of the predictive model.

[1154] "Business negotiation data" refers to data relating to the content and results of commercial transactions recorded in sales activities.

[1155] "Event history" is historical information about events and activities related to past business negotiations.

[1156] "Company characteristic data" is information on the characteristics of a company, such as its industry, size, performance, and geographic location.

[1157] A "means of collection" is a method or device for obtaining the required data using a database query or API.

[1158] "Preprocessing" is the process of preparing data for analysis and model building through processes such as data cleaning, filling in missing data, and removing outliers.

[1159] A "machine learning algorithm" is a set of mathematical and statistical methods for training predictive models based on data.

[1160] "Probability of success" is a numerical representation of the likelihood that a particular business deal will be successful.

[1161] The "optimal partner" is a partner company selected to increase the probability of success in business negotiations.

[1162] "Business negotiation materials" are documents that include the purpose of the business negotiation, introductions to collaborating companies, past success stories, proposal details, etc.

[1163] "Progress" is information that indicates the stage at which the negotiation is taking place and how it is progressing.

[1164] "Result data" is data indicating whether or not a deal was concluded, or other final results.

[1165] A "continuous optimization means" is a method or apparatus for periodically updating a predictive model using sales outcome data to improve its accuracy.

[1166] A "user interface" is software that provides the input and display screens for a user to interact with a system.

[1167] MODE FOR CARRYING OUT THE INVENTION

[1168] The system of the present invention is designed to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. This system is mainly composed of a server, terminals, and users. The role of each will be explained in detail below.

[1169] Server Features

[1170] The server first collects past negotiation data, event history, and company characteristics data. This collection is done using APIs and database queries. The specific hardware and software used are a database management system (DBMS) and an HTTP client library. The data collected at this stage includes detailed logs and information, which are necessary for subsequent processing.

[1171] The server then preprocesses the collected data. Specifically, it uses Python's Pandas library to clean the data, impute missing data, and remove outliers. The preprocessed data is then formatted and used to train a model using machine learning algorithms. For this training, it applies Sci-Kit Learn's random forest and regression analysis algorithms.

[1172] Once the model training is complete, the server receives basic information about new business deals sent by the user and uses this information to predict the most suitable partner companies. In this process, the trained machine learning model is applied to generate prediction results. The predicted partner companies are generated as a candidate list and returned to the terminal along with the success rate and past success stories.

[1173] The server also has the function of automatically generating business negotiation materials. These materials include introductions to partner companies, past success stories, and proposals tailored to the purpose of the business negotiations, and are created using template generation software. These generated materials are also sent to the terminal and made available for the user to review and edit.

[1174] Device Features

[1175] Users interface with the system via a terminal. First, when starting a new business negotiation, they use the terminal's input interface to enter basic information such as "nationwide expansion of new products" and "target market." This information is then sent from the terminal to the server.

[1176] The terminal displays the forecast results and business negotiation materials of partner companies generated by the server. The user can proceed with business negotiations based on this information. Specifically, by making a presentation using the materials displayed on the terminal, the probability of success in business negotiations can be increased.

[1177] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal, and this information is sent to the server and stored in a database.

[1178] User Roles

[1179] The users are primarily salespeople who use this system to conduct sales negotiations. They input basic information about new sales negotiations through their terminals and act based on the information provided by the system at each step of the negotiation.

[1180] Specific examples

[1181] Consider the case of planning a nationwide rollout of a new product. The user inputs information about "nationwide rollout of new product" and "target market" into the terminal. The server proposes "Company A, Company B, and Company C" as the most suitable collaborating companies based on past business negotiation data, event history, and company characteristic data. The server then automatically generates business negotiation materials based on these companies and sends them to the terminal. The user can use high-quality business negotiation materials to make an effective presentation and increase the chances of success in the business negotiation.

[1182] Prompt Sentence Examples

[1183] "We have started a business negotiation regarding the nationwide rollout of a new product. Please generate a list of partner companies and automatically create business negotiation materials. Basic information for the business negotiation: new product features, target market."

[1184] The above is a specific embodiment for carrying out the present invention. This system allows salespeople to significantly reduce the time and effort required to create sales materials and select partner companies, allowing them to focus on the content of the sales negotiations. This improves the efficiency of sales activities and the success rate.

[1185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1186] Program processing flow

[1187] Step 1:

[1188] Data collection

[1189] The server uses APIs and database queries to collect past deal data, event history, and company characteristics data.

[1190] Input: API endpoints for databases and external systems

[1191] Output: The collected raw dataset

[1192] What happens: The server connects to the database and sends SQL queries to retrieve opportunity data. It also makes HTTP requests to external APIs to retrieve additional company information, thereby gathering additional information not stored in the database.

[1193] Step 2:

[1194] Data Preprocessing

[1195] The server uses Python's Pandas library to clean the collected data, completing missing data and removing outliers.

[1196] Input: Collected raw dataset

[1197] Output: Preprocessed clean dataset

[1198] Specific operations: Impute missing values ​​in the data with the mean or median, filter outliers based on conditions, and standardize the data into a consistent format.

[1199] Step 3:

[1200] Training a machine learning model

[1201] The server uses Sci-kit Learn to train machine learning models such as random forests and regression analysis using preprocessed datasets.

[1202] Input: Preprocessed clean dataset

[1203] Output: A trained machine learning model

[1204] How it works: The server splits the clean dataset into training and testing data, and then applies random forest and regression analysis algorithms to train the model. During this process, it adjusts the model's hyperparameters to maximize predictive performance.

[1205] Step 4:

[1206] Entering new business information

[1207] The user inputs basic information about the new business negotiation (e.g., nationwide expansion of a new product, target market) via the user interface of the terminal.

[1208] Input: Basic information about the opportunity

[1209] Output: Negotiation information sent from the device to the server

[1210] Specific operation: The user enters basic information about the business deal into the input field on the terminal and clicks the "Send" button, which sends the entered information to the server.

[1211] Step 5:

[1212] Prediction of optimal partner companies

[1213] The server preprocesses the received business negotiation information and then uses the trained machine learning model to predict the most suitable partner companies.

[1214] Input: Entered business information

[1215] Output: Predicted list of collaborating companies

[1216] How it works: The server preprocesses the sales negotiation information and inputs it into a trained machine learning model. The model predicts which partners have a high probability of success and generates a list of the results.

[1217] Step 6:

[1218] Generate a list of potential partner companies

[1219] The server generates a list of candidate collaborating companies based on the prediction results and sends it to the terminal.

[1220] Input: Predicted list of collaborating companies

[1221] Output: Candidate list sent to terminal

[1222] Specific operation: A list including the probability of success and past success cases for each predicted partner company is generated and sent to the terminal.

[1223] Step 7:

[1224] Automatic generation of sales documents

[1225] The server automatically generates business negotiation materials based on the predicted partner company information and sends them to the terminal.

[1226] Input: Predicted partner company information

[1227] Output: Automatically generated business documents (PDF, etc.)

[1228] Specific operation: Generate sales documents using templates that include introductions to partner companies, past success stories, and proposal details, and send them to the terminal in PDF format or other formats.

[1229] Step 8:

[1230] Entering the progress and results of sales negotiations

[1231] As the negotiation progresses, the user inputs the progress and results of the negotiation via the terminal.

[1232] Input: Opportunity status and results

[1233] Output: Entered negotiation result data (sent to server)

[1234] Specific operation: The user enters the progress and results into the progress input screen on the device, clicks the "Save" button and sends the data to the server.

[1235] Step 9:

[1236] Continuously training the model

[1237] The server uses the input sales outcome data to continuously train and optimize the machine learning model.

[1238] Input: Updated Opportunity Outcome Data

[1239] Output: An optimized machine learning model

[1240] Specific operation: Retrain using saved sales outcome data to improve the model's predictive accuracy.

[1241] The above is the specific processing flow of this system.

[1242] (Application example 1)

[1243] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1244] Traditional sales negotiations require a lot of time and effort to collect data, select partners with a high probability of success, and create sales negotiation materials. Furthermore, efficient operation of robots and optimization of production plans within factories have been issues. An integrated system is needed to streamline these processes and improve sales negotiation and production efficiency.

[1245] 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.

[1246] In this invention, the server includes means for collecting past negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for new negotiations and predicting the most suitable partner company based on the information, means for automatically generating negotiation materials based on the predicted partner company, means for following up on the results of negotiations and continuously optimizing the model, means for collecting past production data and maintenance records and analyzing the operating status and production success rate of each work robot, means for proposing an optimal production schedule and robot placement, and means for automatically generating operation instructions and maintenance procedures, thereby enabling efficient negotiation activities and production line operations.

[1247] "Past business negotiation data" refers to all detailed information relating to business negotiations that have taken place in the past, including the performance and results of specific business negotiations.

[1248] "Event history" refers to information that records a series of events in a business meeting or other related activity, and includes, for example, meeting dates and attendee lists.

[1249] "Corporate characteristic data" refers to information about the characteristics and attributes of a specific company, including, for example, the size and performance of the company, its position within the industry, and so on.

[1250] A "machine learning algorithm" is a computational method that extracts patterns and rules based on past data and makes predictions and classifications for new data.

[1251] "Success probability" refers to the probability that a particular business negotiation will be successful, and is a value calculated based on analysis of past data.

[1252] The "best-fit collaborating company" refers to the company that is predicted to be able to provide the most advantageous and effective cooperation in a particular business negotiation.

[1253] "Business negotiation materials" refers to documents and presentation materials necessary to support the progress of business negotiations, including proposals and explanatory materials.

[1254] "Production data" refers to all data related to the production process at a factory or manufacturing site, including, for example, production volume, operating hours, and quality data.

[1255] "Maintenance records" refer to a series of records relating to the maintenance, inspection, and repair of equipment and machinery, and include, for example, the date and time of maintenance and the specific work carried out.

[1256] "Operating status" refers to the status of a robot or machine that indicates whether it is operating normally, and is data that includes operating time, error status, etc.

[1257] The "production success probability" is the probability that a specific production schedule or task will be successful, and is also a value calculated based on an analysis of past data.

[1258] An "operation instruction manual" refers to a document that lists specific instructions and procedures for production work, including the order of work and the materials to be used.

[1259] A "maintenance procedure manual" refers to a document that describes the procedures and methods for performing maintenance, inspection, and repairs on equipment and machinery, and includes specific work procedures.

[1260] The system of the present invention is designed to improve the efficiency of business negotiation activities and the success rate of business negotiations. This system is composed of entities such as a server, terminals, and users.

[1261] The server collects past deal data, event history, and company characteristic data. The collected data is retrieved using APIs or database queries and stored in a database. The server then preprocesses the collected data, cleaning it, filling in missing data, and removing outliers. This preprocessed data is used to train a machine learning algorithm. Specifically, past successful and unsuccessful deals are used as training data to build a model that predicts the probability of deal success. This model is created using algorithms such as regression analysis and random forests.

[1262] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, this information includes "nationwide expansion of a new product" and "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[1263] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include introductions to partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and modify.

[1264] As the negotiation progresses, the user inputs the progress into the terminal. This negotiation result data is sent back to the server and stored in the database. Using this data, the server continuously trains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[1265] Furthermore, it also improves the efficiency of production lines within factories. The server collects past production data and maintenance records, and analyzes the operating status and production success rate of each work robot. It proposes optimal production schedules and robot placement, and automatically generates operation instructions and maintenance procedures. This enables efficient operation of robots within factories.

[1266] As a concrete example, the following prompt statements can be used to optimize the design of a new production line:

[1267] "In order to optimize the design of a new production line, please propose the optimal robot placement and maintenance schedule using past production data. The past data includes the operating status and maintenance records of each robot. Please predict the optimal operating time and maintenance timing for each robot on the new production line, and generate the optimal production schedule based on the results."

[1268] The hardware used includes a robot control unit and a server for data analysis, and the software uses Python, Scikit-learn, Pandas, etc. This will improve the efficiency of sales activities and production activities within the factory.

[1269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1270] Step 1:

[1271] The server collects past deal data, event history, and company characteristic data using APIs or database queries. The input is raw deal data, event data, and company data obtained from the database, and the output is a collection of these raw data. Specific operations include executing database queries and reading the results.

[1272] Step 2:

[1273] The server preprocesses the collected raw data. The input is raw data, and the output is cleaned data. Specific data processing includes data cleaning, imputing missing data, and removing outliers. Pandas is used for this processing.

[1274] Step 3:

[1275] The server trains a machine learning model using the preprocessed data. The input is the cleaned sales opportunity data, event data, and company data, and the output is a trained model for predicting the probability of success. Specifically, the model is built using algorithms such as random forests and Scikit-learn.

[1276] Step 4:

[1277] The user inputs basic information for a new business negotiation via a terminal. The input is basic information for the business negotiation, such as "nationwide expansion of a new product" or "target market," and the output is the business negotiation information entered by the user. Specific operations include data input via a user interface.

[1278] Step 5:

[1279] The terminal sends the entered business negotiation information to the server. The input is the business negotiation information entered by the user, and the output is the transfer of this information to the server. A specific operation is the sending of an HTTP request.

[1280] Step 6:

[1281] The server uses a trained machine learning model to predict the optimal partner based on the received business negotiation information. The input is the business negotiation information sent to the server, and the output is a list of candidate partner companies and their success rate. Specific data operations include applying the model and calculating the predicted value.

[1282] Step 7:

[1283] The server automatically generates sales negotiation materials based on the predicted partner companies. The input is a list of candidate partner companies and the success probability, and the output is the sales negotiation materials. In operation, the sales negotiation materials are created using a text generation model, etc.

[1284] Step 8:

[1285] The terminal presents the generated sales negotiation materials to the user, allowing the user to review and modify them. The input is the sales negotiation materials, and the output is the sales negotiation materials reviewed and modified by the user. Operation includes providing display and editing functions via a user interface.

[1286] Step 9:

[1287] As the negotiation progresses, the user inputs the progress status into the terminal. The input is negotiation progress information, and the output is the progress data entered by the user. The operation includes recording the progress information and inputting it into the terminal.

[1288] Step 10:

[1289] The terminal sends the entered progress data to the server. The input is the negotiation progress data, and the output is the transfer of this data to the server. The operation is the sending of an HTTP request.

[1290] Step 11:

[1291] The server stores the received progress data in a database and continuously trains and optimizes the machine learning model. The input is the sales negotiation result data, and the output is the optimized machine learning model. Specific operations include data accumulation, model retraining, and evaluation.

[1292] 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.

[1293] The system of the present invention aims to improve the efficiency of sales negotiation activities by sales representatives and increase the success rate of sales negotiations. Furthermore, by combining it with an emotion engine that recognizes the user's emotions and utilizes them in sales negotiations, it aims to improve the quality of sales negotiations. The system is composed of entities: a server, a terminal, and a user, and each entity operates as follows.

[1294] First, the server collects past business negotiation data, event history, and company characteristic data. The collected data is retrieved via API or database query, and the contents and results of business negotiations, event details, and company characteristic information are stored in the database.

[1295] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Using past examples of successful and unsuccessful deals as training data, a model is built to predict the probability of a deal being successful. This model is created using algorithms such as regression analysis and random forests.

[1296] When a user starts a new business negotiation, they input basic information about the negotiation via their device. For example, they input information such as "nationwide expansion of a new product" or "target market." This input information is sent from the device to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The results of this prediction are generated as a list of candidate partner companies and are sent back to the device along with the predicted success rate and past success stories.

[1297] Furthermore, the server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiation. The generated business negotiation materials are sent to the terminal and made available for the user to review and edit.

[1298] In addition, the system of the present invention includes an emotion engine that recognizes the user's emotions. The emotion engine has the function of extracting and analyzing emotional data from voice, facial expressions, input speed, etc. while the user is operating the terminal. For example, if the user is feeling stressed, the system can detect this and present advice to help the user relax or simpler operating procedures.

[1299] As a concrete example, when planning the nationwide rollout of a new product, the user inputs basic business negotiation information into the device, and the server suggests three optimal partner companies: Company A, Company B, and Company C. Furthermore, the device's emotion engine analyzes the user's emotions, and if tension is detected, the server provides simple operating procedures to relax the user. The server then automatically generates business negotiation materials, allowing the user to proceed with the negotiation based on high-quality materials.

[1300] As the negotiation progresses, the user periodically enters the progress and results into the device. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[1301] The system of this invention not only enables salespeople to significantly reduce the time and effort required to create sales documents and select partner companies, but also improves the quality of sales negotiations by using an emotion engine, resulting in more efficient sales activities and improved results.

[1302] The above is a specific embodiment for carrying out the present invention.

[1303] The processing flow will be explained below.

[1304] Step 1:

[1305] The server collects past sales data, event history, and company characteristics data using APIs and database queries. This data includes transaction history, sales activity logs, and public company information.

[1306] Step 2:

[1307] The server preprocesses the collected data. Specifically, it cleans the data, removes noise, fills in missing data, and removes outliers. It also standardizes and normalizes the data format to convert it into an analyzable format.

[1308] Step 3:

[1309] The server uses the preprocessed data to train a machine learning algorithm. It uses algorithms such as regression analysis and random forests to build a model that predicts the probability of a deal being successful. This model uses examples of successful and unsuccessful deals as training data.

[1310] Step 4:

[1311] The user uses the terminal to input basic information about a new business. For example, the user enters details of the business, such as "nationwide expansion of a new product" or "target market," into an input form.

[1312] Step 5:

[1313] The terminal sends the business negotiation information entered by the user to the server, which automatically converts the input information into the required format and passes it on to the server.

[1314] Step 6:

[1315] Based on the business negotiation information received by the server, the machine learning model it has built is used to predict the most suitable partner company. The model calculates the probability of success of the business negotiation and generates a list of candidate partner companies.

[1316] Step 7:

[1317] The server sends a list of predicted partner companies to the device, which displays the success rate of each partner company and related success stories.

[1318] Step 8:

[1319] The server automatically generates business documents based on the selected partner companies. The documents include company introductions, success stories, proposals, etc. The documents are automatically created according to a format.

[1320] Step 9:

[1321] The terminal displays the generated sales negotiation materials to the user, who can then review the materials and make any necessary corrections. The materials are also updated in accordance with the progress of the sales negotiation.

[1322] Step 10:

[1323] The server uses an emotion engine to recognize the user's emotions, and extracts the user's emotional data by analyzing facial expressions and voice using data from the device's camera and microphone.

[1324] Step 11:

[1325] The server provides advice tailored to the progress of the business negotiation based on the user's emotional data analyzed by the emotion engine. If the user is feeling stressed, it will suggest appropriate relief measures, such as suggestions for relaxing.

[1326] Step 12:

[1327] The user inputs the progress and results of the business negotiation into the terminal. The input data includes the success or failure of the business negotiation, the contract amount, the required time, etc.

[1328] Step 13:

[1329] The terminal sends the entered negotiation result data to the server, which stores it in a database and manages the negotiation results.

[1330] Step 14:

[1331] The server uses the sales negotiation result data to retrain and optimize the partner company success model. The collected new sales negotiation result data is reflected in the model to improve prediction accuracy.

[1332] Through the above steps, the system of the present invention improves the efficiency of sales negotiation activities by sales representatives, increases the success rate of negotiations, and improves the quality of negotiations by utilizing user emotion data, thereby realizing more efficient sales activities and improved results.

[1333] Example 2

[1334] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1335] While conventional sales negotiation support systems can perform basic procedures such as preprocessing sales negotiation data and selecting partner companies, they lack comprehensive functionality to improve the quality of sales negotiations. Furthermore, because they lack advice or operational support that takes users' emotions into consideration, users often feel stressed or find it difficult to operate the system. Therefore, there is a need to improve the efficiency of overall sales negotiation activities and the success rate of sales negotiations.

[1336] 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.

[1337] In this invention, the server includes means for collecting past business negotiation data, event history, and company characteristic data, means for preprocessing the collected data and constructing a model for predicting the success rate using a machine learning algorithm, means for having a user input basic information for a new business negotiation and predicting the most suitable partner company based on the information, means for automatically generating business negotiation materials based on the predicted partner company, means for following up on the results of the business negotiation and continuously optimizing the model, emotion recognition means for extracting and analyzing emotion data from voice, facial expression, input speed, etc., and means for presenting relaxation advice and simple operating procedures to the user using the emotion data. This makes it possible to improve the quality of the entire business negotiation and provide an environment in which the user can proceed with the business negotiation without stress.

[1338] "Business negotiation data" is data containing information about business negotiations that have taken place in the past, including the dates of the business negotiations, participating companies, business negotiation content, and results.

[1339] "Event history" is a record of past events and activities, including not only business meetings but also exhibitions, seminars, networking events, etc.

[1340] "Company characteristic data" refers to data that indicates basic information and characteristics of a company, including the company's size, industry, capital, location, etc.

[1341] "Preprocessing" refers to a series of operations to convert collected data into a format that is easier to analyze, such as cleaning the data, filling in missing data, and removing outliers.

[1342] A "machine learning algorithm" is an algorithm that uses large amounts of data to learn patterns and perform predictions, classification, and optimization. Examples include regression models and random forests.

[1343] A "model for predicting success probability" is a mathematical model for predicting the success probability of a sales negotiation based on past sales negotiation data. It is constructed using a machine learning algorithm.

[1344] "Cooperating companies" are companies selected to cooperate and collaborate in business negotiations and projects.

[1345] "Business materials" are documents, slides, and a set of materials prepared to support the progress of business negotiations, including proposal details, past success stories, company introductions, etc.

[1346] "Emotion recognition means" is a technology for detecting and analyzing a user's emotional state. It infers the user's emotions from voice, facial expressions, input speed, etc.

[1347] "Relaxation advice" is a suggestion or instruction to encourage the user to relax when they are feeling stressed.

[1348] A "user interface" is a screen or input device that allows a user to interact with a system. This includes terminal screens and input forms.

[1349] "API" stands for Application Program Interface, an interface for exchanging data and functions between software programs.

[1350] A "database query" is a set of instructions used to retrieve, insert, update, or delete data from a database.

[1351] The system of the present invention is configured so that a server, a terminal, and a user work together to improve the efficiency of business negotiation activities and increase the success rate of business negotiations. In particular, a specific embodiment of a business negotiation support system including an emotion recognition function will be described.

[1352] First, the server collects past sales negotiation data, event history, and company characteristics data. This is done using APIs and database queries. Specifically, it uses Amazon Athena to execute database queries and saves the data in an Amazon S3 bucket. This data includes sales negotiation dates, participating companies, sales negotiation content, and results.

[1353] The server then preprocesses the collected data using data manipulation libraries such as Pandas and NumPy to clean the data, impute missing data, remove outliers, and convert it into an analyzable format, such as by imputing NULL values ​​and removing outliers.

[1354] Based on the preprocessed data, the server uses machine learning algorithms to build a model that predicts the probability of a deal being successful. For this, it uses Scikit-learn to train a random forest model or a regression analysis model. The trained model is saved in Pickle format and later used for prediction.

[1355] When a user starts a new business negotiation, they input basic information about the negotiation via their terminal. The user uses the terminal's input form to enter information such as "nationwide expansion of new products" and "target market" and presses the send button. The terminal then sends this information to the server.

[1356] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format. The terminal displays the results on the screen so that the user can confirm and modify them.

[1357] Furthermore, the server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. LaTeX templates are used to generate the documents, and they are output in PDF format. The generated documents are sent to the terminal and made available for the user to review and edit.

[1358] The system of the present invention includes an emotion recognition means for recognizing the user's emotions. The device uses a camera and microphone to collect the user's facial expressions, voice, input speed, etc., and transmits them to a server. The server then analyzes the user's emotion data using an emotion recognition API (e.g., Microsoft Azure's emotion recognition API). If the user is feeling stressed, the server presents relaxation advice and simple operating instructions.

[1359] As the negotiation progresses, the user periodically enters the progress and results of the negotiation into the device. This data is then sent back to the server and stored in a database. The server then uses the new data to retrain the machine learning model, optimizing it and improving its prediction accuracy.

[1360] Example prompt sentence:

[1361] 1. Please suggest the best partner company for the nationwide rollout of our new product.

[1362] 2. Please predict the probability of success for a business negotiation that sets "men in their 20s" as the target market.

[1363] 3. Provide relaxation advice if the user is feeling tense.

[1364] In this way, the system of the present invention comprehensively supports business negotiation activities and aims to improve efficiency in order to increase the success rate of business negotiations. In addition, by using emotion recognition means, it reduces the mental burden on the user and provides a more comfortable and effective business negotiation environment.

[1365] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1366] Step 1: Data collection

[1367] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs and database queries. Specifically, the server uses Amazon Athena to execute database queries to retrieve deal data. The retrieved data is stored in Amazon S3.

[1368] Input: API request, database query

[1369] Output: Opportunity data, event history, and company characteristics data stored in Amazon S3

[1370] What happens: The server sends an API request and runs a query in Amazon Athena to collect data.

[1371] Step 2: Data Preprocessing

[1372] The server preprocesses the collected data by cleaning it, filling in missing data, and removing outliers. The server uses Pandas and NumPy to perform these operations and convert it into an analyzable format.

[1373] Input: Raw data retrieved from S3

[1374] Output: Preprocessed data (NumPy array format)

[1375] Specific operation: The server uses Pandas to interpolate NULL values ​​and remove outliers. The preprocessed data is converted into a NumPy array.

[1376] Step 3: Model Building

[1377] The server uses the preprocessed data to train a machine learning algorithm. Specifically, it uses Scikit-learn to train a random forest model. The trained model is saved in Pickle format.

[1378] Input: Preprocessed data

[1379] Output: Trained machine learning model (in Pickle format)

[1380] What it does: The server uses Scikit-learn to train and save the model.

[1381] Step 4: Enter business information

[1382] When starting a new business negotiation, the user inputs basic information about the business via the terminal. The user enters information such as "nationwide expansion of new products" and "target market" into the input form on the terminal and presses the send button.

[1383] Input: Basic information about the deal (nationwide launch of new products, target market, etc.)

[1384] Output: The basic information of the opportunity sent to the server

[1385] Specific behavior: A user enters information into a form on a device and presses the submit button.

[1386] Step 5: Opportunity forecasting and results presentation

[1387] The server receives the business negotiation information entered by the user and uses a machine learning model to predict the most suitable partner companies. The prediction results (a list of partner companies and the probability of success) are returned to the terminal in JSON format.

[1388] Input: Opportunity information submitted by the user

[1389] Output: Prediction results (list of collaborating companies, success probability)

[1390] Specific operation: The server inputs sales information into the model, generates prediction results, and sends them back to the device.

[1391] Step 6: Generate sales documents

[1392] The server automatically generates business documents based on the predicted partner companies. The documents include information about the partner companies, past success stories, and proposal details. The generated documents are sent to the terminal in PDF format.

[1393] Input: Predicted partner information

[1394] Output: Negotiation materials (PDF format)

[1395] Specific operation: The server generates business documents using a LaTeX template and sends them to the terminal.

[1396] Step 7: Emotion Recognition

[1397] The server extracts and analyzes emotional data from voice, facial expressions, input speed, etc. when the user operates the device. The server analyzes the user's emotions using an emotion recognition API.

[1398] Input: Data sent from your device, such as voice, facial expressions, and typing speed

[1399] Output: Analysis results of emotion data

[1400] Specific operation: The server uses the emotion recognition API to analyze the emotion data and determine the user's emotional state.

[1401] Step 8: Offer relaxation advice

[1402] The server provides relaxation advice and simple operation procedures based on the results of emotion recognition. If the user is feeling stressed, corresponding advice will be displayed on the screen.

[1403] Input: Emotion data analysis results

[1404] Output: Relaxation advice and simple operating instructions

[1405] Specific operation: The server generates advice based on the results of emotion analysis and sends it to the device.

[1406] Step 9: Enter opportunity progress and retrain the model

[1407] Users periodically enter the progress and results of sales negotiations into their devices. This data is sent to the server and stored in a database. The server then retrains the machine learning model using the new data, optimizing the model and improving its prediction accuracy.

[1408] Input: Negotiation status and results

[1409] Output: An updated machine learning model

[1410] Specific operation: The user inputs the progress data of the sales negotiations on the device and sends it to the server, which then retrains the model based on this data.

[1411] (Application example 2)

[1412] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1413] Current sales negotiation systems and sales activities are unable to properly grasp customer emotions and reactions, making it difficult to optimize the progress of sales negotiations. In particular, in brick-and-mortar stores, sales staff are required to discern customer emotions and respond appropriately, but this is difficult in practice, affecting sales negotiations and sales results. Efficiently generating appropriate sales negotiation materials and making proposals to customers is also a major challenge.

[1414] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting past negotiation data, event history, and company characteristic data; means for preprocessing the collected data and constructing a model for predicting the success probability using a machine learning algorithm; means for having a user input basic information about a new negotiation and predicting the optimal partner company based on the information; means for automatically generating negotiation materials based on the predicted partner company; means for following up on the results of the negotiation and continuously optimizing the model; means for acquiring the customer's facial expressions and voice from a terminal device in real time and analyzing their emotions; means for providing advice on the progress of the negotiation based on the analyzed emotion data; and means for sending the automatically generated negotiation materials to the customer as electronic data. This makes it possible to appropriately understand the customer's emotions and reactions, optimize the progress of the negotiation, and improve sales results.

[1415] "Sales negotiation data" refers to the content and results of sales negotiations, customer information, and all data related to sales negotiations.

[1416] "Event history" refers to records of past business negotiations and related events.

[1417] "Company characteristic data" refers to characteristic information such as a company's industry, size, business model, etc.

[1418] A "machine learning algorithm" refers to a computational method for analyzing data and performing pattern recognition and prediction.

[1419] "Cooperating companies" refer to companies with which we have cooperative relationships in business negotiations and projects.

[1420] "Business negotiation materials" refers to documents and data that summarize the information and proposals necessary to advance business negotiations.

[1421] "Follow-up" refers to the activity of tracking and checking the progress and results of a business negotiation and taking action as necessary.

[1422] "Terminal device" refers to an electronic device operated by a user, such as smart glasses or a smartphone.

[1423] "Emotion analysis" refers to the process of determining a person's emotional state based on facial expressions and voice data.

[1424] "Providing advice" means that the system presents the user with next actions or suggestions.

[1425] "Electronic data" refers to information or documents stored in digital form.

[1426]

[1427] This invention is a system that aims to support sales in brick-and-mortar stores, improving the efficiency of sales negotiations when sales staff use smart glasses to deal with customers, thereby increasing the success rate.

[1428] The server collects past deal data, event history, and company characteristics data. This data is retrieved using APIs or database queries. The collected data is stored in a database.

[1429] The server then preprocesses the collected data. Specifically, it cleans the data, fills in missing data, removes outliers, and converts it into an analyzable format. This preprocessed data is then used to train a machine learning algorithm. Past examples of successful and unsuccessful deals are used as training data to build a model that predicts the probability of a deal being successful. Algorithms such as regression analysis and random forests are used.

[1430] The user (sales staff) wears the smart glasses and inputs basic information about the business negotiation when a customer visits the store. For example, they input information about the products the customer is interested in and their past purchase history. This input information is sent from the smart glasses to the server. The server receives this information and predicts the most suitable partner companies based on the machine learning model it has built. The prediction results are generated as a list of candidate partner companies and are displayed on the smart glasses along with the predicted success rate and past success stories.

[1431] The terminal device (smart glasses) equipped with an emotion engine captures the customer's facial expressions and voice in real time and analyzes their emotions. For example, the smart glasses' camera and microphone can analyze the customer's facial expressions and tone of voice to determine their emotional state. The system detects this and provides the sales staff with advice on how to relax or appropriate operating procedures for the progress of the sales negotiation.

[1432] For example, when a salesperson is negotiating with a customer who is interested in a new product, the system can calculate the customer's level of interest from facial expression analysis and instruct them to provide a detailed product explanation.If the customer expresses concern about the price, the system can advise them to present a special discount offer.

[1433] Furthermore, the server automatically generates sales documents based on the predicted partner companies. The sales documents include information about the partner companies, past success stories, and proposals that match the purpose of the sales negotiation. The generated sales documents are sent to the smart glasses and made available for review and modification by the sales staff.

[1434] As the negotiation progresses, the user periodically enters progress and results. This negotiation result data is then sent back to the server and stored in the database. Using this data, the server retrains and optimizes the partner company success model. This improves the model's prediction accuracy and further increases the success rate of negotiations.

[1435] Examples of prompts for generative AI models include:

[1436] "A customer is interested in a new product. Please create a document detailing the product and offering a price discount."

[1437] Such a system provides sales staff with highly accurate information on how to create sales materials and conduct sales negotiations appropriately, thereby significantly improving the optimization of sales negotiations and the success rate of sales negotiations.

[1438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1439] Step 1:

[1440] The server collects past deal data, event history, and company characteristic data. This data is retrieved using APIs or database queries and stored in a database. The input is deal data, event history, and company characteristic data, and the output is stored in the database as collected data.

[1441] Step 2:

[1442] The server preprocesses the collected data by cleaning it, filling in missing data, removing outliers, and converting it into an analyzable format. The input is the collected raw data, and the output is preprocessed, analyzable data. This prepares the data in a format suitable for analysis.

[1443] Step 3:

[1444] The server uses the preprocessed data to train a machine learning algorithm. Using examples of past successful and unsuccessful deals as training data, it builds a model that predicts the probability of a deal's success. This model is created using algorithms such as regression analysis and random forests. The input is the preprocessed, analyzable data, and the output is a predictive model.

[1445] Step 4:

[1446] The user inputs basic information about the business negotiation using the smart glasses. The input information is sent from the smart glasses to the server. The input is the basic information about the business negotiation, and the output is the basic information about the business negotiation sent to the server.

[1447] Step 5:

[1448] The server receives basic information about the business negotiation and predicts the most suitable partner companies based on a machine learning model. The prediction results are generated as a list of candidate partner companies and displayed on the smart glasses along with the probability of success of the business negotiation and past success stories. The input is the basic information about the business negotiation, and the output is a list of candidate partner companies.

[1449] Step 6:

[1450] The terminal device (smart glasses) captures the customer's facial expressions and voice in real time and analyzes their emotions. Based on the analysis results, it provides advice to the sales staff. The input is the customer's facial expressions and voice data, and the output is the emotion analysis results and advice. This makes it possible to determine the customer's emotional state in real time.

[1451] Step 7:

[1452] The server automatically generates business negotiation materials based on the predicted partner companies. The business negotiation materials include information about the partner companies, past success stories, and proposals that match the purpose of the business negotiations, and are provided to the smart glasses. The input is a list of potential partner companies, and the output is the automatically generated business negotiation materials.

[1453] Step 8:

[1454] Users periodically input the progress and results of sales negotiations and send this to the server. The sales negotiation result data is stored in the server's database. The input is the sales negotiation progress and result data, and the output is the sales negotiation result data stored on the server. This allows the system to continuously retrain and optimize the model.

[1455] Step 9:

[1456] The server uses the sales outcome data to retrain and optimize the predictive model, improving the model's predictive accuracy and further increasing the success rate of future sales. The input is the sales outcome data, and the output is the optimized predictive model.

[1457]

[1458] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1459] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1460] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1461] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1462] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1463] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1464] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1465] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1466] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1467] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1468] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1469] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1470] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) me...

Claims

1. A means of collecting past business negotiation data, event history, and company characteristic data; A means for preprocessing the collected data and constructing a model for predicting the probability of success using a machine learning algorithm; A means for prompting a user to input basic information about a new business negotiation and predicting the most suitable partner company based on the information; means for automatically generating business negotiation materials based on the predicted cooperating companies; The system includes means for following up on the results of the sales negotiations and continuously optimizing said model.

2. The system according to claim 1 , further comprising means for providing a user interface for inputting basic information about a business deal.

3. The system of claim 1 , further comprising means for collecting past deal data, event history, and company characteristic data using an API or database query.

Images