system

Abstract

We provide the system. [Solution] A means for receiving customer information and interview content and storing it in a database, A means of searching for similar past data based on saved customer information and interview content to generate optimal proposals and estimates, A means for the user to edit and modify the generated estimate, A means to save the revised estimate back into the database, A means for the user to display the aforementioned estimate and proposal and to guide the customer based on it, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] When serving customers and making proposals, differences in skills and knowledge among sales staff may affect customer satisfaction. Also, it is difficult to quickly create optimal proposals from past customer data and similar cases, and as a result, quotations and proposals may be delayed. Furthermore, the modification of quotation content is complicated, and improvement in the efficiency of the sales process is required.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving customer information and interview content and storing it in a database; means for searching for similar past data based on the stored customer information and interview content to generate optimal proposals and estimates; means for the user to edit and modify the content of the generated estimates; means for the modified estimates to be stored in the database again; and means for the user to display the content of the estimates and proposals and guide customers based on them. This system enables sales representatives to quickly create consistent, high-quality proposals and estimates and to effectively guide customers.

[0006] "Customer information" refers to various pieces of information about a customer, such as their name, contact information, desired products or services, budget, and intended use.

[0007] "Interview content" refers to information such as hopes, requests, and needs that sales representatives obtain through dialogue with customers.

[0008] A "database" is a system for systematically storing and managing customer information, interview content, and past proposal and quotation data.

[0009] "Optimal proposal" refers to selecting products and services that best meet customer needs based on similar past data.

[0010] A "quote" is a document that clearly specifies the details and price of the product or service being proposed.

[0011] "Editing and modification" refers to the user changing, adding, or deleting the generated estimate.

[0012] "User" refers to a sales representative who uses this system to input customer information and view / modify quotes.

[0013] A "machine learning algorithm" is a computational method that learns patterns and trends based on past data and uses that knowledge to make predictions and perform analyses on new data.

[0014] "Feedback" refers to additional information received after a service has been provided, such as customer responses and evaluations. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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 multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] 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.

[0020] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[0037] Specific processing of the program

[0038] 1. Entering customer interview data

[0039] The user logs into the terminal and enters customer information and interview details.

[0040] Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[0041] The terminal checks the integrity of the entered data and confirms that all required fields are filled in.

[0042] After verification, the device sends the data to the server.

[0043] 2. Saving interview data

[0044] The server parses the received customer data and saves it as a new entry in the database. During saving, it performs an integrity check on the input data to ensure there are no similar duplicate entries.

[0045] 3. Comparison and analysis with past data

[0046] The server searches past data in the database and extracts cases similar to the entered interview data.

[0047] The server uses machine learning algorithms (e.g., KNN, linear regression) to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[0048] 4. Generating estimates and information

[0049] Based on the analysis results obtained, the server selects the most suitable products and services and automatically generates a quote.

[0050] Example: "High-performance laptop, creative software package, total price: 130,000 yen"

[0051] The server sends the generated quote and information to the user's terminal.

[0052] 5. Displaying the estimate

[0053] The terminal displays the received quote and information on its screen.

[0054] Users can review the content and make corrections as needed.

[0055] 6. Revision of the estimate

[0056] The user makes revisions to the estimate.

[0057] Example: Add "Additional Warranty Service (2 years)" and adjust the estimated price to "150,000 yen".

[0058] The terminal sends the changes to the server.

[0059] 7. Re-save the changes

[0060] The server parses the received modifications and saves them back to the database.

[0061] The server recalculates the revised estimate and verifies its consistency.

[0062] 8. Preparation for guiding and serving customers

[0063] The terminal displays the final quote and proposal, and can be presented to the customer in print or digital format.

[0064] Based on the revised quotes and information, users provide high-quality customer service.

[0065] 9. Recording of customer service results

[0066] Users input customer service results and feedback into a terminal.

[0067] The device sends feedback data to the server.

[0068] The server saves the feedback to a database for future analysis.

[0069] Specific example

[0070] Customer interview data entry

[0071] For example, a user might input customer information for "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is then sent from the terminal to the server and stored in the database.

[0072] Comparison and analysis with past data

[0073] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable recommendation.

[0074] Estimate and guide generation

[0075] In this case, the server generates an estimate of 130,000 yen for a "high-performance laptop" and a "creative software package," and sends it to the user's terminal.

[0076] Estimate revision and notification

[0077] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[0078] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide a consistent, high-quality service.

[0079] The following describes the processing flow.

[0080] Step 1:

[0081] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0082] Step 2:

[0083] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0084] Step 3:

[0085] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[0086] Step 4:

[0087] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0088] Step 5:

[0089] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0090] Step 6:

[0091] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[0092] Step 7:

[0093] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[0094] Step 8:

[0095] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[0096] Step 9:

[0097] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[0098] Step 10:

[0099] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[0100] Step 11:

[0101] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[0102] Step 12:

[0103] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[0104] Step 13:

[0105] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0106] Step 14:

[0107] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0108] Step 15:

[0109] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0110] Step 16:

[0111] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[0112] Through the steps outlined above, this system handles everything from collecting customer data and generating optimal proposals to revising quotes and supporting high-quality customer service. This enables all crew members to provide consistent, high-quality service.

[0113] (Example 1)

[0114] 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."

[0115] Traditional customer service systems require manual input of customer information and generation of quotes, resulting in significant time and effort, as well as a high risk of human error. Furthermore, referencing past data to provide optimal solutions is difficult, requiring more advanced technology to improve customer satisfaction. Additionally, maintaining data integrity is challenging due to the difficulty in consistently managing user modifications.

[0116] 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.

[0117] In this invention, the server includes means for the user to input customer information and interview content into a terminal, and for the terminal to send the data to the server after confirmation; means for the server to parse the received customer data and save it as a new entry in a database; and means for the server to search past data in the database, extract cases similar to the input data using a machine learning algorithm, and automatically generate optimal proposals and estimates. This automates everything from inputting customer information to generating optimal proposals, enabling efficient and consistent customer service.

[0118] "Customer information" refers to data that includes the customer's name, contact information, purchase history, and information about the services or products they request.

[0119] "Interview content" refers to information gathered through dialogue with customers, such as their needs, desired products and services, budget, and intended use.

[0120] A "terminal" is an electronic device, such as a computer or mobile device, that a user operates.

[0121] A "server" is a central processing unit for receiving, processing, storing, and transmitting data.

[0122] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0123] A "machine learning algorithm" is a mathematical model or method used for data analysis and prediction, learning rules and patterns from past data.

[0124] A "quote" is a document or data that shows the price of goods or services offered to a customer.

[0125] A "proposal" is a suggestion for the best product or service based on the customer's needs.

[0126] "Feedback" refers to information that includes opinions, evaluations, and impressions received from customers.

[0127] "Consistency" is a concept that refers to a state in which data is consistent and free from contradictions or errors.

[0128] This invention can be implemented using a server equipped with an operating system, a user-operated terminal, and software components to coordinate them. The main hardware configuration of this system includes a database server, an application server, and a user-operated computer or mobile terminal.

[0129] Input and transmission of customer interview data

[0130] The user logs into the terminal and enters customer information and interview details. For example, they might enter information such as "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work." This data undergoes a consistency check, and after confirming that all required fields are filled in, it is sent to the server.

[0131] Saving interview data

[0132] The server parses the received customer data and saves it as a new entry in a database (e.g., MySQL®). During saving, it verifies that there are no similar duplicate data entries and that the data is consistent. For example, based on the information of a customer named "Ichiro Tanaka," it re-verifies data with similar desired products and budgets.

[0133] Comparison and analysis with past data

[0134] The server searches past data in the database and extracts cases similar to the input interview data. In this case, a high-speed search engine such as ElasticSearch® is used to efficiently extract data. Next, the server evaluates the similarity using the displayed machine learning algorithms. For example, algorithms such as KNN (nearest neighbor search) and linear regression are implemented using Scikit-learn.

[0135] Estimate and guide generation

[0136] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." This quotation document is then sent to the user's terminal.

[0137] Displaying and modifying estimates

[0138] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. For example, it is possible to add an additional warranty service (2 years) and adjust the quote so that the total amount comes to 150,000 yen. The revised quote is then sent back to the server.

[0139] Re-save the changes

[0140] The server parses the received revisions and saves them back into the database. The revised estimate is also checked for consistency and verified again.

[0141] Final check-in and preparation for customer service

[0142] The terminal displays the final quote and proposal. This information is presented to the customer in digital or printable format. The user then uses this information to provide high-quality customer service. For example, they can print the revised quote and explanatory document to make a more specific proposal to the customer.

[0143] Record of customer service results

[0144] Users input customer service results and feedback into a terminal. This feedback data is sent to a server and stored in a database.

[0145] Examples of prompt statements

[0146] "Customer Name: Ichiro Tanaka, Desired Product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[0147] In this way, the system automates and optimizes the entire process from customer information input to generating optimal proposals, adjusting quotes, and final customer support, enabling efficient and consistent service delivery.

[0148] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0149] Step 1:

[0150] The user enters customer information and interview details into the terminal. Specifically, they enter data such as customer name, product preference, budget, and intended use into the input fields. Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work". The terminal checks the integrity of the entered data and verifies that all required fields are filled in. If there are no problems, the data is sent to the server.

[0151] Input: Customer information and interview details

[0152] Output: Customer data sent to the server

[0153] Step 2:

[0154] The server parses the received customer data. Specifically, it analyzes the received JSON data and extracts values ​​corresponding to each field (customer name, product preference, budget, and intended use). Next, it saves this data as a new entry in the database. For example, it saves it to a MySQL database using an INSERT statement. During saving, it also performs data integrity checks and checks for duplicate data.

[0155] Input: Received customer data

[0156] Output: Customer data stored in the database

[0157] Step 3:

[0158] The server searches past data in the database and extracts similar cases. Specifically, it efficiently searches past interview data using tools such as Elasticsearch. Next, it applies machine learning algorithms (e.g., KNN, linear regression) based on similar cases to calculate the optimal proposal. This proposal is generated by considering successful cases and proposal content extracted from past similar cases.

[0159] Input: New customer data

[0160] Output: Generation of optimal proposals and estimates

[0161] Step 4:

[0162] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." These quotation documents are generated in text or PDF format and sent to the user's terminal.

[0163] Input: Analysis results (proposal)

[0164] Output: Generated quotation document

[0165] Step 5:

[0166] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. Specifically, they can add an "additional warranty service (2 years)" to the quote and revise the final amount to 150,000 yen. The revised content is then sent back to the server.

[0167] Input: Received quotation document

[0168] Output: Revised estimate

[0169] Step 6:

[0170] The server parses the received modifications and resaves them in the database. Specifically, it analyzes the modified estimate document and saves it as a new entry in the database. In addition, consistency checks and recalculations are performed based on the modified data.

[0171] Input: Revised quote details

[0172] Output: Corrected data saved again in the database

[0173] Step 7:

[0174] The terminal displays the final quote and proposal, preparing them for presentation to the user in print or digital format. The user then uses this information to provide high-quality customer service, specifically by using the revised quote and accompanying documents to make concrete proposals to the customer.

[0175] Input: Final quote and proposal

[0176] Output: Quotation document presented to the customer

[0177] Step 8:

[0178] The user inputs the results of the customer service and customer feedback into a terminal. The input feedback data is sent from the terminal to the server, which stores it in a database. Specifically, the feedback content is entered in text format and stored in the appropriate field in the database.

[0179] Input: Service results and customer feedback

[0180] Output: Feedback information stored in the database

[0181] (Application Example 1)

[0182] 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."

[0183] In traditional manufacturing, optimizing manufacturing processes and generating proposals required significant time and effort, and the management and estimation of these processes were inefficient. Furthermore, responding to problems arising in the manufacturing process in real time was difficult, often resulting in decreased productivity and cost efficiency.

[0184] 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.

[0185] In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for collecting manufacturing process data based on the stored customer information and interview content and generating optimal proposals and estimates, and means for the user to edit and modify the content of the generated estimates. This enables optimization of the manufacturing process and efficient estimate generation.

[0186] "Customer information" refers to basic information and requests regarding customers in the manufacturing environment.

[0187] "Hearing content" refers to information that shows the specific needs and requirements collected from customers during manufacturing operations.

[0188] A "database" is a system for centrally storing and managing customer information, interview results, and other related data.

[0189] "Means of preservation" refers to methods or devices that provide the function of writing collected information into a database and storing it permanently.

[0190] "Manufacturing process data" refers to information about specific work stages and conditions related to manufacturing operations.

[0191] A "proposal" refers to the optimal solution or method derived from similar past data and current needs.

[0192] An "estimate" is the result of calculating the manufacturing costs and other related expenses based on the proposal.

[0193] "Means of editing and modification" refers to functions or devices that allow users to manually change and modify the generated estimates and proposals.

[0194] "Manufacturing operations" refers to all tasks and processes involved in the production of a product.

[0195] "Means of guidance" refers to methods and devices for presenting users with optimal proposals and estimates, and for providing instructions and guidance at the manufacturing site.

[0196] "Manufacturing results" refer to information about the final outcomes or results obtained after executing a manufacturing process.

[0197] "Production feedback" refers to opinions and information, such as suggestions for improvement and evaluations, obtained after manufacturing operations have been carried out.

[0198] A "machine learning algorithm" is a statistical method and mathematical model used to process large amounts of historical data, recognize patterns, and predict future outcomes.

[0199] To implement this invention, a system is needed to collect customer information and interview data related to the manufacturing process and store it in a database. This system consists of a robot installed on the manufacturing site, a server that processes the data, and software components to coordinate them. Specifically, it uses Python and Scikit-learn to implement machine learning algorithms (such as KNN).

[0200] First, the terminal inputs customer information and interview details. For example, information such as "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Usage: Mass production" is entered. The terminal performs a data integrity check on the entered data to confirm that all required fields are filled in accurately. After that, the data is sent to the server.

[0201] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During saving, the integrity of the input data is checked again to confirm that there is no similar duplicate data. Next, the server searches for similar past data in the database and uses a machine learning algorithm to extract cases similar to the new data. In this process, Scikit-learn's KNN (neighborhood association algorithm) is used to calculate the similarity of the data and generate the best suggestions and estimates.

[0202] The generated estimate and proposal are sent back to the terminal and displayed on the user's screen. The user can review this information and edit or modify it as needed. For example, they might add an "additional warranty service (3 years)" to adjust the final budget to "3.2 million yen." The modified information is then sent back from the terminal to the server and saved again in the database.

[0203] Once the final estimate and proposal are confirmed, the user presents them to the workers involved in the manufacturing process and provides specific instructions. The user also inputs the results of the manufacturing operations and production feedback into a terminal, sends them to a server, and stores them in a database. This feedback is used for future analysis and leads to improvements in the optimal manufacturing process.

[0204] Examples of specific prompt messages include the following:

[0205] "Customer Name: Jiro Sato, Desired Product: New Automotive Parts, Budget: 5 million yen, Purpose: Mass production of high-performance engines"

[0206] By using such prompt statements, the system can process data quickly and efficiently, and propose and estimate the optimal manufacturing process.

[0207] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0208] Step 1:

[0209] The terminal inputs customer information and interview details. This input includes customer name, desired product, budget, and intended use. The terminal performs a consistency check on this information to ensure that all required fields are filled in accurately. A specific example of input would be: "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Intended use: Mass production."

[0210] Step 2:

[0211] The terminal sends the input data, after integrity checks have been completed, to the server. The transmitted data includes customer information and interview details. The terminal initiates data transmission and manages the communication until the data reaches the server.

[0212] Step 3:

[0213] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During this process, it performs another consistency check to ensure there are no similar duplicate data entries. The server accurately parses the data and adds it to the database as structured data.

[0214] Step 4:

[0215] The server searches for similar historical data within the database. Specifically, it matches the data against past customer information and extracts data with similar conditions. The server uses a machine learning algorithm to calculate the similarity of the data and generates optimal suggestions and estimates. The algorithm used is Scikit-learn's KNN (neighborhood association algorithm).

[0216] Step 5:

[0217] The server sends the generated quote and proposal to the terminal. The transmitted data includes the proposal, detailed product information, and the estimated price. A typical output might be a quote such as, "Industrial robot, additional warranty service (3 years), total: 3.2 million yen."

[0218] Step 6:

[0219] The terminal displays the received quote and proposal details on the user's screen. The user can review this information and edit or modify it as needed. For example, they can extend the warranty period or add additional services.

[0220] Step 7:

[0221] If the user modifies the estimate, the terminal resends the modified data to the server. The server receives the modified data and saves it again in the database. Based on the modifications, a consistency check is performed again, and the final estimate is confirmed.

[0222] Step 8:

[0223] Once the final estimate and proposal are confirmed, the terminal presents them to the workers involved in the manufacturing process. The user then provides specific instructions and prepares to begin the manufacturing operations.

[0224] Step 9:

[0225] After a manufacturing task is completed, the user inputs the results and production feedback into a terminal. The terminal sends the input feedback data to a server, which stores it in a database. This feedback data is used to improve the quality of future suggestions.

[0226] 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.

[0227] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. Furthermore, this system incorporates an emotion engine that recognizes user emotions, thereby adjusting optimal proposals and estimates based on the user's emotions. The entire process consists of a terminal operated by the user, a server that performs the processing, and software components that coordinate these.

[0228] Specific processing of the program

[0229] 1. Entering customer interview data

[0230] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0231] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0232] After the terminal verifies the integrity of the data, it sends the input data to the server.

[0233] 2. Saving interview data

[0234] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0235] 3. Comparison and analysis with past data

[0236] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0237] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal. For example, it uses methods such as the KNN algorithm or linear regression.

[0238] 4. Generating estimates and information

[0239] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[0240] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[0241] 5. Viewing and modifying estimates

[0242] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[0243] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[0244] The terminal sends the changes to the server.

[0245] 6. Re-save the changes

[0246] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[0247] 7. Preparation for guiding and serving customers

[0248] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0249] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0250] 8. Recording of customer service results

[0251] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0252] The device sends feedback data to the server.

[0253] The server stores the feedback in a database to help create future proposals and estimates.

[0254] 9. Integrating an emotion engine

[0255] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions. This analysis is performed using the device's camera and microphone.

[0256] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, if the user is feeling stressed, it will offer simpler and easier-to-understand suggestions.

[0257] The server stores the detected emotion data in a database and uses it for future proposals and quotes.

[0258] Specific example

[0259] Customer interview data entry and emotion recognition

[0260] For example, a user might input customer information, such as "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is sent from the terminal to the server and stored in the database. Simultaneously, an emotion engine analyzes the user's voice tone and facial expressions to detect if they are relaxed.

[0261] Comparison and analysis with past data, and adjustment based on sentiment.

[0262] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable suggestion. Furthermore, it refers to emotional data and presents standard suggestions to users in a relaxed state.

[0263] Estimate revision and notification

[0264] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[0265] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine enables customized suggestions that resonate with the user's emotions.

[0266] The following describes the processing flow.

[0267] Step 1:

[0268] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0269] Step 2:

[0270] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0271] Step 3:

[0272] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[0273] Step 4:

[0274] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0275] Step 5:

[0276] The emotion engine analyzes the user's voice tone and facial expressions to detect emotions. This analysis is performed using the device's camera and microphone.

[0277] Step 6:

[0278] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, it will offer standard suggestions if the user is relaxed and simpler suggestions if they are stressed.

[0279] Step 7:

[0280] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0281] Step 8:

[0282] The server evaluates the similarity using machine learning algorithms and analyzes high - priority cases. For example, it calculates the most suitable proposal using methods such as the KNN algorithm or linear regression.

[0283] Step 9:

[0284] Based on the obtained analysis results, the server selects the optimal products and services and automatically generates a quotation. For example, it generates a quotation such as "High - performance notebook computer, creative software package, total amount: 130,000 yen".

[0285] Step 10:

[0286] The server sends the generated quotation and guidance content to the user's terminal. The transmitted data includes quotation details and proposed content.

[0287] Step 11:

[0288] The terminal displays the received quotation and guidance content on the screen. The user can check the content and make corrections if necessary.

[0289] Step 12:

[0290] The user makes corrections to the quotation. For example, adds "Additional warranty service (2 years)" and modifies the quotation amount to "150,000 yen".

[0291] Step 13:

[0292] The terminal sends the correction content to the server. The correction data includes the added warranty service and the revised total amount.

[0293] Step 14:

[0294] The server parses the received correction content, re - saves it in the database, recalculates the revised quotation, and checks the overall consistency.

[0295] Step 15:

[0296] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0297] Step 16:

[0298] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0299] Step 17:

[0300] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0301] Step 18:

[0302] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[0303] In this way, the entire process is carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine allows for customized suggestions that resonate with the user's emotions.

[0304] (Example 2)

[0305] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0306] In the conventional system, the input and management of customer information were complicated, and it often took a long time to compare and analyze with past data. Also, in order for the user to make a high-quality proposal to the customer, it was necessary to manually generate an optimal proposal and estimate based on the content of the hearing, resulting in low efficiency. Furthermore, proposals and estimates were not adjusted considering the user's feelings, and improving customer satisfaction was an issue.

[0307] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving customer information and the content of the hearing and storing them in a database, means for searching for past similar data based on the stored customer information and the content of the hearing and generating an optimal proposal and estimate using a machine learning algorithm, and means for recognizing the user's feelings and adjusting the proposal and estimate based on those feelings. As a result, efficient management of customer information and automatic generation of optimal proposals and estimates become possible, and it becomes possible to provide high-quality services that take into account the user's feelings.

[0308] "Customer information" refers to information regarding the customer's name, address, contact information, and products indicating purchase history and interests.

[0309] "The content of the hearing" refers to information regarding the customer's needs, desires, budget, and usage purpose collected based on interviews and conversations with the customer.

[0310] "Database" refers to a digital data storage system for efficiently storing, managing, and searching customer information and the content of the hearing.

[0311] "Machine learning algorithm" refers to a computational method for learning rules and patterns from data and making future proposals and predictions. Specifically, it includes the k-nearest neighbor method (KNN) and linear regression, etc.

[0312] "Proposal" refers to the content that indicates and recommends optimal products and services based on the customer's needs and desires.

[0313] A "quote" refers to a document that specifically calculates and presents the price and conditions of a product or service based on a proposal.

[0314] "Emotion recognition" refers to a technology that analyzes a user's voice tone and facial expressions to detect their emotional state. This analysis utilizes natural language processing engines and facial recognition engines.

[0315] "Editing and modification" refers to the process where a user reviews the estimates and proposals generated by the system and makes changes as needed.

[0316] The system of this invention inputs and manages customer information and interview content, compares and analyzes it with past data, and generates optimal proposals and estimates. Furthermore, by incorporating an emotion engine that recognizes user emotions, it adjusts optimal proposals and estimates based on the user's emotions. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[0317] The system's hardware configuration includes user terminals (e.g., PCs and tablets), a database server for storing customer information, and an application server for data processing. The emotion engine operates using a camera and microphone connected to the user's terminal.

[0318] The software includes database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., scikit-learn, TENSORFLOW®), natural language processing engines, and facial recognition engines. These software components work together to efficiently input, store, retrieve, and analyze data.

[0319] As a concrete example, consider a scenario where a user logs into a terminal and inputs new customer information and interview details. The input data is checked for integrity by the terminal and sent to the server. The server receives the data and stores it in a database. Next, the server uses a machine learning algorithm to search past data and generate the optimal proposal. The generated proposal and estimate are sent to the user's terminal, where the user can review and modify the content. The modified estimate is sent back to the server and stored in the database.

[0320] A key feature of this system is its emotion engine, which analyzes the user's tone of voice and facial expressions in real time, adjusting suggestions and quotes based on the user's emotions. For example, if the user is relaxed, it can provide standard suggestions, while if they are stressed, it can offer simpler and easier-to-understand suggestions.

[0321] Example of a prompt

[0322] The following is an example of a prompt to input into a generative AI model:

[0323] The customer's request for a high-performance laptop is based on a budget of ¥150,000, and its intended use is creative work. Based on this information, generate an optimal product proposal and quote. Please assume the customer is relaxed and provide a standard proposal.

[0324] This embodiment allows for a rapid and efficient execution of the entire process. Furthermore, the incorporation of an emotion engine enables customized suggestions that resonate with the user's emotions, thereby improving user satisfaction.

[0325] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0326] Step 1:

[0327] The user logs into the terminal and enters new customer information and interview details.

[0328] Input: Customer name, desired product, budget, intended use, and other information gathered during the interview.

[0329] Specific action: The user enters "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work" into the terminal.

[0330] Step 2:

[0331] The terminal checks the integrity of the entered data.

[0332] Input: Customer information entered in Step 1

[0333] Specific actions: The terminal checks whether all required fields are filled in and whether the data format is correct. For example, it verifies that the budget is in numerical format.

[0334] Step 3:

[0335] After the terminal verifies the integrity of the data, it sends the input data to the server.

[0336] Input: Customer information whose integrity has been verified.

[0337] Output: Data to send to the server

[0338] Specific operation: The terminal encrypts the data and sends the following information to the server: "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0339] Step 4:

[0340] The server parses the received customer data and saves it as a new entry in the database.

[0341] Input: Customer data sent from the terminal

[0342] Output: New entries saved in the database

[0343] Specific operation: The server parses the received data in JSON format and uses SQL queries to save "Customer ID, Customer Name, Desired Product, Budget, and Usage" to the database.

[0344] Step 5:

[0345] The server searches past data in the database and extracts cases similar to the entered interview data.

[0346] Input: Newly entered customer data

[0347] Output: Data of extracted similar cases

[0348] Specific operation: Use an SQL query to extract data from the database that matches the criteria "Desired product: High-performance laptop, Budget range: 100,000 to 200,000 yen".

[0349] Step 6:

[0350] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[0351] Input: Data of extracted similar cases

[0352] Output: Best proposal and estimate

[0353] Specific operation: The server uses the KNN algorithm to calculate similarity scores and generates proposals for "high-performance laptop" and "creative software package, total cost: 130,000 yen".

[0354] Step 7:

[0355] The server automatically generates an estimate based on the analysis results obtained and sends it to the user's terminal.

[0356] Input: Analysis results

[0357] Output: Generated quote and its submission

[0358] Specific operation: The server generates a quotation, encrypts it, and sends it to the terminal. For example, it sends a quotation for "high-performance laptop 100,000 yen, creative software package 30,000 yen, total 130,000 yen".

[0359] Step 8:

[0360] The device displays the received quote, and the user can review and modify it.

[0361] Input: Estimate data sent from the server

[0362] Output: Revised estimate

[0363] Specific operation: The user can check the quote displayed on the screen and "add an additional warranty service (2 years) and adjust the price to 150,000 yen."

[0364] Step 9:

[0365] The terminal sends the revised estimate to the server.

[0366] Input: Revised estimate data

[0367] Output: Data to send to the server

[0368] Specific action: Encrypt the changes and send them to the server.

[0369] Step 10:

[0370] The server parses the corrected data and saves it back to the database.

[0371] Input: Estimate data including revisions

[0372] Output: New entry to the database

[0373] Specific operation: The server re-parses the corrected data and uses an SQL query to add a new entry to the database containing "Additional Warranty Service (2 years)".

[0374] Step 11:

[0375] The terminal displays the final quote and proposal, preparing the user to present it to the customer.

[0376] Input: Confirmed estimate data

[0377] Output: Final estimate displayed on the user screen

[0378] Specific operation: The terminal displays the estimate and proposal on the screen and provides the functionality to print or save them in digital format.

[0379] Step 12:

[0380] Users input customer service results and feedback into a terminal and send them to the server.

[0381] Input: Service results and customer feedback

[0382] Output: Data to send to the server

[0383] Specific operation: The user enters feedback such as "The customer was satisfied with the proposal and decided to purchase," and sends it to the server.

[0384] Step 13:

[0385] The server saves the received feedback data to a database.

[0386] Input: Feedback data submitted by the user

[0387] Output: Feedback entries saved in the database

[0388] Specific operation: The server parses the feedback data and saves it to a database. This data is then used to generate future proposals and estimates.

[0389] Step 14:

[0390] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions.

[0391] Input: Real-time audio and video data

[0392] Output: Detected sentiment data

[0393] Specific operation: Using the device's camera and microphone, it performs voice tone analysis and facial recognition to detect emotions such as "relaxed state" and "stressed state" in real time.

[0394] Step 15:

[0395] The server receives the detected emotion data and adjusts suggestions and estimates based on it.

[0396] Input: Detected sentiment data

[0397] Output: Adjusted proposals and quotes

[0398] Specific operation: The server analyzes emotional data and makes adjustments based on the situation, such as simplifying complex suggestions if the user is experiencing stress.

[0399] Step 16:

[0400] The server stores the detected emotion data in a database.

[0401] Input: Detected sentiment data

[0402] Output: Sentiment data entries stored in the database

[0403] Specific operation: The server parses the sentiment data and stores it in a database. This data is then used to flexibly respond to future proposal and estimate generation.

[0404] (Application Example 2)

[0405] 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".

[0406] In today's brick-and-mortar stores, there is a demand for providing customers with the most suitable proposals and quotes quickly and accurately. Furthermore, considering customer emotions and providing individually customized service leads to increased customer satisfaction. However, traditional systems require considerable time and effort to manage customer information and generate optimal proposals, making it difficult to provide proposals that reflect customer emotions in real time. This results in a decline in the quality of service and makes it difficult to improve customer satisfaction.

[0407] 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.

[0408] In this invention, the server includes means for receiving customer information and interview content and storing it in a database; means for searching for similar past data based on the stored customer information and interview content to generate optimal proposals and estimates; means for analyzing customer emotions in real time; and means for adjusting proposals and estimates based on customer emotions. This enables the provision of quick and accurate proposals and estimates to customers in physical stores, as well as individualized responses that are attentive to customer emotions.

[0409] "Customer information" refers to information that includes details such as the customer's name, contact information, desired products or services, budget, and intended use.

[0410] "Hearing content" refers to information obtained through dialogue with customers, including detailed requests, needs, and feedback.

[0411] A "database" is a system for efficiently storing, searching, and managing customer information, interview content, past proposal and quotation data, sentiment data, and other similar information.

[0412] "Similar data" refers to cases extracted from data of other customers collected in the past that are similar to the stored customer information and interview content.

[0413] A "proposal" is a plan to select and present the most suitable products or services based on the customer's requests and needs.

[0414] A "quote" is a document that details the price of goods, the fees for services, options, etc., calculated based on a proposal.

[0415] "Editing and modification" refers to the act of a user manually changing and readjusting the content of a generated proposal or estimate.

[0416] "Methods for analyzing emotions in real time" refer to technologies that use cameras and microphones to analyze a customer's facial expressions and tone of voice to identify their emotional state at that time.

[0417] "Means for adjusting proposals and estimates based on emotions" refers to technologies that automatically modify proposals and estimates to make them more appropriate based on analyzed emotions.

[0418] A "server" is a computer system that processes, stores, and retrieves data, and is a device that supports the management of customer information and the generation of proposals and estimates.

[0419] This invention is a system designed to streamline customer service in physical stores and improve customer satisfaction. This system integrates customer interview data input, real-time sentiment analysis using an emotion engine, comparison and analysis with past data, and creation and revision of estimates, enabling the provision of quick and accurate proposals and estimates.

[0420] Hardware and software configuration

[0421] 1. Terminal

[0422] The system includes smart glasses for use by store staff. These smart glasses have a built-in camera, microphone, and display, and are used for inputting customer information and analyzing customer facial expressions and voices in real time. The smart glasses also include a customer information input interface and a quotation display interface.

[0423] 2. Server

[0424] A server is a computer system for processing and storing customer information, interview content, historical data, and sentiment data. The server includes the following software components:

[0425] Database Server: Stores and manages customer data, interview content, historical data, and sentiment data. Specific software used includes database management systems such as MySQL and PostgreSQL.

[0426] Machine learning algorithms: Generate optimal suggestions and estimates from historically similar data. Specifically, build and apply models such as the KNN algorithm and linear regression using scikit-learn or TensorFlow.

[0427] Emotion Engine: Analyzes customer emotions in real time from their facial expressions and voice. This uses emotion recognition models based on OpenCV and TensorFlow.

[0428] System operation

[0429] Customer data entry and sentiment analysis

[0430] The user enters their name, desired product, budget, and intended use through smart glasses. For example, they might enter "Customer Name: Taro Yamada, Desired Product: High-performance laptop, Budget: 150,000 yen, Intended Use: Creative work." The entered data is sent to a server and stored in a database. Simultaneously, the camera and microphone built into the smart glasses analyze the customer's facial expressions and voice in real time, generating emotion data. As a result of the analysis, for example, a "relaxed state" might be detected.

[0431] Data analysis and proposal generation

[0432] The server searches for similar past data in the database and generates the optimal suggestion based on the interview content and sentiment data. Specifically, it analyzes data from customers who previously requested a "high-performance laptop" using the KNN algorithm and generates a suggestion that matches the criteria. For example, it might generate a suggestion such as "high-performance laptop, creative software package, total price: 130,000 yen."

[0433] Viewing and modifying estimates

[0434] The generated quote is displayed on the smart glasses' screen. The user can, for example, add an "additional warranty service (2 years)" and modify the quote amount to "150,000 yen". The modified data is then sent back to the server and stored in the database.

[0435] Proposal presentation to the customer

[0436] The final quote and proposal are displayed on smart glasses, which the user then presents to the customer. By providing customers with real-time, optimized proposals, it is possible to deliver high-quality service.

[0437] Specific example

[0438] Customer "Taro Yamada" visited the store requesting a high-performance laptop, with a budget of 150,000 yen. The user entered the information through smart glasses.

[0439] The emotion engine detects the customer's relaxed state.

[0440] By comparing past data with similar cases, the optimal suggestion, "High-performance laptop, creative software package, total price 130,000 yen," is generated and displayed.

[0441] The user reviewed the quote, added the "additional warranty service (2 years)," and revised the final amount to "150,000 yen."

[0442] The final quote and proposal are presented to the customer.

[0443] Example of a prompt

[0444] Customer information:

[0445] Name: Taro Yamada

[0446] Desired item: High-performance laptop

[0447] Budget: 150,000 yen

[0448] Usage: Creative work

[0449] Detected emotions:

[0450] relax

[0451] Based on past data, please generate the optimal proposal and estimate.

[0452] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0453] Step 1:

[0454] Enter customer information and interview details.

[0455] The user enters customer information (name, desired product, budget, and intended use) through smart glasses. For example, they might enter "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work." The terminal verifies the integrity of the entered data and then sends it to the server.

[0456] Input: Customer name, desired product, budget, purpose of use

[0457] Output: Customer information data sent to the server

[0458] Step 2:

[0459] sentiment analysis

[0460] The device (smart glasses) uses its built-in camera and microphone to analyze the customer's facial expressions and voice in real time, generating emotion data. For example, a "relaxed state" might be detected. The analysis results are then sent to a server.

[0461] Input: Customer facial expression and voice data

[0462] Output: Emotional data sent to the server

[0463] Step 3:

[0464] Save to database

[0465] The server saves the received customer information and sentiment data as new entries in the database. During saving, it verifies that all required fields are filled in and checks for any similar duplicate data.

[0466] Input: Customer information data, sentiment data

[0467] Output: New entries saved to the database

[0468] Step 4:

[0469] Comparison and analysis with past data

[0470] The server searches historical data in the database and extracts cases similar to the entered customer information and sentiment data. This search is performed efficiently using database queries. Furthermore, machine learning algorithms are used to evaluate the similarity and calculate the optimal recommendation.

[0471] Input: Customer information data, sentiment data

[0472] Output: Similar cases from past data and optimal suggestions

[0473] Step 5:

[0474] Generate and send quotes

[0475] Based on the analysis results obtained by the server, the optimal products and services are selected and an estimate is automatically generated. For example, an estimate such as "High-performance laptop, creative software package, total: 130,000 yen" is generated. The generated estimate and information are sent to the user's terminal.

[0476] Input: Analysis results, optimal suggestions

[0477] Output: Generated quote and information

[0478] Step 6:

[0479] Viewing and modifying estimates

[0480] The terminal displays the received quote and information. The user reviews the content and makes corrections as needed. For example, they might add "additional warranty service (2 years)" and change the quote amount to "150,000 yen". The corrected information is then sent back to the server.

[0481] Input: Generated quote and information

[0482] Output: Revised estimate

[0483] Step 7:

[0484] Save the changes

[0485] The server parses the received modifications and saves them back to the database. The revised estimate is recalculated, and the overall consistency is verified.

[0486] Input: Revised quote details

[0487] Output: Modified entries saved again in the database

[0488] Step 8:

[0489] Presentation of proposal

[0490] The terminal displays the final estimate and proposal, which the user presents to the customer in the physical store. The user then uses this information to provide high-quality customer service, thereby improving customer satisfaction.

[0491] Input: Final estimate and proposal details

[0492] Output: Final quote to present to the customer

[0493] 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.

[0494] 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.

[0495] 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.

[0496] [Second Embodiment]

[0497] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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).

[0503] 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.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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".

[0509] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[0510] Specific processing of the program

[0511] 1. Entering customer interview data

[0512] The user logs into the terminal and enters customer information and interview details.

[0513] Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[0514] The terminal checks the integrity of the entered data and confirms that all required fields are filled in.

[0515] After verification, the device sends the data to the server.

[0516] 2. Saving interview data

[0517] The server parses the received customer data and saves it as a new entry in the database. During saving, it performs an integrity check on the input data to ensure there are no similar duplicate entries.

[0518] 3. Comparison and analysis with past data

[0519] The server searches past data in the database and extracts cases similar to the entered interview data.

[0520] The server uses machine learning algorithms (e.g., KNN, linear regression) to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[0521] 4. Generating estimates and information

[0522] Based on the analysis results obtained, the server selects the most suitable products and services and automatically generates a quote.

[0523] Example: "High-performance laptop, creative software package, total price: 130,000 yen"

[0524] The server sends the generated quote and information to the user's terminal.

[0525] 5. Displaying the estimate

[0526] The terminal displays the received quote and information on its screen.

[0527] Users can review the content and make corrections as needed.

[0528] 6. Revision of the estimate

[0529] The user makes revisions to the estimate.

[0530] Example: Add "Additional Warranty Service (2 years)" and adjust the estimated price to "150,000 yen".

[0531] The terminal sends the changes to the server.

[0532] 7. Re-save the changes

[0533] The server parses the received modifications and saves them back to the database.

[0534] The server recalculates the revised estimate and verifies its consistency.

[0535] 8. Preparation for guiding and serving customers

[0536] The terminal displays the final quote and proposal, and can be presented to the customer in print or digital format.

[0537] Based on the revised quotes and information, users provide high-quality customer service.

[0538] 9. Recording of customer service results

[0539] Users input customer service results and feedback into a terminal.

[0540] The device sends feedback data to the server.

[0541] The server saves the feedback to a database for future analysis.

[0542] Specific example

[0543] Customer interview data entry

[0544] For example, a user might input customer information for "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is then sent from the terminal to the server and stored in the database.

[0545] Comparison and analysis with past data

[0546] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable recommendation.

[0547] Estimate and guide generation

[0548] In this case, the server generates an estimate of 130,000 yen for a "high-performance laptop" and a "creative software package," and sends it to the user's terminal.

[0549] Estimate revision and notification

[0550] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[0551] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide a consistent, high-quality service.

[0552] The following describes the processing flow.

[0553] Step 1:

[0554] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0555] Step 2:

[0556] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0557] Step 3:

[0558] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[0559] Step 4:

[0560] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0561] Step 5:

[0562] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0563] Step 6:

[0564] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[0565] Step 7:

[0566] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[0567] Step 8:

[0568] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[0569] Step 9:

[0570] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[0571] Step 10:

[0572] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[0573] Step 11:

[0574] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[0575] Step 12:

[0576] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[0577] Step 13:

[0578] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0579] Step 14:

[0580] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0581] Step 15:

[0582] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0583] Step 16:

[0584] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[0585] Through the steps outlined above, this system handles everything from collecting customer data and generating optimal proposals to revising quotes and supporting high-quality customer service. This enables all crew members to provide consistent, high-quality service.

[0586] (Example 1)

[0587] 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."

[0588] Traditional customer service systems require manual input of customer information and generation of quotes, resulting in significant time and effort, as well as a high risk of human error. Furthermore, referencing past data to provide optimal solutions is difficult, requiring more advanced technology to improve customer satisfaction. Additionally, maintaining data integrity is challenging due to the difficulty in consistently managing user modifications.

[0589] 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.

[0590] In this invention, the server includes means for the user to input customer information and interview content into a terminal, and for the terminal to send the data to the server after confirmation; means for the server to parse the received customer data and save it as a new entry in a database; and means for the server to search past data in the database, extract cases similar to the input data using a machine learning algorithm, and automatically generate optimal proposals and estimates. This automates everything from inputting customer information to generating optimal proposals, enabling efficient and consistent customer service.

[0591] "Customer information" refers to data that includes the customer's name, contact information, purchase history, and information about the services or products they request.

[0592] "Interview content" refers to information gathered through dialogue with customers, such as their needs, desired products and services, budget, and intended use.

[0593] A "terminal" is an electronic device, such as a computer or mobile device, that a user operates.

[0594] A "server" is a central processing unit for receiving, processing, storing, and transmitting data.

[0595] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0596] A "machine learning algorithm" is a mathematical model or method used for data analysis and prediction, learning rules and patterns from past data.

[0597] A "quote" is a document or data that shows the price of goods or services offered to a customer.

[0598] A "proposal" is a suggestion for the best product or service based on the customer's needs.

[0599] "Feedback" refers to information that includes opinions, evaluations, and impressions received from customers.

[0600] "Consistency" is a concept that refers to a state in which data is consistent and free from contradictions or errors.

[0601] This invention can be implemented using a server equipped with an operating system, a user-operated terminal, and software components to coordinate them. The main hardware configuration of this system includes a database server, an application server, and a user-operated computer or mobile terminal.

[0602] Input and transmission of customer interview data

[0603] The user logs into the terminal and enters customer information and interview details. For example, they might enter information such as "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work." This data undergoes a consistency check, and after confirming that all required fields are filled in, it is sent to the server.

[0604] Saving interview data

[0605] The server parses the received customer data and saves it as a new entry in a database (e.g., MySQL). During saving, it verifies that there are no similar duplicate data entries and that the data is consistent. For example, based on the information of a customer named "Ichiro Tanaka," it re-verifies data with similar desired products and budgets.

[0606] Comparison and analysis with past data

[0607] The server searches historical data in the database and extracts cases similar to the input interview data. In this case, a high-speed search engine such as Elasticsearch is used to efficiently extract data. Next, the server evaluates the similarity using the displayed machine learning algorithms. For example, algorithms such as KNN (nearest neighbor search) and linear regression are implemented using Scikit-learn.

[0608] Estimate and guide generation

[0609] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." This quotation document is then sent to the user's terminal.

[0610] Displaying and modifying estimates

[0611] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. For example, it is possible to add an additional warranty service (2 years) and adjust the quote so that the total amount comes to 150,000 yen. The revised quote is then sent back to the server.

[0612] Re-save the changes

[0613] The server parses the received revisions and saves them back into the database. The revised estimate is also checked for consistency and verified again.

[0614] Final check-in and preparation for customer service

[0615] The terminal displays the final quote and proposal. This information is presented to the customer in digital or printable format. The user then uses this information to provide high-quality customer service. For example, they can print the revised quote and explanatory document to make a more specific proposal to the customer.

[0616] Record of customer service results

[0617] Users input customer service results and feedback into a terminal. This feedback data is sent to a server and stored in a database.

[0618] Examples of prompt statements

[0619] "Customer Name: Ichiro Tanaka, Desired Product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[0620] In this way, the system automates and optimizes the entire process from customer information input to generating optimal proposals, adjusting quotes, and final customer support, enabling efficient and consistent service delivery.

[0621] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0622] Step 1:

[0623] The user enters customer information and interview details into the terminal. Specifically, they enter data such as customer name, product preference, budget, and intended use into the input fields. Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work". The terminal checks the integrity of the entered data and verifies that all required fields are filled in. If there are no problems, the data is sent to the server.

[0624] Input: Customer information and interview details

[0625] Output: Customer data sent to the server

[0626] Step 2:

[0627] The server parses the received customer data. Specifically, it analyzes the received JSON data and extracts values ​​corresponding to each field (customer name, product preference, budget, and intended use). Next, it saves this data as a new entry in the database. For example, it saves it to a MySQL database using an INSERT statement. During saving, it also performs data integrity checks and checks for duplicate data.

[0628] Input: Received customer data

[0629] Output: Customer data stored in the database

[0630] Step 3:

[0631] The server searches past data in the database and extracts similar cases. Specifically, it efficiently searches past interview data using tools such as Elasticsearch. Next, it applies machine learning algorithms (e.g., KNN, linear regression) based on similar cases to calculate the optimal proposal. This proposal is generated by considering successful cases and proposal content extracted from past similar cases.

[0632] Input: New customer data

[0633] Output: Generation of optimal proposals and estimates

[0634] Step 4:

[0635] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." These quotation documents are generated in text or PDF format and sent to the user's terminal.

[0636] Input: Analysis results (proposal)

[0637] Output: Generated quotation document

[0638] Step 5:

[0639] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. Specifically, they can add an "additional warranty service (2 years)" to the quote and revise the final amount to 150,000 yen. The revised content is then sent back to the server.

[0640] Input: Received quotation document

[0641] Output: Revised estimate

[0642] Step 6:

[0643] The server parses the received modifications and resaves them in the database. Specifically, it analyzes the modified estimate document and saves it as a new entry in the database. In addition, consistency checks and recalculations are performed based on the modified data.

[0644] Input: Revised quote details

[0645] Output: Corrected data saved again in the database

[0646] Step 7:

[0647] The terminal displays the final quote and proposal, preparing them for presentation to the user in print or digital format. The user then uses this information to provide high-quality customer service, specifically by using the revised quote and accompanying documents to make concrete proposals to the customer.

[0648] Input: Final quote and proposal

[0649] Output: Quotation document presented to the customer

[0650] Step 8:

[0651] The user inputs the results of the customer service and customer feedback into a terminal. The input feedback data is sent from the terminal to the server, which stores it in a database. Specifically, the feedback content is entered in text format and stored in the appropriate field in the database.

[0652] Input: Service results and customer feedback

[0653] Output: Feedback information stored in the database

[0654] (Application Example 1)

[0655] 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."

[0656] In traditional manufacturing, optimizing manufacturing processes and generating proposals required significant time and effort, and the management and estimation of these processes were inefficient. Furthermore, responding to problems arising in the manufacturing process in real time was difficult, often resulting in decreased productivity and cost efficiency.

[0657] 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.

[0658] In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for collecting manufacturing process data based on the stored customer information and interview content and generating optimal proposals and estimates, and means for the user to edit and modify the content of the generated estimates. This enables optimization of the manufacturing process and efficient estimate generation.

[0659] "Customer information" refers to basic information and requests regarding customers in the manufacturing environment.

[0660] "Hearing content" refers to information that shows the specific needs and requirements collected from customers during manufacturing operations.

[0661] A "database" is a system for centrally storing and managing customer information, interview results, and other related data.

[0662] "Means of preservation" refers to methods or devices that provide the function of writing collected information into a database and storing it permanently.

[0663] "Manufacturing process data" refers to information about specific work stages and conditions related to manufacturing operations.

[0664] A "proposal" refers to the optimal solution or method derived from similar past data and current needs.

[0665] An "estimate" is the result of calculating the manufacturing costs and other related expenses based on the proposal.

[0666] "Means of editing and modification" refers to functions or devices that allow users to manually change and modify the generated estimates and proposals.

[0667] "Manufacturing operations" refers to all tasks and processes involved in the production of a product.

[0668] "Means of guidance" refers to methods and devices for presenting users with optimal proposals and estimates, and for providing instructions and guidance at the manufacturing site.

[0669] "Manufacturing results" refer to information about the final outcomes or results obtained after executing a manufacturing process.

[0670] "Production feedback" refers to opinions and information, such as suggestions for improvement and evaluations, obtained after manufacturing operations have been carried out.

[0671] A "machine learning algorithm" is a statistical method and mathematical model used to process large amounts of historical data, recognize patterns, and predict future outcomes.

[0672] To implement this invention, a system is needed to collect customer information and interview data related to the manufacturing process and store it in a database. This system consists of a robot installed on the manufacturing site, a server that processes the data, and software components to coordinate them. Specifically, it uses Python and Scikit-learn to implement machine learning algorithms (such as KNN).

[0673] First, the terminal inputs customer information and interview details. For example, information such as "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Usage: Mass production" is entered. The terminal performs a data integrity check on the entered data to confirm that all required fields are filled in accurately. After that, the data is sent to the server.

[0674] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During saving, the integrity of the input data is checked again to confirm that there is no similar duplicate data. Next, the server searches for similar past data in the database and uses a machine learning algorithm to extract cases similar to the new data. In this process, Scikit-learn's KNN (neighborhood association algorithm) is used to calculate the similarity of the data and generate the best suggestions and estimates.

[0675] The generated estimate and proposal are sent back to the terminal and displayed on the user's screen. The user can review this information and edit or modify it as needed. For example, they might add an "additional warranty service (3 years)" to adjust the final budget to "3.2 million yen." The modified information is then sent back from the terminal to the server and saved again in the database.

[0676] Once the final estimate and proposal are confirmed, the user presents them to the workers involved in the manufacturing process and provides specific instructions. The user also inputs the results of the manufacturing operations and production feedback into a terminal, sends them to a server, and stores them in a database. This feedback is used for future analysis and leads to improvements in the optimal manufacturing process.

[0677] Examples of specific prompt messages include the following:

[0678] "Customer Name: Jiro Sato, Desired Product: New Automotive Parts, Budget: 5 million yen, Purpose: Mass production of high-performance engines"

[0679] By using such prompt statements, the system can process data quickly and efficiently, and propose and estimate the optimal manufacturing process.

[0680] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0681] Step 1:

[0682] The terminal inputs customer information and interview details. This input includes customer name, desired product, budget, and intended use. The terminal performs a consistency check on this information to ensure that all required fields are filled in accurately. A specific example of input would be: "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Intended use: Mass production."

[0683] Step 2:

[0684] The terminal sends the input data, after integrity checks have been completed, to the server. The transmitted data includes customer information and interview details. The terminal initiates data transmission and manages the communication until the data reaches the server.

[0685] Step 3:

[0686] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During this process, it performs another consistency check to ensure there are no similar duplicate data entries. The server accurately parses the data and adds it to the database as structured data.

[0687] Step 4:

[0688] The server searches for similar historical data within the database. Specifically, it matches the data against past customer information and extracts data with similar conditions. The server uses a machine learning algorithm to calculate the similarity of the data and generates optimal suggestions and estimates. The algorithm used is Scikit-learn's KNN (neighborhood association algorithm).

[0689] Step 5:

[0690] The server sends the generated quote and proposal to the terminal. The transmitted data includes the proposal, detailed product information, and the estimated price. A typical output might be a quote such as, "Industrial robot, additional warranty service (3 years), total: 3.2 million yen."

[0691] Step 6:

[0692] The terminal displays the received quote and proposal details on the user's screen. The user can review this information and edit or modify it as needed. For example, they can extend the warranty period or add additional services.

[0693] Step 7:

[0694] If the user modifies the estimate, the terminal resends the modified data to the server. The server receives the modified data and saves it again in the database. Based on the modifications, a consistency check is performed again, and the final estimate is confirmed.

[0695] Step 8:

[0696] Once the final estimate and proposal are confirmed, the terminal presents them to the workers involved in the manufacturing process. The user then provides specific instructions and prepares to begin the manufacturing operations.

[0697] Step 9:

[0698] After a manufacturing task is completed, the user inputs the results and production feedback into a terminal. The terminal sends the input feedback data to a server, which stores it in a database. This feedback data is used to improve the quality of future suggestions.

[0699] 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.

[0700] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. Furthermore, this system incorporates an emotion engine that recognizes user emotions, thereby adjusting optimal proposals and estimates based on the user's emotions. The entire process consists of a terminal operated by the user, a server that performs the processing, and software components that coordinate these.

[0701] Specific processing of the program

[0702] 1. Entering customer interview data

[0703] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0704] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0705] After the terminal verifies the integrity of the data, it sends the input data to the server.

[0706] 2. Saving interview data

[0707] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0708] 3. Comparison and analysis with past data

[0709] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0710] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal. For example, it uses methods such as the KNN algorithm or linear regression.

[0711] 4. Generating estimates and information

[0712] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[0713] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[0714] 5. Viewing and modifying estimates

[0715] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[0716] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[0717] The terminal sends the changes to the server.

[0718] 6. Re-save the changes

[0719] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[0720] 7. Preparation for guiding and serving customers

[0721] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0722] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0723] 8. Recording of customer service results

[0724] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0725] The device sends feedback data to the server.

[0726] The server stores the feedback in a database to help create future proposals and estimates.

[0727] 9. Integrating an emotion engine

[0728] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions. This analysis is performed using the device's camera and microphone.

[0729] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, if the user is feeling stressed, it will offer simpler and easier-to-understand suggestions.

[0730] The server stores the detected emotion data in a database and uses it for future proposals and quotes.

[0731] Specific example

[0732] Customer interview data entry and emotion recognition

[0733] For example, a user might input customer information, such as "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is sent from the terminal to the server and stored in the database. Simultaneously, an emotion engine analyzes the user's voice tone and facial expressions to detect if they are relaxed.

[0734] Comparison and analysis with past data, and adjustment based on sentiment.

[0735] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable suggestion. Furthermore, it refers to emotional data and presents standard suggestions to users in a relaxed state.

[0736] Estimate revision and notification

[0737] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[0738] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine enables customized suggestions that resonate with the user's emotions.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0742] Step 2:

[0743] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[0744] Step 3:

[0745] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[0746] Step 4:

[0747] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[0748] Step 5:

[0749] The emotion engine analyzes the user's voice tone and facial expressions to detect emotions. This analysis is performed using the device's camera and microphone.

[0750] Step 6:

[0751] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, it will offer standard suggestions if the user is relaxed and simpler suggestions if they are stressed.

[0752] Step 7:

[0753] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[0754] Step 8:

[0755] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[0756] Step 9:

[0757] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[0758] Step 10:

[0759] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[0760] Step 11:

[0761] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[0762] Step 12:

[0763] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[0764] Step 13:

[0765] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[0766] Step 14:

[0767] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[0768] Step 15:

[0769] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[0770] Step 16:

[0771] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[0772] Step 17:

[0773] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[0774] Step 18:

[0775] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[0776] In this way, the entire process is carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine allows for customized suggestions that resonate with the user's emotions.

[0777] (Example 2)

[0778] 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".

[0779] Traditional systems made customer information input and management cumbersome, and comparing and analyzing data with past data was often time-consuming. Furthermore, for users to provide high-quality proposals to customers, they had to manually generate optimal proposals and estimates based on interview content, which was inefficient. Additionally, proposals and estimates were not adjusted to take into account user emotions, making improving customer satisfaction a challenge.

[0780] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for searching for similar past data based on the stored customer information and interview content and generating optimal proposals and estimates using a machine learning algorithm, and means for recognizing the user's emotions and adjusting proposals and estimates based on those emotions. This enables efficient management of customer information and automatic generation of optimal proposals and estimates, making it possible to provide high-quality services that are attentive to the user's emotions.

[0781] "Customer information" refers to information about the customer, including their name, address, contact information, purchase history, and products they have shown interest in.

[0782] "Interview content" refers to information about customer needs, wishes, budget, and intended use, collected through interviews and conversations with customers.

[0783] A "database" refers to a digital data storage system used to efficiently store, manage, and retrieve customer information and interview transcripts.

[0784] A "machine learning algorithm" refers to a computational method used to learn rules and patterns from data and make future suggestions or predictions. Specifically, this includes methods such as K-nearest neighbors (KNN) and linear regression.

[0785] A "proposal" refers to a recommendation or suggestion that presents the most suitable products or services based on the customer's needs and preferences.

[0786] A "quote" refers to a document that specifically calculates and presents the price and conditions of a product or service based on a proposal.

[0787] "Emotion recognition" refers to a technology that analyzes a user's voice tone and facial expressions to detect their emotional state. This analysis utilizes natural language processing engines and facial recognition engines.

[0788] "Editing and modification" refers to the process where a user reviews the estimates and proposals generated by the system and makes changes as needed.

[0789] The system of this invention inputs and manages customer information and interview content, compares and analyzes it with past data, and generates optimal proposals and estimates. Furthermore, by incorporating an emotion engine that recognizes user emotions, it adjusts optimal proposals and estimates based on the user's emotions. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[0790] The system's hardware configuration includes user terminals (e.g., PCs and tablets), a database server for storing customer information, and an application server for data processing. The emotion engine operates using a camera and microphone connected to the user's terminal.

[0791] The software includes database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., scikit-learn, TensorFlow), natural language processing engines, and facial recognition engines. These software components work together to efficiently input, store, retrieve, and analyze data.

[0792] As a concrete example, consider a scenario where a user logs into a terminal and inputs new customer information and interview details. The input data is checked for integrity by the terminal and sent to the server. The server receives the data and stores it in a database. Next, the server uses a machine learning algorithm to search past data and generate the optimal proposal. The generated proposal and estimate are sent to the user's terminal, where the user can review and modify the content. The modified estimate is sent back to the server and stored in the database.

[0793] A key feature of this system is its emotion engine, which analyzes the user's tone of voice and facial expressions in real time, adjusting suggestions and quotes based on the user's emotions. For example, if the user is relaxed, it can provide standard suggestions, while if they are stressed, it can offer simpler and easier-to-understand suggestions.

[0794] Example of a prompt

[0795] The following is an example of a prompt to input into a generative AI model:

[0796] The customer's request for a high-performance laptop is based on a budget of ¥150,000, and its intended use is creative work. Based on this information, generate an optimal product proposal and quote. Please assume the customer is relaxed and provide a standard proposal.

[0797] This embodiment allows for a rapid and efficient execution of the entire process. Furthermore, the incorporation of an emotion engine enables customized suggestions that resonate with the user's emotions, thereby improving user satisfaction.

[0798] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0799] Step 1:

[0800] The user logs into the terminal and enters new customer information and interview details.

[0801] Input: Customer name, desired product, budget, intended use, and other information gathered during the interview.

[0802] Specific action: The user enters "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work" into the terminal.

[0803] Step 2:

[0804] The terminal checks the integrity of the entered data.

[0805] Input: Customer information entered in Step 1

[0806] Specific actions: The terminal checks whether all required fields are filled in and whether the data format is correct. For example, it verifies that the budget is in numerical format.

[0807] Step 3:

[0808] After the terminal verifies the integrity of the data, it sends the input data to the server.

[0809] Input: Customer information whose integrity has been verified.

[0810] Output: Data to send to the server

[0811] Specific operation: The terminal encrypts the data and sends the following information to the server: "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[0812] Step 4:

[0813] The server parses the received customer data and saves it as a new entry in the database.

[0814] Input: Customer data sent from the terminal

[0815] Output: New entries saved in the database

[0816] Specific operation: The server parses the received data in JSON format and uses SQL queries to save "Customer ID, Customer Name, Desired Product, Budget, and Usage" to the database.

[0817] Step 5:

[0818] The server searches past data in the database and extracts cases similar to the entered interview data.

[0819] Input: Newly entered customer data

[0820] Output: Data of extracted similar cases

[0821] Specific operation: Use an SQL query to extract data from the database that matches the criteria "Desired product: High-performance laptop, Budget range: 100,000 to 200,000 yen".

[0822] Step 6:

[0823] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[0824] Input: Data of extracted similar cases

[0825] Output: Best proposal and estimate

[0826] Specific operation: The server uses the KNN algorithm to calculate similarity scores and generates proposals for "high-performance laptop" and "creative software package, total cost: 130,000 yen".

[0827] Step 7:

[0828] The server automatically generates an estimate based on the analysis results obtained and sends it to the user's terminal.

[0829] Input: Analysis results

[0830] Output: Generated quote and its submission

[0831] Specific operation: The server generates a quotation, encrypts it, and sends it to the terminal. For example, it sends a quotation for "high-performance laptop 100,000 yen, creative software package 30,000 yen, total 130,000 yen".

[0832] Step 8:

[0833] The device displays the received quote, and the user can review and modify it.

[0834] Input: Estimate data sent from the server

[0835] Output: Revised estimate

[0836] Specific operation: The user can check the quote displayed on the screen and "add an additional warranty service (2 years) and adjust the price to 150,000 yen."

[0837] Step 9:

[0838] The terminal sends the revised estimate to the server.

[0839] Input: Revised estimate data

[0840] Output: Data to send to the server

[0841] Specific action: Encrypt the changes and send them to the server.

[0842] Step 10:

[0843] The server parses the corrected data and saves it back to the database.

[0844] Input: Estimate data including revisions

[0845] Output: New entry to the database

[0846] Specific operation: The server re-parses the corrected data and uses an SQL query to add a new entry to the database containing "Additional Warranty Service (2 years)".

[0847] Step 11:

[0848] The terminal displays the final quote and proposal, preparing the user to present it to the customer.

[0849] Input: Confirmed estimate data

[0850] Output: Final estimate displayed on the user screen

[0851] Specific operation: The terminal displays the estimate and proposal on the screen and provides the functionality to print or save them in digital format.

[0852] Step 12:

[0853] Users input customer service results and feedback into a terminal and send them to the server.

[0854] Input: Service results and customer feedback

[0855] Output: Data to send to the server

[0856] Specific operation: The user enters feedback such as "The customer was satisfied with the proposal and decided to purchase," and sends it to the server.

[0857] Step 13:

[0858] The server saves the received feedback data to a database.

[0859] Input: Feedback data submitted by the user

[0860] Output: Feedback entries saved in the database

[0861] Specific operation: The server parses the feedback data and saves it to a database. This data is then used to generate future proposals and estimates.

[0862] Step 14:

[0863] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions.

[0864] Input: Real-time audio and video data

[0865] Output: Detected sentiment data

[0866] Specific operation: Using the device's camera and microphone, it performs voice tone analysis and facial recognition to detect emotions such as "relaxed state" and "stressed state" in real time.

[0867] Step 15:

[0868] The server receives the detected emotion data and adjusts suggestions and estimates based on it.

[0869] Input: Detected sentiment data

[0870] Output: Adjusted proposals and quotes

[0871] Specific operation: The server analyzes emotional data and makes adjustments based on the situation, such as simplifying complex suggestions if the user is experiencing stress.

[0872] Step 16:

[0873] The server stores the detected emotion data in a database.

[0874] Input: Detected sentiment data

[0875] Output: Sentiment data entries stored in the database

[0876] Specific operation: The server parses the sentiment data and stores it in a database. This data is then used to flexibly respond to future proposal and estimate generation.

[0877] (Application Example 2)

[0878] 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."

[0879] In today's brick-and-mortar stores, there is a demand for providing customers with the most suitable proposals and quotes quickly and accurately. Furthermore, considering customer emotions and providing individually customized service leads to increased customer satisfaction. However, traditional systems require considerable time and effort to manage customer information and generate optimal proposals, making it difficult to provide proposals that reflect customer emotions in real time. This results in a decline in the quality of service and makes it difficult to improve customer satisfaction.

[0880] 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.

[0881] In this invention, the server includes means for receiving customer information and interview content and storing it in a database; means for searching for similar past data based on the stored customer information and interview content to generate optimal proposals and estimates; means for analyzing customer emotions in real time; and means for adjusting proposals and estimates based on customer emotions. This enables the provision of quick and accurate proposals and estimates to customers in physical stores, as well as individualized responses that are attentive to customer emotions.

[0882] "Customer information" refers to information that includes details such as the customer's name, contact information, desired products or services, budget, and intended use.

[0883] "Hearing content" refers to information obtained through dialogue with customers, including detailed requests, needs, and feedback.

[0884] A "database" is a system for efficiently storing, searching, and managing customer information, interview content, past proposal and quotation data, sentiment data, and other similar information.

[0885] "Similar data" refers to cases extracted from data of other customers collected in the past that are similar to the stored customer information and interview content.

[0886] A "proposal" is a plan to select and present the most suitable products or services based on the customer's requests and needs.

[0887] A "quote" is a document that details the price of goods, the fees for services, options, etc., calculated based on a proposal.

[0888] "Editing and modification" refers to the act of a user manually changing and readjusting the content of a generated proposal or estimate.

[0889] "Methods for analyzing emotions in real time" refer to technologies that use cameras and microphones to analyze a customer's facial expressions and tone of voice to identify their emotional state at that time.

[0890] "Means for adjusting proposals and estimates based on emotions" refers to technologies that automatically modify proposals and estimates to make them more appropriate based on analyzed emotions.

[0891] A "server" is a computer system that processes, stores, and retrieves data, and is a device that supports the management of customer information and the generation of proposals and estimates.

[0892] This invention is a system designed to streamline customer service in physical stores and improve customer satisfaction. This system integrates customer interview data input, real-time sentiment analysis using an emotion engine, comparison and analysis with past data, and creation and revision of estimates, enabling the provision of quick and accurate proposals and estimates.

[0893] Hardware and software configuration

[0894] 1. Terminal

[0895] The system includes smart glasses for use by store staff. These smart glasses have a built-in camera, microphone, and display, and are used for inputting customer information and analyzing customer facial expressions and voices in real time. The smart glasses also include a customer information input interface and a quotation display interface.

[0896] 2. Server

[0897] A server is a computer system for processing and storing customer information, interview content, historical data, and sentiment data. The server includes the following software components:

[0898] Database Server: Stores and manages customer data, interview content, historical data, and sentiment data. Specific software used includes database management systems such as MySQL and PostgreSQL.

[0899] Machine learning algorithms: Generate optimal suggestions and estimates from historically similar data. Specifically, build and apply models such as the KNN algorithm and linear regression using scikit-learn or TensorFlow.

[0900] Emotion Engine: Analyzes customer emotions in real time from their facial expressions and voice. This uses emotion recognition models based on OpenCV and TensorFlow.

[0901] System operation

[0902] Customer data entry and sentiment analysis

[0903] The user enters their name, desired product, budget, and intended use through smart glasses. For example, they might enter "Customer Name: Taro Yamada, Desired Product: High-performance laptop, Budget: 150,000 yen, Intended Use: Creative work." The entered data is sent to a server and stored in a database. Simultaneously, the camera and microphone built into the smart glasses analyze the customer's facial expressions and voice in real time, generating emotion data. As a result of the analysis, for example, a "relaxed state" might be detected.

[0904] Data analysis and proposal generation

[0905] The server searches for similar past data in the database and generates the optimal suggestion based on the interview content and sentiment data. Specifically, it analyzes data from customers who previously requested a "high-performance laptop" using the KNN algorithm and generates a suggestion that matches the criteria. For example, it might generate a suggestion such as "high-performance laptop, creative software package, total price: 130,000 yen."

[0906] Viewing and modifying estimates

[0907] The generated quote is displayed on the smart glasses' screen. The user can, for example, add an "additional warranty service (2 years)" and modify the quote amount to "150,000 yen". The modified data is then sent back to the server and stored in the database.

[0908] Proposal presentation to the customer

[0909] The final quote and proposal are displayed on smart glasses, which the user then presents to the customer. By providing customers with real-time, optimized proposals, it is possible to deliver high-quality service.

[0910] Specific example

[0911] Customer "Taro Yamada" visited the store requesting a high-performance laptop, with a budget of 150,000 yen. The user entered the information through smart glasses.

[0912] The emotion engine detects the customer's relaxed state.

[0913] By comparing past data with similar cases, the optimal suggestion, "High-performance laptop, creative software package, total price 130,000 yen," is generated and displayed.

[0914] The user reviewed the quote, added the "additional warranty service (2 years)," and revised the final amount to "150,000 yen."

[0915] The final quote and proposal are presented to the customer.

[0916] Example of a prompt

[0917] Customer information:

[0918] Name: Taro Yamada

[0919] Desired item: High-performance laptop

[0920] Budget: 150,000 yen

[0921] Usage: Creative work

[0922] Detected emotions:

[0923] relax

[0924] Based on past data, please generate the optimal proposal and estimate.

[0925] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0926] Step 1:

[0927] Enter customer information and interview details.

[0928] The user enters customer information (name, desired product, budget, and intended use) through smart glasses. For example, they might enter "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work." The terminal verifies the integrity of the entered data and then sends it to the server.

[0929] Input: Customer name, desired product, budget, purpose of use

[0930] Output: Customer information data sent to the server

[0931] Step 2:

[0932] sentiment analysis

[0933] The device (smart glasses) uses its built-in camera and microphone to analyze the customer's facial expressions and voice in real time, generating emotion data. For example, a "relaxed state" might be detected. The analysis results are then sent to a server.

[0934] Input: Customer facial expression and voice data

[0935] Output: Emotional data sent to the server

[0936] Step 3:

[0937] Save to database

[0938] The server saves the received customer information and sentiment data as new entries in the database. During saving, it verifies that all required fields are filled in and checks for any similar duplicate data.

[0939] Input: Customer information data, sentiment data

[0940] Output: New entries saved to the database

[0941] Step 4:

[0942] Comparison and analysis with past data

[0943] The server searches historical data in the database and extracts cases similar to the entered customer information and sentiment data. This search is performed efficiently using database queries. Furthermore, machine learning algorithms are used to evaluate the similarity and calculate the optimal recommendation.

[0944] Input: Customer information data, sentiment data

[0945] Output: Similar cases from past data and optimal suggestions

[0946] Step 5:

[0947] Generate and send quotes

[0948] Based on the analysis results obtained by the server, the optimal products and services are selected and an estimate is automatically generated. For example, an estimate such as "High-performance laptop, creative software package, total: 130,000 yen" is generated. The generated estimate and information are sent to the user's terminal.

[0949] Input: Analysis results, optimal suggestions

[0950] Output: Generated quote and information

[0951] Step 6:

[0952] Viewing and modifying estimates

[0953] The terminal displays the received quote and information. The user reviews the content and makes corrections as needed. For example, they might add "additional warranty service (2 years)" and change the quote amount to "150,000 yen". The corrected information is then sent back to the server.

[0954] Input: Generated quote and information

[0955] Output: Revised estimate

[0956] Step 7:

[0957] Save the changes

[0958] The server parses the received modifications and saves them back to the database. The revised estimate is recalculated, and the overall consistency is verified.

[0959] Input: Revised quote details

[0960] Output: Modified entries saved again in the database

[0961] Step 8:

[0962] Presentation of proposal

[0963] The terminal displays the final estimate and proposal, which the user presents to the customer in the physical store. The user then uses this information to provide high-quality customer service, thereby improving customer satisfaction.

[0964] Input: Final estimate and proposal details

[0965] Output: Final quote to present to the customer

[0966] 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.

[0967] 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.

[0968] 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.

[0969] [Third Embodiment]

[0970] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0971] 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.

[0972] 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).

[0973] 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.

[0974] 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.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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".

[0982] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[0983] Specific processing of the program

[0984] 1. Entering customer interview data

[0985] The user logs into the terminal and enters customer information and interview details.

[0986] Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[0987] The terminal checks the integrity of the entered data and confirms that all required fields are filled in.

[0988] After verification, the device sends the data to the server.

[0989] 2. Saving interview data

[0990] The server parses the received customer data and saves it as a new entry in the database. During saving, it performs an integrity check on the input data to ensure there are no similar duplicate entries.

[0991] 3. Comparison and analysis with past data

[0992] The server searches past data in the database and extracts cases similar to the entered interview data.

[0993] The server uses machine learning algorithms (e.g., KNN, linear regression) to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[0994] 4. Generating estimates and information

[0995] Based on the analysis results obtained, the server selects the most suitable products and services and automatically generates a quote.

[0996] Example: "High-performance laptop, creative software package, total price: 130,000 yen"

[0997] The server sends the generated quote and information to the user's terminal.

[0998] 5. Displaying the estimate

[0999] The terminal displays the received quote and information on its screen.

[1000] Users can review the content and make corrections as needed.

[1001] 6. Revision of the estimate

[1002] The user makes revisions to the estimate.

[1003] Example: Add "Additional Warranty Service (2 years)" and adjust the estimated price to "150,000 yen".

[1004] The terminal sends the changes to the server.

[1005] 7. Re-save the changes

[1006] The server parses the received modifications and saves them back to the database.

[1007] The server recalculates the revised estimate and verifies its consistency.

[1008] 8. Preparation for guiding and serving customers

[1009] The terminal displays the final quote and proposal, and can be presented to the customer in print or digital format.

[1010] Based on the revised quotes and information, users provide high-quality customer service.

[1011] 9. Recording of customer service results

[1012] Users input customer service results and feedback into a terminal.

[1013] The device sends feedback data to the server.

[1014] The server saves the feedback to a database for future analysis.

[1015] Specific example

[1016] Customer interview data entry

[1017] For example, a user might input customer information for "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is then sent from the terminal to the server and stored in the database.

[1018] Comparison and analysis with past data

[1019] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable recommendation.

[1020] Estimate and guide generation

[1021] In this case, the server generates an estimate of 130,000 yen for a "high-performance laptop" and a "creative software package," and sends it to the user's terminal.

[1022] Estimate revision and notification

[1023] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[1024] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide a consistent, high-quality service.

[1025] The following describes the processing flow.

[1026] Step 1:

[1027] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1028] Step 2:

[1029] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1030] Step 3:

[1031] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[1032] Step 4:

[1033] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1034] Step 5:

[1035] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1036] Step 6:

[1037] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[1038] Step 7:

[1039] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1040] Step 8:

[1041] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1042] Step 9:

[1043] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1044] Step 10:

[1045] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1046] Step 11:

[1047] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[1048] Step 12:

[1049] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1050] Step 13:

[1051] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1052] Step 14:

[1053] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1054] Step 15:

[1055] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1056] Step 16:

[1057] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[1058] Through the steps outlined above, this system handles everything from collecting customer data and generating optimal proposals to revising quotes and supporting high-quality customer service. This enables all crew members to provide consistent, high-quality service.

[1059] (Example 1)

[1060] 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."

[1061] Traditional customer service systems require manual input of customer information and generation of quotes, resulting in significant time and effort, as well as a high risk of human error. Furthermore, referencing past data to provide optimal solutions is difficult, requiring more advanced technology to improve customer satisfaction. Additionally, maintaining data integrity is challenging due to the difficulty in consistently managing user modifications.

[1062] 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.

[1063] In this invention, the server includes means for the user to input customer information and interview content into a terminal, and for the terminal to send the data to the server after confirmation; means for the server to parse the received customer data and save it as a new entry in a database; and means for the server to search past data in the database, extract cases similar to the input data using a machine learning algorithm, and automatically generate optimal proposals and estimates. This automates everything from inputting customer information to generating optimal proposals, enabling efficient and consistent customer service.

[1064] "Customer information" refers to data that includes the customer's name, contact information, purchase history, and information about the services or products they request.

[1065] "Interview content" refers to information gathered through dialogue with customers, such as their needs, desired products and services, budget, and intended use.

[1066] A "terminal" is an electronic device, such as a computer or mobile device, that a user operates.

[1067] A "server" is a central processing unit for receiving, processing, storing, and transmitting data.

[1068] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1069] A "machine learning algorithm" is a mathematical model or method used for data analysis and prediction, learning rules and patterns from past data.

[1070] A "quote" is a document or data that shows the price of goods or services offered to a customer.

[1071] A "proposal" is a suggestion for the best product or service based on the customer's needs.

[1072] "Feedback" refers to information that includes opinions, evaluations, and impressions received from customers.

[1073] "Consistency" is a concept that refers to a state in which data is consistent and free from contradictions or errors.

[1074] This invention can be implemented using a server equipped with an operating system, a user-operated terminal, and software components to coordinate them. The main hardware configuration of this system includes a database server, an application server, and a user-operated computer or mobile terminal.

[1075] Input and transmission of customer interview data

[1076] The user logs into the terminal and enters customer information and interview details. For example, they might enter information such as "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work." This data undergoes a consistency check, and after confirming that all required fields are filled in, it is sent to the server.

[1077] Saving interview data

[1078] The server parses the received customer data and saves it as a new entry in a database (e.g., MySQL). During saving, it verifies that there are no similar duplicate data entries and that the data is consistent. For example, based on the information of a customer named "Ichiro Tanaka," it re-verifies data with similar desired products and budgets.

[1079] Comparison and analysis with past data

[1080] The server searches historical data in the database and extracts cases similar to the input interview data. In this case, a high-speed search engine such as Elasticsearch is used to efficiently extract data. Next, the server evaluates the similarity using the displayed machine learning algorithms. For example, algorithms such as KNN (nearest neighbor search) and linear regression are implemented using Scikit-learn.

[1081] Estimate and guide generation

[1082] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." This quotation document is then sent to the user's terminal.

[1083] Displaying and modifying estimates

[1084] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. For example, it is possible to add an additional warranty service (2 years) and adjust the quote so that the total amount comes to 150,000 yen. The revised quote is then sent back to the server.

[1085] Re-save the changes

[1086] The server parses the received revisions and saves them back into the database. The revised estimate is also checked for consistency and verified again.

[1087] Final check-in and preparation for customer service

[1088] The terminal displays the final quote and proposal. This information is presented to the customer in digital or printable format. The user then uses this information to provide high-quality customer service. For example, they can print the revised quote and explanatory document to make a more specific proposal to the customer.

[1089] Record of customer service results

[1090] Users input customer service results and feedback into a terminal. This feedback data is sent to a server and stored in a database.

[1091] Examples of prompt statements

[1092] "Customer Name: Ichiro Tanaka, Desired Product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[1093] In this way, the system automates and optimizes the entire process from customer information input to generating optimal proposals, adjusting quotes, and final customer support, enabling efficient and consistent service delivery.

[1094] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1095] Step 1:

[1096] The user enters customer information and interview details into the terminal. Specifically, they enter data such as customer name, product preference, budget, and intended use into the input fields. Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work". The terminal checks the integrity of the entered data and verifies that all required fields are filled in. If there are no problems, the data is sent to the server.

[1097] Input: Customer information and interview details

[1098] Output: Customer data sent to the server

[1099] Step 2:

[1100] The server parses the received customer data. Specifically, it analyzes the received JSON data and extracts values ​​corresponding to each field (customer name, product preference, budget, and intended use). Next, it saves this data as a new entry in the database. For example, it saves it to a MySQL database using an INSERT statement. During saving, it also performs data integrity checks and checks for duplicate data.

[1101] Input: Received customer data

[1102] Output: Customer data stored in the database

[1103] Step 3:

[1104] The server searches past data in the database and extracts similar cases. Specifically, it efficiently searches past interview data using tools such as Elasticsearch. Next, it applies machine learning algorithms (e.g., KNN, linear regression) based on similar cases to calculate the optimal proposal. This proposal is generated by considering successful cases and proposal content extracted from past similar cases.

[1105] Input: New customer data

[1106] Output: Generation of optimal proposals and estimates

[1107] Step 4:

[1108] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." These quotation documents are generated in text or PDF format and sent to the user's terminal.

[1109] Input: Analysis results (proposal)

[1110] Output: Generated quotation document

[1111] Step 5:

[1112] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. Specifically, they can add an "additional warranty service (2 years)" to the quote and revise the final amount to 150,000 yen. The revised content is then sent back to the server.

[1113] Input: Received quotation document

[1114] Output: Revised estimate

[1115] Step 6:

[1116] The server parses the received modifications and resaves them in the database. Specifically, it analyzes the modified estimate document and saves it as a new entry in the database. In addition, consistency checks and recalculations are performed based on the modified data.

[1117] Input: Revised quote details

[1118] Output: Corrected data saved again in the database

[1119] Step 7:

[1120] The terminal displays the final quote and proposal, preparing them for presentation to the user in print or digital format. The user then uses this information to provide high-quality customer service, specifically by using the revised quote and accompanying documents to make concrete proposals to the customer.

[1121] Input: Final quote and proposal

[1122] Output: Quotation document presented to the customer

[1123] Step 8:

[1124] The user inputs the results of the customer service and customer feedback into a terminal. The input feedback data is sent from the terminal to the server, which stores it in a database. Specifically, the feedback content is entered in text format and stored in the appropriate field in the database.

[1125] Input: Service results and customer feedback

[1126] Output: Feedback information stored in the database

[1127] (Application Example 1)

[1128] 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."

[1129] In traditional manufacturing, optimizing manufacturing processes and generating proposals required significant time and effort, and the management and estimation of these processes were inefficient. Furthermore, responding to problems arising in the manufacturing process in real time was difficult, often resulting in decreased productivity and cost efficiency.

[1130] 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.

[1131] In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for collecting manufacturing process data based on the stored customer information and interview content and generating optimal proposals and estimates, and means for the user to edit and modify the content of the generated estimates. This enables optimization of the manufacturing process and efficient estimate generation.

[1132] "Customer information" refers to basic information and requests regarding customers in the manufacturing environment.

[1133] "Hearing content" refers to information that shows the specific needs and requirements collected from customers during manufacturing operations.

[1134] A "database" is a system for centrally storing and managing customer information, interview results, and other related data.

[1135] "Means of preservation" refers to methods or devices that provide the function of writing collected information into a database and storing it permanently.

[1136] "Manufacturing process data" refers to information about specific work stages and conditions related to manufacturing operations.

[1137] A "proposal" refers to the optimal solution or method derived from similar past data and current needs.

[1138] An "estimate" is the result of calculating the manufacturing costs and other related expenses based on the proposal.

[1139] "Means of editing and modification" refers to functions or devices that allow users to manually change and modify the generated estimates and proposals.

[1140] "Manufacturing operations" refers to all tasks and processes involved in the production of a product.

[1141] "Means of guidance" refers to methods and devices for presenting users with optimal proposals and estimates, and for providing instructions and guidance at the manufacturing site.

[1142] "Manufacturing results" refer to information about the final outcomes or results obtained after executing a manufacturing process.

[1143] "Production feedback" refers to opinions and information, such as suggestions for improvement and evaluations, obtained after manufacturing operations have been carried out.

[1144] A "machine learning algorithm" is a statistical method and mathematical model used to process large amounts of historical data, recognize patterns, and predict future outcomes.

[1145] To implement this invention, a system is needed to collect customer information and interview data related to the manufacturing process and store it in a database. This system consists of a robot installed on the manufacturing site, a server that processes the data, and software components to coordinate them. Specifically, it uses Python and Scikit-learn to implement machine learning algorithms (such as KNN).

[1146] First, the terminal inputs customer information and interview details. For example, information such as "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Usage: Mass production" is entered. The terminal performs a data integrity check on the entered data to confirm that all required fields are filled in accurately. After that, the data is sent to the server.

[1147] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During saving, the integrity of the input data is checked again to confirm that there is no similar duplicate data. Next, the server searches for similar past data in the database and uses a machine learning algorithm to extract cases similar to the new data. In this process, Scikit-learn's KNN (neighborhood association algorithm) is used to calculate the similarity of the data and generate the best suggestions and estimates.

[1148] The generated estimate and proposal are sent back to the terminal and displayed on the user's screen. The user can review this information and edit or modify it as needed. For example, they might add an "additional warranty service (3 years)" to adjust the final budget to "3.2 million yen." The modified information is then sent back from the terminal to the server and saved again in the database.

[1149] Once the final estimate and proposal are confirmed, the user presents them to the workers involved in the manufacturing process and provides specific instructions. The user also inputs the results of the manufacturing operations and production feedback into a terminal, sends them to a server, and stores them in a database. This feedback is used for future analysis and leads to improvements in the optimal manufacturing process.

[1150] Examples of specific prompt messages include the following:

[1151] "Customer Name: Jiro Sato, Desired Product: New Automotive Parts, Budget: 5 million yen, Purpose: Mass production of high-performance engines"

[1152] By using such prompt statements, the system can process data quickly and efficiently, and propose and estimate the optimal manufacturing process.

[1153] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1154] Step 1:

[1155] The terminal inputs customer information and interview details. This input includes customer name, desired product, budget, and intended use. The terminal performs a consistency check on this information to ensure that all required fields are filled in accurately. A specific example of input would be: "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Intended use: Mass production."

[1156] Step 2:

[1157] The terminal sends the input data, after integrity checks have been completed, to the server. The transmitted data includes customer information and interview details. The terminal initiates data transmission and manages the communication until the data reaches the server.

[1158] Step 3:

[1159] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During this process, it performs another consistency check to ensure there are no similar duplicate data entries. The server accurately parses the data and adds it to the database as structured data.

[1160] Step 4:

[1161] The server searches for similar historical data within the database. Specifically, it matches the data against past customer information and extracts data with similar conditions. The server uses a machine learning algorithm to calculate the similarity of the data and generates optimal suggestions and estimates. The algorithm used is Scikit-learn's KNN (neighborhood association algorithm).

[1162] Step 5:

[1163] The server sends the generated quote and proposal to the terminal. The transmitted data includes the proposal, detailed product information, and the estimated price. A typical output might be a quote such as, "Industrial robot, additional warranty service (3 years), total: 3.2 million yen."

[1164] Step 6:

[1165] The terminal displays the received quote and proposal details on the user's screen. The user can review this information and edit or modify it as needed. For example, they can extend the warranty period or add additional services.

[1166] Step 7:

[1167] If the user modifies the estimate, the terminal resends the modified data to the server. The server receives the modified data and saves it again in the database. Based on the modifications, a consistency check is performed again, and the final estimate is confirmed.

[1168] Step 8:

[1169] Once the final estimate and proposal are confirmed, the terminal presents them to the workers involved in the manufacturing process. The user then provides specific instructions and prepares to begin the manufacturing operations.

[1170] Step 9:

[1171] After a manufacturing task is completed, the user inputs the results and production feedback into a terminal. The terminal sends the input feedback data to a server, which stores it in a database. This feedback data is used to improve the quality of future suggestions.

[1172] 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.

[1173] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. Furthermore, this system incorporates an emotion engine that recognizes user emotions, thereby adjusting optimal proposals and estimates based on the user's emotions. The entire process consists of a terminal operated by the user, a server that performs the processing, and software components that coordinate these.

[1174] Specific processing of the program

[1175] 1. Entering customer interview data

[1176] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1177] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1178] After the terminal verifies the integrity of the data, it sends the input data to the server.

[1179] 2. Saving interview data

[1180] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1181] 3. Comparison and analysis with past data

[1182] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1183] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal. For example, it uses methods such as the KNN algorithm or linear regression.

[1184] 4. Generating estimates and information

[1185] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1186] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1187] 5. Viewing and modifying estimates

[1188] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1189] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1190] The terminal sends the changes to the server.

[1191] 6. Re-save the changes

[1192] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1193] 7. Preparation for guiding and serving customers

[1194] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1195] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1196] 8. Recording of customer service results

[1197] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1198] The device sends feedback data to the server.

[1199] The server stores the feedback in a database to help create future proposals and estimates.

[1200] 9. Integrating an emotion engine

[1201] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions. This analysis is performed using the device's camera and microphone.

[1202] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, if the user is feeling stressed, it will offer simpler and easier-to-understand suggestions.

[1203] The server stores the detected emotion data in a database and uses it for future proposals and quotes.

[1204] Specific example

[1205] Customer interview data entry and emotion recognition

[1206] For example, a user might input customer information, such as "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is sent from the terminal to the server and stored in the database. Simultaneously, an emotion engine analyzes the user's voice tone and facial expressions to detect if they are relaxed.

[1207] Comparison and analysis with past data, and adjustment based on sentiment.

[1208] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable suggestion. Furthermore, it refers to emotional data and presents standard suggestions to users in a relaxed state.

[1209] Estimate revision and notification

[1210] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[1211] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine enables customized suggestions that resonate with the user's emotions.

[1212] The following describes the processing flow.

[1213] Step 1:

[1214] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1215] Step 2:

[1216] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1217] Step 3:

[1218] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[1219] Step 4:

[1220] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1221] Step 5:

[1222] The emotion engine analyzes the user's voice tone and facial expressions to detect emotions. This analysis is performed using the device's camera and microphone.

[1223] Step 6:

[1224] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, it will offer standard suggestions if the user is relaxed and simpler suggestions if they are stressed.

[1225] Step 7:

[1226] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1227] Step 8:

[1228] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[1229] Step 9:

[1230] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1231] Step 10:

[1232] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1233] Step 11:

[1234] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1235] Step 12:

[1236] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1237] Step 13:

[1238] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[1239] Step 14:

[1240] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1241] Step 15:

[1242] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1243] Step 16:

[1244] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1245] Step 17:

[1246] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1247] Step 18:

[1248] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[1249] In this way, the entire process is carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine allows for customized suggestions that resonate with the user's emotions.

[1250] (Example 2)

[1251] 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."

[1252] Traditional systems made customer information input and management cumbersome, and comparing and analyzing data with past data was often time-consuming. Furthermore, for users to provide high-quality proposals to customers, they had to manually generate optimal proposals and estimates based on interview content, which was inefficient. Additionally, proposals and estimates were not adjusted to take into account user emotions, making improving customer satisfaction a challenge.

[1253] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for searching for similar past data based on the stored customer information and interview content and generating optimal proposals and estimates using a machine learning algorithm, and means for recognizing the user's emotions and adjusting proposals and estimates based on those emotions. This enables efficient management of customer information and automatic generation of optimal proposals and estimates, making it possible to provide high-quality services that are attentive to the user's emotions.

[1254] "Customer information" refers to information about the customer, including their name, address, contact information, purchase history, and products they have shown interest in.

[1255] "Interview content" refers to information about customer needs, wishes, budget, and intended use, collected through interviews and conversations with customers.

[1256] A "database" refers to a digital data storage system used to efficiently store, manage, and retrieve customer information and interview transcripts.

[1257] A "machine learning algorithm" refers to a computational method used to learn rules and patterns from data and make future suggestions or predictions. Specifically, this includes methods such as K-nearest neighbors (KNN) and linear regression.

[1258] A "proposal" refers to a recommendation or suggestion that presents the most suitable products or services based on the customer's needs and preferences.

[1259] A "quote" refers to a document that specifically calculates and presents the price and conditions of a product or service based on a proposal.

[1260] "Emotion recognition" refers to a technology that analyzes a user's voice tone and facial expressions to detect their emotional state. This analysis utilizes natural language processing engines and facial recognition engines.

[1261] "Editing and modification" refers to the process where a user reviews the estimates and proposals generated by the system and makes changes as needed.

[1262] The system of this invention inputs and manages customer information and interview content, compares and analyzes it with past data, and generates optimal proposals and estimates. Furthermore, by incorporating an emotion engine that recognizes user emotions, it adjusts optimal proposals and estimates based on the user's emotions. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[1263] The system's hardware configuration includes user terminals (e.g., PCs and tablets), a database server for storing customer information, and an application server for data processing. The emotion engine operates using a camera and microphone connected to the user's terminal.

[1264] The software includes database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., scikit-learn, TensorFlow), natural language processing engines, and facial recognition engines. These software components work together to efficiently input, store, retrieve, and analyze data.

[1265] As a concrete example, consider a scenario where a user logs into a terminal and inputs new customer information and interview details. The input data is checked for integrity by the terminal and sent to the server. The server receives the data and stores it in a database. Next, the server uses a machine learning algorithm to search past data and generate the optimal proposal. The generated proposal and estimate are sent to the user's terminal, where the user can review and modify the content. The modified estimate is sent back to the server and stored in the database.

[1266] A key feature of this system is its emotion engine, which analyzes the user's tone of voice and facial expressions in real time, adjusting suggestions and quotes based on the user's emotions. For example, if the user is relaxed, it can provide standard suggestions, while if they are stressed, it can offer simpler and easier-to-understand suggestions.

[1267] Example of a prompt

[1268] The following is an example of a prompt to input into a generative AI model:

[1269] The customer's request for a high-performance laptop is based on a budget of ¥150,000, and its intended use is creative work. Based on this information, generate an optimal product proposal and quote. Please assume the customer is relaxed and provide a standard proposal.

[1270] This embodiment allows for a rapid and efficient execution of the entire process. Furthermore, the incorporation of an emotion engine enables customized suggestions that resonate with the user's emotions, thereby improving user satisfaction.

[1271] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1272] Step 1:

[1273] The user logs into the terminal and enters new customer information and interview details.

[1274] Input: Customer name, desired product, budget, intended use, and other information gathered during the interview.

[1275] Specific action: The user enters "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work" into the terminal.

[1276] Step 2:

[1277] The terminal checks the integrity of the entered data.

[1278] Input: Customer information entered in Step 1

[1279] Specific actions: The terminal checks whether all required fields are filled in and whether the data format is correct. For example, it verifies that the budget is in numerical format.

[1280] Step 3:

[1281] After the terminal verifies the integrity of the data, it sends the input data to the server.

[1282] Input: Customer information whose integrity has been verified.

[1283] Output: Data to send to the server

[1284] Specific operation: The terminal encrypts the data and sends the following information to the server: "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1285] Step 4:

[1286] The server parses the received customer data and saves it as a new entry in the database.

[1287] Input: Customer data sent from the terminal

[1288] Output: New entries saved in the database

[1289] Specific operation: The server parses the received data in JSON format and uses SQL queries to save "Customer ID, Customer Name, Desired Product, Budget, and Usage" to the database.

[1290] Step 5:

[1291] The server searches past data in the database and extracts cases similar to the entered interview data.

[1292] Input: Newly entered customer data

[1293] Output: Data of extracted similar cases

[1294] Specific operation: Use an SQL query to extract data from the database that matches the criteria "Desired product: High-performance laptop, Budget range: 100,000 to 200,000 yen".

[1295] Step 6:

[1296] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[1297] Input: Data of extracted similar cases

[1298] Output: Best proposal and estimate

[1299] Specific operation: The server uses the KNN algorithm to calculate similarity scores and generates proposals for "high-performance laptop" and "creative software package, total cost: 130,000 yen".

[1300] Step 7:

[1301] The server automatically generates an estimate based on the analysis results obtained and sends it to the user's terminal.

[1302] Input: Analysis results

[1303] Output: Generated quote and its submission

[1304] Specific operation: The server generates a quotation, encrypts it, and sends it to the terminal. For example, it sends a quotation for "high-performance laptop 100,000 yen, creative software package 30,000 yen, total 130,000 yen".

[1305] Step 8:

[1306] The device displays the received quote, and the user can review and modify it.

[1307] Input: Estimate data sent from the server

[1308] Output: Revised estimate

[1309] Specific operation: The user can check the quote displayed on the screen and "add an additional warranty service (2 years) and adjust the price to 150,000 yen."

[1310] Step 9:

[1311] The terminal sends the revised estimate to the server.

[1312] Input: Revised estimate data

[1313] Output: Data to send to the server

[1314] Specific action: Encrypt the changes and send them to the server.

[1315] Step 10:

[1316] The server parses the corrected data and saves it back to the database.

[1317] Input: Estimate data including revisions

[1318] Output: New entry to the database

[1319] Specific operation: The server re-parses the corrected data and uses an SQL query to add a new entry to the database containing "Additional Warranty Service (2 years)".

[1320] Step 11:

[1321] The terminal displays the final quote and proposal, preparing the user to present it to the customer.

[1322] Input: Confirmed estimate data

[1323] Output: Final estimate displayed on the user screen

[1324] Specific operation: The terminal displays the estimate and proposal on the screen and provides the functionality to print or save them in digital format.

[1325] Step 12:

[1326] Users input customer service results and feedback into a terminal and send them to the server.

[1327] Input: Service results and customer feedback

[1328] Output: Data to send to the server

[1329] Specific operation: The user enters feedback such as "The customer was satisfied with the proposal and decided to purchase," and sends it to the server.

[1330] Step 13:

[1331] The server saves the received feedback data to a database.

[1332] Input: Feedback data submitted by the user

[1333] Output: Feedback entries saved in the database

[1334] Specific operation: The server parses the feedback data and saves it to a database. This data is then used to generate future proposals and estimates.

[1335] Step 14:

[1336] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions.

[1337] Input: Real-time audio and video data

[1338] Output: Detected sentiment data

[1339] Specific operation: Using the device's camera and microphone, it performs voice tone analysis and facial recognition to detect emotions such as "relaxed state" and "stressed state" in real time.

[1340] Step 15:

[1341] The server receives the detected emotion data and adjusts suggestions and estimates based on it.

[1342] Input: Detected sentiment data

[1343] Output: Adjusted proposals and quotes

[1344] Specific operation: The server analyzes emotional data and makes adjustments based on the situation, such as simplifying complex suggestions if the user is experiencing stress.

[1345] Step 16:

[1346] The server stores the detected emotion data in a database.

[1347] Input: Detected sentiment data

[1348] Output: Sentiment data entries stored in the database

[1349] Specific operation: The server parses the sentiment data and stores it in a database. This data is then used to flexibly respond to future proposal and estimate generation.

[1350] (Application Example 2)

[1351] 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."

[1352] In today's brick-and-mortar stores, there is a demand for providing customers with the most suitable proposals and quotes quickly and accurately. Furthermore, considering customer emotions and providing individually customized service leads to increased customer satisfaction. However, traditional systems require considerable time and effort to manage customer information and generate optimal proposals, making it difficult to provide proposals that reflect customer emotions in real time. This results in a decline in the quality of service and makes it difficult to improve customer satisfaction.

[1353] 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.

[1354] In this invention, the server includes means for receiving customer information and interview content and storing it in a database; means for searching for similar past data based on the stored customer information and interview content to generate optimal proposals and estimates; means for analyzing customer emotions in real time; and means for adjusting proposals and estimates based on customer emotions. This enables the provision of quick and accurate proposals and estimates to customers in physical stores, as well as individualized responses that are attentive to customer emotions.

[1355] "Customer information" refers to information that includes details such as the customer's name, contact information, desired products or services, budget, and intended use.

[1356] "Hearing content" refers to information obtained through dialogue with customers, including detailed requests, needs, and feedback.

[1357] A "database" is a system for efficiently storing, searching, and managing customer information, interview content, past proposal and quotation data, sentiment data, and other similar information.

[1358] "Similar data" refers to cases extracted from data of other customers collected in the past that are similar to the stored customer information and interview content.

[1359] A "proposal" is a plan to select and present the most suitable products or services based on the customer's requests and needs.

[1360] A "quote" is a document that details the price of goods, the fees for services, options, etc., calculated based on a proposal.

[1361] "Editing and modification" refers to the act of a user manually changing and readjusting the content of a generated proposal or estimate.

[1362] "Methods for analyzing emotions in real time" refer to technologies that use cameras and microphones to analyze a customer's facial expressions and tone of voice to identify their emotional state at that time.

[1363] "Means for adjusting proposals and estimates based on emotions" refers to technologies that automatically modify proposals and estimates to make them more appropriate based on analyzed emotions.

[1364] A "server" is a computer system that processes, stores, and retrieves data, and is a device that supports the management of customer information and the generation of proposals and estimates.

[1365] This invention is a system designed to streamline customer service in physical stores and improve customer satisfaction. This system integrates customer interview data input, real-time sentiment analysis using an emotion engine, comparison and analysis with past data, and creation and revision of estimates, enabling the provision of quick and accurate proposals and estimates.

[1366] Hardware and software configuration

[1367] 1. Terminal

[1368] The system includes smart glasses for use by store staff. These smart glasses have a built-in camera, microphone, and display, and are used for inputting customer information and analyzing customer facial expressions and voices in real time. The smart glasses also include a customer information input interface and a quotation display interface.

[1369] 2. Server

[1370] A server is a computer system for processing and storing customer information, interview content, historical data, and sentiment data. The server includes the following software components:

[1371] Database Server: Stores and manages customer data, interview content, historical data, and sentiment data. Specific software used includes database management systems such as MySQL and PostgreSQL.

[1372] Machine learning algorithms: Generate optimal suggestions and estimates from historically similar data. Specifically, build and apply models such as the KNN algorithm and linear regression using scikit-learn or TensorFlow.

[1373] Emotion Engine: Analyzes customer emotions in real time from their facial expressions and voice. This uses emotion recognition models based on OpenCV and TensorFlow.

[1374] System operation

[1375] Customer data entry and sentiment analysis

[1376] The user enters their name, desired product, budget, and intended use through smart glasses. For example, they might enter "Customer Name: Taro Yamada, Desired Product: High-performance laptop, Budget: 150,000 yen, Intended Use: Creative work." The entered data is sent to a server and stored in a database. Simultaneously, the camera and microphone built into the smart glasses analyze the customer's facial expressions and voice in real time, generating emotion data. As a result of the analysis, for example, a "relaxed state" might be detected.

[1377] Data analysis and proposal generation

[1378] The server searches for similar past data in the database and generates the optimal suggestion based on the interview content and sentiment data. Specifically, it analyzes data from customers who previously requested a "high-performance laptop" using the KNN algorithm and generates a suggestion that matches the criteria. For example, it might generate a suggestion such as "high-performance laptop, creative software package, total price: 130,000 yen."

[1379] Viewing and modifying estimates

[1380] The generated quote is displayed on the smart glasses' screen. The user can, for example, add an "additional warranty service (2 years)" and modify the quote amount to "150,000 yen". The modified data is then sent back to the server and stored in the database.

[1381] Proposal presentation to the customer

[1382] The final quote and proposal are displayed on smart glasses, which the user then presents to the customer. By providing customers with real-time, optimized proposals, it is possible to deliver high-quality service.

[1383] Specific example

[1384] Customer "Taro Yamada" visited the store requesting a high-performance laptop, with a budget of 150,000 yen. The user entered the information through smart glasses.

[1385] The emotion engine detects the customer's relaxed state.

[1386] By comparing past data with similar cases, the optimal suggestion, "High-performance laptop, creative software package, total price 130,000 yen," is generated and displayed.

[1387] The user reviewed the quote, added the "additional warranty service (2 years)," and revised the final amount to "150,000 yen."

[1388] The final quote and proposal are presented to the customer.

[1389] Example of a prompt

[1390] Customer information:

[1391] Name: Taro Yamada

[1392] Desired item: High-performance laptop

[1393] Budget: 150,000 yen

[1394] Usage: Creative work

[1395] Detected emotions:

[1396] relax

[1397] Based on past data, please generate the optimal proposal and estimate.

[1398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1399] Step 1:

[1400] Enter customer information and interview details.

[1401] The user enters customer information (name, desired product, budget, and intended use) through smart glasses. For example, they might enter "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work." The terminal verifies the integrity of the entered data and then sends it to the server.

[1402] Input: Customer name, desired product, budget, purpose of use

[1403] Output: Customer information data sent to the server

[1404] Step 2:

[1405] sentiment analysis

[1406] The device (smart glasses) uses its built-in camera and microphone to analyze the customer's facial expressions and voice in real time, generating emotion data. For example, a "relaxed state" might be detected. The analysis results are then sent to a server.

[1407] Input: Customer facial expression and voice data

[1408] Output: Emotional data sent to the server

[1409] Step 3:

[1410] Save to database

[1411] The server saves the received customer information and sentiment data as new entries in the database. During saving, it verifies that all required fields are filled in and checks for any similar duplicate data.

[1412] Input: Customer information data, sentiment data

[1413] Output: New entries saved to the database

[1414] Step 4:

[1415] Comparison and analysis with past data

[1416] The server searches historical data in the database and extracts cases similar to the entered customer information and sentiment data. This search is performed efficiently using database queries. Furthermore, machine learning algorithms are used to evaluate the similarity and calculate the optimal recommendation.

[1417] Input: Customer information data, sentiment data

[1418] Output: Similar cases from past data and optimal suggestions

[1419] Step 5:

[1420] Generate and send quotes

[1421] Based on the analysis results obtained by the server, the optimal products and services are selected and an estimate is automatically generated. For example, an estimate such as "High-performance laptop, creative software package, total: 130,000 yen" is generated. The generated estimate and information are sent to the user's terminal.

[1422] Input: Analysis results, optimal suggestions

[1423] Output: Generated quote and information

[1424] Step 6:

[1425] Viewing and modifying estimates

[1426] The terminal displays the received quote and information. The user reviews the content and makes corrections as needed. For example, they might add "additional warranty service (2 years)" and change the quote amount to "150,000 yen". The corrected information is then sent back to the server.

[1427] Input: Generated quote and information

[1428] Output: Revised estimate

[1429] Step 7:

[1430] Save the changes

[1431] The server parses the received modifications and saves them back to the database. The revised estimate is recalculated, and the overall consistency is verified.

[1432] Input: Revised quote details

[1433] Output: Modified entries saved again in the database

[1434] Step 8:

[1435] Presentation of proposal

[1436] The terminal displays the final estimate and proposal, which the user presents to the customer in the physical store. The user then uses this information to provide high-quality customer service, thereby improving customer satisfaction.

[1437] Input: Final estimate and proposal details

[1438] Output: Final quote to present to the customer

[1439] 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.

[1440] 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.

[1441] 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.

[1442] [Fourth Embodiment]

[1443] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1444] 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.

[1445] 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).

[1446] 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.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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".

[1456] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[1457] Specific processing of the program

[1458] 1. Entering customer interview data

[1459] The user logs into the terminal and enters customer information and interview details.

[1460] Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[1461] The terminal checks the integrity of the entered data and confirms that all required fields are filled in.

[1462] After verification, the device sends the data to the server.

[1463] 2. Saving interview data

[1464] The server parses the received customer data and saves it as a new entry in the database. During saving, it performs an integrity check on the input data to ensure there are no similar duplicate entries.

[1465] 3. Comparison and analysis with past data

[1466] The server searches past data in the database and extracts cases similar to the entered interview data.

[1467] The server uses machine learning algorithms (e.g., KNN, linear regression) to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[1468] 4. Generating estimates and information

[1469] Based on the analysis results obtained, the server selects the most suitable products and services and automatically generates a quote.

[1470] Example: "High-performance laptop, creative software package, total price: 130,000 yen"

[1471] The server sends the generated quote and information to the user's terminal.

[1472] 5. Displaying the estimate

[1473] The terminal displays the received quote and information on its screen.

[1474] Users can review the content and make corrections as needed.

[1475] 6. Revision of the estimate

[1476] The user makes revisions to the estimate.

[1477] Example: Add "Additional Warranty Service (2 years)" and adjust the estimated price to "150,000 yen".

[1478] The terminal sends the changes to the server.

[1479] 7. Re-save the changes

[1480] The server parses the received modifications and saves them back to the database.

[1481] The server recalculates the revised estimate and verifies its consistency.

[1482] 8. Preparation for guiding and serving customers

[1483] The terminal displays the final quote and proposal, and can be presented to the customer in print or digital format.

[1484] Based on the revised quotes and information, users provide high-quality customer service.

[1485] 9. Recording of customer service results

[1486] Users input customer service results and feedback into a terminal.

[1487] The device sends feedback data to the server.

[1488] The server saves the feedback to a database for future analysis.

[1489] Specific example

[1490] Customer interview data entry

[1491] For example, a user might input customer information for "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is then sent from the terminal to the server and stored in the database.

[1492] Comparison and analysis with past data

[1493] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable recommendation.

[1494] Estimate and guide generation

[1495] In this case, the server generates an estimate of 130,000 yen for a "high-performance laptop" and a "creative software package," and sends it to the user's terminal.

[1496] Estimate revision and notification

[1497] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[1498] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide a consistent, high-quality service.

[1499] The following describes the processing flow.

[1500] Step 1:

[1501] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1502] Step 2:

[1503] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1504] Step 3:

[1505] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[1506] Step 4:

[1507] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1508] Step 5:

[1509] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1510] Step 6:

[1511] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[1512] Step 7:

[1513] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1514] Step 8:

[1515] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1516] Step 9:

[1517] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1518] Step 10:

[1519] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1520] Step 11:

[1521] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[1522] Step 12:

[1523] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1524] Step 13:

[1525] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1526] Step 14:

[1527] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1528] Step 15:

[1529] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1530] Step 16:

[1531] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[1532] Through the steps outlined above, this system handles everything from collecting customer data and generating optimal proposals to revising quotes and supporting high-quality customer service. This enables all crew members to provide consistent, high-quality service.

[1533] (Example 1)

[1534] 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".

[1535] Traditional customer service systems require manual input of customer information and generation of quotes, resulting in significant time and effort, as well as a high risk of human error. Furthermore, referencing past data to provide optimal solutions is difficult, requiring more advanced technology to improve customer satisfaction. Additionally, maintaining data integrity is challenging due to the difficulty in consistently managing user modifications.

[1536] 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.

[1537] In this invention, the server includes means for the user to input customer information and interview content into a terminal, and for the terminal to send the data to the server after confirmation; means for the server to parse the received customer data and save it as a new entry in a database; and means for the server to search past data in the database, extract cases similar to the input data using a machine learning algorithm, and automatically generate optimal proposals and estimates. This automates everything from inputting customer information to generating optimal proposals, enabling efficient and consistent customer service.

[1538] "Customer information" refers to data that includes the customer's name, contact information, purchase history, and information about the services or products they request.

[1539] "Interview content" refers to information gathered through dialogue with customers, such as their needs, desired products and services, budget, and intended use.

[1540] A "terminal" is an electronic device, such as a computer or mobile device, that a user operates.

[1541] A "server" is a central processing unit for receiving, processing, storing, and transmitting data.

[1542] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1543] A "machine learning algorithm" is a mathematical model or method used for data analysis and prediction, learning rules and patterns from past data.

[1544] A "quote" is a document or data that shows the price of goods or services offered to a customer.

[1545] A "proposal" is a suggestion for the best product or service based on the customer's needs.

[1546] "Feedback" refers to information that includes opinions, evaluations, and impressions received from customers.

[1547] "Consistency" is a concept that refers to a state in which data is consistent and free from contradictions or errors.

[1548] This invention can be implemented using a server equipped with an operating system, a user-operated terminal, and software components to coordinate them. The main hardware configuration of this system includes a database server, an application server, and a user-operated computer or mobile terminal.

[1549] Input and transmission of customer interview data

[1550] The user logs into the terminal and enters customer information and interview details. For example, they might enter information such as "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work." This data undergoes a consistency check, and after confirming that all required fields are filled in, it is sent to the server.

[1551] Saving interview data

[1552] The server parses the received customer data and saves it as a new entry in a database (e.g., MySQL). During saving, it verifies that there are no similar duplicate data entries and that the data is consistent. For example, based on the information of a customer named "Ichiro Tanaka," it re-verifies data with similar desired products and budgets.

[1553] Comparison and analysis with past data

[1554] The server searches historical data in the database and extracts cases similar to the input interview data. In this case, a high-speed search engine such as Elasticsearch is used to efficiently extract data. Next, the server evaluates the similarity using the displayed machine learning algorithms. For example, algorithms such as KNN (nearest neighbor search) and linear regression are implemented using Scikit-learn.

[1555] Estimate and guide generation

[1556] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." This quotation document is then sent to the user's terminal.

[1557] Displaying and modifying estimates

[1558] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. For example, it is possible to add an additional warranty service (2 years) and adjust the quote so that the total amount comes to 150,000 yen. The revised quote is then sent back to the server.

[1559] Re-save the changes

[1560] The server parses the received revisions and saves them back into the database. The revised estimate is also checked for consistency and verified again.

[1561] Final check-in and preparation for customer service

[1562] The terminal displays the final quote and proposal. This information is presented to the customer in digital or printable format. The user then uses this information to provide high-quality customer service. For example, they can print the revised quote and explanatory document to make a more specific proposal to the customer.

[1563] Record of customer service results

[1564] Users input customer service results and feedback into a terminal. This feedback data is sent to a server and stored in a database.

[1565] Examples of prompt statements

[1566] "Customer Name: Ichiro Tanaka, Desired Product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work"

[1567] In this way, the system automates and optimizes the entire process from customer information input to generating optimal proposals, adjusting quotes, and final customer support, enabling efficient and consistent service delivery.

[1568] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1569] Step 1:

[1570] The user enters customer information and interview details into the terminal. Specifically, they enter data such as customer name, product preference, budget, and intended use into the input fields. Example: "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work". The terminal checks the integrity of the entered data and verifies that all required fields are filled in. If there are no problems, the data is sent to the server.

[1571] Input: Customer information and interview details

[1572] Output: Customer data sent to the server

[1573] Step 2:

[1574] The server parses the received customer data. Specifically, it analyzes the received JSON data and extracts values ​​corresponding to each field (customer name, product preference, budget, and intended use). Next, it saves this data as a new entry in the database. For example, it saves it to a MySQL database using an INSERT statement. During saving, it also performs data integrity checks and checks for duplicate data.

[1575] Input: Received customer data

[1576] Output: Customer data stored in the database

[1577] Step 3:

[1578] The server searches past data in the database and extracts similar cases. Specifically, it efficiently searches past interview data using tools such as Elasticsearch. Next, it applies machine learning algorithms (e.g., KNN, linear regression) based on similar cases to calculate the optimal proposal. This proposal is generated by considering successful cases and proposal content extracted from past similar cases.

[1579] Input: New customer data

[1580] Output: Generation of optimal proposals and estimates

[1581] Step 4:

[1582] Based on the analysis results, the server selects the most suitable products and services and automatically generates a quotation document. For example, it might generate a proposal such as "High-performance laptop, creative software package, total: 130,000 yen." These quotation documents are generated in text or PDF format and sent to the user's terminal.

[1583] Input: Analysis results (proposal)

[1584] Output: Generated quotation document

[1585] Step 5:

[1586] The terminal displays the received quote and information on the screen. The user reviews the content and makes corrections if necessary. Specifically, they can add an "additional warranty service (2 years)" to the quote and revise the final amount to 150,000 yen. The revised content is then sent back to the server.

[1587] Input: Received quotation document

[1588] Output: Revised estimate

[1589] Step 6:

[1590] The server parses the received modifications and resaves them in the database. Specifically, it analyzes the modified estimate document and saves it as a new entry in the database. In addition, consistency checks and recalculations are performed based on the modified data.

[1591] Input: Revised quote details

[1592] Output: Corrected data saved again in the database

[1593] Step 7:

[1594] The terminal displays the final quote and proposal, preparing them for presentation to the user in print or digital format. The user then uses this information to provide high-quality customer service, specifically by using the revised quote and accompanying documents to make concrete proposals to the customer.

[1595] Input: Final quote and proposal

[1596] Output: Quotation document presented to the customer

[1597] Step 8:

[1598] The user inputs the results of the customer service and customer feedback into a terminal. The input feedback data is sent from the terminal to the server, which stores it in a database. Specifically, the feedback content is entered in text format and stored in the appropriate field in the database.

[1599] Input: Service results and customer feedback

[1600] Output: Feedback information stored in the database

[1601] (Application Example 1)

[1602] 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".

[1603] In traditional manufacturing, optimizing manufacturing processes and generating proposals required significant time and effort, and the management and estimation of these processes were inefficient. Furthermore, responding to problems arising in the manufacturing process in real time was difficult, often resulting in decreased productivity and cost efficiency.

[1604] 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.

[1605] In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for collecting manufacturing process data based on the stored customer information and interview content and generating optimal proposals and estimates, and means for the user to edit and modify the content of the generated estimates. This enables optimization of the manufacturing process and efficient estimate generation.

[1606] "Customer information" refers to basic information and requests regarding customers in the manufacturing environment.

[1607] "Hearing content" refers to information that shows the specific needs and requirements collected from customers during manufacturing operations.

[1608] A "database" is a system for centrally storing and managing customer information, interview results, and other related data.

[1609] "Means of preservation" refers to methods or devices that provide the function of writing collected information into a database and storing it permanently.

[1610] "Manufacturing process data" refers to information about specific work stages and conditions related to manufacturing operations.

[1611] A "proposal" refers to the optimal solution or method derived from similar past data and current needs.

[1612] An "estimate" is the result of calculating the manufacturing costs and other related expenses based on the proposal.

[1613] "Means of editing and modification" refers to functions or devices that allow users to manually change and modify the generated estimates and proposals.

[1614] "Manufacturing operations" refers to all operations and processes related to the production of products.

[1615] "Means of guidance" refers to methods and devices for presenting optimal proposals and estimates to users and providing instructions and guidance at the manufacturing site.

[1616] "Manufacturing operation results" refers to information regarding the final achievements and results obtained after executing the manufacturing process.

[1617] "Production feedback" refers to opinions and information such as improvements and evaluations obtained after conducting manufacturing operations.

[1618] "Machine learning algorithms" are statistical methods and mathematical models for processing large amounts of past data, recognizing patterns, and predicting future results.

[1619] To implement this invention, a system is required to collect customer information and hearing content related to the manufacturing process and store them in a database. This system is composed of robots installed at the manufacturing site, servers for processing data, and software components for coordinating them. Specifically, Python and Scikit-learn are used to implement machine learning algorithms (such as KNN).

[1620] First, the terminal inputs customer information and hearing content. For example, information such as "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Usage: Mass production" is input. The input data is checked for integrity on the terminal to confirm whether all required items are accurately filled. Then, the data is sent to the server.

[1621] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During saving, the integrity of the input data is checked again to confirm that there is no similar duplicate data. Next, the server searches for similar past data in the database and uses a machine learning algorithm to extract cases similar to the new data. In this process, Scikit-learn's KNN (neighborhood association algorithm) is used to calculate the similarity of the data and generate the best suggestions and estimates.

[1622] The generated estimate and proposal are sent back to the terminal and displayed on the user's screen. The user can review this information and edit or modify it as needed. For example, they might add an "additional warranty service (3 years)" to adjust the final budget to "3.2 million yen." The modified information is then sent back from the terminal to the server and saved again in the database.

[1623] Once the final estimate and proposal are confirmed, the user presents them to the workers involved in the manufacturing process and provides specific instructions. The user also inputs the results of the manufacturing operations and production feedback into a terminal, sends them to a server, and stores them in a database. This feedback is used for future analysis and leads to improvements in the optimal manufacturing process.

[1624] Examples of specific prompt messages include the following:

[1625] "Customer Name: Jiro Sato, Desired Product: New Automotive Parts, Budget: 5 million yen, Purpose: Mass production of high-performance engines"

[1626] By using such prompt statements, the system can process data quickly and efficiently, and propose and estimate the optimal manufacturing process.

[1627] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1628] Step 1:

[1629] The terminal inputs customer information and interview details. This input includes customer name, desired product, budget, and intended use. The terminal performs a consistency check on this information to ensure that all required fields are filled in accurately. A specific example of input would be: "Customer name: Taro Yamada, Desired product: Industrial robot, Budget: 3 million yen, Intended use: Mass production."

[1630] Step 2:

[1631] The terminal sends the input data, after integrity checks have been completed, to the server. The transmitted data includes customer information and interview details. The terminal initiates data transmission and manages the communication until the data reaches the server.

[1632] Step 3:

[1633] The server analyzes the received customer information and interview content and saves it as a new entry in the database. During this process, it performs another consistency check to ensure there are no similar duplicate data entries. The server accurately parses the data and adds it to the database as structured data.

[1634] Step 4:

[1635] The server searches for similar historical data within the database. Specifically, it matches the data against past customer information and extracts data with similar conditions. The server uses a machine learning algorithm to calculate the similarity of the data and generates optimal suggestions and estimates. The algorithm used is Scikit-learn's KNN (neighborhood association algorithm).

[1636] Step 5:

[1637] The server sends the generated quote and proposal to the terminal. The transmitted data includes the proposal, detailed product information, and the estimated price. A typical output might be a quote such as, "Industrial robot, additional warranty service (3 years), total: 3.2 million yen."

[1638] Step 6:

[1639] The terminal displays the received quote and proposal details on the user's screen. The user can review this information and edit or modify it as needed. For example, they can extend the warranty period or add additional services.

[1640] Step 7:

[1641] If the user modifies the estimate, the terminal resends the modified data to the server. The server receives the modified data and saves it again in the database. Based on the modifications, a consistency check is performed again, and the final estimate is confirmed.

[1642] Step 8:

[1643] Once the final estimate and proposal are confirmed, the terminal presents them to the workers involved in the manufacturing process. The user then provides specific instructions and prepares to begin the manufacturing operations.

[1644] Step 9:

[1645] After a manufacturing task is completed, the user inputs the results and production feedback into a terminal. The terminal sends the input feedback data to a server, which stores it in a database. This feedback data is used to improve the quality of future suggestions.

[1646] 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.

[1647] To implement this invention, it is necessary to build a system that inputs and manages customer information and interview content, compares and analyzes it with past data, generates optimal proposals and estimates, and ultimately provides high-quality guidance to customers. Furthermore, this system incorporates an emotion engine that recognizes user emotions, thereby adjusting optimal proposals and estimates based on the user's emotions. The entire process consists of a terminal operated by the user, a server that performs the processing, and software components that coordinate these.

[1648] Specific processing of the program

[1649] 1. Entering customer interview data

[1650] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1651] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1652] After the terminal verifies the integrity of the data, it sends the input data to the server.

[1653] 2. Saving interview data

[1654] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1655] 3. Comparison and analysis with past data

[1656] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1657] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal. For example, it uses methods such as the KNN algorithm or linear regression.

[1658] 4. Generating estimates and information

[1659] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1660] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1661] 5. Viewing and modifying estimates

[1662] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1663] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1664] The terminal sends the changes to the server.

[1665] 6. Re-save the changes

[1666] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1667] 7. Preparation for guiding and serving customers

[1668] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1669] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1670] 8. Recording of customer service results

[1671] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1672] The device sends feedback data to the server.

[1673] The server stores the feedback in a database to help create future proposals and estimates.

[1674] 9. Integrating an emotion engine

[1675] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions. This analysis is performed using the device's camera and microphone.

[1676] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, if the user is feeling stressed, it will offer simpler and easier-to-understand suggestions.

[1677] The server stores the detected emotion data in a database and uses it for future proposals and quotes.

[1678] Specific example

[1679] Customer interview data entry and emotion recognition

[1680] For example, a user might input customer information, such as "Ichiro Tanaka," specifying that the customer desires a "high-performance laptop," has a budget of "150,000 yen," and intends to use it for "creative work." This information is sent from the terminal to the server and stored in the database. Simultaneously, an emotion engine analyzes the user's voice tone and facial expressions to detect if they are relaxed.

[1681] Comparison and analysis with past data, and adjustment based on sentiment.

[1682] The server uses this new customer information to search for similar past cases and derives suggestions using machine learning algorithms. Specifically, it analyzes data from other customers who previously requested a "high-performance laptop" to provide the most suitable suggestion. Furthermore, it refers to emotional data and presents standard suggestions to users in a relaxed state.

[1683] Estimate revision and notification

[1684] The user reviews the quote, adds "additional warranty service (2 years)," and adjusts the final amount to "150,000 yen." The changes are resent from the terminal, and the server saves these changes back into the database. The final quote is confirmed, and the user presents it to the customer.

[1685] This allows the entire process to be carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine enables customized suggestions that resonate with the user's emotions.

[1686] The following describes the processing flow.

[1687] Step 1:

[1688] The user logs into the terminal and enters new customer information and interview details. For example, they might enter "Customer name: Ichiro Tanaka, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1689] Step 2:

[1690] The terminal checks the integrity of the entered data. It verifies that all required fields are filled in and that the data format is correct.

[1691] Step 3:

[1692] After the terminal verifies the integrity of the input data, it sends it to the server. The transmitted data includes customer name, desired product, budget, and intended use.

[1693] Step 4:

[1694] The server parses the received customer data and saves it as a new entry in the database. During saving, it checks the integrity of the input data and verifies that there is no similar duplicate data.

[1695] Step 5:

[1696] The emotion engine analyzes the user's voice tone and facial expressions to detect emotions. This analysis is performed using the device's camera and microphone.

[1697] Step 6:

[1698] The server receives the detected emotion data and adjusts its suggestions and estimates accordingly. For example, it will offer standard suggestions if the user is relaxed and simpler suggestions if they are stressed.

[1699] Step 7:

[1700] The server searches past data in the database and extracts cases similar to the input interview data. This search is performed efficiently using database queries.

[1701] Step 8:

[1702] The server uses machine learning algorithms to evaluate similarity and analyzes high-scoring cases. For example, it uses methods such as the KNN algorithm or linear regression to calculate the most suitable proposal.

[1703] Step 9:

[1704] Based on the analysis results obtained, the server selects the optimal products and services and automatically generates a quote. For example, it might generate a quote such as "High-performance laptop, creative software package, total: 130,000 yen."

[1705] Step 10:

[1706] The server sends the generated quote and information to the user's terminal. The transmitted data includes the quote details and proposal.

[1707] Step 11:

[1708] The terminal displays the received quote and information on its screen. The user can review the content and make corrections as needed.

[1709] Step 12:

[1710] The user modifies the estimate. For example, they might add an "additional warranty service (2 years)" and adjust the estimate so that the total amount becomes "150,000 yen".

[1711] Step 13:

[1712] The device sends the correction details to the server. The correction data includes any added warranty services and the total cost after the correction.

[1713] Step 14:

[1714] The server parses the received modifications and saves them back to the database. It then recalculates the revised estimate and verifies the overall consistency.

[1715] Step 15:

[1716] The terminal displays the final quote and proposal, allowing the user to present it to the customer in print or digital format.

[1717] Step 16:

[1718] Based on the revised quotes and information, users provide high-quality customer service. This allows them to offer customers the best possible proposals and quotes.

[1719] Step 17:

[1720] Users input the results of their customer service interactions and customer feedback into a terminal. This includes customer reactions and additional requests.

[1721] Step 18:

[1722] The terminal sends feedback data to the server. The server stores the feedback in a database and uses it to create future proposals and estimates.

[1723] In this way, the entire process is carried out quickly and efficiently, enabling all crew members to provide consistent, high-quality service. Furthermore, the integration of an emotion engine allows for customized suggestions that resonate with the user's emotions.

[1724] (Example 2)

[1725] 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".

[1726] Traditional systems made customer information input and management cumbersome, and comparing and analyzing data with past data was often time-consuming. Furthermore, for users to provide high-quality proposals to customers, they had to manually generate optimal proposals and estimates based on interview content, which was inefficient. Additionally, proposals and estimates were not adjusted to take into account user emotions, making improving customer satisfaction a challenge.

[1727] In Example 2, the identification processing performed by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving customer information and interview content and storing it in a database, means for searching for similar past data based on the stored customer information and interview content and generating optimal proposals and estimates using a machine learning algorithm, and means for recognizing the user's emotions and adjusting proposals and estimates based on those emotions. This enables efficient management of customer information and automatic generation of optimal proposals and estimates, making it possible to provide high-quality services that are attentive to the user's emotions.

[1728] "Customer information" refers to information about the customer, including their name, address, contact information, purchase history, and products they have shown interest in.

[1729] "Interview content" refers to information about customer needs, wishes, budget, and intended use, collected through interviews and conversations with customers.

[1730] A "database" refers to a digital data storage system used to efficiently store, manage, and retrieve customer information and interview transcripts.

[1731] A "machine learning algorithm" refers to a computational method used to learn rules and patterns from data and make future suggestions or predictions. Specifically, this includes methods such as K-nearest neighbors (KNN) and linear regression.

[1732] A "proposal" refers to a recommendation or suggestion that presents the most suitable products or services based on the customer's needs and preferences.

[1733] A "quote" refers to a document that specifically calculates and presents the price and conditions of a product or service based on a proposal.

[1734] "Emotion recognition" refers to a technology that analyzes a user's voice tone and facial expressions to detect their emotional state. This analysis utilizes natural language processing engines and facial recognition engines.

[1735] "Editing and modification" refers to the process where a user reviews the estimates and proposals generated by the system and makes changes as needed.

[1736] The system of this invention inputs and manages customer information and interview content, compares and analyzes it with past data, and generates optimal proposals and estimates. Furthermore, by incorporating an emotion engine that recognizes user emotions, it adjusts optimal proposals and estimates based on the user's emotions. This system consists of a terminal operated by the user, a server that performs processing, and software components that link these together.

[1737] The system's hardware configuration includes user terminals (e.g., PCs and tablets), a database server for storing customer information, and an application server for data processing. The emotion engine operates using a camera and microphone connected to the user's terminal.

[1738] The software includes database management systems (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., scikit-learn, TensorFlow), natural language processing engines, and facial recognition engines. These software components work together to efficiently input, store, retrieve, and analyze data.

[1739] As a concrete example, consider a scenario where a user logs into a terminal and inputs new customer information and interview details. The input data is checked for integrity by the terminal and sent to the server. The server receives the data and stores it in a database. Next, the server uses a machine learning algorithm to search past data and generate the optimal proposal. The generated proposal and estimate are sent to the user's terminal, where the user can review and modify the content. The modified estimate is sent back to the server and stored in the database.

[1740] A key feature of this system is its emotion engine, which analyzes the user's tone of voice and facial expressions in real time, adjusting suggestions and quotes based on the user's emotions. For example, if the user is relaxed, it can provide standard suggestions, while if they are stressed, it can offer simpler and easier-to-understand suggestions.

[1741] Example of a prompt

[1742] The following is an example of a prompt to input into a generative AI model:

[1743] The customer's request for a high-performance laptop is based on a budget of ¥150,000, and its intended use is creative work. Based on this information, generate an optimal product proposal and quote. Please assume the customer is relaxed and provide a standard proposal.

[1744] This embodiment allows for a rapid and efficient execution of the entire process. Furthermore, the incorporation of an emotion engine enables customized suggestions that resonate with the user's emotions, thereby improving user satisfaction.

[1745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1746] Step 1:

[1747] The user logs into the terminal and enters new customer information and interview details.

[1748] Input: Customer name, desired product, budget, intended use, and other information gathered during the interview.

[1749] Specific action: The user enters "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work" into the terminal.

[1750] Step 2:

[1751] The terminal checks the integrity of the entered data.

[1752] Input: Customer information entered in Step 1

[1753] Specific actions: The terminal checks whether all required fields are filled in and whether the data format is correct. For example, it verifies that the budget is in numerical format.

[1754] Step 3:

[1755] After the terminal verifies the integrity of the data, it sends the input data to the server.

[1756] Input: Customer information whose integrity has been verified.

[1757] Output: Data to send to the server

[1758] Specific operation: The terminal encrypts the data and sends the following information to the server: "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Usage: Creative work".

[1759] Step 4:

[1760] The server parses the received customer data and saves it as a new entry in the database.

[1761] Input: Customer data sent from the terminal

[1762] Output: New entries saved in the database

[1763] Specific operation: The server parses the received data in JSON format and uses SQL queries to save "Customer ID, Customer Name, Desired Product, Budget, and Usage" to the database.

[1764] Step 5:

[1765] The server searches past data in the database and extracts cases similar to the entered interview data.

[1766] Input: Newly entered customer data

[1767] Output: Data of extracted similar cases

[1768] Specific operation: Use an SQL query to extract data from the database that matches the criteria "Desired product: High-performance laptop, Budget range: 100,000 to 200,000 yen".

[1769] Step 6:

[1770] The server uses machine learning algorithms to evaluate similarity, analyzes high-scoring cases, and calculates the most suitable proposal.

[1771] Input: Data of extracted similar cases

[1772] Output: Best proposal and estimate

[1773] Specific operation: The server uses the KNN algorithm to calculate similarity scores and generates proposals for "high-performance laptop" and "creative software package, total cost: 130,000 yen".

[1774] Step 7:

[1775] The server automatically generates an estimate based on the analysis results obtained and sends it to the user's terminal.

[1776] Input: Analysis results

[1777] Output: Generated quote and its submission

[1778] Specific operation: The server generates a quotation, encrypts it, and sends it to the terminal. For example, it sends a quotation for "high-performance laptop 100,000 yen, creative software package 30,000 yen, total 130,000 yen".

[1779] Step 8:

[1780] The device displays the received quote, and the user can review and modify it.

[1781] Input: Estimate data sent from the server

[1782] Output: Revised estimate

[1783] Specific operation: The user can check the quote displayed on the screen and "add an additional warranty service (2 years) and adjust the price to 150,000 yen."

[1784] Step 9:

[1785] The terminal sends the revised estimate to the server.

[1786] Input: Revised estimate data

[1787] Output: Data to send to the server

[1788] Specific action: Encrypt the changes and send them to the server.

[1789] Step 10:

[1790] The server parses the corrected data and saves it back to the database.

[1791] Input: Estimate data including revisions

[1792] Output: New entry to the database

[1793] Specific operation: The server re-parses the corrected data and uses an SQL query to add a new entry to the database containing "Additional Warranty Service (2 years)".

[1794] Step 11:

[1795] The terminal displays the final quote and proposal, preparing the user to present it to the customer.

[1796] Input: Confirmed estimate data

[1797] Output: Final estimate displayed on the user screen

[1798] Specific operation: The terminal displays the estimate and proposal on the screen and provides the functionality to print or save them in digital format.

[1799] Step 12:

[1800] Users input customer service results and feedback into a terminal and send them to the server.

[1801] Input: Service results and customer feedback

[1802] Output: Data to send to the server

[1803] Specific operation: The user enters feedback such as "The customer was satisfied with the proposal and decided to purchase," and sends it to the server.

[1804] Step 13:

[1805] The server saves the received feedback data to a database.

[1806] Input: Feedback data submitted by the user

[1807] Output: Feedback entries saved in the database

[1808] Specific operation: The server parses the feedback data and saves it to a database. This data is then used to generate future proposals and estimates.

[1809] Step 14:

[1810] The emotion engine analyzes the user's voice tone and facial expressions in real time to detect emotions.

[1811] Input: Real-time audio and video data

[1812] Output: Detected sentiment data

[1813] Specific operation: Using the device's camera and microphone, it performs voice tone analysis and facial recognition to detect emotions such as "relaxed state" and "stressed state" in real time.

[1814] Step 15:

[1815] The server receives the detected emotion data and adjusts suggestions and estimates based on it.

[1816] Input: Detected sentiment data

[1817] Output: Adjusted proposals and quotes

[1818] Specific operation: The server analyzes emotional data and makes adjustments based on the situation, such as simplifying complex suggestions if the user is experiencing stress.

[1819] Step 16:

[1820] The server stores the detected emotion data in a database.

[1821] Input: Detected sentiment data

[1822] Output: Sentiment data entries stored in the database

[1823] Specific operation: The server parses the sentiment data and stores it in a database. This data is then used to flexibly respond to future proposal and estimate generation.

[1824] (Application Example 2)

[1825] 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".

[1826] In today's brick-and-mortar stores, there is a demand for providing customers with the most suitable proposals and quotes quickly and accurately. Furthermore, considering customer emotions and providing individually customized service leads to increased customer satisfaction. However, traditional systems require considerable time and effort to manage customer information and generate optimal proposals, making it difficult to provide proposals that reflect customer emotions in real time. This results in a decline in the quality of service and makes it difficult to improve customer satisfaction.

[1827] 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.

[1828] In this invention, the server includes means for receiving customer information and interview content and storing it in a database; means for searching for similar past data based on the stored customer information and interview content to generate optimal proposals and estimates; means for analyzing customer emotions in real time; and means for adjusting proposals and estimates based on customer emotions. This enables the provision of quick and accurate proposals and estimates to customers in physical stores, as well as individualized responses that are attentive to customer emotions.

[1829] "Customer information" refers to information that includes details such as the customer's name, contact information, desired products or services, budget, and intended use.

[1830] "Hearing content" refers to information obtained through dialogue with customers, including detailed requests, needs, and feedback.

[1831] A "database" is a system for efficiently storing, searching, and managing customer information, interview content, past proposal and quotation data, sentiment data, and other similar information.

[1832] "Similar data" refers to cases extracted from data of other customers collected in the past that are similar to the stored customer information and interview content.

[1833] A "proposal" is a plan to select and present the most suitable products or services based on the customer's requests and needs.

[1834] A "quote" is a document that details the price of goods, the fees for services, options, etc., calculated based on a proposal.

[1835] "Editing and modification" refers to the act of a user manually changing and readjusting the content of a generated proposal or estimate.

[1836] "Methods for analyzing emotions in real time" refer to technologies that use cameras and microphones to analyze a customer's facial expressions and tone of voice to identify their emotional state at that time.

[1837] "Means for adjusting proposals and estimates based on emotions" refers to technologies that automatically modify proposals and estimates to make them more appropriate based on analyzed emotions.

[1838] A "server" is a computer system that processes, stores, and retrieves data, and is a device that supports the management of customer information and the generation of proposals and estimates.

[1839] This invention is a system designed to streamline customer service in physical stores and improve customer satisfaction. This system integrates customer interview data input, real-time sentiment analysis using an emotion engine, comparison and analysis with past data, and creation and revision of estimates, enabling the provision of quick and accurate proposals and estimates.

[1840] Hardware and software configuration

[1841] 1. Terminal

[1842] The system includes smart glasses for use by store staff. These smart glasses have a built-in camera, microphone, and display, and are used for inputting customer information and analyzing customer facial expressions and voices in real time. The smart glasses also include a customer information input interface and a quotation display interface.

[1843] 2. Server

[1844] A server is a computer system for processing and storing customer information, interview content, historical data, and sentiment data. The server includes the following software components:

[1845] Database Server: Stores and manages customer data, interview content, historical data, and sentiment data. Specific software used includes database management systems such as MySQL and PostgreSQL.

[1846] Machine learning algorithms: Generate optimal suggestions and estimates from historically similar data. Specifically, build and apply models such as the KNN algorithm and linear regression using scikit-learn or TensorFlow.

[1847] Emotion Engine: Analyzes customer emotions in real time from their facial expressions and voice. This uses emotion recognition models based on OpenCV and TensorFlow.

[1848] System operation

[1849] Customer data entry and sentiment analysis

[1850] The user enters their name, desired product, budget, and intended use through smart glasses. For example, they might enter "Customer Name: Taro Yamada, Desired Product: High-performance laptop, Budget: 150,000 yen, Intended Use: Creative work." The entered data is sent to a server and stored in a database. Simultaneously, the camera and microphone built into the smart glasses analyze the customer's facial expressions and voice in real time, generating emotion data. As a result of the analysis, for example, a "relaxed state" might be detected.

[1851] Data analysis and proposal generation

[1852] The server searches for similar past data in the database and generates the optimal suggestion based on the interview content and sentiment data. Specifically, it analyzes data from customers who previously requested a "high-performance laptop" using the KNN algorithm and generates a suggestion that matches the criteria. For example, it might generate a suggestion such as "high-performance laptop, creative software package, total price: 130,000 yen."

[1853] Viewing and modifying estimates

[1854] The generated quote is displayed on the smart glasses' screen. The user can, for example, add an "additional warranty service (2 years)" and modify the quote amount to "150,000 yen". The modified data is then sent back to the server and stored in the database.

[1855] Proposal presentation to the customer

[1856] The final quote and proposal are displayed on smart glasses, which the user then presents to the customer. By providing customers with real-time, optimized proposals, it is possible to deliver high-quality service.

[1857] Specific example

[1858] Customer "Taro Yamada" visited the store requesting a high-performance laptop, with a budget of 150,000 yen. The user entered the information through smart glasses.

[1859] The emotion engine detects the customer's relaxed state.

[1860] By comparing past data with similar cases, the optimal suggestion, "High-performance laptop, creative software package, total price 130,000 yen," is generated and displayed.

[1861] The user reviewed the quote, added the "additional warranty service (2 years)," and revised the final amount to "150,000 yen."

[1862] The final quote and proposal are presented to the customer.

[1863] Example of a prompt

[1864] Customer information:

[1865] Name: Taro Yamada

[1866] Desired item: High-performance laptop

[1867] Budget: 150,000 yen

[1868] Usage: Creative work

[1869] Detected emotions:

[1870] relax

[1871] Based on past data, please generate the optimal proposal and estimate.

[1872] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1873] Step 1:

[1874] Enter customer information and interview details.

[1875] The user enters customer information (name, desired product, budget, and intended use) through smart glasses. For example, they might enter "Customer name: Taro Yamada, Desired product: High-performance laptop, Budget: 150,000 yen, Intended use: Creative work." The terminal verifies the integrity of the entered data and then sends it to the server.

[1876] Input: Customer name, desired product, budget, purpose of use

[1877] Output: Customer information data sent to the server

[1878] Step 2:

[1879] sentiment analysis

[1880] The device (smart glasses) uses its built-in camera and microphone to analyze the customer's facial expressions and voice in real time, generating emotion data. For example, a "relaxed state" might be detected. The analysis results are then sent to a server.

[1881] Input: Customer facial expression and voice data

[1882] Output: Emotional data sent to the server

[1883] Step 3:

[1884] Save to database

[1885] The server saves the received customer information and sentiment data as new entries in the database. During saving, it verifies that all required fields are filled in and checks for any similar duplicate data.

[1886] Input: Customer information data, sentiment data

[1887] Output: New entries saved to the database

[1888] Step 4:

[1889] Comparison and analysis with past data

[1890] The server searches historical data in the database and extracts cases similar to the entered customer information and sentiment data. This search is performed efficiently using database queries. Furthermore, machine learning algorithms are used to evaluate the similarity and calculate the optimal recommendation.

[1891] Input: Customer information data, sentiment data

[1892] Output: Similar cases from past data and optimal suggestions

[1893] Step 5:

[1894] Generate and send quotes

[1895] Based on the analysis results obtained by the server, the optimal products and services are selected and an estimate is automatically generated. For example, an estimate such as "High-performance laptop, creative software package, total: 130,000 yen" is generated. The generated estimate and information are sent to the user's terminal.

[1896] Input: Analysis results, optimal suggestions

[1897] Output: Generated quote and information

[1898] Step 6:

[1899] Viewing and modifying estimates

[1900] The terminal displays the received quote and information. The user reviews the content and makes corrections as needed. For example, they might add "additional warranty service (2 years)" and change the quote amount to "150,000 yen". The corrected information is then sent back to the server.

[1901] Input: Generated quote and information

[1902] Output: Revised estimate

[1903] Step 7:

[1904] Save the changes

[1905] The server parses the received modifications and saves them back to the database. The revised estimate is recalculated, and the overall consistency is verified.

[1906] Input: Revised quote details

[1907] Output: Modified entries saved again in the database

[1908] Step 8:

[1909] Presentation of proposal

[1910] The terminal displays the final estimate and proposal, which the user presents to the customer in the physical store. The user then uses this information to provide high-quality customer service, thereby improving customer satisfaction.

[1911] Input: Final estimate and proposal details

[1912] Output: Final quote to present to the customer

[1913] 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.

[1914] 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.

[1915] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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."

[1922] 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.

[1923] 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.

[1924] 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.

[1925] 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.

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] The following is further disclosed regarding the embodiments described above.

[1935] (Claim 1)

[1936] A means of receiving customer information and interview content and storing it in a database,

[1937] A means of searching for similar past data based on saved customer information and interview content to generate optimal proposals and estimates,

[1938] A means for the user to edit and modify the generated estimate,

[1939] A means to save the revised estimate back into the database,

[1940] A means for the user to display the aforementioned estimate and proposal and to guide the customer based on it,

[1941] A system that includes this.

[1942] (Claim 2)

[1943] The system according to claim 1, comprising means for receiving customer service results and customer feedback from users and storing them in a database.

[1944] (Claim 3)

[1945] The system according to claim 1, comprising means for generating optimal suggestions and estimates from similar past data using a machine learning algorithm.

[1946] "Example 1"

[1947] (Claim 1)

[1948] A means by which the user inputs customer information and interview details into a terminal, and after the terminal confirms the data, sends the data to a server.

[1949] A means for the server to parse the customer data it receives and save it as a new entry in the database,

[1950] A server searches past data in a database, uses a machine learning algorithm to extract cases similar to the input data, and automatically generates optimal proposals and estimates.

[1951] A means by which the server sends the generated estimate to the terminal, and the terminal displays the contents,

[1952] A means for a user to modify the estimate using a terminal and send the modified content to the server,

[1953] The server resaves the revised estimate details to the database and verifies their integrity.

[1954] A means for users to display the final estimate and proposal and guide customers through the process,

[1955] A system that includes this.

[1956] (Claim 2)

[1957] The system according to claim 1, comprising means for receiving customer service results and customer feedback from users and storing them in a database.

[1958] (Claim 3)

[1959] The system according to claim 1, comprising means for generating optimal suggestions and estimates from similar past data using a machine learning algorithm.

[1960] "Application Example 1"

[1961] (Claim 1)

[1962] A means of receiving customer information and interview content and storing it in a database,

[1963] A means of collecting manufacturing process data based on stored customer information and interview content, and generating optimal proposals and estimates.

[1964] A means for the user to edit and modify the generated estimate,

[1965] A means to save the revised estimate back into the database,

[1966] A means for displaying the aforementioned estimate and proposal to the user and guiding them through the manufacturing process based thereon,

[1967] A system that includes this.

[1968] (Claim 2)

[1969] The system according to claim 1, comprising means for receiving manufacturing operation results and production feedback from users and storing them in a database.

[1970] (Claim 3)

[1971] The system according to claim 1, comprising means for generating optimal suggestions and estimates for manufacturing operations from similar past data using a machine learning algorithm.

[1972] "Example 2 of combining an emotion engine"

[1973] (Claim 1)

[1974] A means of receiving customer information and interview content and storing it in a database,

[1975] A means of searching for similar past data based on saved customer information and interview content, and generating optimal proposals and estimates using machine learning algorithms,

[1976] A means for the user to edit and modify the generated estimate,

[1977] A means to save the revised estimate back into the database,

[1978] A means for the user to display the aforementioned estimate and proposal and to guide the customer based on it,

[1979] A means of recognizing user emotions and adjusting suggestions and estimates based on those emotions,

[1980] A system that includes this.

[1981] (Claim 2)

[1982] The system according to claim 1, comprising means for receiving customer service results and customer feedback from users and storing them in a database.

[1983] (Claim 3)

[1984] The system according to claim 1, comprising means for generating optimal suggestions and estimates from similar past data using a machine learning algorithm.

[1985] "Application example 2 when combining with an emotional engine"

[1986] (Claim 1)

[1987] A means of receiving customer information and interview content and storing it in a database,

[1988] A means of searching for similar past data based on saved customer information and ...

Claims

1. A means of receiving customer information and interview content and storing it in a database, A means of searching for similar past data based on saved customer information and interview content to generate optimal proposals and estimates, A means for the user to edit and modify the generated estimate, A means to save the revised estimate back into the database, A means for the user to display the aforementioned estimate and proposal and to guide the customer based on it, A system that includes this.

2. The system according to claim 1, comprising means for receiving customer service results and customer feedback from users and storing them in a database.

3. The system according to claim 1, comprising means for generating optimal suggestions and estimates from similar past data using a machine learning algorithm.

Images