system

Abstract

We provide the system. [Solution] A means for acquiring customer information and order performance data for corporate sales, A means for training a machine learning model with the aforementioned acquired data, A means for predicting future customer needs using the aforementioned trained machine learning model, A means for selecting the optimal product or service based on the aforementioned predicted needs, A means for automatically generating a proposal including the selected products or services, A means to enable the user to view and edit the aforementioned proposal on their terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional corporate sales, predicting customer needs and proposal activities based on them mainly rely on experience and intuition, so there is a problem that it is difficult to make efficient and accurate proposals. Furthermore, it is difficult to quickly match appropriate products and services to the diverse needs of customers, and it is difficult to improve customer satisfaction. As a result, the burden on sales staff has increased, which has contributed to weakening the competitiveness of enterprises.

Means for Solving the Problems

[0005] This invention provides a system that predicts future customer needs by acquiring customer information and order performance data from corporate sales and training a machine learning model with it. Specifically, it includes means for training a machine learning model with the acquired data and using this to predict future customer needs. Furthermore, it includes means for selecting the most suitable products and services based on the predicted needs and automatically generating a proposal document including these. It also includes means for allowing the generated proposal document to be viewed and edited on the user's terminal, enabling quick and appropriate proposals to be made to customers. This aims to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0006] "Corporate sales" refers to commercial transactions conducted between companies, and specifically to sales activities aimed at selling goods or services.

[0007] "Customer information" refers to detailed data about a specific customer, including, for example, company name, industry, and past transaction history.

[0008] "Order history data" refers to records of orders received in the past, including information such as the transaction amount, the details of the goods or services, and the order date.

[0009] A "machine learning model" refers to an algorithm or statistical model that learns data patterns and uses those learning results to make predictions and decisions.

[0010] "Needs forecasting" refers to predicting the products and services that customers will need in the future.

[0011] "Products" refer to tangible goods that a company sells.

[0012] "Services" refer to intangible value-added activities provided by a company.

[0013] A "proposal" is a document used to propose a product or service to a customer, and it includes information such as its advantages, price, and delivery date.

[0014] The "user terminal" refers to a computer or mobile device used by a user, and is a device for accessing and operating the system.

[0015] The "template" refers to a prototype for document creation, and provides a stereotyped format and configuration.

[0016] The "detailed data" refers to specific and detailed information about products or services, including price, delivery date, characteristics, etc.

[0017] "Editable" refers to a state where a user can change, add, or delete existing content.

Brief Description of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[0040] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[0041] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[0042] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[0043] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. Finally, the user sends the completed proposal to the client.

[0044] Specific example

[0045] 1. Data Collection and Learning Phase

[0046] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[0047] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[0048] 2. Needs Prediction Phase

[0049] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[0050] 3. Solution Matching Phase

[0051] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[0052] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[0053] 4. Proposal Generation Phase

[0054] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[0055] Proposal: Solution Proposal for Company A's New Production Line

[0056] 1. Background and Objectives

[0057] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0058] 2. Proposed Solutions

[0059] Production equipment X: This latest model features high efficiency and low energy consumption.

[0060] Price: \XXXXXXX

[0061] Delivery time: Approximately 2 months

[0062] Production management software Y: It includes real-time data management and analysis functions.

[0063] Price: \XXXXXX

[0064] Delivery time: Approximately 1 month

[0065] 3. Superiority

[0066] High production efficiency and low operating costs are possible.

[0067] We also provide comprehensive support after implementation.

[0068] 4. Next Steps

[0069] Please contact us if you have any questions or concerns.

[0070] We will schedule a meeting for a more detailed discussion.

[0071] 5. User Review and Editing Phase

[0072] Users can review this proposal on their devices, modify specific wording, and insert additional information.

[0073] Finally, the edited proposal is sent to company A.

[0074] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate proposals that are optimally suited to those needs. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0075] The following describes the processing flow.

[0076] Step 1:

[0077] The server retrieves customer information and order history data for corporate sales from the database. Customer information includes company name, industry, and past transaction history, while order history data includes transaction amount and details of purchased products and services.

[0078] Step 2:

[0079] The server preprocesses the retrieved data. This preprocessing includes cleaning the data, imputing missing values, and removing outliers. For example, it may fill in incomplete transaction information and remove illogical numbers.

[0080] Step 3:

[0081] The server feeds pre-processed data into a machine learning model and trains it. Specifically, it uses random forests and deep learning algorithms to learn customers' past purchasing patterns.

[0082] Step 4:

[0083] The server uses a trained machine learning model to predict the future needs of corporate sales customers. For example, it might predict that a particular customer may install a new production line in the next quarter.

[0084] Step 5:

[0085] The server selects the optimal products and services based on anticipated needs. This process involves searching the company's internal solution database for suitable products and services and gathering detailed data such as price, delivery time, and characteristics.

[0086] Step 6:

[0087] The server automatically generates a proposal using information on the selected products and services. The proposal includes details of specific solutions that address anticipated needs, benefits, pricing, and delivery timelines.

[0088] Step 7:

[0089] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0090] Step 8:

[0091] Users review the proposal content and make edits such as changing specific wording or inserting additional information. For example, they may customize it to suit the customer's characteristics or make minor adjustments.

[0092] Step 9:

[0093] The user reviews the completed proposal and sends it to the client. This process ensures that the client receives a quick and appropriate proposal.

[0094] (Example 1)

[0095] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In corporate sales, predicting customers' future needs and proposing the most suitable products and services based on those needs requires collecting and analyzing a large amount of information. However, this takes a tremendous amount of time and effort, hindering efficient sales activities. Furthermore, proposal writing is often done manually, leading to problems such as errors and wasted time. To solve these problems, there is a need for highly accurate customer needs prediction and automated proposal generation that requires minimal effort.

[0097] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0098] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training the acquired data using a machine learning model and performing missing value imputation and outlier removal; and means for predicting future customer needs using the trained machine learning model. This enables efficient and highly accurate prediction of customer needs and automatic generation of proposals.

[0099] "Corporate sales customer information" refers to data about customers in corporate sales, including information such as the name of the customer company, industry, address, contact information, and transaction history.

[0100] "Order history data" refers to data related to past transactions, including information such as order date, order details, order amount, name of the ordering company, delivery date, and payment status.

[0101] A "machine learning model" is an algorithm that learns from data and refers to a system that makes predictions and classifications by finding specific patterns or rules.

[0102] "Missing value imputation" is the process of filling in missing values ​​in data, and is performed to improve data consistency and analytical accuracy.

[0103] "Outlier removal" is the process of detecting and removing abnormal or extreme values ​​from data, and is performed to improve the reliability of the analysis results.

[0104] "Future customer needs" refer to predictions of the products and services that customers will need in the future, derived from past customer behavior and market trends.

[0105] An "optimal product or service" is one that best meets anticipated customer needs and exceeds customer expectations.

[0106] A "proposal" is a document that summarizes the content of a proposal to a customer, and includes details, pricing, delivery dates, and characteristics of the products or services to be offered.

[0107] "User terminal" refers to a device such as a computer, tablet, or smartphone used by a user, and is used when viewing and editing information on the system.

[0108] Modes for carrying out the invention

[0109] This invention is a system for efficiently predicting customer needs and creating proposals for corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[0110] First, the server retrieves customer information and order history data for corporate sales. This data is collected from a database (for example, MySQL® or PostgreSQL). The collected data includes the customer company's name, industry, address, contact information, and transaction history. This data is stored in the database and used for subsequent processing.

[0111] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values. For example, it uses df.fillna(method='ffill') to impute missing values ​​in the data. It also uses Z-scores to remove outliers. This is a method for detecting and removing outliers, such as df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[0112] The server feeds preprocessed data into a machine learning model and trains the model. This process uses algorithms such as Random Forest and Deep Learning (e.g., Scikit-learn and TENSORFLOW®). For example, it trains the model using code like `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`, and then saves the trained model.

[0113] Next, the server uses the trained model to predict the customer's future needs based on the new data. For example, it might predict that customer company A is likely to install a new production line in the next quarter, using a method like model.predict(new_data).

[0114] Based on predicted needs, the server selects the most suitable products and services from the company's solution database. This is done using SQL queries such as SELECT FROM solutions WHERE need = 'new_production_line'. Furthermore, detailed data such as price, delivery time, and characteristics are added. For example, this might involve processing `solution_data['price'] = get_price('product_x')`.

[0115] The server then automatically generates a proposal document containing the selected products and services. This process uses the Python Jinja2 template engine. The proposal document is created by rendering the template using methods such as `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[0116] The generated proposal will be created in the following format:

[0117] Proposal: Solution Proposal for Company A's New Production Line

[0118] 1. Background and Objectives

[0119] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0120] 2. Proposed Solutions

[0121] Production equipment X: This latest model features high efficiency and low energy consumption.

[0122] Price: \XXXXXXX

[0123] Delivery time: Approximately 2 months

[0124] Production management software Y: It includes real-time data management and analysis functions.

[0125] Price: \XXXXXX

[0126] Delivery time: Approximately 1 month

[0127] 3. Superiority

[0128] High production efficiency and low operating costs are possible.

[0129] We also provide comprehensive support after implementation.

[0130] 4. Next Steps

[0131] Please contact us if you have any questions or concerns.

[0132] We will schedule a meeting for a more detailed discussion.

[0133] The generated proposal is sent from the server to the user's terminal. The user can review it on their terminal and modify specific wording or insert additional information. A PDF editor (e.g., Adobe Acrobat) is used for editing. Finally, the user sends the edited proposal to the customer. For example, they might send it to the customer using `send_to_customer('final_proposal.pdf')`.

[0134] As a concrete example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model. By using this system, it is possible to improve the efficiency of corporate sales and enhance customer satisfaction.

[0135] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0136] System program processing flow

[0137] Step 1: Data acquisition and preprocessing

[0138] The server retrieves customer information and order history data for corporate sales from the database. The input is a database query, and the output is the collected raw data.

[0139] Specific operation: The server executes SQL queries such as "SELECT FROM customer_data" and "SELECT FROM sales_data" to retrieve data from the database.

[0140] The server preprocesses the acquired raw data. This includes imputing missing values ​​and removing outliers. The input is the acquired raw data, and the output is the preprocessed data.

[0141] Specific operation: Missing values ​​are imputed using df.fillna(method='ffill'), and outliers are removed by applying the Z-score and processing it as follows: df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[0142] Step 2: Training the machine learning model

[0143] The server trains a machine learning model using preprocessed data. The input is the preprocessed data, and the output is the trained model.

[0144] Specific operation: The server uses the Scikit-learn Random Forest algorithm and trains the model using `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`.

[0145] After training, the server saves the trained model. The input is the trained model, and the output is the saved model file.

[0146] Specific operation: Save the model to a file like this: model.save('model.pkl').

[0147] Step 3: Predicting Customer Needs

[0148] The server uses a trained model to predict future customer needs based on new data. The input is new customer data and the trained model, and the output is the predicted customer needs.

[0149] Specific operation: Predicts input data like model.predict(new_data).

[0150] Step 4: Solution Matching

[0151] The server selects the most suitable products and services from the company's solution database based on predicted needs. The input is the predicted needs, and the output is information on the selected products and services.

[0152] Specific operation: The server executes an SQL query like "SELECT FROM solutions WHERE need = 'predicted_need'" to select the appropriate solution.

[0153] The server adds detailed data such as price, delivery time, and characteristics to the information of the selected products and services. The input is the selected solution information, and the output is the solution information with the added detailed data.

[0154] Specific operation: Additional information is retrieved like this: solution_data['price'] = get_price('product_x').

[0155] Step 5: Proposal Generation

[0156] The server automatically generates a proposal based on the selected product or service information. The input is solution information with detailed data attached, and the output is the generated proposal.

[0157] Specific operation: Using Python's Jinja2 template engine, a proposal is generated using `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[0158] Step 6: Review and edit the proposal

[0159] The server sends the generated proposal to the user's terminal. The input is the generated proposal, and the output is the proposal sent to the user's terminal.

[0160] Specific operation: Send a file like this: send_to_user('proposal.pdf').

[0161] The user reviews the proposal on their device and edits it as needed. The input is the submitted proposal, and the output is the edited proposal.

[0162] Specific operation: The user edits the proposal using a PDF editor such as Adobe Acrobat.

[0163] The user sends the edited proposal to the client. The input is the edited proposal, and the output is the proposal sent to the client.

[0164] Specific action: Send the proposal using a method like send_to_customer('final_proposal.pdf').

[0165] Through the steps outlined above, this system aims to improve the efficiency of corporate sales and enhance customer satisfaction. For example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model.

[0166] (Application Example 1)

[0167] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0168] The challenge is to provide a system that can accurately predict customer purchasing needs in physical stores and make effective suggestions. Furthermore, the challenge is to enable store staff to quickly and accurately suggest the most suitable products to customers.

[0169] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0170] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal including the selected product or service; means for enabling the proposal to be viewed and edited on a user terminal; means for collecting purchase history and behavioral data of customers visiting physical stores in real time; and means for suggesting the optimal product to store staff at physical stores. As a result, it becomes possible to predict customer needs in real time and make accurate product suggestions in physical stores, just as in corporate sales.

[0171] "Corporate sales" refers to all sales activities that target companies and organizations as customers.

[0172] "Customer information" refers to all data related to a customer, such as transaction history and purchasing patterns.

[0173] "Order history data" refers to data that includes detailed information and transaction history of products that have been ordered in the past.

[0174] A "machine learning model" refers to an algorithm that learns patterns and makes predictions based on a large amount of data.

[0175] "Customer needs" refer to the demands for goods and services that customers currently and in the future require.

[0176] "Products or services" refers to all specific goods and services provided to customers.

[0177] A "proposal" refers to a document that details the products or services offered to a customer.

[0178] A "user terminal" refers to a digital device used by a user to receive and edit information.

[0179] A "physical store" refers to a physical store where customers can go in person to purchase goods or services.

[0180] "Purchase history" refers to a record of products and services that a customer has purchased in the past.

[0181] "Behavioral data" refers to data about customers' actions and behavioral patterns when they visit a store.

[0182] "Store staff" refers to employees who handle customer service and product recommendations in a physical store.

[0183] "Real-time" refers to information processing and data collection occurring almost instantaneously.

[0184] This invention provides a system for predicting customer needs in corporate sales and physical stores and automatically generating optimal proposals. The system is primarily implemented through the collaboration of a server, terminals, and users.

[0185] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. The server then preprocesses the collected data, including imputing missing values ​​and removing outliers. The preprocessed data is fed into a machine learning model for training. Machine learning models such as random forests and deep learning are used. The trained model is then used to predict the future needs of corporate sales customers.

[0186] Next, the server selects the most suitable products and services based on the predicted needs. This selection is done by searching the company's internal solution database for information on appropriate products and services, and adding detailed data such as price, delivery time, and characteristics. The server then automatically generates a proposal based on this information. This generated proposal is sent from the server to the user's terminal, where the user can review and edit it. For example, they can change specific wording or insert additional information.

[0187] In physical stores, the system collects purchase history and behavioral data in real time when customers visit. The server uses this data to train machine learning models and predict customer needs in the physical store. Store staff are provided with user terminals where they can review and edit optimal product and service recommendations and provide them to customers. This entire process is performed using software tools such as Python, Flask, scikit-learn, and Pandas.

[0188] As a concrete example, if a customer visits a physical store and has previously purchased "Product A," "Product B," and "Product C" based on their past purchase history, the server can suggest "Product D" on their next visit. It is also possible to add a "5% discount" offer to the suggestion. An example of a specific prompt message is as follows:

[0189] Target customer: Mr. / Ms. Tanaka

[0190] Purchase history: ["Product A", "Product B", "Product C"]

[0191] Behavior pattern: Visits the store on weekday afternoons.

[0192] Question:

[0193] Please generate product recommendations for the customer's next visit.

[0194] This system improves the accuracy of predicting customer needs in both physical stores and corporate sales, enabling more effective proposals. This, in turn, leads to increased customer satisfaction and maximized sales efficiency.

[0195] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0196] Step 1:

[0197] The server retrieves customer information and order history data for corporate sales. This includes basic customer information, past transaction history, and data on purchased products and services. This data is stored in a database for use in subsequent processing.

[0198] Input: Customer information, order history data

[0199] Data processing: Storage in a database

[0200] Output: Data stored in the database

[0201] Step 2:

[0202] The server preprocesses the acquired data. This preprocessing includes imputing missing values ​​and removing outliers. This step prepares the data so that machine learning models can learn efficiently.

[0203] Input: Raw data stored in the database

[0204] Data processing: Missing value imputation, outlier removal

[0205] Output: Preprocessed data

[0206] Step 3:

[0207] The server trains machine learning models using pre-processed data. For example, it uses algorithms such as random forests or deep learning to build models that predict future customer needs.

[0208] Input: Preprocessed data

[0209] Data processing: Training machine learning models

[0210] Output: Trained model

[0211] Step 4:

[0212] The server uses a trained model to predict customer needs. Based on these predictions, it lists the products and services that customers are most likely to purchase next.

[0213] Input: Trained model, customer data

[0214] Data processing: Needs prediction

[0215] Output: Predicted needs list

[0216] Step 5:

[0217] The server selects the optimal products and services based on anticipated needs. This selection process utilizes an internal solution database, supplemented with detailed data such as price, delivery time, and characteristics.

[0218] Input: Predicted needs list, solution database

[0219] Data processing: Product / service selection and addition of detailed data.

[0220] Output: Optimal product / service list

[0221] Step 6:

[0222] The server automatically generates a proposal based on the selected products and services. The generated proposal includes detailed information such as price, delivery date, and characteristics.

[0223] Input: List of optimal products and services

[0224] Data processing: Automated generation of proposals

[0225] Output: Proposal

[0226] Step 7:

[0227] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0228] Input: Proposal

[0229] Data processing: Sending proposals

[0230] Output: Proposal viewable on the user's terminal

[0231] Step 8:

[0232] In physical stores, the server collects the purchase history and behavioral data of visiting customers in real time. Based on this data, the server uses machine learning models to predict the customer's next purchasing behavior.

[0233] Input: Real-time purchase history and behavioral data

[0234] Data processing: Real-time data collection and analysis

[0235] Output: Predicted customer purchasing trends

[0236] Step 9:

[0237] In physical stores, store staff use user terminals to provide optimal product recommendations. These recommendations are automatically generated by the system, and staff then customize them before presenting them to customers.

[0238] Input: Predicted purchasing trends, generated proposals

[0239] Data processing: Customization and presentation of proposals

[0240] Output: Customized proposal

[0241] Therefore, this system enables efficient and effective prediction and proposal of customer needs in corporate sales and physical stores through a series of steps.

[0242] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0243] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[0244] First, the server retrieves customer information and order history data for corporate sales from the database. This data is stored in the database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[0245] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[0246] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[0247] Furthermore, the generated proposal can be modified based on the user's emotions through the emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. The emotional information recognized by the emotion engine is used for selecting proposal templates and dynamically modifying the content of the proposal. For example, if the user is feeling stressed, the emotion engine will detect this and help modify the proposal content to be more concise and intuitive.

[0248] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. The emotion engine recognizes the user's emotions and can further adjust the proposal during the editing process.

[0249] Specific example

[0250] 1. Data Collection and Learning Phase

[0251] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[0252] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[0253] 2. Needs Prediction Phase

[0254] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[0255] 3. Solution Matching Phase

[0256] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[0257] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[0258] 4. Proposal Generation Phase

[0259] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[0260] Proposal: Solution Proposal for Company A's New Production Line

[0261] 1. Background and Objectives

[0262] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0263] 2. Proposed Solutions

[0264] Production equipment X: This latest model features high efficiency and low energy consumption.

[0265] Price: \XXXXXXX

[0266] Delivery time: Approximately 2 months

[0267] Production management software Y: It includes real-time data management and analysis functions.

[0268] Price: \XXXXXX

[0269] Delivery time: Approximately 1 month

[0270] 3. Superiority

[0271] High production efficiency and low operating costs are possible.

[0272] We also provide comprehensive support after implementation.

[0273] 4. Next Steps

[0274] Please contact us if you have any questions or concerns.

[0275] We will schedule a meeting for a more detailed discussion.

[0276] 5. Proposal Review and Editing Phase

[0277] The server sends the generated proposal to the user's terminal. The user reviews the proposal on their terminal and modifies the content based on the emotional information recognized by the emotion engine.

[0278] For example, if the emotion engine detects that a user is experiencing stress, it will suggest modifying the proposal to make it more concise and intuitive.

[0279] 6. Final confirmation and transmission phase

[0280] The user reviews the final edited proposal and sends it to the client. This process ensures that the proposal is delivered quickly and appropriately, taking into account the user's emotional state.

[0281] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0282] The following describes the processing flow.

[0283] Step 1:

[0284] The server retrieves customer information and order fulfillment data for corporate business from the database. This includes company name, industry type, past transaction history, transaction amount, and details of the products and services purchased.

[0285] Step 2:

[0286] The server preprocesses the retrieved data. Specifically, it performs data cleaning, such as filling in missing values and removing outliers. For example, if there is missing data for a specific company, it is filled in from other data.

[0287] Step 3:

[0288] The server inputs the preprocessed data into a machine learning model and trains the model. Algorithms such as random forest and deep learning can be used. This enables learning about customer purchase patterns and trends.

[0289] Step 4:

[0290] The server uses the trained machine learning model to predict future customer needs. For example, it predicts the likelihood that a specific customer will add a new production line in the next quarter.

[0291] Step 5:

[0292] The server selects the optimal products and services based on the predicted needs. The server searches for and selects appropriate products and services from the in-house solution database. The search results include detailed data such as the price, delivery date, and characteristics of the products and services.

[0293] Step 6:

[0294] The server automatically generates a proposal based on the information of the selected products and services. The proposal describes details, advantages, price, delivery date, etc. of the products and services that can be supplied.

[0295] Step 7:

[0296] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0297] Step 8:

[0298] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. This allows the system to understand the user's emotional state while they are editing the proposal.

[0299] Step 9:

[0300] The server receives emotional information recognized by the emotion engine and dynamically changes the proposal template selection and content suggestions. For example, if the user is feeling stressed, the server will make the proposal concise and easy to understand.

[0301] Step 10:

[0302] Users review the proposal content and make edits, such as changing specific wording or inserting additional information. They also refer to revision suggestions provided by the sentiment engine.

[0303] Step 11:

[0304] The user reviews the finalized proposal and sends it to the client. At this stage, the proposal takes the user's emotional state into consideration.

[0305] Through the processing steps described above, it becomes possible to accurately predict the customer needs of corporate sales and provide optimal proposals that reflect the user's emotional state using the emotion engine.

[0306] (Example 2)

[0307] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0308] In corporate sales, there is a problem that it is difficult to efficiently predict customer needs and create a proposal. In addition, by creating a proposal without considering the emotional state of the user, an optimal proposal may not be made. As a result, there is a problem that the efficiency and accuracy of sales activities are hindered, and the improvement of customer satisfaction is also hindered.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring customer information and order performance data for corporate sales, means for preprocessing the acquired data, means for training the preprocessed data using a machine learning model, means for predicting future customer needs using the trained machine learning model, means for selecting an optimal product or service based on the predicted needs, means for automatically generating a proposal including the selected product or service, means for enabling confirmation and editing of the proposal on the user terminal, and means for analyzing the user's emotion and adjusting the content of the proposal based on the user's emotion. Thereby, it becomes possible to accurately predict the customer needs of corporate sales and automatically generate an optimal proposal considering the emotional state of the user.

[0310] "Corporate sales" refers to sales activities targeting corporations (companies), and is mainly a business of providing and selling products and services in business-to-business transactions.

[0311] "Customer information" refers to data related to customers held by a company, and includes, for example, customer name, address, contact information, transaction history, purchase history, etc.

[0312] "Order performance data" refers to data related to orders received by a company so far, and specifically includes information such as order quantity, amount, time, customer name, etc.

[0313] "Preprocessing" refers to the process of preparing data to be suitable for machine learning models, and includes, for example, imputing missing values, removing outliers, and normalizing data.

[0314] A "machine learning model" is a model that learns from data and uses the results of that learning to make predictions and classifications on new data. Examples of algorithms include random forests and deep learning.

[0315] "Needs forecasting" refers to using historical data and machine learning models to predict future customer demands and the products and services they will need.

[0316] "Product or service selection" refers to choosing the appropriate product or service based on anticipated customer needs.

[0317] "Automatic proposal generation" refers to the automatic creation of proposals based on information about selected products and services.

[0318] "Emotion analysis" refers to a technology that analyzes a user's voice tone, facial expressions, and typing speed to recognize their emotions.

[0319] "Means of enabling editing" refers to functions or methods that allow users to view the generated proposal on their device and make changes or corrections.

[0320] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[0321] System Configuration

[0322] First, the server retrieves customer information and order history data for corporate sales from the database. This data includes, for example, the customer's name, previous purchase history, and transaction amount. The data retrieved by the server is stored in the database and used for subsequent processing.

[0323] Next, the server preprocesses the collected data. Preprocessing includes imputing missing values ​​and removing outliers. For example, the Python library "pandas" is used to clean the data. Commands such as "fillna" and "dropna" are used in the "pandas" library.

[0324] Machine learning models

[0325] The server feeds pre-processed data into a machine learning model and trains it. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. The trained model is then used to predict the future needs of corporate sales customers. Specifically, it utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[0326] Needs forecasting

[0327] Next, the server uses the trained model to predict the future needs of customer companies. For example, based on corporate sales data, it might predict that customer company A may install a new production line in the next quarter.

[0328] Solution Selection

[0329] The server selects the optimal products and services based on predicted needs. It searches the company's solution database for information on suitable products and services and adds detailed data such as price, delivery time, and characteristics. For example, it might use an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[0330] Automatic proposal generation

[0331] The server automatically generates a proposal based on the collected data. This process involves using a template to fill in information about the selected products and services. The generated proposal will look like this:

[0332] Proposal: Solution Proposal for Company A's New Production Line

[0333] 1. Background and Objectives

[0334] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0335] 2. Proposed Solutions

[0336] Production equipment X: This latest model features high efficiency and low energy consumption.

[0337] Price: ¥100,000

[0338] Delivery time: Approximately 2 months

[0339] Production management software Y: It includes real-time data management and analysis functions.

[0340] Price: ¥50,000

[0341] Delivery time: Approximately 1 month

[0342] 3. Superiority

[0343] High production efficiency and low operating costs are possible.

[0344] We also provide comprehensive support after implementation.

[0345] 4. Next Steps

[0346] Please contact us if you have any questions or concerns.

[0347] We will schedule a meeting for a more detailed discussion.

[0348] Utilizing the Emotion Engine

[0349] Furthermore, the proposal can be modified based on the user's emotions through an emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. Based on this emotional information, it dynamically selects a proposal template and modifies the content of the proposal.

[0350] Review and edit the proposal.

[0351] The generated proposal is sent from the server to the user's terminal, where the user can review and edit it as needed. Users can change specific expressions, insert additional information, and perform other operations. The emotion engine further supports the editing process, adjusting the proposal content according to the user's emotional state.

[0352] Final confirmation and submission

[0353] The user reviews the final edited proposal and sends it to the client. This ensures that the proposal is delivered quickly and appropriately, taking the user's emotional state into consideration.

[0354] Example of a prompt

[0355] An example of a prompt message is: "Predict the production equipment and software that client company A may need in the next quarter, and generate an optimal proposal based on that data."

[0356] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0358] Program processing steps

[0359] Step 1: Data Collection

[0360] Server operation:

[0361] The server retrieves corporate sales customer information and order history data from the database. Specifically, it extracts the necessary data using SQL queries. For example, it executes a command such as "SELECT FROM customer_information WHERE period = 'past 1 year'".

[0362] Input: Database

[0363] Output: Customer information and order history data

[0364] Step 2: Data Preprocessing

[0365] Server operation:

[0366] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values ​​(e.g., imputing with the median) and removing outliers (e.g., removing outliers using the 3σ rule). The data is cleaned using the Python "pandas" library. Commands such as "fillna" and "dropna" from "pandas" are used.

[0367] Input: Retrieved data

[0368] Output: Preprocessed data

[0369] Step 3: Training the machine learning model

[0370] Server operation:

[0371] The server trains machine learning models using preprocessed data. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. It utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[0372] Input: Preprocessed data

[0373] Output: Trained model

[0374] Step 4: Needs Prediction

[0375] Server operation:

[0376] The server uses a trained model to predict the future needs of customer companies. For example, it runs "model.predict(new input data)" to predict the likelihood that customer company A will install a new production line.

[0377] Input: Trained model, customer information

[0378] Output: Predicted needs

[0379] Step 5: Solution Selection

[0380] Server operation:

[0381] The server selects the optimal product or service based on the predicted needs. It searches the company's solution database for information on the relevant product or service and collects detailed data such as price, delivery time, and characteristics. It uses an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[0382] Input: Predicted needs, solution database

[0383] Output: Information on the best products and services

[0384] Step 6: Automatic proposal generation

[0385] Server operation:

[0386] The server automatically generates proposals based on the collected data. This process involves using templates to fill in information about the selected products and services. Specifically, the proposal is generated in the following format:

[0387] Proposal: Solution Proposal for Company A's New Production Line

[0388] 1. Background and Objectives

[0389] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0390] 2. Proposed Solutions

[0391] Production equipment X: This latest model features high efficiency and low energy consumption.

[0392] Price: ¥100,000

[0393] Delivery time: Approximately 2 months

[0394] Production management software Y: It includes real-time data management and analysis functions.

[0395] Price: ¥50,000

[0396] Delivery time: Approximately 1 month

[0397] 3. Superiority

[0398] High production efficiency and low operating costs are possible.

[0399] We also provide comprehensive support after implementation.

[0400] 4. Next Steps

[0401] Please contact us if you have any questions or concerns.

[0402] We will schedule a meeting for a more detailed discussion.

[0403] Input: Information on the best products and services

[0404] Output: Automated proposal

[0405] Step 7: Correction by the emotion engine

[0406] How the emotion engine works:

[0407] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. For example, it uses data from the camera, microphone, and keyboard input speed. If the user is stressed, the emotion engine will modify the proposal content in a concise and intuitive manner.

[0408] Input: Proposal, user sentiment data

[0409] Output: Proposal revised based on emotions

[0410] Step 8: Review and edit the proposal

[0411] Server operation:

[0412] The server sends the generated proposal to the user's terminal.

[0413] User actions:

[0414] Users can view the proposal on their device and edit it as needed. For example, they can change a specific phrase to "Special discount price: ¥90,000".

[0415] Input: Proposal

[0416] Output: Edited proposal

[0417] Step 9: Final confirmation and submission

[0418] User actions:

[0419] The user reviews the completed proposal and sends it to the client. This can be done via email or a dedicated sales support tool.

[0420] Input: Edited proposal

[0421] Output: Proposal sent to the customer

[0422] By utilizing this system, it becomes possible to accurately predict the customer needs of corporate sales representatives and quickly provide optimal proposals that take into account the emotional state of the users.

[0423] (Application Example 2)

[0424] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0425] There is a need to improve the efficiency of predicting customer needs and creating proposals in corporate sales. However, existing systems often provide uniform proposals without considering customer emotions or the specific circumstances, limiting their effectiveness in improving sales results. Furthermore, more advanced data analysis and user interface optimization are necessary to ensure the speed and accuracy of proposals. The goal is to improve the efficiency and customer satisfaction of corporate sales by solving these problems.

[0426] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0427] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal document including the selected product or service; means for enabling the proposal document to be viewed and edited on a user terminal; means for recognizing the user's emotional state; means for dynamically modifying the content of the proposal document based on the emotional state; and means for executing electronic payment. This makes it possible to accurately predict customer needs in corporate sales activities, automatically generate proposal documents that match the user's emotional state, and provide convenient electronic payment.

[0428] "Customer information" refers to various data about customers in corporate sales, and more specifically includes information such as the name, industry, address, contact information, purchase history, and transaction history of the customer company.

[0429] "Order performance data" refers to data detailing transactions that corporate sales have received in the past, and more specifically includes order date, order amount, ordered items, delivery date, name of trading company, and completion status.

[0430] A "machine learning model" refers to a computational model that uses algorithms to make predictions, classifications, and recommendations based on large amounts of data. Specifically, this includes techniques such as random forests and deep learning.

[0431] "Needs forecasting" refers to the process of using machine learning models to predict the products and services that corporate sales customers may need in the future.

[0432] "Product or service selection" refers to the process of choosing the most suitable product or service from multiple options based on anticipated customer needs.

[0433] "Automatic proposal generation" refers to the process of compiling proposal details into a document format for the customer based on the selected product or service, and this document is generated automatically.

[0434] "Emotional state recognition" refers to the technology that analyzes data such as the user's voice tone, facial expressions, and typing speed to determine the user's emotional state.

[0435] "Dynamic modification" refers to the process of changing the content of a proposal in real time based on the recognized emotional state of the user.

[0436] "Electronic payment" refers to the process of paying for goods or services using various online or mobile payment methods.

[0437] The system of this invention is realized through the collaboration of a server, terminal, user, and emotion engine. This system is specifically implemented in the following manner. Various hardware and software are used in this system.

[0438] Data Acquisition and Preprocessing

[0439] The server retrieves customer information and order history data for corporate sales from the database. This data includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. MySQL or PostgreSQL are used as the database management system.

[0440] The server preprocesses the acquired data, including imputing missing values ​​and removing outliers. Data processing libraries such as Python or R (e.g., Pandas, Numpy) are used for data formatting.

[0441] Training machine learning models

[0442] The server uses pre-processed data to train machine learning models. Libraries such as TensorFlow and PyTorch are used for this purpose. The models employ algorithms such as random forests and deep learning.

[0443] Needs forecasting

[0444] The server uses a trained model to predict the customer's future needs. For example, it makes predictions using prompts such as, "Based on customer B's purchase history over the past year, predict what they are likely to buy next."

[0445] Solution matching and proposal creation

[0446] The server selects the most suitable products and services based on predicted needs and automatically generates a proposal including detailed data such as price, delivery time, and characteristics. Solution matching refers to the company's internal solution database, and natural language generation models (e.g., GPT-3®) are used to generate the proposal.

[0447] Recognizing emotional states and revising proposals

[0448] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and typing speed to recognize the user's emotional state. The emotion engine used includes options such as Azure® Emotion API and IBM Watson® Emotion Analysis. Based on the recognized emotional state, the content of the proposal is dynamically modified. Specifically, when the user is feeling stressed, a prompt such as "Please make the proposal more concise and intuitive" is displayed.

[0449] Review and editing of the proposal

[0450] Users review and edit proposals generated on their devices. Mobile applications using React Native or Flutter® are suitable for this purpose. After editing, users make final confirmations on the proposal and send it to the client.

[0451] Electronic payment

[0452] After final confirmation of the proposal, electronic payment can be made with a single touch using a terminal. Online payment services such as PayPal and Stripe are used for electronic payments. This system accurately predicts customer needs in corporate sales activities, automatically generates proposals that match the user's emotions, and provides convenient electronic payment.

[0453] Specific example

[0454] For example, the server predicts what customer B is likely to buy next based on their purchase history over the past year. Based on the prediction, it selects appropriate products and services and generates a proposal. Furthermore, when the user reviews the proposal, if the emotion engine detects that they are experiencing stress, it prompts them to "make the proposal more concise and intuitive" and revise the content. After final confirmation, the user can then make an electronic payment to purchase the product with a single touch.

[0455] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0456] Step 1:

[0457] Data collection

[0458] The server retrieves customer information and order history data for corporate sales from a database. This includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. The database management system used is MySQL or PostgreSQL. Database queries are executed as input to extract the necessary data. The extracted dataset is obtained as output.

[0459] Step 2:

[0460] Data preprocessing

[0461] The server preprocesses the retrieved data. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. It uses Python's Pandas and NumPy libraries to format the data. The dataset extracted in the previous step is used as input. The output is the preprocessed dataset.

[0462] Step 3:

[0463] Training machine learning models

[0464] The server trains a machine learning model using preprocessed data. The libraries used are TensorFlow and PyTorch, and the models employ algorithms such as random forests and deep learning. The input is the preprocessed dataset obtained in the previous step. The output is a trained machine learning model.

[0465] Step 4:

[0466] Needs forecasting

[0467] The server uses a trained model to predict the customer's future needs. The prompt is "Predict what customer B is likely to purchase next, based on their purchase history over the past year." The input is the current customer data and the prompt. The output is the predicted needs (the products or services the customer is likely to purchase next).

[0468] Step 5:

[0469] Solution Matching

[0470] The server selects the optimal product or service based on predicted needs, adding detailed data such as price, delivery time, and characteristics. Predicted needs and the company's internal solutions database are used as input. The output provides detailed information about the selected product or service.

[0471] Step 6:

[0472] Automatic generation of proposals

[0473] The server automatically generates proposals based on information about the selected products and services. It uses a natural language generation model (e.g., GPT-3). Detailed information about the selected products and services is used as input. The output is an automatically generated proposal.

[0474] Step 7:

[0475] Recognition of emotional states

[0476] The device analyzes the user's voice tone, facial expressions, and typing speed using an emotion engine (e.g., Azure Emotion API, IBM Watson Emotion Analysis) to recognize the user's emotional state. Real-time user data is used as input. The user's emotional state is obtained as output.

[0477] Step 8:

[0478] Dynamic editing of proposals

[0479] The proposal content is dynamically modified based on the emotional state recognized by the emotion engine. Specifically, if the user is stressed, a prompt message such as "Please make the proposal content more concise and intuitive" is used. The emotional state and the existing proposal are used as input. The modified proposal is obtained as output.

[0480] Step 9:

[0481] Proposal review and electronic payment

[0482] The user reviews and edits the proposal generated on the terminal and makes a final confirmation. Afterward, they execute electronic payment with a single touch. The user's edited proposal and electronic payment request are used as input. The output is the edited proposal and confirmation of the completed payment.

[0483] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0484] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0485] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0486] [Second Embodiment]

[0487] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0488] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0489] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0490] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0491] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0492] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0493] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0494] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0495] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0496] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0497] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0498] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0499] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[0500] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[0501] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[0502] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[0503] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. Finally, the user sends the completed proposal to the client.

[0504] Specific example

[0505] 1. Data Collection and Learning Phase

[0506] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[0507] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[0508] 2. Needs Prediction Phase

[0509] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[0510] 3. Solution Matching Phase

[0511] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[0512] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[0513] 4. Proposal Generation Phase

[0514] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[0515] Proposal: Solution Proposal for Company A's New Production Line

[0516] 1. Background and Objectives

[0517] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0518] 2. Proposed Solutions

[0519] Production equipment X: This latest model features high efficiency and low energy consumption.

[0520] Price: \XXXXXXX

[0521] Delivery time: Approximately 2 months

[0522] Production management software Y: It includes real-time data management and analysis functions.

[0523] Price: \XXXXXX

[0524] Delivery time: Approximately 1 month

[0525] 3. Superiority

[0526] High production efficiency and low operating costs are possible.

[0527] We also provide comprehensive support after implementation.

[0528] 4. Next Steps

[0529] Please contact us if you have any questions or concerns.

[0530] We will schedule a meeting for a more detailed discussion.

[0531] 5. User Review and Editing Phase

[0532] Users can review this proposal on their devices, modify specific wording, and insert additional information.

[0533] Finally, the edited proposal is sent to company A.

[0534] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate proposals that are optimally suited to those needs. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The server retrieves customer information and order history data for corporate sales from the database. Customer information includes company name, industry, and past transaction history, while order history data includes transaction amount and details of purchased products and services.

[0538] Step 2:

[0539] The server preprocesses the retrieved data. This preprocessing includes cleaning the data, imputing missing values, and removing outliers. For example, it may fill in incomplete transaction information and remove illogical numbers.

[0540] Step 3:

[0541] The server feeds pre-processed data into a machine learning model and trains it. Specifically, it uses random forests and deep learning algorithms to learn customers' past purchasing patterns.

[0542] Step 4:

[0543] The server uses a trained machine learning model to predict the future needs of corporate sales customers. For example, it might predict that a particular customer may install a new production line in the next quarter.

[0544] Step 5:

[0545] The server selects the optimal products and services based on anticipated needs. This process involves searching the company's internal solution database for suitable products and services and gathering detailed data such as price, delivery time, and characteristics.

[0546] Step 6:

[0547] The server automatically generates a proposal using information on the selected products and services. The proposal includes details of specific solutions that address anticipated needs, benefits, pricing, and delivery timelines.

[0548] Step 7:

[0549] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0550] Step 8:

[0551] Users review the proposal content and make edits such as changing specific wording or inserting additional information. For example, they may customize it to suit the customer's characteristics or make minor adjustments.

[0552] Step 9:

[0553] The user reviews the completed proposal and sends it to the client. This process ensures that the client receives a quick and appropriate proposal.

[0554] (Example 1)

[0555] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0556] In corporate sales, predicting customers' future needs and proposing the most suitable products and services based on those needs requires collecting and analyzing a large amount of information. However, this takes a tremendous amount of time and effort, hindering efficient sales activities. Furthermore, proposal writing is often done manually, leading to problems such as errors and wasted time. To solve these problems, there is a need for highly accurate customer needs prediction and automated proposal generation that requires minimal effort.

[0557] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0558] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training the acquired data using a machine learning model and performing missing value imputation and outlier removal; and means for predicting future customer needs using the trained machine learning model. This enables efficient and highly accurate prediction of customer needs and automatic generation of proposals.

[0559] "Corporate sales customer information" refers to data about customers in corporate sales, including information such as the name of the customer company, industry, address, contact information, and transaction history.

[0560] "Order history data" refers to data related to past transactions, including information such as order date, order details, order amount, name of the ordering company, delivery date, and payment status.

[0561] A "machine learning model" is an algorithm that learns from data and refers to a system that makes predictions and classifications by finding specific patterns or rules.

[0562] "Missing value imputation" is the process of filling in missing values ​​in data, and is performed to improve data consistency and analytical accuracy.

[0563] "Outlier removal" is the process of detecting and removing abnormal or extreme values ​​from data, and is performed to improve the reliability of the analysis results.

[0564] "Future customer needs" refer to predictions of the products and services that customers will need in the future, derived from past customer behavior and market trends.

[0565] An "optimal product or service" is one that best meets anticipated customer needs and exceeds customer expectations.

[0566] A "proposal" is a document that summarizes the content of a proposal to a customer, and includes details, pricing, delivery dates, and characteristics of the products or services to be offered.

[0567] "User terminal" refers to a device such as a computer, tablet, or smartphone used by a user, and is used when viewing and editing information on the system.

[0568] Modes for carrying out the invention

[0569] This invention is a system for efficiently predicting customer needs and creating proposals for corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[0570] First, the server retrieves customer information and order history data for corporate sales. This data is collected from a database (e.g., MySQL or PostgreSQL). The collected data includes the customer company's name, industry, address, contact information, and transaction history. This data is stored in the database and used for subsequent processing.

[0571] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values. For example, it uses df.fillna(method='ffill') to impute missing values ​​in the data. It also uses Z-scores to remove outliers. This is a method for detecting and removing outliers, such as df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[0572] The server feeds preprocessed data into a machine learning model and trains the model. This process uses algorithms such as Random Forest and Deep Learning (e.g., Scikit-learn or TensorFlow). For example, it trains the model using code like `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`, and then saves the trained model.

[0573] Next, the server uses the trained model to predict the customer's future needs based on the new data. For example, it might predict that customer company A is likely to install a new production line in the next quarter, using a method like model.predict(new_data).

[0574] Based on predicted needs, the server selects the most suitable products and services from the company's solution database. This is done using SQL queries such as SELECT FROM solutions WHERE need = 'new_production_line'. Furthermore, detailed data such as price, delivery time, and characteristics are added. For example, this might involve processing `solution_data['price'] = get_price('product_x')`.

[0575] The server then automatically generates a proposal document containing the selected products and services. This process uses the Python Jinja2 template engine. The proposal document is created by rendering the template using methods such as `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[0576] The generated proposal will be created in the following format:

[0577] Proposal: Solution Proposal for Company A's New Production Line

[0578] 1. Background and Objectives

[0579] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0580] 2. Proposed Solutions

[0581] Production equipment X: This latest model features high efficiency and low energy consumption.

[0582] Price: \XXXXXXX

[0583] Delivery time: Approximately 2 months

[0584] Production management software Y: It includes real-time data management and analysis functions.

[0585] Price: \XXXXXX

[0586] Delivery time: Approximately 1 month

[0587] 3. Superiority

[0588] High production efficiency and low operating costs are possible.

[0589] We also provide comprehensive support after implementation.

[0590] 4. Next Steps

[0591] Please contact us if you have any questions or concerns.

[0592] We will schedule a meeting for a more detailed discussion.

[0593] The generated proposal is sent from the server to the user's terminal. The user can review it on their terminal and modify specific wording or insert additional information. A PDF editor (e.g., Adobe Acrobat) is used for editing. Finally, the user sends the edited proposal to the customer. For example, they might send it to the customer using `send_to_customer('final_proposal.pdf')`.

[0594] As a concrete example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model. By using this system, it is possible to improve the efficiency of corporate sales and enhance customer satisfaction.

[0595] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0596] System program processing flow

[0597] Step 1: Data acquisition and preprocessing

[0598] The server retrieves customer information and order history data for corporate sales from the database. The input is a database query, and the output is the collected raw data.

[0599] Specific operation: The server executes SQL queries such as "SELECT FROM customer_data" and "SELECT FROM sales_data" to retrieve data from the database.

[0600] The server preprocesses the acquired raw data. This includes imputing missing values ​​and removing outliers. The input is the acquired raw data, and the output is the preprocessed data.

[0601] Specific operation: Missing values ​​are imputed using df.fillna(method='ffill'), and outliers are removed by applying the Z-score and processing it as follows: df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[0602] Step 2: Training the machine learning model

[0603] The server trains a machine learning model using preprocessed data. The input is the preprocessed data, and the output is the trained model.

[0604] Specific operation: The server uses the Scikit-learn Random Forest algorithm and trains the model using `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`.

[0605] After training, the server saves the trained model. The input is the trained model, and the output is the saved model file.

[0606] Specific operation: Save the model to a file like this: model.save('model.pkl').

[0607] Step 3: Predicting Customer Needs

[0608] The server uses a trained model to predict future customer needs based on new data. The input is new customer data and the trained model, and the output is the predicted customer needs.

[0609] Specific operation: Predicts input data like model.predict(new_data).

[0610] Step 4: Solution Matching

[0611] The server selects the most suitable products and services from the company's solution database based on predicted needs. The input is the predicted needs, and the output is information on the selected products and services.

[0612] Specific operation: The server executes an SQL query like "SELECT FROM solutions WHERE need = 'predicted_need'" to select the appropriate solution.

[0613] The server adds detailed data such as price, delivery time, and characteristics to the information of the selected products and services. The input is the selected solution information, and the output is the solution information with the added detailed data.

[0614] Specific operation: Additional information is retrieved like this: solution_data['price'] = get_price('product_x').

[0615] Step 5: Proposal Generation

[0616] The server automatically generates a proposal based on the selected product or service information. The input is solution information with detailed data attached, and the output is the generated proposal.

[0617] Specific operation: Using Python's Jinja2 template engine, a proposal is generated using `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[0618] Step 6: Review and edit the proposal

[0619] The server sends the generated proposal to the user's terminal. The input is the generated proposal, and the output is the proposal sent to the user's terminal.

[0620] Specific operation: Send a file like this: send_to_user('proposal.pdf').

[0621] The user reviews the proposal on their device and edits it as needed. The input is the submitted proposal, and the output is the edited proposal.

[0622] Specific operation: The user edits the proposal using a PDF editor such as Adobe Acrobat.

[0623] The user sends the edited proposal to the client. The input is the edited proposal, and the output is the proposal sent to the client.

[0624] Specific action: Send the proposal using a method like send_to_customer('final_proposal.pdf').

[0625] Through the steps outlined above, this system aims to improve the efficiency of corporate sales and enhance customer satisfaction. For example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model.

[0626] (Application Example 1)

[0627] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0628] The challenge is to provide a system that can accurately predict customer purchasing needs in physical stores and make effective suggestions. Furthermore, the challenge is to enable store staff to quickly and accurately suggest the most suitable products to customers.

[0629] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0630] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal including the selected product or service; means for enabling the proposal to be viewed and edited on a user terminal; means for collecting purchase history and behavioral data of customers visiting physical stores in real time; and means for suggesting the optimal product to store staff at physical stores. As a result, it becomes possible to predict customer needs in real time and make accurate product suggestions in physical stores, just as in corporate sales.

[0631] "Corporate sales" refers to all sales activities that target companies and organizations as customers.

[0632] "Customer information" refers to all data related to a customer, such as transaction history and purchasing patterns.

[0633] "Order history data" refers to data that includes detailed information and transaction history of products that have been ordered in the past.

[0634] A "machine learning model" refers to an algorithm that learns patterns and makes predictions based on a large amount of data.

[0635] "Customer needs" refer to the demands for goods and services that customers currently and in the future require.

[0636] "Products or services" refers to all specific goods and services provided to customers.

[0637] A "proposal" refers to a document that details the products or services offered to a customer.

[0638] A "user terminal" refers to a digital device used by a user to receive and edit information.

[0639] A "physical store" refers to a physical store where customers can go in person to purchase goods or services.

[0640] "Purchase history" refers to a record of products and services that a customer has purchased in the past.

[0641] "Behavioral data" refers to data about customers' actions and behavioral patterns when they visit a store.

[0642] "Store staff" refers to employees who handle customer service and product recommendations in a physical store.

[0643] "Real-time" refers to information processing and data collection occurring almost instantaneously.

[0644] This invention provides a system for predicting customer needs in corporate sales and physical stores and automatically generating optimal proposals. The system is primarily implemented through the collaboration of a server, terminals, and users.

[0645] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. The server then preprocesses the collected data, including imputing missing values ​​and removing outliers. The preprocessed data is fed into a machine learning model for training. Machine learning models such as random forests and deep learning are used. The trained model is then used to predict the future needs of corporate sales customers.

[0646] Next, the server selects the most suitable products and services based on the predicted needs. This selection is done by searching the company's internal solution database for information on appropriate products and services, and adding detailed data such as price, delivery time, and characteristics. The server then automatically generates a proposal based on this information. This generated proposal is sent from the server to the user's terminal, where the user can review and edit it. For example, they can change specific wording or insert additional information.

[0647] In physical stores, the system collects purchase history and behavioral data in real time when customers visit. The server uses this data to train machine learning models and predict customer needs in the physical store. Store staff are provided with user terminals where they can review and edit optimal product and service recommendations and provide them to customers. This entire process is performed using software tools such as Python, Flask, scikit-learn, and Pandas.

[0648] As a concrete example, if a customer visits a physical store and has previously purchased "Product A," "Product B," and "Product C" based on their past purchase history, the server can suggest "Product D" on their next visit. It is also possible to add a "5% discount" offer to the suggestion. An example of a specific prompt message is as follows:

[0649] Target customer: Mr. / Ms. Tanaka

[0650] Purchase history: ["Product A", "Product B", "Product C"]

[0651] Behavior pattern: Visits the store on weekday afternoons.

[0652] Question:

[0653] Please generate product recommendations for the customer's next visit.

[0654] This system improves the accuracy of predicting customer needs in both physical stores and corporate sales, enabling more effective proposals. This, in turn, leads to increased customer satisfaction and maximized sales efficiency.

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

[0656] Step 1:

[0657] The server retrieves customer information and order history data for corporate sales. This includes basic customer information, past transaction history, and data on purchased products and services. This data is stored in a database for use in subsequent processing.

[0658] Input: Customer information, order history data

[0659] Data processing: Storage in a database

[0660] Output: Data stored in the database

[0661] Step 2:

[0662] The server preprocesses the acquired data. This preprocessing includes imputing missing values ​​and removing outliers. This step prepares the data so that machine learning models can learn efficiently.

[0663] Input: Raw data stored in the database

[0664] Data processing: Missing value imputation, outlier removal

[0665] Output: Preprocessed data

[0666] Step 3:

[0667] The server trains machine learning models using pre-processed data. For example, it uses algorithms such as random forests or deep learning to build models that predict future customer needs.

[0668] Input: Preprocessed data

[0669] Data processing: Training machine learning models

[0670] Output: Trained model

[0671] Step 4:

[0672] The server uses a trained model to predict customer needs. Based on these predictions, it lists the products and services that customers are most likely to purchase next.

[0673] Input: Trained model, customer data

[0674] Data processing: Needs prediction

[0675] Output: Predicted needs list

[0676] Step 5:

[0677] The server selects the optimal products and services based on anticipated needs. This selection process utilizes an internal solution database, supplemented with detailed data such as price, delivery time, and characteristics.

[0678] Input: Predicted needs list, solution database

[0679] Data processing: Product / service selection and addition of detailed data.

[0680] Output: Optimal product / service list

[0681] Step 6:

[0682] The server automatically generates a proposal based on the selected products and services. The generated proposal includes detailed information such as price, delivery date, and characteristics.

[0683] Input: List of optimal products and services

[0684] Data processing: Automated generation of proposals

[0685] Output: Proposal

[0686] Step 7:

[0687] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0688] Input: Proposal

[0689] Data processing: Sending proposals

[0690] Output: Proposal viewable on the user's terminal

[0691] Step 8:

[0692] In physical stores, the server collects the purchase history and behavioral data of visiting customers in real time. Based on this data, the server uses machine learning models to predict the customer's next purchasing behavior.

[0693] Input: Real-time purchase history and behavioral data

[0694] Data processing: Real-time data collection and analysis

[0695] Output: Predicted customer purchasing trends

[0696] Step 9:

[0697] In physical stores, store staff use user terminals to provide optimal product recommendations. These recommendations are automatically generated by the system, and staff then customize them before presenting them to customers.

[0698] Input: Predicted purchasing trends, generated proposals

[0699] Data processing: Customization and presentation of proposals

[0700] Output: Customized proposal

[0701] Therefore, this system enables efficient and effective prediction and proposal of customer needs in corporate sales and physical stores through a series of steps.

[0702] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0703] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[0704] First, the server retrieves customer information and order history data for corporate sales from the database. This data is stored in the database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[0705] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[0706] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[0707] Furthermore, the generated proposal can be modified based on the user's emotions through the emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. The emotional information recognized by the emotion engine is used for selecting proposal templates and dynamically modifying the content of the proposal. For example, if the user is feeling stressed, the emotion engine will detect this and help modify the proposal content to be more concise and intuitive.

[0708] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. The emotion engine recognizes the user's emotions and can further adjust the proposal during the editing process.

[0709] Specific example

[0710] 1. Data Collection and Learning Phase

[0711] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[0712] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[0713] 2. Needs Prediction Phase

[0714] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[0715] 3. Solution Matching Phase

[0716] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[0717] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[0718] 4. Proposal Generation Phase

[0719] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[0720] Proposal: Solution Proposal for Company A's New Production Line

[0721] 1. Background and Objectives

[0722] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0723] 2. Proposed Solutions

[0724] Production equipment X: This latest model features high efficiency and low energy consumption.

[0725] Price: \XXXXXXX

[0726] Delivery time: Approximately 2 months

[0727] Production management software Y: It includes real-time data management and analysis functions.

[0728] Price: \XXXXXX

[0729] Delivery time: Approximately 1 month

[0730] 3. Superiority

[0731] High production efficiency and low operating costs are possible.

[0732] We also provide comprehensive support after implementation.

[0733] 4. Next Steps

[0734] Please contact us if you have any questions or concerns.

[0735] We will schedule a meeting for a more detailed discussion.

[0736] 5. Proposal Review and Editing Phase

[0737] The server sends the generated proposal to the user's terminal. The user reviews the proposal on their terminal and modifies the content based on the emotional information recognized by the emotion engine.

[0738] For example, if the emotion engine detects that a user is experiencing stress, it will suggest modifying the proposal to make it more concise and intuitive.

[0739] 6. Final confirmation and transmission phase

[0740] The user reviews the final edited proposal and sends it to the client. This process ensures that the proposal is delivered quickly and appropriately, taking into account the user's emotional state.

[0741] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0742] The following describes the processing flow.

[0743] Step 1:

[0744] The server retrieves customer information and order history data for corporate sales from the database. This includes company name, industry, past transaction history, transaction amount, and details of purchased products and services.

[0745] Step 2:

[0746] The server preprocesses the acquired data. Specifically, it cleans the data, including imputing missing values ​​and removing outliers. For example, if there is missing data for a particular company, it will fill it in using other data.

[0747] Step 3:

[0748] The server feeds pre-processed data into a machine learning model and trains it. Algorithms used include random forests and deep learning. This allows the model to learn customer purchasing patterns and trends.

[0749] Step 4:

[0750] The server uses a trained machine learning model to predict future customer needs. For example, it might predict that a particular customer is likely to add a new production line in the next quarter.

[0751] Step 5:

[0752] The server selects the optimal products and services based on anticipated needs. The server searches and selects appropriate products and services from the company's internal solution database. The search results include detailed data such as price, delivery time, and characteristics of the products and services.

[0753] Step 6:

[0754] The server automatically generates a proposal based on the information of the selected products and services. The proposal includes details of the products and services that can be supplied, their benefits, pricing, and delivery dates.

[0755] Step 7:

[0756] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[0757] Step 8:

[0758] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. This allows the system to understand the user's emotional state while they are editing the proposal.

[0759] Step 9:

[0760] The server receives emotional information recognized by the emotion engine and dynamically changes the proposal template selection and content suggestions. For example, if the user is feeling stressed, the server will make the proposal concise and easy to understand.

[0761] Step 10:

[0762] Users review the proposal content and make edits, such as changing specific wording or inserting additional information. They also refer to revision suggestions provided by the sentiment engine.

[0763] Step 11:

[0764] The user reviews the finalized proposal and sends it to the client. At this stage, the proposal takes the user's emotional state into consideration.

[0765] Through the processing steps described above, it becomes possible to accurately predict the customer needs of corporate sales and provide optimal proposals that reflect the user's emotional state using the emotion engine.

[0766] (Example 2)

[0767] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0768] In corporate sales, there is a problem in efficiently predicting customer needs and creating proposals. Furthermore, creating proposals without considering the user's emotional state can result in inadequate solutions. This hinders improvements in the efficiency and accuracy of sales activities, as well as in customer satisfaction.

[0769] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring corporate sales customer information and order performance data, means for preprocessing the acquired data, means for training a machine learning model on the preprocessed data, means for predicting future customer needs using the trained machine learning model, means for selecting the optimal product or service based on the predicted needs, means for automatically generating a proposal document including the selected product or service, means for allowing the proposal document to be viewed and edited on a user terminal, and means for analyzing the user's emotions and adjusting the content of the proposal document based on the user's emotions. This makes it possible to accurately predict corporate sales customer needs and automatically generate an optimal proposal that takes into account the user's emotional state.

[0770] "Corporate sales" refers to sales activities targeting corporations (companies), primarily involving the provision and sale of products and services in business-to-business transactions.

[0771] "Customer information" refers to data about customers held by a company, including, for example, customer names, addresses, contact information, transaction history, and purchase history.

[0772] "Order history data" refers to data on orders a company has received to date, and specifically includes information such as order quantity, amount, date, and customer name.

[0773] "Preprocessing" refers to the process of preparing data to be suitable for machine learning models, and includes, for example, imputing missing values, removing outliers, and normalizing data.

[0774] A "machine learning model" is a model that learns from data and uses the results of that learning to make predictions and classifications on new data. Examples of algorithms include random forests and deep learning.

[0775] "Needs forecasting" refers to using historical data and machine learning models to predict future customer demands and the products and services they will need.

[0776] "Product or service selection" refers to choosing the appropriate product or service based on anticipated customer needs.

[0777] "Automatic proposal generation" refers to the automatic creation of proposals based on information about selected products and services.

[0778] "Emotion analysis" refers to a technology that analyzes a user's voice tone, facial expressions, and typing speed to recognize their emotions.

[0779] "Means of enabling editing" refers to functions or methods that allow users to view the generated proposal on their device and make changes or corrections.

[0780] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[0781] System Configuration

[0782] First, the server retrieves customer information and order history data for corporate sales from the database. This data includes, for example, the customer's name, previous purchase history, and transaction amount. The data retrieved by the server is stored in the database and used for subsequent processing.

[0783] Next, the server preprocesses the collected data. Preprocessing includes imputing missing values ​​and removing outliers. For example, the Python library "pandas" is used to clean the data. Commands such as "fillna" and "dropna" are used in the "pandas" library.

[0784] Machine learning models

[0785] The server feeds pre-processed data into a machine learning model and trains it. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. The trained model is then used to predict the future needs of corporate sales customers. Specifically, it utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[0786] Needs forecasting

[0787] Next, the server uses the trained model to predict the future needs of customer companies. For example, based on corporate sales data, it might predict that customer company A may install a new production line in the next quarter.

[0788] Solution Selection

[0789] The server selects the optimal products and services based on predicted needs. It searches the company's solution database for information on suitable products and services and adds detailed data such as price, delivery time, and characteristics. For example, it might use an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[0790] Automatic proposal generation

[0791] The server automatically generates a proposal based on the collected data. This process involves using a template to fill in information about the selected products and services. The generated proposal will look like this:

[0792] Proposal: Solution Proposal for Company A's New Production Line

[0793] 1. Background and Objectives

[0794] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0795] 2. Proposed Solutions

[0796] Production equipment X: This latest model features high efficiency and low energy consumption.

[0797] Price: ¥100,000

[0798] Delivery time: Approximately 2 months

[0799] Production management software Y: It includes real-time data management and analysis functions.

[0800] Price: ¥50,000

[0801] Delivery time: Approximately 1 month

[0802] 3. Superiority

[0803] High production efficiency and low operating costs are possible.

[0804] We also provide comprehensive support after implementation.

[0805] 4. Next Steps

[0806] Please contact us if you have any questions or concerns.

[0807] We will schedule a meeting for a more detailed discussion.

[0808] Utilizing the Emotion Engine

[0809] Furthermore, the proposal can be modified based on the user's emotions through an emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. Based on this emotional information, it dynamically selects a proposal template and modifies the content of the proposal.

[0810] Review and edit the proposal.

[0811] The generated proposal is sent from the server to the user's terminal, where the user can review and edit it as needed. Users can change specific expressions, insert additional information, and perform other operations. The emotion engine further supports the editing process, adjusting the proposal content according to the user's emotional state.

[0812] Final confirmation and submission

[0813] The user reviews the final edited proposal and sends it to the client. This ensures that the proposal is delivered quickly and appropriately, taking the user's emotional state into consideration.

[0814] Example of a prompt

[0815] An example of a prompt message is: "Predict the production equipment and software that client company A may need in the next quarter, and generate an optimal proposal based on that data."

[0816] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0817] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0818] Program processing steps

[0819] Step 1: Data Collection

[0820] Server operation:

[0821] The server retrieves corporate sales customer information and order history data from the database. Specifically, it extracts the necessary data using SQL queries. For example, it executes a command such as "SELECT FROM customer_information WHERE period = 'past 1 year'".

[0822] Input: Database

[0823] Output: Customer information and order history data

[0824] Step 2: Data Preprocessing

[0825] Server operation:

[0826] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values ​​(e.g., imputing with the median) and removing outliers (e.g., removing outliers using the 3σ rule). The data is cleaned using the Python "pandas" library. Commands such as "fillna" and "dropna" from "pandas" are used.

[0827] Input: Retrieved data

[0828] Output: Preprocessed data

[0829] Step 3: Training the machine learning model

[0830] Server operation:

[0831] The server trains machine learning models using preprocessed data. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. It utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[0832] Input: Preprocessed data

[0833] Output: Trained model

[0834] Step 4: Needs Prediction

[0835] Server operation:

[0836] The server uses a trained model to predict the future needs of customer companies. For example, it runs "model.predict(new input data)" to predict the likelihood that customer company A will install a new production line.

[0837] Input: Trained model, customer information

[0838] Output: Predicted needs

[0839] Step 5: Solution Selection

[0840] Server operation:

[0841] The server selects the optimal product or service based on the predicted needs. It searches the company's solution database for information on the relevant product or service and collects detailed data such as price, delivery time, and characteristics. It uses an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[0842] Input: Predicted needs, solution database

[0843] Output: Information on the best products and services

[0844] Step 6: Automatic proposal generation

[0845] Server operation:

[0846] The server automatically generates proposals based on the collected data. This process involves using templates to fill in information about the selected products and services. Specifically, the proposal is generated in the following format:

[0847] Proposal: Solution Proposal for Company A's New Production Line

[0848] 1. Background and Objectives

[0849] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0850] 2. Proposed Solutions

[0851] Production equipment X: This latest model features high efficiency and low energy consumption.

[0852] Price: ¥100,000

[0853] Delivery time: Approximately 2 months

[0854] Production management software Y: It includes real-time data management and analysis functions.

[0855] Price: ¥50,000

[0856] Delivery time: Approximately 1 month

[0857] 3. Superiority

[0858] High production efficiency and low operating costs are possible.

[0859] We also provide comprehensive support after implementation.

[0860] 4. Next Steps

[0861] Please contact us if you have any questions or concerns.

[0862] We will schedule a meeting for a more detailed discussion.

[0863] Input: Information on the best products and services

[0864] Output: Automated proposal

[0865] Step 7: Correction by the emotion engine

[0866] How the emotion engine works:

[0867] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. For example, it uses data from the camera, microphone, and keyboard input speed. If the user is stressed, the emotion engine will modify the proposal content in a concise and intuitive manner.

[0868] Input: Proposal, user sentiment data

[0869] Output: Proposal revised based on emotions

[0870] Step 8: Review and edit the proposal

[0871] Server operation:

[0872] The server sends the generated proposal to the user's terminal.

[0873] User actions:

[0874] Users can view the proposal on their device and edit it as needed. For example, they can change a specific phrase to "Special discount price: ¥90,000".

[0875] Input: Proposal

[0876] Output: Edited proposal

[0877] Step 9: Final confirmation and submission

[0878] User actions:

[0879] The user reviews the completed proposal and sends it to the client. This can be done via email or a dedicated sales support tool.

[0880] Input: Edited proposal

[0881] Output: Proposal sent to the customer

[0882] By utilizing this system, it becomes possible to accurately predict the customer needs of corporate sales representatives and quickly provide optimal proposals that take into account the emotional state of the users.

[0883] (Application Example 2)

[0884] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0885] There is a need to improve the efficiency of predicting customer needs and creating proposals in corporate sales. However, existing systems often provide uniform proposals without considering customer emotions or the specific circumstances, limiting their effectiveness in improving sales results. Furthermore, more advanced data analysis and user interface optimization are necessary to ensure the speed and accuracy of proposals. The goal is to improve the efficiency and customer satisfaction of corporate sales by solving these problems.

[0886] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0887] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal document including the selected product or service; means for enabling the proposal document to be viewed and edited on a user terminal; means for recognizing the user's emotional state; means for dynamically modifying the content of the proposal document based on the emotional state; and means for executing electronic payment. This makes it possible to accurately predict customer needs in corporate sales activities, automatically generate proposal documents that match the user's emotional state, and provide convenient electronic payment.

[0888] "Customer information" refers to various data about customers in corporate sales, and more specifically includes information such as the name, industry, address, contact information, purchase history, and transaction history of the customer company.

[0889] "Order performance data" refers to data detailing transactions that corporate sales have received in the past, and more specifically includes order date, order amount, ordered items, delivery date, name of trading company, and completion status.

[0890] A "machine learning model" refers to a computational model that uses algorithms to make predictions, classifications, and recommendations based on large amounts of data. Specifically, this includes techniques such as random forests and deep learning.

[0891] "Needs forecasting" refers to the process of using machine learning models to predict the products and services that corporate sales customers may need in the future.

[0892] "Product or service selection" refers to the process of choosing the most suitable product or service from multiple options based on anticipated customer needs.

[0893] "Automatic proposal generation" refers to the process of compiling proposal details into a document format for the customer based on the selected product or service, and this document is generated automatically.

[0894] "Emotional state recognition" refers to the technology that analyzes data such as the user's voice tone, facial expressions, and typing speed to determine the user's emotional state.

[0895] "Dynamic modification" refers to the process of changing the content of a proposal in real time based on the recognized emotional state of the user.

[0896] "Electronic payment" refers to the process of paying for goods or services using various online or mobile payment methods.

[0897] The system of this invention is realized through the collaboration of a server, terminal, user, and emotion engine. This system is specifically implemented in the following manner. Various hardware and software are used in this system.

[0898] Data Acquisition and Preprocessing

[0899] The server retrieves customer information and order history data for corporate sales from the database. This data includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. MySQL or PostgreSQL are used as the database management system.

[0900] The server preprocesses the acquired data, including imputing missing values ​​and removing outliers. Data processing libraries such as Python or R (e.g., Pandas, Numpy) are used for data formatting.

[0901] Training machine learning models

[0902] The server uses pre-processed data to train machine learning models. Libraries such as TensorFlow and PyTorch are used for this purpose. The models employ algorithms such as random forests and deep learning.

[0903] Needs forecasting

[0904] The server uses a trained model to predict the customer's future needs. For example, it makes predictions using prompts such as, "Based on customer B's purchase history over the past year, predict what they are likely to buy next."

[0905] Solution matching and proposal creation

[0906] The server automatically selects the most suitable products and services based on predicted needs and generates a proposal that includes detailed data such as price, delivery time, and characteristics. Solution matching is performed by referencing the company's internal solution database, and a natural language generation model (e.g., GPT-3) is used to generate the proposal.

[0907] Recognizing emotional states and revising proposals

[0908] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and typing speed to recognize the user's emotional state. The emotion engine used may include Azure Emotion API or IBM Watson Emotion Analysis. Based on the recognized emotional state, the content of the proposal is dynamically modified. Specifically, when the user is feeling stressed, a prompt such as "Please make the proposal more concise and intuitive" is displayed.

[0909] Review and editing of the proposal

[0910] Users review and edit proposals generated on their devices. Mobile applications using React Native or Flutter are suitable for this purpose. After editing, users make final checks on the proposal and send it to the client.

[0911] Electronic payment

[0912] After final confirmation of the proposal, electronic payment can be made with a single touch using a terminal. Online payment services such as PayPal and Stripe are used for electronic payments. This system accurately predicts customer needs in corporate sales activities, automatically generates proposals that match the user's emotions, and provides convenient electronic payment.

[0913] Specific example

[0914] For example, the server predicts what customer B is likely to buy next based on their purchase history over the past year. Based on the prediction, it selects appropriate products and services and generates a proposal. Furthermore, when the user reviews the proposal, if the emotion engine detects that they are experiencing stress, it prompts them to "make the proposal more concise and intuitive" and revise the content. After final confirmation, the user can then make an electronic payment to purchase the product with a single touch.

[0915] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0916] Step 1:

[0917] Data collection

[0918] The server retrieves customer information and order history data for corporate sales from a database. This includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. The database management system used is MySQL or PostgreSQL. Database queries are executed as input to extract the necessary data. The extracted dataset is obtained as output.

[0919] Step 2:

[0920] Data preprocessing

[0921] The server preprocesses the retrieved data. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. It uses Python's Pandas and NumPy libraries to format the data. The dataset extracted in the previous step is used as input. The output is the preprocessed dataset.

[0922] Step 3:

[0923] Training machine learning models

[0924] The server trains a machine learning model using preprocessed data. The libraries used are TensorFlow and PyTorch, and the models employ algorithms such as random forests and deep learning. The input is the preprocessed dataset obtained in the previous step. The output is a trained machine learning model.

[0925] Step 4:

[0926] Needs forecasting

[0927] The server uses a trained model to predict the customer's future needs. The prompt is "Predict what customer B is likely to purchase next, based on their purchase history over the past year." The input is the current customer data and the prompt. The output is the predicted needs (the products or services the customer is likely to purchase next).

[0928] Step 5:

[0929] Solution Matching

[0930] The server selects the optimal product or service based on predicted needs, adding detailed data such as price, delivery time, and characteristics. Predicted needs and the company's internal solutions database are used as input. The output provides detailed information about the selected product or service.

[0931] Step 6:

[0932] Automatic generation of proposals

[0933] The server automatically generates proposals based on information about the selected products and services. It uses a natural language generation model (e.g., GPT-3). Detailed information about the selected products and services is used as input. The output is an automatically generated proposal.

[0934] Step 7:

[0935] Recognition of emotional states

[0936] The device analyzes the user's voice tone, facial expressions, and typing speed using an emotion engine (e.g., Azure Emotion API, IBM Watson Emotion Analysis) to recognize the user's emotional state. Real-time user data is used as input. The user's emotional state is obtained as output.

[0937] Step 8:

[0938] Dynamic editing of proposals

[0939] The proposal content is dynamically modified based on the emotional state recognized by the emotion engine. Specifically, if the user is stressed, a prompt message such as "Please make the proposal content more concise and intuitive" is used. The emotional state and the existing proposal are used as input. The modified proposal is obtained as output.

[0940] Step 9:

[0941] Proposal review and electronic payment

[0942] The user reviews and edits the proposal generated on the terminal and makes a final confirmation. Afterward, they execute electronic payment with a single touch. The user's edited proposal and electronic payment request are used as input. The output is the edited proposal and confirmation of the completed payment.

[0943] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0944] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0945] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0946] [Third Embodiment]

[0947] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0948] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0949] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0950] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0951] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0952] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0953] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0954] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0955] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0956] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0957] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0958] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0959] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[0960] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[0961] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[0962] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[0963] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. Finally, the user sends the completed proposal to the client.

[0964] Specific example

[0965] 1. Data Collection and Learning Phase

[0966] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[0967] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[0968] 2. Needs Prediction Phase

[0969] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[0970] 3. Solution Matching Phase

[0971] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[0972] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[0973] 4. Proposal Generation Phase

[0974] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[0975] Proposal: Solution Proposal for Company A's New Production Line

[0976] 1. Background and Objectives

[0977] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[0978] 2. Proposed Solutions

[0979] Production equipment X: This latest model features high efficiency and low energy consumption.

[0980] Price: \XXXXXXX

[0981] Delivery time: Approximately 2 months

[0982] Production management software Y: It includes real-time data management and analysis functions.

[0983] Price: \XXXXXX

[0984] Delivery time: Approximately 1 month

[0985] 3. Superiority

[0986] High production efficiency and low operating costs are possible.

[0987] We also provide comprehensive support after implementation.

[0988] 4. Next Steps

[0989] Please contact us if you have any questions or concerns.

[0990] We will schedule a meeting for a more detailed discussion.

[0991] 5. User Review and Editing Phase

[0992] Users can review this proposal on their devices, modify specific wording, and insert additional information.

[0993] Finally, the edited proposal is sent to company A.

[0994] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate proposals that are optimally suited to those needs. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[0995] The following describes the processing flow.

[0996] Step 1:

[0997] The server retrieves customer information and order history data for corporate sales from the database. Customer information includes company name, industry, and past transaction history, while order history data includes transaction amount and details of purchased products and services.

[0998] Step 2:

[0999] The server preprocesses the retrieved data. This preprocessing includes cleaning the data, imputing missing values, and removing outliers. For example, it may fill in incomplete transaction information and remove illogical numbers.

[1000] Step 3:

[1001] The server feeds pre-processed data into a machine learning model and trains it. Specifically, it uses random forests and deep learning algorithms to learn customers' past purchasing patterns.

[1002] Step 4:

[1003] The server uses a trained machine learning model to predict the future needs of corporate sales customers. For example, it might predict that a particular customer may install a new production line in the next quarter.

[1004] Step 5:

[1005] The server selects the optimal products and services based on anticipated needs. This process involves searching the company's internal solution database for suitable products and services and gathering detailed data such as price, delivery time, and characteristics.

[1006] Step 6:

[1007] The server automatically generates a proposal using information on the selected products and services. The proposal includes details of specific solutions that address anticipated needs, benefits, pricing, and delivery timelines.

[1008] Step 7:

[1009] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1010] Step 8:

[1011] Users review the proposal content and make edits such as changing specific wording or inserting additional information. For example, they may customize it to suit the customer's characteristics or make minor adjustments.

[1012] Step 9:

[1013] The user reviews the completed proposal and sends it to the client. This process ensures that the client receives a quick and appropriate proposal.

[1014] (Example 1)

[1015] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1016] In corporate sales, predicting customers' future needs and proposing the most suitable products and services based on those needs requires collecting and analyzing a large amount of information. However, this takes a tremendous amount of time and effort, hindering efficient sales activities. Furthermore, proposal writing is often done manually, leading to problems such as errors and wasted time. To solve these problems, there is a need for highly accurate customer needs prediction and automated proposal generation that requires minimal effort.

[1017] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1018] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training the acquired data using a machine learning model and performing missing value imputation and outlier removal; and means for predicting future customer needs using the trained machine learning model. This enables efficient and highly accurate prediction of customer needs and automatic generation of proposals.

[1019] "Corporate sales customer information" refers to data about customers in corporate sales, including information such as the name of the customer company, industry, address, contact information, and transaction history.

[1020] "Order history data" refers to data related to past transactions, including information such as order date, order details, order amount, name of the ordering company, delivery date, and payment status.

[1021] A "machine learning model" is an algorithm that learns from data and refers to a system that makes predictions and classifications by finding specific patterns or rules.

[1022] "Missing value imputation" is the process of filling in missing values ​​in data, and is performed to improve data consistency and analytical accuracy.

[1023] "Outlier removal" is the process of detecting and removing abnormal or extreme values ​​from data, and is performed to improve the reliability of the analysis results.

[1024] "Future customer needs" refer to predictions of the products and services that customers will need in the future, derived from past customer behavior and market trends.

[1025] An "optimal product or service" is one that best meets anticipated customer needs and exceeds customer expectations.

[1026] A "proposal" is a document that summarizes the content of a proposal to a customer, and includes details, pricing, delivery dates, and characteristics of the products or services to be offered.

[1027] "User terminal" refers to a device such as a computer, tablet, or smartphone used by a user, and is used when viewing and editing information on the system.

[1028] Modes for carrying out the invention

[1029] This invention is a system for efficiently predicting customer needs and creating proposals for corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[1030] First, the server retrieves customer information and order history data for corporate sales. This data is collected from a database (e.g., MySQL or PostgreSQL). The collected data includes the customer company's name, industry, address, contact information, and transaction history. This data is stored in the database and used for subsequent processing.

[1031] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values. For example, it uses df.fillna(method='ffill') to impute missing values ​​in the data. It also uses Z-scores to remove outliers. This is a method for detecting and removing outliers, such as df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[1032] The server feeds preprocessed data into a machine learning model and trains the model. This process uses algorithms such as Random Forest and Deep Learning (e.g., Scikit-learn or TensorFlow). For example, it trains the model using code like `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`, and then saves the trained model.

[1033] Next, the server uses the trained model to predict the customer's future needs based on the new data. For example, it might predict that customer company A is likely to install a new production line in the next quarter, using a method like model.predict(new_data).

[1034] Based on predicted needs, the server selects the most suitable products and services from the company's solution database. This is done using SQL queries such as SELECT FROM solutions WHERE need = 'new_production_line'. Furthermore, detailed data such as price, delivery time, and characteristics are added. For example, this might involve processing `solution_data['price'] = get_price('product_x')`.

[1035] The server then automatically generates a proposal document containing the selected products and services. This process uses the Python Jinja2 template engine. The proposal document is created by rendering the template using methods such as `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[1036] The generated proposal will be created in the following format:

[1037] Proposal: Solution Proposal for Company A's New Production Line

[1038] 1. Background and Objectives

[1039] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1040] 2. Proposed Solutions

[1041] Production equipment X: This latest model features high efficiency and low energy consumption.

[1042] Price: \XXXXXXX

[1043] Delivery time: Approximately 2 months

[1044] Production management software Y: It includes real-time data management and analysis functions.

[1045] Price: \XXXXXX

[1046] Delivery time: Approximately 1 month

[1047] 3. Superiority

[1048] High production efficiency and low operating costs are possible.

[1049] We also provide comprehensive support after implementation.

[1050] 4. Next Steps

[1051] Please contact us if you have any questions or concerns.

[1052] We will schedule a meeting for a more detailed discussion.

[1053] The generated proposal is sent from the server to the user's terminal. The user can review it on their terminal and modify specific wording or insert additional information. A PDF editor (e.g., Adobe Acrobat) is used for editing. Finally, the user sends the edited proposal to the customer. For example, they might send it to the customer using `send_to_customer('final_proposal.pdf')`.

[1054] As a concrete example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model. By using this system, it is possible to improve the efficiency of corporate sales and enhance customer satisfaction.

[1055] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1056] System program processing flow

[1057] Step 1: Data acquisition and preprocessing

[1058] The server retrieves customer information and order history data for corporate sales from the database. The input is a database query, and the output is the collected raw data.

[1059] Specific operation: The server executes SQL queries such as "SELECT FROM customer_data" and "SELECT FROM sales_data" to retrieve data from the database.

[1060] The server preprocesses the acquired raw data. This includes imputing missing values ​​and removing outliers. The input is the acquired raw data, and the output is the preprocessed data.

[1061] Specific operation: Missing values ​​are imputed using df.fillna(method='ffill'), and outliers are removed by applying the Z-score and processing it as follows: df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[1062] Step 2: Training the machine learning model

[1063] The server trains a machine learning model using preprocessed data. The input is the preprocessed data, and the output is the trained model.

[1064] Specific operation: The server uses the Scikit-learn Random Forest algorithm and trains the model using `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`.

[1065] After training, the server saves the trained model. The input is the trained model, and the output is the saved model file.

[1066] Specific operation: Save the model to a file like this: model.save('model.pkl').

[1067] Step 3: Predicting Customer Needs

[1068] The server uses a trained model to predict future customer needs based on new data. The input is new customer data and the trained model, and the output is the predicted customer needs.

[1069] Specific operation: Predicts input data like model.predict(new_data).

[1070] Step 4: Solution Matching

[1071] The server selects the most suitable products and services from the company's solution database based on predicted needs. The input is the predicted needs, and the output is information on the selected products and services.

[1072] Specific operation: The server executes an SQL query like "SELECT FROM solutions WHERE need = 'predicted_need'" to select the appropriate solution.

[1073] The server adds detailed data such as price, delivery time, and characteristics to the information of the selected products and services. The input is the selected solution information, and the output is the solution information with the added detailed data.

[1074] Specific operation: Additional information is retrieved like this: solution_data['price'] = get_price('product_x').

[1075] Step 5: Proposal Generation

[1076] The server automatically generates a proposal based on the selected product or service information. The input is solution information with detailed data attached, and the output is the generated proposal.

[1077] Specific operation: Using Python's Jinja2 template engine, a proposal is generated using `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[1078] Step 6: Review and edit the proposal

[1079] The server sends the generated proposal to the user's terminal. The input is the generated proposal, and the output is the proposal sent to the user's terminal.

[1080] Specific operation: Send a file like this: send_to_user('proposal.pdf').

[1081] The user reviews the proposal on their device and edits it as needed. The input is the submitted proposal, and the output is the edited proposal.

[1082] Specific operation: The user edits the proposal using a PDF editor such as Adobe Acrobat.

[1083] The user sends the edited proposal to the client. The input is the edited proposal, and the output is the proposal sent to the client.

[1084] Specific action: Send the proposal using a method like send_to_customer('final_proposal.pdf').

[1085] Through the steps outlined above, this system aims to improve the efficiency of corporate sales and enhance customer satisfaction. For example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model.

[1086] (Application Example 1)

[1087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1088] The challenge is to provide a system that can accurately predict customer purchasing needs in physical stores and make effective suggestions. Furthermore, the challenge is to enable store staff to quickly and accurately suggest the most suitable products to customers.

[1089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1090] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal including the selected product or service; means for enabling the proposal to be viewed and edited on a user terminal; means for collecting purchase history and behavioral data of customers visiting physical stores in real time; and means for suggesting the optimal product to store staff at physical stores. As a result, it becomes possible to predict customer needs in real time and make accurate product suggestions in physical stores, just as in corporate sales.

[1091] "Corporate sales" refers to all sales activities that target companies and organizations as customers.

[1092] "Customer information" refers to all data related to a customer, such as transaction history and purchasing patterns.

[1093] "Order history data" refers to data that includes detailed information and transaction history of products that have been ordered in the past.

[1094] A "machine learning model" refers to an algorithm that learns patterns and makes predictions based on a large amount of data.

[1095] "Customer needs" refer to the demands for goods and services that customers currently and in the future require.

[1096] "Products or services" refers to all specific goods and services provided to customers.

[1097] A "proposal" refers to a document that details the products or services offered to a customer.

[1098] A "user terminal" refers to a digital device used by a user to receive and edit information.

[1099] A "physical store" refers to a physical store where customers can go in person to purchase goods or services.

[1100] "Purchase history" refers to a record of products and services that a customer has purchased in the past.

[1101] "Behavioral data" refers to data about customers' actions and behavioral patterns when they visit a store.

[1102] "Store staff" refers to employees who handle customer service and product recommendations in a physical store.

[1103] "Real-time" refers to information processing and data collection occurring almost instantaneously.

[1104] This invention provides a system for predicting customer needs in corporate sales and physical stores and automatically generating optimal proposals. The system is primarily implemented through the collaboration of a server, terminals, and users.

[1105] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. The server then preprocesses the collected data, including imputing missing values ​​and removing outliers. The preprocessed data is fed into a machine learning model for training. Machine learning models such as random forests and deep learning are used. The trained model is then used to predict the future needs of corporate sales customers.

[1106] Next, the server selects the most suitable products and services based on the predicted needs. This selection is done by searching the company's internal solution database for information on appropriate products and services, and adding detailed data such as price, delivery time, and characteristics. The server then automatically generates a proposal based on this information. This generated proposal is sent from the server to the user's terminal, where the user can review and edit it. For example, they can change specific wording or insert additional information.

[1107] In physical stores, the system collects purchase history and behavioral data in real time when customers visit. The server uses this data to train machine learning models and predict customer needs in the physical store. Store staff are provided with user terminals where they can review and edit optimal product and service recommendations and provide them to customers. This entire process is performed using software tools such as Python, Flask, scikit-learn, and Pandas.

[1108] As a concrete example, if a customer visits a physical store and has previously purchased "Product A," "Product B," and "Product C" based on their past purchase history, the server can suggest "Product D" on their next visit. It is also possible to add a "5% discount" offer to the suggestion. An example of a specific prompt message is as follows:

[1109] Target customer: Mr. / Ms. Tanaka

[1110] Purchase history: ["Product A", "Product B", "Product C"]

[1111] Behavior pattern: Visits the store on weekday afternoons.

[1112] Question:

[1113] Please generate product recommendations for the customer's next visit.

[1114] This system improves the accuracy of predicting customer needs in both physical stores and corporate sales, enabling more effective proposals. This, in turn, leads to increased customer satisfaction and maximized sales efficiency.

[1115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1116] Step 1:

[1117] The server retrieves customer information and order history data for corporate sales. This includes basic customer information, past transaction history, and data on purchased products and services. This data is stored in a database for use in subsequent processing.

[1118] Input: Customer information, order history data

[1119] Data processing: Storage in a database

[1120] Output: Data stored in the database

[1121] Step 2:

[1122] The server preprocesses the acquired data. This preprocessing includes imputing missing values ​​and removing outliers. This step prepares the data so that machine learning models can learn efficiently.

[1123] Input: Raw data stored in the database

[1124] Data processing: Missing value imputation, outlier removal

[1125] Output: Preprocessed data

[1126] Step 3:

[1127] The server trains machine learning models using pre-processed data. For example, it uses algorithms such as random forests or deep learning to build models that predict future customer needs.

[1128] Input: Preprocessed data

[1129] Data processing: Training machine learning models

[1130] Output: Trained model

[1131] Step 4:

[1132] The server uses a trained model to predict customer needs. Based on these predictions, it lists the products and services that customers are most likely to purchase next.

[1133] Input: Trained model, customer data

[1134] Data processing: Needs prediction

[1135] Output: Predicted needs list

[1136] Step 5:

[1137] The server selects the optimal products and services based on anticipated needs. This selection process utilizes an internal solution database, supplemented with detailed data such as price, delivery time, and characteristics.

[1138] Input: Predicted needs list, solution database

[1139] Data processing: Product / service selection and addition of detailed data.

[1140] Output: Optimal product / service list

[1141] Step 6:

[1142] The server automatically generates a proposal based on the selected products and services. The generated proposal includes detailed information such as price, delivery date, and characteristics.

[1143] Input: List of optimal products and services

[1144] Data processing: Automated generation of proposals

[1145] Output: Proposal

[1146] Step 7:

[1147] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1148] Input: Proposal

[1149] Data processing: Sending proposals

[1150] Output: Proposal viewable on the user's terminal

[1151] Step 8:

[1152] In physical stores, the server collects the purchase history and behavioral data of visiting customers in real time. Based on this data, the server uses machine learning models to predict the customer's next purchasing behavior.

[1153] Input: Real-time purchase history and behavioral data

[1154] Data processing: Real-time data collection and analysis

[1155] Output: Predicted customer purchasing trends

[1156] Step 9:

[1157] In physical stores, store staff use user terminals to provide optimal product recommendations. These recommendations are automatically generated by the system, and staff then customize them before presenting them to customers.

[1158] Input: Predicted purchasing trends, generated proposals

[1159] Data processing: Customization and presentation of proposals

[1160] Output: Customized proposal

[1161] Therefore, this system enables efficient and effective prediction and proposal of customer needs in corporate sales and physical stores through a series of steps.

[1162] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1163] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[1164] First, the server retrieves customer information and order history data for corporate sales from the database. This data is stored in the database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[1165] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[1166] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[1167] Furthermore, the generated proposal can be modified based on the user's emotions through the emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. The emotional information recognized by the emotion engine is used for selecting proposal templates and dynamically modifying the content of the proposal. For example, if the user is feeling stressed, the emotion engine will detect this and help modify the proposal content to be more concise and intuitive.

[1168] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. The emotion engine recognizes the user's emotions and can further adjust the proposal during the editing process.

[1169] Specific example

[1170] 1. Data Collection and Learning Phase

[1171] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[1172] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[1173] 2. Needs Prediction Phase

[1174] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[1175] 3. Solution Matching Phase

[1176] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[1177] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[1178] 4. Proposal Generation Phase

[1179] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[1180] Proposal: Solution Proposal for Company A's New Production Line

[1181] 1. Background and Objectives

[1182] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1183] 2. Proposed Solutions

[1184] Production equipment X: This latest model features high efficiency and low energy consumption.

[1185] Price: \XXXXXXX

[1186] Delivery time: Approximately 2 months

[1187] Production management software Y: It includes real-time data management and analysis functions.

[1188] Price: \XXXXXX

[1189] Delivery time: Approximately 1 month

[1190] 3. Superiority

[1191] High production efficiency and low operating costs are possible.

[1192] We also provide comprehensive support after implementation.

[1193] 4. Next Steps

[1194] Please contact us if you have any questions or concerns.

[1195] We will schedule a meeting for a more detailed discussion.

[1196] 5. Proposal Review and Editing Phase

[1197] The server sends the generated proposal to the user's terminal. The user reviews the proposal on their terminal and modifies the content based on the emotional information recognized by the emotion engine.

[1198] For example, if the emotion engine detects that a user is experiencing stress, it will suggest modifying the proposal to make it more concise and intuitive.

[1199] 6. Final confirmation and transmission phase

[1200] The user reviews the final edited proposal and sends it to the client. This process ensures that the proposal is delivered quickly and appropriately, taking into account the user's emotional state.

[1201] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[1202] The following describes the processing flow.

[1203] Step 1:

[1204] The server retrieves customer information and order history data for corporate sales from the database. This includes company name, industry, past transaction history, transaction amount, and details of purchased products and services.

[1205] Step 2:

[1206] The server preprocesses the acquired data. Specifically, it cleans the data, including imputing missing values ​​and removing outliers. For example, if there is missing data for a particular company, it will fill it in using other data.

[1207] Step 3:

[1208] The server feeds pre-processed data into a machine learning model and trains it. Algorithms used include random forests and deep learning. This allows the model to learn customer purchasing patterns and trends.

[1209] Step 4:

[1210] The server uses a trained machine learning model to predict future customer needs. For example, it might predict that a particular customer is likely to add a new production line in the next quarter.

[1211] Step 5:

[1212] The server selects the optimal products and services based on anticipated needs. The server searches and selects appropriate products and services from the company's internal solution database. The search results include detailed data such as price, delivery time, and characteristics of the products and services.

[1213] Step 6:

[1214] The server automatically generates a proposal based on the information of the selected products and services. The proposal includes details of the products and services that can be supplied, their benefits, pricing, and delivery dates.

[1215] Step 7:

[1216] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1217] Step 8:

[1218] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. This allows the system to understand the user's emotional state while they are editing the proposal.

[1219] Step 9:

[1220] The server receives emotional information recognized by the emotion engine and dynamically changes the proposal template selection and content suggestions. For example, if the user is feeling stressed, the server will make the proposal concise and easy to understand.

[1221] Step 10:

[1222] Users review the proposal content and make edits, such as changing specific wording or inserting additional information. They also refer to revision suggestions provided by the sentiment engine.

[1223] Step 11:

[1224] The user reviews the finalized proposal and sends it to the client. At this stage, the proposal takes the user's emotional state into consideration.

[1225] Through the processing steps described above, it becomes possible to accurately predict the customer needs of corporate sales and provide optimal proposals that reflect the user's emotional state using the emotion engine.

[1226] (Example 2)

[1227] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1228] In corporate sales, there is a problem in efficiently predicting customer needs and creating proposals. Furthermore, creating proposals without considering the user's emotional state can result in inadequate solutions. This hinders improvements in the efficiency and accuracy of sales activities, as well as in customer satisfaction.

[1229] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring corporate sales customer information and order performance data, means for preprocessing the acquired data, means for training a machine learning model on the preprocessed data, means for predicting future customer needs using the trained machine learning model, means for selecting the optimal product or service based on the predicted needs, means for automatically generating a proposal document including the selected product or service, means for allowing the proposal document to be viewed and edited on a user terminal, and means for analyzing the user's emotions and adjusting the content of the proposal document based on the user's emotions. This makes it possible to accurately predict corporate sales customer needs and automatically generate an optimal proposal that takes into account the user's emotional state.

[1230] "Corporate sales" refers to sales activities targeting corporations (companies), primarily involving the provision and sale of products and services in business-to-business transactions.

[1231] "Customer information" refers to data about customers held by a company, including, for example, customer names, addresses, contact information, transaction history, and purchase history.

[1232] "Order history data" refers to data on orders a company has received to date, and specifically includes information such as order quantity, amount, date, and customer name.

[1233] "Preprocessing" refers to the process of preparing data to be suitable for machine learning models, and includes, for example, imputing missing values, removing outliers, and normalizing data.

[1234] A "machine learning model" is a model that learns from data and uses the results of that learning to make predictions and classifications on new data. Examples of algorithms include random forests and deep learning.

[1235] "Needs forecasting" refers to using historical data and machine learning models to predict future customer demands and the products and services they will need.

[1236] "Product or service selection" refers to choosing the appropriate product or service based on anticipated customer needs.

[1237] "Automatic proposal generation" refers to the automatic creation of proposals based on information about selected products and services.

[1238] "Emotion analysis" refers to a technology that analyzes a user's voice tone, facial expressions, and typing speed to recognize their emotions.

[1239] "Means of enabling editing" refers to functions or methods that allow users to view the generated proposal on their device and make changes or corrections.

[1240] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[1241] System Configuration

[1242] First, the server retrieves customer information and order history data for corporate sales from the database. This data includes, for example, the customer's name, previous purchase history, and transaction amount. The data retrieved by the server is stored in the database and used for subsequent processing.

[1243] Next, the server preprocesses the collected data. Preprocessing includes imputing missing values ​​and removing outliers. For example, the Python library "pandas" is used to clean the data. Commands such as "fillna" and "dropna" are used in the "pandas" library.

[1244] Machine learning models

[1245] The server feeds pre-processed data into a machine learning model and trains it. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. The trained model is then used to predict the future needs of corporate sales customers. Specifically, it utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[1246] Needs forecasting

[1247] Next, the server uses the trained model to predict the future needs of customer companies. For example, based on corporate sales data, it might predict that customer company A may install a new production line in the next quarter.

[1248] Solution Selection

[1249] The server selects the optimal products and services based on predicted needs. It searches the company's solution database for information on suitable products and services and adds detailed data such as price, delivery time, and characteristics. For example, it might use an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[1250] Automatic proposal generation

[1251] The server automatically generates a proposal based on the collected data. This process involves using a template to fill in information about the selected products and services. The generated proposal will look like this:

[1252] Proposal: Solution Proposal for Company A's New Production Line

[1253] 1. Background and Objectives

[1254] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1255] 2. Proposed Solutions

[1256] Production equipment X: This latest model features high efficiency and low energy consumption.

[1257] Price: ¥100,000

[1258] Delivery time: Approximately 2 months

[1259] Production management software Y: It includes real-time data management and analysis functions.

[1260] Price: ¥50,000

[1261] Delivery time: Approximately 1 month

[1262] 3. Superiority

[1263] High production efficiency and low operating costs are possible.

[1264] We also provide comprehensive support after implementation.

[1265] 4. Next Steps

[1266] Please contact us if you have any questions or concerns.

[1267] We will schedule a meeting for a more detailed discussion.

[1268] Utilizing the Emotion Engine

[1269] Furthermore, the proposal can be modified based on the user's emotions through an emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. Based on this emotional information, it dynamically selects a proposal template and modifies the content of the proposal.

[1270] Review and edit the proposal.

[1271] The generated proposal is sent from the server to the user's terminal, where the user can review and edit it as needed. Users can change specific expressions, insert additional information, and perform other operations. The emotion engine further supports the editing process, adjusting the proposal content according to the user's emotional state.

[1272] Final confirmation and submission

[1273] The user reviews the final edited proposal and sends it to the client. This ensures that the proposal is delivered quickly and appropriately, taking the user's emotional state into consideration.

[1274] Example of a prompt

[1275] An example of a prompt message is: "Predict the production equipment and software that client company A may need in the next quarter, and generate an optimal proposal based on that data."

[1276] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[1277] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1278] Program processing steps

[1279] Step 1: Data Collection

[1280] Server operation:

[1281] The server retrieves corporate sales customer information and order history data from the database. Specifically, it extracts the necessary data using SQL queries. For example, it executes a command such as "SELECT FROM customer_information WHERE period = 'past 1 year'".

[1282] Input: Database

[1283] Output: Customer information and order history data

[1284] Step 2: Data Preprocessing

[1285] Server operation:

[1286] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values ​​(e.g., imputing with the median) and removing outliers (e.g., removing outliers using the 3σ rule). The data is cleaned using the Python "pandas" library. Commands such as "fillna" and "dropna" from "pandas" are used.

[1287] Input: Retrieved data

[1288] Output: Preprocessed data

[1289] Step 3: Training the machine learning model

[1290] Server operation:

[1291] The server trains machine learning models using preprocessed data. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. It utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[1292] Input: Preprocessed data

[1293] Output: Trained model

[1294] Step 4: Needs Prediction

[1295] Server operation:

[1296] The server uses a trained model to predict the future needs of customer companies. For example, it runs "model.predict(new input data)" to predict the likelihood that customer company A will install a new production line.

[1297] Input: Trained model, customer information

[1298] Output: Predicted needs

[1299] Step 5: Solution Selection

[1300] Server operation:

[1301] The server selects the optimal product or service based on the predicted needs. It searches the company's solution database for information on the relevant product or service and collects detailed data such as price, delivery time, and characteristics. It uses an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[1302] Input: Predicted needs, solution database

[1303] Output: Information on the best products and services

[1304] Step 6: Automatic proposal generation

[1305] Server operation:

[1306] The server automatically generates proposals based on the collected data. This process involves using templates to fill in information about the selected products and services. Specifically, the proposal is generated in the following format:

[1307] Proposal: Solution Proposal for Company A's New Production Line

[1308] 1. Background and Objectives

[1309] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1310] 2. Proposed Solutions

[1311] Production equipment X: This latest model features high efficiency and low energy consumption.

[1312] Price: ¥100,000

[1313] Delivery time: Approximately 2 months

[1314] Production management software Y: It includes real-time data management and analysis functions.

[1315] Price: ¥50,000

[1316] Delivery time: Approximately 1 month

[1317] 3. Superiority

[1318] High production efficiency and low operating costs are possible.

[1319] We also provide comprehensive support after implementation.

[1320] 4. Next Steps

[1321] Please contact us if you have any questions or concerns.

[1322] We will schedule a meeting for a more detailed discussion.

[1323] Input: Information on the best products and services

[1324] Output: Automated proposal

[1325] Step 7: Correction by the emotion engine

[1326] How the emotion engine works:

[1327] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. For example, it uses data from the camera, microphone, and keyboard input speed. If the user is stressed, the emotion engine will modify the proposal content in a concise and intuitive manner.

[1328] Input: Proposal, user sentiment data

[1329] Output: Proposal revised based on emotions

[1330] Step 8: Review and edit the proposal

[1331] Server operation:

[1332] The server sends the generated proposal to the user's terminal.

[1333] User actions:

[1334] Users can view the proposal on their device and edit it as needed. For example, they can change a specific phrase to "Special discount price: ¥90,000".

[1335] Input: Proposal

[1336] Output: Edited proposal

[1337] Step 9: Final confirmation and submission

[1338] User actions:

[1339] The user reviews the completed proposal and sends it to the client. This can be done via email or a dedicated sales support tool.

[1340] Input: Edited proposal

[1341] Output: Proposal sent to the customer

[1342] By utilizing this system, it becomes possible to accurately predict the customer needs of corporate sales representatives and quickly provide optimal proposals that take into account the emotional state of the users.

[1343] (Application Example 2)

[1344] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1345] There is a need to improve the efficiency of predicting customer needs and creating proposals in corporate sales. However, existing systems often provide uniform proposals without considering customer emotions or the specific circumstances, limiting their effectiveness in improving sales results. Furthermore, more advanced data analysis and user interface optimization are necessary to ensure the speed and accuracy of proposals. The goal is to improve the efficiency and customer satisfaction of corporate sales by solving these problems.

[1346] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1347] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal document including the selected product or service; means for enabling the proposal document to be viewed and edited on a user terminal; means for recognizing the user's emotional state; means for dynamically modifying the content of the proposal document based on the emotional state; and means for executing electronic payment. This makes it possible to accurately predict customer needs in corporate sales activities, automatically generate proposal documents that match the user's emotional state, and provide convenient electronic payment.

[1348] "Customer information" refers to various data about customers in corporate sales, and more specifically includes information such as the name, industry, address, contact information, purchase history, and transaction history of the customer company.

[1349] "Order performance data" refers to data detailing transactions that corporate sales have received in the past, and more specifically includes order date, order amount, ordered items, delivery date, name of trading company, and completion status.

[1350] A "machine learning model" refers to a computational model that uses algorithms to make predictions, classifications, and recommendations based on large amounts of data. Specifically, this includes techniques such as random forests and deep learning.

[1351] "Needs forecasting" refers to the process of using machine learning models to predict the products and services that corporate sales customers may need in the future.

[1352] "Product or service selection" refers to the process of choosing the most suitable product or service from multiple options based on anticipated customer needs.

[1353] "Automatic proposal generation" refers to the process of compiling proposal details into a document format for the customer based on the selected product or service, and this document is generated automatically.

[1354] "Emotional state recognition" refers to the technology that analyzes data such as the user's voice tone, facial expressions, and typing speed to determine the user's emotional state.

[1355] "Dynamic modification" refers to the process of changing the content of a proposal in real time based on the recognized emotional state of the user.

[1356] "Electronic payment" refers to the process of paying for goods or services using various online or mobile payment methods.

[1357] The system of this invention is realized through the collaboration of a server, terminal, user, and emotion engine. This system is specifically implemented in the following manner. Various hardware and software are used in this system.

[1358] Data Acquisition and Preprocessing

[1359] The server retrieves customer information and order history data for corporate sales from the database. This data includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. MySQL or PostgreSQL are used as the database management system.

[1360] The server preprocesses the acquired data, including imputing missing values ​​and removing outliers. Data processing libraries such as Python or R (e.g., Pandas, Numpy) are used for data formatting.

[1361] Training machine learning models

[1362] The server uses pre-processed data to train machine learning models. Libraries such as TensorFlow and PyTorch are used for this purpose. The models employ algorithms such as random forests and deep learning.

[1363] Needs forecasting

[1364] The server uses a trained model to predict the customer's future needs. For example, it makes predictions using prompts such as, "Based on customer B's purchase history over the past year, predict what they are likely to buy next."

[1365] Solution matching and proposal creation

[1366] The server automatically selects the most suitable products and services based on predicted needs and generates a proposal that includes detailed data such as price, delivery time, and characteristics. Solution matching is performed by referencing the company's internal solution database, and a natural language generation model (e.g., GPT-3) is used to generate the proposal.

[1367] Recognizing emotional states and revising proposals

[1368] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and typing speed to recognize the user's emotional state. The emotion engine used may include Azure Emotion API or IBM Watson Emotion Analysis. Based on the recognized emotional state, the content of the proposal is dynamically modified. Specifically, when the user is feeling stressed, a prompt such as "Please make the proposal more concise and intuitive" is displayed.

[1369] Review and editing of the proposal

[1370] Users review and edit proposals generated on their devices. Mobile applications using React Native or Flutter are suitable for this purpose. After editing, users make final checks on the proposal and send it to the client.

[1371] Electronic payment

[1372] After final confirmation of the proposal, electronic payment can be made with a single touch using a terminal. Online payment services such as PayPal and Stripe are used for electronic payments. This system accurately predicts customer needs in corporate sales activities, automatically generates proposals that match the user's emotions, and provides convenient electronic payment.

[1373] Specific example

[1374] For example, the server predicts what customer B is likely to buy next based on their purchase history over the past year. Based on the prediction, it selects appropriate products and services and generates a proposal. Furthermore, when the user reviews the proposal, if the emotion engine detects that they are experiencing stress, it prompts them to "make the proposal more concise and intuitive" and revise the content. After final confirmation, the user can then make an electronic payment to purchase the product with a single touch.

[1375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1376] Step 1:

[1377] Data collection

[1378] The server retrieves customer information and order history data for corporate sales from a database. This includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. The database management system used is MySQL or PostgreSQL. Database queries are executed as input to extract the necessary data. The extracted dataset is obtained as output.

[1379] Step 2:

[1380] Data preprocessing

[1381] The server preprocesses the retrieved data. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. It uses Python's Pandas and NumPy libraries to format the data. The dataset extracted in the previous step is used as input. The output is the preprocessed dataset.

[1382] Step 3:

[1383] Training machine learning models

[1384] The server trains a machine learning model using preprocessed data. The libraries used are TensorFlow and PyTorch, and the models employ algorithms such as random forests and deep learning. The input is the preprocessed dataset obtained in the previous step. The output is a trained machine learning model.

[1385] Step 4:

[1386] Needs forecasting

[1387] The server uses a trained model to predict the customer's future needs. The prompt is "Predict what customer B is likely to purchase next, based on their purchase history over the past year." The input is the current customer data and the prompt. The output is the predicted needs (the products or services the customer is likely to purchase next).

[1388] Step 5:

[1389] Solution Matching

[1390] The server selects the optimal product or service based on predicted needs, adding detailed data such as price, delivery time, and characteristics. Predicted needs and the company's internal solutions database are used as input. The output provides detailed information about the selected product or service.

[1391] Step 6:

[1392] Automatic generation of proposals

[1393] The server automatically generates proposals based on information about the selected products and services. It uses a natural language generation model (e.g., GPT-3). Detailed information about the selected products and services is used as input. The output is an automatically generated proposal.

[1394] Step 7:

[1395] Recognition of emotional states

[1396] The device analyzes the user's voice tone, facial expressions, and typing speed using an emotion engine (e.g., Azure Emotion API, IBM Watson Emotion Analysis) to recognize the user's emotional state. Real-time user data is used as input. The user's emotional state is obtained as output.

[1397] Step 8:

[1398] Dynamic editing of proposals

[1399] The proposal content is dynamically modified based on the emotional state recognized by the emotion engine. Specifically, if the user is stressed, a prompt message such as "Please make the proposal content more concise and intuitive" is used. The emotional state and the existing proposal are used as input. The modified proposal is obtained as output.

[1400] Step 9:

[1401] Proposal review and electronic payment

[1402] The user reviews and edits the proposal generated on the terminal and makes a final confirmation. Afterward, they execute electronic payment with a single touch. The user's edited proposal and electronic payment request are used as input. The output is the edited proposal and confirmation of the completed payment.

[1403] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1404] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1405] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1406] [Fourth Embodiment]

[1407] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1408] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1409] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1410] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1411] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1413] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1414] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1415] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1416] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1417] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1418] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1419] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1420] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[1421] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[1422] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[1423] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[1424] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. Finally, the user sends the completed proposal to the client.

[1425] Specific example

[1426] 1. Data Collection and Learning Phase

[1427] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[1428] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[1429] 2. Needs Prediction Phase

[1430] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[1431] 3. Solution Matching Phase

[1432] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[1433] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[1434] 4. Proposal Generation Phase

[1435] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[1436] Proposal: Solution Proposal for Company A's New Production Line

[1437] 1. Background and Objectives

[1438] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1439] 2. Proposed Solutions

[1440] Production equipment X: This latest model features high efficiency and low energy consumption.

[1441] Price: \XXXXXXX

[1442] Delivery time: Approximately 2 months

[1443] Production management software Y: It includes real-time data management and analysis functions.

[1444] Price: \XXXXXX

[1445] Delivery time: Approximately 1 month

[1446] 3. Superiority

[1447] High production efficiency and low operating costs are possible.

[1448] We also provide comprehensive support after implementation.

[1449] 4. Next Steps

[1450] Please contact us if you have any questions or concerns.

[1451] We will schedule a meeting for a more detailed discussion.

[1452] 5. User Review and Editing Phase

[1453] Users can review this proposal on their devices, modify specific wording, and insert additional information.

[1454] Finally, the edited proposal is sent to company A.

[1455] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate proposals that are optimally suited to those needs. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[1456] The following describes the processing flow.

[1457] Step 1:

[1458] The server retrieves customer information and order history data for corporate sales from the database. Customer information includes company name, industry, and past transaction history, while order history data includes transaction amount and details of purchased products and services.

[1459] Step 2:

[1460] The server preprocesses the retrieved data. This preprocessing includes cleaning the data, imputing missing values, and removing outliers. For example, it may fill in incomplete transaction information and remove illogical numbers.

[1461] Step 3:

[1462] The server feeds pre-processed data into a machine learning model and trains it. Specifically, it uses random forests and deep learning algorithms to learn customers' past purchasing patterns.

[1463] Step 4:

[1464] The server uses a trained machine learning model to predict the future needs of corporate sales customers. For example, it might predict that a particular customer may install a new production line in the next quarter.

[1465] Step 5:

[1466] The server selects the optimal products and services based on anticipated needs. This process involves searching the company's internal solution database for suitable products and services and gathering detailed data such as price, delivery time, and characteristics.

[1467] Step 6:

[1468] The server automatically generates a proposal using information on the selected products and services. The proposal includes details of specific solutions that address anticipated needs, benefits, pricing, and delivery timelines.

[1469] Step 7:

[1470] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1471] Step 8:

[1472] Users review the proposal content and make edits such as changing specific wording or inserting additional information. For example, they may customize it to suit the customer's characteristics or make minor adjustments.

[1473] Step 9:

[1474] The user reviews the completed proposal and sends it to the client. This process ensures that the client receives a quick and appropriate proposal.

[1475] (Example 1)

[1476] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1477] In corporate sales, predicting customers' future needs and proposing the most suitable products and services based on those needs requires collecting and analyzing a large amount of information. However, this takes a tremendous amount of time and effort, hindering efficient sales activities. Furthermore, proposal writing is often done manually, leading to problems such as errors and wasted time. To solve these problems, there is a need for highly accurate customer needs prediction and automated proposal generation that requires minimal effort.

[1478] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1479] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training the acquired data using a machine learning model and performing missing value imputation and outlier removal; and means for predicting future customer needs using the trained machine learning model. This enables efficient and highly accurate prediction of customer needs and automatic generation of proposals.

[1480] "Corporate sales customer information" refers to data about customers in corporate sales, including information such as the name of the customer company, industry, address, contact information, and transaction history.

[1481] "Order history data" refers to data related to past transactions, including information such as order date, order details, order amount, name of the ordering company, delivery date, and payment status.

[1482] A "machine learning model" is an algorithm that learns from data and refers to a system that makes predictions and classifications by finding specific patterns or rules.

[1483] "Missing value imputation" is the process of filling in missing values ​​in data, and is performed to improve data consistency and analytical accuracy.

[1484] "Outlier removal" is the process of detecting and removing abnormal or extreme values ​​from data, and is performed to improve the reliability of the analysis results.

[1485] "Future customer needs" refer to predictions of the products and services that customers will need in the future, derived from past customer behavior and market trends.

[1486] An "optimal product or service" is one that best meets anticipated customer needs and exceeds customer expectations.

[1487] A "proposal" is a document that summarizes the content of a proposal to a customer, and includes details, pricing, delivery dates, and characteristics of the products or services to be offered.

[1488] "User terminal" refers to a device such as a computer, tablet, or smartphone used by a user, and is used when viewing and editing information on the system.

[1489] Modes for carrying out the invention

[1490] This invention is a system for efficiently predicting customer needs and creating proposals for corporate sales. This system is realized through the collaboration of a server, terminals, and users.

[1491] First, the server retrieves customer information and order history data for corporate sales. This data is collected from a database (e.g., MySQL or PostgreSQL). The collected data includes the customer company's name, industry, address, contact information, and transaction history. This data is stored in the database and used for subsequent processing.

[1492] Next, the server preprocesses the collected data. Specifically, it uses the Python Pandas library to impute missing values. For example, it uses df.fillna(method='ffill') to impute missing values ​​in the data. It also uses Z-scores to remove outliers. This is a method for detecting and removing outliers, such as df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[1493] The server feeds preprocessed data into a machine learning model and trains the model. This process uses algorithms such as Random Forest and Deep Learning (e.g., Scikit-learn or TensorFlow). For example, it trains the model using code like `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`, and then saves the trained model.

[1494] Next, the server uses the trained model to predict the customer's future needs based on the new data. For example, it might predict that customer company A is likely to install a new production line in the next quarter, using a method like model.predict(new_data).

[1495] Based on predicted needs, the server selects the most suitable products and services from the company's solution database. This is done using SQL queries such as SELECT FROM solutions WHERE need = 'new_production_line'. Furthermore, detailed data such as price, delivery time, and characteristics are added. For example, this might involve processing `solution_data['price'] = get_price('product_x')`.

[1496] The server then automatically generates a proposal document containing the selected products and services. This process uses the Python Jinja2 template engine. The proposal document is created by rendering the template using methods such as `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[1497] The generated proposal will be created in the following format:

[1498] Proposal: Solution Proposal for Company A's New Production Line

[1499] 1. Background and Objectives

[1500] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1501] 2. Proposed Solutions

[1502] Production equipment X: This latest model features high efficiency and low energy consumption.

[1503] Price: \XXXXXXX

[1504] Delivery time: Approximately 2 months

[1505] Production management software Y: It includes real-time data management and analysis functions.

[1506] Price: \XXXXXX

[1507] Delivery time: Approximately 1 month

[1508] 3. Superiority

[1509] High production efficiency and low operating costs are possible.

[1510] We also provide comprehensive support after implementation.

[1511] 4. Next Steps

[1512] Please contact us if you have any questions or concerns.

[1513] We will schedule a meeting for a more detailed discussion.

[1514] The generated proposal is sent from the server to the user's terminal. The user can review it on their terminal and modify specific wording or insert additional information. A PDF editor (e.g., Adobe Acrobat) is used for editing. Finally, the user sends the edited proposal to the customer. For example, they might send it to the customer using `send_to_customer('final_proposal.pdf')`.

[1515] As a concrete example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model. By using this system, it is possible to improve the efficiency of corporate sales and enhance customer satisfaction.

[1516] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1517] System program processing flow

[1518] Step 1: Data acquisition and preprocessing

[1519] The server retrieves customer information and order history data for corporate sales from the database. The input is a database query, and the output is the collected raw data.

[1520] Specific operation: The server executes SQL queries such as "SELECT FROM customer_data" and "SELECT FROM sales_data" to retrieve data from the database.

[1521] The server preprocesses the acquired raw data. This includes imputing missing values ​​and removing outliers. The input is the acquired raw data, and the output is the preprocessed data.

[1522] Specific operation: Missing values ​​are imputed using df.fillna(method='ffill'), and outliers are removed by applying the Z-score and processing it as follows: df[(np.abs(stats.zscore(df)) < 3).all(axis=1)].

[1523] Step 2: Training the machine learning model

[1524] The server trains a machine learning model using preprocessed data. The input is the preprocessed data, and the output is the trained model.

[1525] Specific operation: The server uses the Scikit-learn Random Forest algorithm and trains the model using `from sklearn.ensemble import RandomForestClassifier` and `model = RandomForestClassifier().fit(X_train, y_train)`.

[1526] After training, the server saves the trained model. The input is the trained model, and the output is the saved model file.

[1527] Specific operation: Save the model to a file like this: model.save('model.pkl').

[1528] Step 3: Predicting Customer Needs

[1529] The server uses a trained model to predict future customer needs based on new data. The input is new customer data and the trained model, and the output is the predicted customer needs.

[1530] Specific operation: Predicts input data like model.predict(new_data).

[1531] Step 4: Solution Matching

[1532] The server selects the most suitable products and services from the company's solution database based on predicted needs. The input is the predicted needs, and the output is information on the selected products and services.

[1533] Specific operation: The server executes an SQL query like "SELECT FROM solutions WHERE need = 'predicted_need'" to select the appropriate solution.

[1534] The server adds detailed data such as price, delivery time, and characteristics to the information of the selected products and services. The input is the selected solution information, and the output is the solution information with the added detailed data.

[1535] Specific operation: Additional information is retrieved like this: solution_data['price'] = get_price('product_x').

[1536] Step 5: Proposal Generation

[1537] The server automatically generates a proposal based on the selected product or service information. The input is solution information with detailed data attached, and the output is the generated proposal.

[1538] Specific operation: Using Python's Jinja2 template engine, a proposal is generated using `template = Template(template_string)` and `proposal = template.render(data=solution_data)`.

[1539] Step 6: Review and edit the proposal

[1540] The server sends the generated proposal to the user's terminal. The input is the generated proposal, and the output is the proposal sent to the user's terminal.

[1541] Specific operation: Send a file like this: send_to_user('proposal.pdf').

[1542] The user reviews the proposal on their device and edits it as needed. The input is the submitted proposal, and the output is the edited proposal.

[1543] Specific operation: The user edits the proposal using a PDF editor such as Adobe Acrobat.

[1544] The user sends the edited proposal to the client. The input is the edited proposal, and the output is the proposal sent to the client.

[1545] Specific action: Send the proposal using a method like send_to_customer('final_proposal.pdf').

[1546] Through the steps outlined above, this system aims to improve the efficiency of corporate sales and enhance customer satisfaction. For example, prompts such as, "Create a program that predicts customer needs in corporate sales and generates optimal proposals," are used as input to the AI ​​model.

[1547] (Application Example 1)

[1548] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1549] The challenge is to provide a system that can accurately predict customer purchasing needs in physical stores and make effective suggestions. Furthermore, the challenge is to enable store staff to quickly and accurately suggest the most suitable products to customers.

[1550] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1551] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal including the selected product or service; means for enabling the proposal to be viewed and edited on a user terminal; means for collecting purchase history and behavioral data of customers visiting physical stores in real time; and means for suggesting the optimal product to store staff at physical stores. As a result, it becomes possible to predict customer needs in real time and make accurate product suggestions in physical stores, just as in corporate sales.

[1552] "Corporate sales" refers to all sales activities that target companies and organizations as customers.

[1553] "Customer information" refers to all data related to a customer, such as transaction history and purchasing patterns.

[1554] "Order history data" refers to data that includes detailed information and transaction history of products that have been ordered in the past.

[1555] A "machine learning model" refers to an algorithm that learns patterns and makes predictions based on a large amount of data.

[1556] "Customer needs" refer to the demands for goods and services that customers currently and in the future require.

[1557] "Products or services" refers to all specific goods and services provided to customers.

[1558] A "proposal" refers to a document that details the products or services offered to a customer.

[1559] A "user terminal" refers to a digital device used by a user to receive and edit information.

[1560] A "physical store" refers to a physical store where customers can go in person to purchase goods or services.

[1561] "Purchase history" refers to a record of products and services that a customer has purchased in the past.

[1562] "Behavioral data" refers to data about customers' actions and behavioral patterns when they visit a store.

[1563] "Store staff" refers to employees who handle customer service and product recommendations in a physical store.

[1564] "Real-time" refers to information processing and data collection occurring almost instantaneously.

[1565] This invention provides a system for predicting customer needs in corporate sales and physical stores and automatically generating optimal proposals. The system is primarily implemented through the collaboration of a server, terminals, and users.

[1566] First, the server retrieves customer information and order history data for corporate sales. This data is stored in a database and used for subsequent processing. The server then preprocesses the collected data, including imputing missing values ​​and removing outliers. The preprocessed data is fed into a machine learning model for training. Machine learning models such as random forests and deep learning are used. The trained model is then used to predict the future needs of corporate sales customers.

[1567] Next, the server selects the most suitable products and services based on the predicted needs. This selection is done by searching the company's internal solution database for information on appropriate products and services, and adding detailed data such as price, delivery time, and characteristics. The server then automatically generates a proposal based on this information. This generated proposal is sent from the server to the user's terminal, where the user can review and edit it. For example, they can change specific wording or insert additional information.

[1568] In physical stores, the system collects purchase history and behavioral data in real time when customers visit. The server uses this data to train machine learning models and predict customer needs in the physical store. Store staff are provided with user terminals where they can review and edit optimal product and service recommendations and provide them to customers. This entire process is performed using software tools such as Python, Flask, scikit-learn, and Pandas.

[1569] As a concrete example, if a customer visits a physical store and has previously purchased "Product A," "Product B," and "Product C" based on their past purchase history, the server can suggest "Product D" on their next visit. It is also possible to add a "5% discount" offer to the suggestion. An example of a specific prompt message is as follows:

[1570] Target customer: Mr. / Ms. Tanaka

[1571] Purchase history: ["Product A", "Product B", "Product C"]

[1572] Behavior pattern: Visits the store on weekday afternoons.

[1573] Question:

[1574] Please generate product recommendations for the customer's next visit.

[1575] This system improves the accuracy of predicting customer needs in both physical stores and corporate sales, enabling more effective proposals. This, in turn, leads to increased customer satisfaction and maximized sales efficiency.

[1576] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1577] Step 1:

[1578] The server retrieves customer information and order history data for corporate sales. This includes basic customer information, past transaction history, and data on purchased products and services. This data is stored in a database for use in subsequent processing.

[1579] Input: Customer information, order history data

[1580] Data processing: Storage in a database

[1581] Output: Data stored in the database

[1582] Step 2:

[1583] The server preprocesses the acquired data. This preprocessing includes imputing missing values ​​and removing outliers. This step prepares the data so that machine learning models can learn efficiently.

[1584] Input: Raw data stored in the database

[1585] Data processing: Missing value imputation, outlier removal

[1586] Output: Preprocessed data

[1587] Step 3:

[1588] The server trains machine learning models using pre-processed data. For example, it uses algorithms such as random forests or deep learning to build models that predict future customer needs.

[1589] Input: Preprocessed data

[1590] Data processing: Training machine learning models

[1591] Output: Trained model

[1592] Step 4:

[1593] The server uses a trained model to predict customer needs. Based on these predictions, it lists the products and services that customers are most likely to purchase next.

[1594] Input: Trained model, customer data

[1595] Data processing: Needs prediction

[1596] Output: Predicted needs list

[1597] Step 5:

[1598] The server selects the optimal products and services based on anticipated needs. This selection process utilizes an internal solution database, supplemented with detailed data such as price, delivery time, and characteristics.

[1599] Input: Predicted needs list, solution database

[1600] Data processing: Product / service selection and addition of detailed data.

[1601] Output: Optimal product / service list

[1602] Step 6:

[1603] The server automatically generates a proposal based on the selected products and services. The generated proposal includes detailed information such as price, delivery date, and characteristics.

[1604] Input: List of optimal products and services

[1605] Data processing: Automated generation of proposals

[1606] Output: Proposal

[1607] Step 7:

[1608] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1609] Input: Proposal

[1610] Data processing: Sending proposals

[1611] Output: Proposal viewable on the user's terminal

[1612] Step 8:

[1613] In physical stores, the server collects the purchase history and behavioral data of visiting customers in real time. Based on this data, the server uses machine learning models to predict the customer's next purchasing behavior.

[1614] Input: Real-time purchase history and behavioral data

[1615] Data processing: Real-time data collection and analysis

[1616] Output: Predicted customer purchasing trends

[1617] Step 9:

[1618] In physical stores, store staff use user terminals to provide optimal product recommendations. These recommendations are automatically generated by the system, and staff then customize them before presenting them to customers.

[1619] Input: Predicted purchasing trends, generated proposals

[1620] Data processing: Customization and presentation of proposals

[1621] Output: Customized proposal

[1622] Therefore, this system enables efficient and effective prediction and proposal of customer needs in corporate sales and physical stores through a series of steps.

[1623] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1624] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[1625] First, the server retrieves customer information and order history data for corporate sales from the database. This data is stored in the database and used for subsequent processing. Next, the server preprocesses the collected data, including imputing missing values ​​and removing outliers.

[1626] The server feeds pre-processed data into a machine learning model and trains it. For example, random forest or deep learning algorithms are used. The trained model is then used to predict the future needs of corporate sales customers.

[1627] Next, the server selects the most suitable products and services based on the predicted needs. The server searches the company's solution database for information on appropriate products and services and adds detailed data such as price, delivery time, and characteristics. Based on this information, the server automatically generates a proposal.

[1628] Furthermore, the generated proposal can be modified based on the user's emotions through the emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. The emotional information recognized by the emotion engine is used for selecting proposal templates and dynamically modifying the content of the proposal. For example, if the user is feeling stressed, the emotion engine will detect this and help modify the proposal content to be more concise and intuitive.

[1629] The generated proposal is sent from the server to the user's terminal. The user can review the proposal on their terminal and edit it as needed. For example, they can change specific wording or insert additional information. The emotion engine recognizes the user's emotions and can further adjust the proposal during the editing process.

[1630] Specific example

[1631] 1. Data Collection and Learning Phase

[1632] The server collects corporate sales transaction data for the past year. This data includes the customer company's industry, transaction amount, and the products and services purchased.

[1633] The server preprocesses this data and feeds it into a machine learning model. For example, it might predict that customer company A may install a new production line in the next quarter.

[1634] 2. Needs Prediction Phase

[1635] The server uses a pre-trained model to predict the equipment and software that customer company A will need.

[1636] 3. Solution Matching Phase

[1637] Based on the predicted needs, the server selects production equipment X and production management software Y suitable for company A.

[1638] Detailed data, including the price, delivery time, and characteristics of the product or service, should be included in the proposal.

[1639] 4. Proposal Generation Phase

[1640] The server automatically generates a proposal based on the selected product and service information. For example, a proposal like the following might be generated:

[1641] Proposal: Solution Proposal for Company A's New Production Line

[1642] 1. Background and Objectives

[1643] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1644] 2. Proposed Solutions

[1645] Production equipment X: This latest model features high efficiency and low energy consumption.

[1646] Price: \XXXXXXX

[1647] Delivery time: Approximately 2 months

[1648] Production management software Y: It includes real-time data management and analysis functions.

[1649] Price: \XXXXXX

[1650] Delivery time: Approximately 1 month

[1651] 3. Superiority

[1652] High production efficiency and low operating costs are possible.

[1653] We also provide comprehensive support after implementation.

[1654] 4. Next Steps

[1655] Please contact us if you have any questions or concerns.

[1656] We will schedule a meeting for a more detailed discussion.

[1657] 5. Proposal Review and Editing Phase

[1658] The server sends the generated proposal to the user's terminal. The user reviews the proposal on their terminal and modifies the content based on the emotional information recognized by the emotion engine.

[1659] For example, if the emotion engine detects that a user is experiencing stress, it will suggest modifying the proposal to make it more concise and intuitive.

[1660] 6. Final confirmation and transmission phase

[1661] The user reviews the final edited proposal and sends it to the client. This process ensures that the proposal is delivered quickly and appropriately, taking into account the user's emotional state.

[1662] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[1663] The following describes the processing flow.

[1664] Step 1:

[1665] The server retrieves customer information and order history data for corporate sales from the database. This includes company name, industry, past transaction history, transaction amount, and details of purchased products and services.

[1666] Step 2:

[1667] The server preprocesses the acquired data. Specifically, it cleans the data, including imputing missing values ​​and removing outliers. For example, if there is missing data for a particular company, it will fill it in using other data.

[1668] Step 3:

[1669] The server feeds pre-processed data into a machine learning model and trains it. Algorithms used include random forests and deep learning. This allows the model to learn customer purchasing patterns and trends.

[1670] Step 4:

[1671] The server uses a trained machine learning model to predict future customer needs. For example, it might predict that a particular customer is likely to add a new production line in the next quarter.

[1672] Step 5:

[1673] The server selects the optimal products and services based on anticipated needs. The server searches and selects appropriate products and services from the company's internal solution database. The search results include detailed data such as price, delivery time, and characteristics of the products and services.

[1674] Step 6:

[1675] The server automatically generates a proposal based on the information of the selected products and services. The proposal includes details of the products and services that can be supplied, their benefits, pricing, and delivery dates.

[1676] Step 7:

[1677] The server sends the generated proposal to the user's terminal. The user can then review the proposal on their terminal and edit it as needed.

[1678] Step 8:

[1679] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. This allows the system to understand the user's emotional state while they are editing the proposal.

[1680] Step 9:

[1681] The server receives emotional information recognized by the emotion engine and dynamically changes the proposal template selection and content suggestions. For example, if the user is feeling stressed, the server will make the proposal concise and easy to understand.

[1682] Step 10:

[1683] Users review the proposal content and make edits, such as changing specific wording or inserting additional information. They also refer to revision suggestions provided by the sentiment engine.

[1684] Step 11:

[1685] The user reviews the finalized proposal and sends it to the client. At this stage, the proposal takes the user's emotional state into consideration.

[1686] Through the processing steps described above, it becomes possible to accurately predict the customer needs of corporate sales and provide optimal proposals that reflect the user's emotional state using the emotion engine.

[1687] (Example 2)

[1688] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1689] In corporate sales, there is a problem in efficiently predicting customer needs and creating proposals. Furthermore, creating proposals without considering the user's emotional state can result in inadequate solutions. This hinders improvements in the efficiency and accuracy of sales activities, as well as in customer satisfaction.

[1690] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring corporate sales customer information and order performance data, means for preprocessing the acquired data, means for training a machine learning model on the preprocessed data, means for predicting future customer needs using the trained machine learning model, means for selecting the optimal product or service based on the predicted needs, means for automatically generating a proposal document including the selected product or service, means for allowing the proposal document to be viewed and edited on a user terminal, and means for analyzing the user's emotions and adjusting the content of the proposal document based on the user's emotions. This makes it possible to accurately predict corporate sales customer needs and automatically generate an optimal proposal that takes into account the user's emotional state.

[1691] "Corporate sales" refers to sales activities targeting corporations (companies), primarily involving the provision and sale of products and services in business-to-business transactions.

[1692] "Customer information" refers to data about customers held by a company, including, for example, customer names, addresses, contact information, transaction history, and purchase history.

[1693] "Order history data" refers to data on orders a company has received to date, and specifically includes information such as order quantity, amount, date, and customer name.

[1694] "Preprocessing" refers to the process of preparing data to be suitable for machine learning models, and includes, for example, imputing missing values, removing outliers, and normalizing data.

[1695] A "machine learning model" is a model that learns from data and uses the results of that learning to make predictions and classifications on new data. Examples of algorithms include random forests and deep learning.

[1696] "Needs forecasting" refers to using historical data and machine learning models to predict future customer demands and the products and services they will need.

[1697] "Product or service selection" refers to choosing the appropriate product or service based on anticipated customer needs.

[1698] "Automatic proposal generation" refers to the automatic creation of proposals based on information about selected products and services.

[1699] "Emotion analysis" refers to a technology that analyzes a user's voice tone, facial expressions, and typing speed to recognize their emotions.

[1700] "Means of enabling editing" refers to functions or methods that allow users to view the generated proposal on their device and make changes or corrections.

[1701] This invention is a system for efficiently predicting customer needs and creating proposals in corporate sales. This system is realized through the collaboration of a server, terminals, users, and an emotion engine.

[1702] System Configuration

[1703] First, the server retrieves customer information and order history data for corporate sales from the database. This data includes, for example, the customer's name, previous purchase history, and transaction amount. The data retrieved by the server is stored in the database and used for subsequent processing.

[1704] Next, the server preprocesses the collected data. Preprocessing includes imputing missing values ​​and removing outliers. For example, the Python library "pandas" is used to clean the data. Commands such as "fillna" and "dropna" are used in the "pandas" library.

[1705] Machine learning models

[1706] The server feeds pre-processed data into a machine learning model and trains it. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. The trained model is then used to predict the future needs of corporate sales customers. Specifically, it utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[1707] Needs forecasting

[1708] Next, the server uses the trained model to predict the future needs of customer companies. For example, based on corporate sales data, it might predict that customer company A may install a new production line in the next quarter.

[1709] Solution Selection

[1710] The server selects the optimal products and services based on predicted needs. It searches the company's solution database for information on suitable products and services and adds detailed data such as price, delivery time, and characteristics. For example, it might use an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[1711] Automatic proposal generation

[1712] The server automatically generates a proposal based on the collected data. This process involves using a template to fill in information about the selected products and services. The generated proposal will look like this:

[1713] Proposal: Solution Proposal for Company A's New Production Line

[1714] 1. Background and Objectives

[1715] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1716] 2. Proposed Solutions

[1717] Production equipment X: This latest model features high efficiency and low energy consumption.

[1718] Price: ¥100,000

[1719] Delivery time: Approximately 2 months

[1720] Production management software Y: It includes real-time data management and analysis functions.

[1721] Price: ¥50,000

[1722] Delivery time: Approximately 1 month

[1723] 3. Superiority

[1724] High production efficiency and low operating costs are possible.

[1725] We also provide comprehensive support after implementation.

[1726] 4. Next Steps

[1727] Please contact us if you have any questions or concerns.

[1728] We will schedule a meeting for a more detailed discussion.

[1729] Utilizing the Emotion Engine

[1730] Furthermore, the proposal can be modified based on the user's emotions through an emotion engine. Specifically, the emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. Based on this emotional information, it dynamically selects a proposal template and modifies the content of the proposal.

[1731] Review and edit the proposal.

[1732] The generated proposal is sent from the server to the user's terminal, where the user can review and edit it as needed. Users can change specific expressions, insert additional information, and perform other operations. The emotion engine further supports the editing process, adjusting the proposal content according to the user's emotional state.

[1733] Final confirmation and submission

[1734] The user reviews the final edited proposal and sends it to the client. This ensures that the proposal is delivered quickly and appropriately, taking the user's emotional state into consideration.

[1735] Example of a prompt

[1736] An example of a prompt message is: "Predict the production equipment and software that client company A may need in the next quarter, and generate an optimal proposal based on that data."

[1737] As described above, the present invention is a system that can accurately predict customer needs in corporate sales and automatically generate optimal proposals that take into account the user's emotional state using an emotion engine. By using this system, it is possible to improve the efficiency and accuracy of sales activities and enhance customer satisfaction.

[1738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1739] Program processing steps

[1740] Step 1: Data Collection

[1741] Server operation:

[1742] The server retrieves corporate sales customer information and order history data from the database. Specifically, it extracts the necessary data using SQL queries. For example, it executes a command such as "SELECT FROM customer_information WHERE period = 'past 1 year'".

[1743] Input: Database

[1744] Output: Customer information and order history data

[1745] Step 2: Data Preprocessing

[1746] Server operation:

[1747] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values ​​(e.g., imputing with the median) and removing outliers (e.g., removing outliers using the 3σ rule). The data is cleaned using the Python "pandas" library. Commands such as "fillna" and "dropna" from "pandas" are used.

[1748] Input: Retrieved data

[1749] Output: Preprocessed data

[1750] Step 3: Training the machine learning model

[1751] Server operation:

[1752] The server trains machine learning models using preprocessed data. The algorithms used include, for example, Scikit-learn's Random Forest and deep learning models using TensorFlow. It utilizes Scikit-learn's RandomForestClassifier and TensorFlow's neural networks.

[1753] Input: Preprocessed data

[1754] Output: Trained model

[1755] Step 4: Needs Prediction

[1756] Server operation:

[1757] The server uses a trained model to predict the future needs of customer companies. For example, it runs "model.predict(new input data)" to predict the likelihood that customer company A will install a new production line.

[1758] Input: Trained model, customer information

[1759] Output: Predicted needs

[1760] Step 5: Solution Selection

[1761] Server operation:

[1762] The server selects the optimal product or service based on the predicted needs. It searches the company's solution database for information on the relevant product or service and collects detailed data such as price, delivery time, and characteristics. It uses an SQL query to execute the command "SELECT FROM solution WHERE needs = 'new production line'".

[1763] Input: Predicted needs, solution database

[1764] Output: Information on the best products and services

[1765] Step 6: Automatic proposal generation

[1766] Server operation:

[1767] The server automatically generates proposals based on the collected data. This process involves using templates to fill in information about the selected products and services. Specifically, the proposal is generated in the following format:

[1768] Proposal: Solution Proposal for Company A's New Production Line

[1769] 1. Background and Objectives

[1770] Company A is planning to set up a new production line and needs to select the necessary equipment and software.

[1771] 2. Proposed Solutions

[1772] Production equipment X: This latest model features high efficiency and low energy consumption.

[1773] Price: ¥100,000

[1774] Delivery time: Approximately 2 months

[1775] Production management software Y: It includes real-time data management and analysis functions.

[1776] Price: ¥50,000

[1777] Delivery time: Approximately 1 month

[1778] 3. Superiority

[1779] High production efficiency and low operating costs are possible.

[1780] We also provide comprehensive support after implementation.

[1781] 4. Next Steps

[1782] Please contact us if you have any questions or concerns.

[1783] We will schedule a meeting for a more detailed discussion.

[1784] Input: Information on the best products and services

[1785] Output: Automated proposal

[1786] Step 7: Correction by the emotion engine

[1787] How the emotion engine works:

[1788] The emotion engine analyzes the user's voice tone, facial expressions, and typing speed to recognize their emotions. For example, it uses data from the camera, microphone, and keyboard input speed. If the user is stressed, the emotion engine will modify the proposal content in a concise and intuitive manner.

[1789] Input: Proposal, user sentiment data

[1790] Output: Proposal revised based on emotions

[1791] Step 8: Review and edit the proposal

[1792] Server operation:

[1793] The server sends the generated proposal to the user's terminal.

[1794] User actions:

[1795] Users can view the proposal on their device and edit it as needed. For example, they can change a specific phrase to "Special discount price: ¥90,000".

[1796] Input: Proposal

[1797] Output: Edited proposal

[1798] Step 9: Final confirmation and submission

[1799] User actions:

[1800] The user reviews the completed proposal and sends it to the client. This can be done via email or a dedicated sales support tool.

[1801] Input: Edited proposal

[1802] Output: Proposal sent to the customer

[1803] By utilizing this system, it becomes possible to accurately predict the customer needs of corporate sales representatives and quickly provide optimal proposals that take into account the emotional state of the users.

[1804] (Application Example 2)

[1805] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1806] There is a need to improve the efficiency of predicting customer needs and creating proposals in corporate sales. However, existing systems often provide uniform proposals without considering customer emotions or the specific circumstances, limiting their effectiveness in improving sales results. Furthermore, more advanced data analysis and user interface optimization are necessary to ensure the speed and accuracy of proposals. The goal is to improve the efficiency and customer satisfaction of corporate sales by solving these problems.

[1807] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1808] In this invention, the server includes means for acquiring customer information and order performance data for corporate sales; means for training a machine learning model with the acquired data; means for predicting future customer needs using the trained machine learning model; means for selecting the optimal product or service based on the predicted needs; means for automatically generating a proposal document including the selected product or service; means for enabling the proposal document to be viewed and edited on a user terminal; means for recognizing the user's emotional state; means for dynamically modifying the content of the proposal document based on the emotional state; and means for executing electronic payment. This makes it possible to accurately predict customer needs in corporate sales activities, automatically generate proposal documents that match the user's emotional state, and provide convenient electronic payment.

[1809] "Customer information" refers to various data about customers in corporate sales, and more specifically includes information such as the name, industry, address, contact information, purchase history, and transaction history of the customer company.

[1810] "Order performance data" refers to data detailing transactions that corporate sales have received in the past, and more specifically includes order date, order amount, ordered items, delivery date, name of trading company, and completion status.

[1811] A "machine learning model" refers to a computational model that uses algorithms to make predictions, classifications, and recommendations based on large amounts of data. Specifically, this includes techniques such as random forests and deep learning.

[1812] "Needs forecasting" refers to the process of using machine learning models to predict the products and services that corporate sales customers may need in the future.

[1813] "Product or service selection" refers to the process of choosing the most suitable product or service from multiple options based on anticipated customer needs.

[1814] "Automatic proposal generation" refers to the process of compiling proposal details into a document format for the customer based on the selected product or service, and this document is generated automatically.

[1815] "Emotional state recognition" refers to the technology that analyzes data such as the user's voice tone, facial expressions, and typing speed to determine the user's emotional state.

[1816] "Dynamic modification" refers to the process of changing the content of a proposal in real time based on the recognized emotional state of the user.

[1817] "Electronic payment" refers to the process of paying for goods or services using various online or mobile payment methods.

[1818] The system of this invention is realized through the collaboration of a server, terminal, user, and emotion engine. This system is specifically implemented in the following manner. Various hardware and software are used in this system.

[1819] Data Acquisition and Preprocessing

[1820] The server retrieves customer information and order history data for corporate sales from the database. This data includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. MySQL or PostgreSQL are used as the database management system.

[1821] The server preprocesses the acquired data, including imputing missing values ​​and removing outliers. Data processing libraries such as Python or R (e.g., Pandas, Numpy) are used for data formatting.

[1822] Training machine learning models

[1823] The server uses pre-processed data to train machine learning models. Libraries such as TensorFlow and PyTorch are used for this purpose. The models employ algorithms such as random forests and deep learning.

[1824] Needs forecasting

[1825] The server uses a trained model to predict the customer's future needs. For example, it makes predictions using prompts such as, "Based on customer B's purchase history over the past year, predict what they are likely to buy next."

[1826] Solution matching and proposal creation

[1827] The server automatically selects the most suitable products and services based on predicted needs and generates a proposal that includes detailed data such as price, delivery time, and characteristics. Solution matching is performed by referencing the company's internal solution database, and a natural language generation model (e.g., GPT-3) is used to generate the proposal.

[1828] Recognizing emotional states and revising proposals

[1829] The device uses an emotion engine to analyze the user's voice tone, facial expressions, and typing speed to recognize the user's emotional state. The emotion engine used may include Azure Emotion API or IBM Watson Emotion Analysis. Based on the recognized emotional state, the content of the proposal is dynamically modified. Specifically, when the user is feeling stressed, a prompt such as "Please make the proposal more concise and intuitive" is displayed.

[1830] Review and editing of the proposal

[1831] Users review and edit proposals generated on their devices. Mobile applications using React Native or Flutter are suitable for this purpose. After editing, users make final checks on the proposal and send it to the client.

[1832] Electronic payment

[1833] After final confirmation of the proposal, electronic payment can be made with a single touch using a terminal. Online payment services such as PayPal and Stripe are used for electronic payments. This system accurately predicts customer needs in corporate sales activities, automatically generates proposals that match the user's emotions, and provides convenient electronic payment.

[1834] Specific example

[1835] For example, the server predicts what customer B is likely to buy next based on their purchase history over the past year. Based on the prediction, it selects appropriate products and services and generates a proposal. Furthermore, when the user reviews the proposal, if the emotion engine detects that they are experiencing stress, it prompts them to "make the proposal more concise and intuitive" and revise the content. After final confirmation, the user can then make an electronic payment to purchase the product with a single touch.

[1836] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1837] Step 1:

[1838] Data collection

[1839] The server retrieves customer information and order history data for corporate sales from a database. This includes information such as the customer company's name, industry, address, contact information, purchase history, and transaction history. The database management system used is MySQL or PostgreSQL. Database queries are executed as input to extract the necessary data. The extracted dataset is obtained as output.

[1840] Step 2:

[1841] Data preprocessing

[1842] The server preprocesses the retrieved data. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. It uses Python's Pandas and NumPy libraries to format the data. The dataset extracted in the previous step is used as input. The output is the preprocessed dataset.

[1843] Step 3:

[1844] Training machine learning models

[1845] The server trains a machine learning model using preprocessed data. The libraries used are TensorFlow and PyTorch, and the models employ algorithms such as random forests and deep learning. The input is the preprocessed dataset obtained in the previous step. The output is a trained machine learning model.

[1846] Step 4:

[1847] Needs forecasting

[1848] The server uses a trained model to predict the customer's future needs. The prompt is "Predict what customer B is likely to purchase next, based on their purchase history over the past year." The input is the current customer data and the prompt. The output is the predicted needs (the products or services the customer is likely to purchase next).

[1849] Step 5:

[1850] Solution Matching

[1851] The server selects the optimal product or service based on predicted needs, adding detailed data such as price, delivery time, and characteristics. Predicted needs and the company's internal solutions database are used as input. The output provides detailed information about the selected product or service.

[1852] Step 6:

[1853] Automatic generation of proposals

[1854] The server automatically generates proposals based on information about the selected products and services. It uses a natural language generation model (e.g., GPT-3). Detailed information about the selected products and services is used as input. The output is an automatically generated proposal.

[1855] Step 7:

[1856] Recognition of emotional states

[1857] The device analyzes the user's voice tone, facial expressions, and typing speed using an emotion engine (e.g., Azure Emotion API, IBM Watson Emotion Analysis) to recognize the user's emotional state. Real-time user data is used as input. The user's emotional state is obtained as output.

[1858] Step 8:

[1859] Dynamic editing of proposals

[1860] The proposal content is dynamically modified based on the emotional state recognized by the emotion engine. Specifically, if the user is stressed, a prompt message such as "Please make the proposal content more concise and intuitive" is used. The emotional state and the existing proposal are used as input. The modified proposal is obtained as output.

[1861] Step 9:

[1862] Proposal review and electronic payment

[1863] The user reviews and edits the proposal generated on the terminal and makes a final confirmation. Afterward, they execute electronic payment with a single touch. The user's edited proposal and electronic payment request are used as input. The output is the edited proposal and confirmation of the completed payment.

[1864] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1865] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1866] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1867] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1868] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1869] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1870] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1871] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1872] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1873] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1874] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1875] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1876] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1877] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1878] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1879] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1880] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1881] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1882] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1883] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1884] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1885] The following is further disclosed regarding the embodiments described above.

[1886] (Claim 1)

[1887] A means of acquiring customer information and order performance data for corporate sales,

[1888] A means for training a machine learning model with the aforementioned acquired data,

[1889] A means for predicting future customer needs using the aforementioned trained machine learning model,

[1890] A means for selecting the optimal product or service based on the aforementioned predicted needs,

[1891] A means for automatically generating a proposal including the selected products or services,

[1892] A means to enable the user to view and edit the aforementioned proposal on their terminal,

[1893] A system that includes this.

[1894] (Claim 2)

[1895] The system according to claim 1, further comprising means for selecting a proposal template that is appropriate to the customer's industry and needs.

[1896] (Claim 3)

[1897] The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs.

[1898] "Example 1"

[1899] (Claim 1)

[1900] A means of obtaining customer information and order performance data for corporate sales,

[1901] The acquired data is trained using a machine learning model, and means are used to impute missing values ​​and remove outliers.

[1902] A means for predicting future customer needs using the aforementioned trained machine learning model,

[1903] A means for selecting the optimal product or service based on the aforementioned predicted needs,

[1904] A means for automatically generating a proposal including the selected products or services,

[1905] A means to enable the user to view and edit the aforementioned proposal on their terminal,

[1906] A system that includes this.

[1907] (Claim 2)

[1908] The system according to claim 1, further comprising means for selecting a proposal template that is appropriate to the customer's industry and needs.

[1909] (Claim 3)

[1910] The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs.

[1911] "Application Example 1"

[1912] (Claim 1)

[1913] A means of acquiring customer information and order performance data for corporate sales,

[1914] A means for training a machine learning model with the aforementioned acquired data,

[1915] A means for predicting future customer needs using the aforementioned trained machine learning model,

[1916] A means for selecting the optimal product or service based on the aforementioned predicted needs,

[1917] A means for automatically generating a proposal including the selected products or services,

[1918] A means to enable the user to view and edit the aforementioned proposal on their terminal,

[1919] A means of collecting the purchase history and behavioral data of customers visiting physical stores in real time,

[1920] A means of suggesting the most suitable products to store staff in physical stores,

[1921] A system that includes this.

[1922] (Claim 2)

[1923] The system according to claim 1, further comprising means for selecting a proposal template that is appropriate to the customer's industry and needs.

[1924] (Claim 3)

[1925] The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs.

[1926] "Example 2 of combining an emotion engine"

[1927] (Claim 1)

[1928] A means of acquiring customer information and order performance data for corporate sales,

[1929] Means for preprocessing the acquired data,

[1930] A means for training a machine learning model with the aforementioned preprocessed data,

[1931] A means for predicting future customer needs using the aforementioned trained machine learning model,

[1932] A means for selecting the optimal product or service based on the aforementioned predicted needs,

[1933] A means for automatically generating a proposal including the selected products or services,

[1934] A means to enable the user to view and edit the aforementioned proposal on their terminal,

[1935] A means for analyzing the user's emotions and adjusting the content of the proposal based on the user's emotions,

[1936] A system that includes this.

[1937] (Claim 2)

[1938] The system according to claim 1, further comprising means for selecting a proposal template that is appropriate to the customer's industry and needs.

[1939] (Claim 3)

[1940] The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs.

[1941] "Application example 2 when combining with an emotional engine"

[1942] (Claim 1)

[1943] A means of acquiring customer information and order performance data for corporate sales,

[1944] A means for training a machine learning model with the aforementioned acquired data,

[1945] A means for predicting future customer needs using the aforementioned trained machine learning model,

[1946] A means for selecting the optimal product or service based on the aforementioned predicted needs,

[1947] A means for automatically generating a proposal including the selected products or services,

[1948] A means to enable the user to view and edit the aforementioned proposal on their terminal,

[1949] Means for recognizing the emotional state of the user,

[1950] A means for dynamically modifying the content of the proposal based on the aforementioned emotional state,

[1951] Means of performing electronic payments,

[1952] A system that includes this.

[1953] (Claim 2)

[1954] The system according to claim 1, further comprising means for selecting a proposal template that is appropriate to the customer's industry and needs.

[1955] (Claim 3)

[1956] The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs. [Explanation of symbols]

[1957] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring customer information and order performance data for corporate sales, A means for training a machine learning model with the aforementioned acquired data, A means for predicting future customer needs using the aforementioned trained machine learning model, A means for selecting the optimal product or service based on the aforementioned predicted needs, A means for automatically generating a proposal including the selected products or services, A means to enable the user to view and edit the aforementioned proposal on their terminal, A system that includes this.

2. The system according to claim 1, further comprising means for selecting a proposal template that suits the customer's industry and needs.

3. The system according to claim 1, further comprising means for adding detailed data, including price, delivery date, and characteristics of products and services, based on the predicted needs.

Images