system

Abstract

The system according to this embodiment aims to automate sales activities and accumulate internal know-how. [Solution] The system according to the embodiment comprises a generation unit, a reply unit, an estimation unit, an analysis unit, an investigation unit, and a question and answer unit. The generation unit automatically generates a list of new customers. The reply unit automatically replies to inquiries based on the list generated by the generation unit. The estimation unit automatically generates an estimate based on the content of the reply from the reply unit. The analysis unit analyzes customer behavior based on the estimate generated by the estimation unit. The investigation unit conducts a competitive analysis based on the results of the analysis by the analysis unit. The question and answer unit creates anticipated questions and answers based on the information obtained by the investigation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In the conventional technology, the automation of business activities and the accumulation of in-house know-how have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to automate business activities and accumulate in-house know-how.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a generation unit, a reply unit, an estimation unit, an analysis unit, a research unit, and a question-and-answer unit. The generation unit automatically generates a list of new customers. The reply unit automatically replies to inquiries based on the list generated by the generation unit. The estimation unit automatically generates an estimate based on the content of the reply from the reply unit. The analysis unit analyzes customer behavior based on the estimate generated by the estimation unit. The research unit conducts competitive research based on the results of the analysis by the analysis unit. The question-and-answer unit creates anticipated questions and answers based on the information obtained by the research unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate sales activities and accumulate internal know-how. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The sales activity automation system according to an embodiment of the present invention is a tool that automates sales activities and preserves internal know-how in industries where the changes are rapid and product descriptions are difficult (such as IT companies, retail industries, and real estate industries). This sales activity automation system has a function to automatically generate new customer lists based on conditions such as industry, region, related keywords, and sales volume. For example, when searching for new IT-related customers in a specific region, the AI ​​automatically generates a list of companies that meet the conditions. It also has a function to automatically create appropriate reply and follow-up emails in response to customer inquiries. For example, when a question about a product comes in, the AI ​​generates the optimal reply based on past inquiry history. Furthermore, it has a function to automatically generate quotations from product and service price lists. For example, when multiple products are selected, the AI ​​automatically calculates the total amount and generates a quotation. Furthermore, it has a customer behavior analysis function to create marketing strategies from purchase history and access history. For example, for customers who frequently purchase a particular product, the AI ​​proposes the most suitable promotion for that customer. Furthermore, it has a competitive analysis function to analyze the differentiating points of the company's products and services. For example, the AI ​​analyzes the advantages of the company's products compared to those of competitors and creates a report. Furthermore, it includes a function to create anticipated questions and answers before direct negotiations with customers. For example, based on past negotiation data, the AI ​​generates frequently asked questions and their answers and provides them to sales representatives. These functions aim to improve operational efficiency, understand customer needs, and realize optimal proposals by utilizing advanced technology and artificial intelligence. It identifies areas where customers are likely to have questions and provides information to facilitate smooth communication. As a result, the sales activity automation system automates sales activities and allows for the retention of internal know-how.

[0029] The automated sales activity system according to this embodiment comprises a generation unit, a reply unit, a quotation unit, an analysis unit, a research unit, and a question and answer unit. The generation unit automatically generates a list of new customers. The generation unit automatically generates a list of new customers based on conditions such as industry, region, relevant keywords, and sales volume. For example, if the generation unit is looking for new IT-related customers in a specific region, the AI ​​automatically generates a list of companies that meet the conditions. The generation unit can also generate a list of customers specializing in a specific industry. The generation unit can also list companies with a specific sales volume. The reply unit automatically replies to inquiries based on the list generated by the generation unit. The reply unit automatically creates appropriate reply and follow-up emails in response to customer inquiries. For example, if the reply unit receives a question about a product, the AI ​​generates the optimal reply based on past inquiry history. The reply unit can also automatically create follow-up emails. The reply unit can also customize the reply content according to the content of the inquiry. The quotation unit automatically generates quotations based on the content of the replies received by the reply unit. The Quotation Department automatically generates quotes from price lists for products and services. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quote. The Quotation Department can also automatically create quotes for specific services. The Quotation Department can also automatically adjust quote content in response to price list updates. The Analytics Department analyzes customer behavior based on the quotes generated by the Quotation Department. The Analytics Department creates marketing strategies from purchase history and access history. For example, the AI ​​in the Analytics Department suggests the most suitable promotions for customers who frequently purchase a particular product. The Analytics Department can also identify products of interest based on customer access history. The Analytics Department can also analyze customer behavior patterns and predict future behavior. The Research Department conducts competitive research based on the results analyzed by the Analytics Department. The Research Department analyzes the differentiating points of its own products and services. For example, the Research Department uses AI to analyze the advantages of its own products compared to those of competitors and creates a report.The research department can, for example, analyze the pricing strategies of competitors. The research department can, for example, analyze the marketing strategies of competitors. The question and answer department creates anticipated questions and answers based on the information obtained by the research department. The question and answer department creates anticipated questions and answers before direct negotiations with customers. For example, the question and answer department uses AI to generate frequently asked questions and answers based on past negotiation data and provides them to sales representatives. The question and answer department can also, for example, automatically generate questions and answers about specific products. The question and answer department can also, for example, automatically create negotiation scenarios. As a result, the sales activity automation system according to this embodiment can automate sales activities and retain internal know-how.

[0030] The generation unit automatically generates new customer lists. For example, it automatically generates new customer lists based on conditions such as industry, region, relevant keywords, and sales volume. Specifically, the generation unit collects data from publicly available databases and company information websites on the internet, and the AI ​​analyzes this data to list companies that meet the criteria. For example, when searching for new IT-related customers in a specific region, the AI ​​scans the company database for that region and extracts companies containing IT-related keywords. Furthermore, the AI ​​considers information such as the company's sales volume and number of employees, and adds the company that best fits the criteria to the list. The generation unit can also generate customer lists specialized for specific industries. For example, when generating a customer list specialized in the manufacturing industry, the AI ​​extracts companies based on manufacturing-related keywords and industry codes and creates a list. It can also list companies with a specific sales volume. For example, when targeting companies with annual sales of 100 million yen or more, the AI ​​analyzes the companies' financial data and adds companies that meet the criteria to the list. This allows the generation unit to efficiently and accurately generate new customer lists necessary for sales activities. Furthermore, the generation unit can periodically update the generated lists to reflect new information. For example, if a company's industry or sales volume changes, the AI ​​automatically updates the list to provide the latest information. This allows the generation unit to always provide new customer lists based on the most up-to-date information, improving the efficiency of sales activities.

[0031] The reply unit automatically responds to inquiries based on lists generated by the generation unit. For example, the reply unit automatically creates appropriate reply and follow-up emails in response to customer inquiries. Specifically, the AI ​​analyzes past inquiry history and FAQ databases to generate the optimal reply content. For example, if a question about a product is received, the AI ​​automatically generates an appropriate answer based on similar past inquiries. Furthermore, the reply unit can also automatically create follow-up emails. For example, after a certain period has elapsed since the initial inquiry, it can automatically send a follow-up email to maintain customer interest. The reply unit can also customize reply content according to the content of the inquiry. For example, if a customer shows interest in a particular product, it can generate a reply that includes information and promotions related to that product. This allows the reply unit to quickly provide appropriate replies that meet customer needs and improve customer satisfaction. Furthermore, the reply unit can analyze the effectiveness of the reply content and continuously improve it. For example, it can analyze the open rate and click-through rate of reply emails to identify effective reply content. This allows the reply unit to always provide optimal replies and maximize the effectiveness of sales activities.

[0032] The Quotation Department automatically generates quotations based on the responses received by the Reply Department. For example, the Quotation Department automatically generates quotations from product and service price lists. Specifically, the AI ​​refers to a price database of products and services and creates a quotation that meets the customer's needs. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quotation. The Quotation Department can also automatically create quotations for specific services. For example, when creating a quotation for a customized service, the AI ​​analyzes the content and scope of the service and calculates an appropriate price. Furthermore, the Quotation Department can automatically adjust the quotation content in response to price list updates. For example, if the price list is changed, the AI ​​automatically reflects the new prices and provides the latest quotation. This allows the Quotation Department to always provide accurate and up-to-date quotations quickly and gain customer trust. In addition, the Quotation Department can manage the history of quotations and optimize future quotations based on past quotation data. For example, it can analyze past quotation data to identify the optimal pricing under specific conditions. This allows the Quotation Department to create quotations efficiently and effectively and improve the results of sales activities.

[0033] The analytics department analyzes customer behavior based on estimates generated by the estimation department. For example, the analytics department creates marketing strategies from purchase history and website access history. Specifically, AI analyzes customer purchase history and website access data to identify customer interests. For instance, the AI ​​suggests the most suitable promotions for customers who frequently purchase a particular product. Furthermore, the analytics department can identify products of interest based on customer access history. For example, it provides information and promotions related to a product to customers who frequently visit a specific product page. The analytics department can also analyze customer behavior patterns and predict future behavior. For example, based on past purchase and access history, it predicts which products a customer is most likely to purchase next and provides promotions at the appropriate time. This allows the analytics department to accurately understand customer needs and implement effective marketing strategies. Additionally, the analytics department can segment customers and suggest optimal strategies for specific segments. For example, it can offer premium services and benefits to customers who frequently purchase expensive products. This allows the analytics department to improve customer satisfaction and increase repeat customers.

[0034] The research department conducts competitive analysis based on the results analyzed by the analysis department. For example, the research department analyzes the differentiating points of its own products and services. Specifically, AI collects product information and marketing strategies of competitors and compares them with its own products. For example, AI analyzes the advantages of its own products compared to those of competitors and creates a report. Furthermore, the research department can also analyze the pricing strategies of competitors. For example, it collects pricing data from competitors and analyzes price fluctuations and trends with AI. This provides information to optimize its own pricing strategy. The research department can also analyze the marketing strategies of competitors. For example, it collects advertising campaigns and promotional activities from competitors and analyzes their effectiveness with AI. This provides insights to improve its own marketing strategies. In addition, the research department can monitor the trends of new products and services from competitors and respond quickly. For example, if a competitor announces a new product, AI collects that information and reflects it in its own product development and marketing strategy. This allows the research department to always understand the competitive environment and support quick and appropriate responses.

[0035] The Q&A unit creates anticipated questions and answers based on information obtained by the research unit. For example, the Q&A unit creates anticipated questions and answers before direct negotiations with customers. Specifically, the AI ​​analyzes past negotiation data and competitor information to generate common questions and their answers. For example, if questions about a particular product are anticipated, the AI ​​generates answers that include detailed information and benefits about that product. Furthermore, the Q&A unit can also automatically create negotiation scenarios. For example, the AI ​​generates a scenario that includes the flow of the negotiation and key points, and provides it to the sales representative. This allows the sales representative to prepare in advance and conduct effective negotiations. The Q&A unit can also create customized anticipated questions and answers for specific customers. For example, it generates optimal questions and answers based on the customer's industry and past transaction history. This allows the sales representative to respond appropriately to the customer's needs. Furthermore, the Q&A unit can collect feedback after negotiations and continuously improve the accuracy of the anticipated questions and answers. For example, based on post-negotiation feedback, the AI ​​reviews the answers and scenarios and incorporates them into the next negotiation. This allows the Q&A section to consistently provide highly accurate anticipated questions and answers based on the latest information, thereby improving the results of sales activities.

[0036] The generation unit can automatically generate new customer lists based on conditions such as industry, region, relevant keywords, and sales volume. For example, if the generation unit is looking for new IT-related customers in a specific region, the AI ​​will automatically generate a list of companies that meet the conditions. The generation unit can also generate customer lists specialized in specific industries. The generation unit can also list companies with a specific sales volume. This enables efficient sales activities by automatically generating new customer lists based on conditions. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can automatically generate new customer lists using an AI model that takes conditions such as industry, region, relevant keywords, and sales volume as input and outputs new customer lists.

[0037] The reply function can automatically generate appropriate replies and follow-up emails in response to customer inquiries. For example, if a product-related question is received, the AI ​​will generate the optimal reply based on past inquiry history. The reply function can also automatically generate follow-up emails. The reply function can also customize the reply content according to the content of the inquiry. This enables a quick response by automatically generating appropriate replies and follow-up emails. Some or all of the above processes in the reply function may be performed using AI, or not. For example, the reply function can automatically generate replies using an AI model that takes customer inquiries as input and outputs appropriate reply content.

[0038] The estimation unit can automatically generate estimates from price lists of products and services. For example, if multiple products are selected, the AI ​​will automatically calculate the total price and generate an estimate. The estimation unit can also automatically create estimates for specific services. The estimation unit can also automatically adjust the estimate content in response to price list updates. This enables rapid estimate creation by automatically generating estimates from price lists of products and services. Some or all of the above processes in the estimation unit may be performed using AI, or not. For example, the estimation unit can automatically generate estimates using an AI model that takes a price list of products and services as input and outputs an estimate.

[0039] The analytics department can create marketing strategies from purchase history and access history. For example, the analytics department can use AI to suggest the most suitable promotions to customers who frequently purchase a particular product. The analytics department can also identify products of interest based on customer access history. The analytics department can also analyze customer behavior patterns and predict future behavior. This allows for proposals tailored to customer needs by creating marketing strategies from purchase history and access history. Some or all of the above processes in the analytics department may be performed using AI, or not. For example, the analytics department can create marketing strategies using an AI model that takes purchase history and access history as input and outputs marketing strategies.

[0040] The research department can analyze the differentiating points of its own products and services. For example, the research department can use AI to analyze the advantages of its own products compared to those of competitors and create a report. The research department can also analyze the pricing strategies of competitors. The research department can also analyze the marketing strategies of competitors. By analyzing the differentiating points of its own products and services, it becomes possible to differentiate itself from competitors. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can analyze differentiating points using an AI model that takes competitor product information as input and outputs the advantages of its own products.

[0041] The Q&A unit can create anticipated questions and answers before direct negotiations with customers. For example, the Q&A unit uses AI to generate frequently asked questions and their answers based on past negotiation data and provides them to sales representatives. The Q&A unit can also automatically generate questions and answers about specific products. The Q&A unit can also automatically create negotiation scenarios. This allows for more efficient preparation for negotiations by creating anticipated questions and answers before direct negotiations with customers. Some or all of the above processes in the Q&A unit may be performed using AI, or not. For example, the Q&A unit can create anticipated questions and answers using an AI model that takes past negotiation data as input and outputs anticipated questions and answers.

[0042] The generation unit can analyze past customer list generation history and select the optimal generation method. For example, the generation unit can select a generation method with a high success rate from past generation history and apply it. For example, the generation unit can find the optimal generation method under specific conditions and use it. The generation unit can also, for example, try out new generation methods and find the optimal one. In this way, the optimal generation method can be selected by analyzing past generation history. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can select a generation method using an AI model that takes past generation history data as input and outputs the optimal generation method.

[0043] The generation unit can filter new customer lists based on the user's current business situation and areas of interest. For example, the generation unit can analyze the user's business situation and include highly relevant customers in the list. For example, the generation unit can consider the user's areas of interest and prioritize listing customers in specific industries or regions. For example, the generation unit can include customers with a specific sales volume in the list based on the user's current business needs. This allows for the generation of highly relevant customer lists by filtering based on the user's business situation and areas of interest. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform filtering using an AI model that takes data on the user's business situation and areas of interest as input and outputs a filtered customer list.

[0044] The generation unit can prioritize listing highly relevant customers by considering the user's geographical location when generating a new customer list. For example, the generation unit can prioritize listing nearby customers based on the user's current location. For example, the generation unit can prioritize listing customers within the user's business area by considering the user's business area. For example, the generation unit can prioritize listing easily accessible customers based on the user's travel range. In this way, by considering the user's geographical location, highly relevant customers can be prioritized. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform listing using an AI model that takes the user's geographical location information as input and outputs a list of highly relevant customers.

[0045] The generation unit can analyze a user's social media activity and list relevant customers when generating a new customer list. For example, the generation unit can list relevant customers based on the user's social media followers. For example, the generation unit can analyze the content of a user's social media posts and list customers in areas of interest. For example, the generation unit can list customers with whom the user has a close relationship based on their social media interactions. In this way, relevant customers can be listed by analyzing the user's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform listing using an AI model that takes user social media activity data as input and outputs a list of relevant customers.

[0046] The reply unit can adjust the level of detail in its replies based on the importance of the inquiry. For example, it can generate detailed replies for high-importance inquiries, or concise replies for low-importance inquiries. For example, it can adjust the level of detail in its replies in stages according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in replies based on the importance of the inquiry. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust the level of detail using an AI model that takes inquiry importance data as input and outputs the level of detail in the replies.

[0047] The reply unit can apply different reply algorithms depending on the category of the inquiry when sending a reply. For example, the reply unit can apply a product-specific reply algorithm to a product-related inquiry, a service-specific reply algorithm to a service-related inquiry, and a technical-specific reply algorithm to a technical inquiry. By applying different reply algorithms depending on the category of the inquiry, more appropriate replies can be provided. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can apply an algorithm using an AI model that takes inquiry category data as input and outputs a reply algorithm.

[0048] The reply unit can determine the priority of replies based on when the inquiry was submitted. For example, the reply unit may prioritize replies to recently submitted inquiries. For example, the reply unit may prioritize replies to older inquiries. For example, the reply unit may adjust the priority of replies in stages according to the submission date. This enables efficient handling by determining the priority of replies based on when the inquiry was submitted. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can determine the priority using an AI model that takes inquiry submission date data as input and outputs the priority of replies.

[0049] The reply unit can adjust the order of replies based on the relevance of the inquiries. For example, the reply unit may prioritize replies to highly relevant inquiries. For example, the reply unit may postpone replies to less relevant inquiries. For example, the reply unit may adjust the order of replies in stages according to relevance. This allows for efficient responses by adjusting the order of replies based on the relevance of the inquiries. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can adjust the order using an AI model that takes inquiry relevance data as input and outputs the order of replies.

[0050] The estimation unit can adjust the level of detail in an estimate based on the importance of the product when generating an estimate. For example, the estimation unit generates a detailed estimate for high-importance products. For example, the estimation unit generates a concise estimate for low-importance products. For example, the estimation unit adjusts the level of detail in an estimate in stages according to importance. This makes it possible to create estimates efficiently by adjusting the level of detail in an estimate based on the importance of the product. Some or all of the above processes in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the level of detail using an AI model that takes product importance data as input and outputs the level of detail in the estimate.

[0051] The estimation unit can apply different estimation algorithms depending on the product category when generating estimates. For example, the estimation unit can apply a product-specific estimation algorithm to product estimates, a service-specific estimation algorithm to service estimates, and a technical-specific estimation algorithm to technical estimates. By applying different estimation algorithms depending on the product category, more accurate estimates can be obtained. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can apply an algorithm using an AI model that takes product category data as input and outputs an estimation algorithm.

[0052] The estimation unit can determine the priority of estimates based on the submission date of the products when generating estimates. For example, the estimation unit may prioritize generating estimates for recently submitted products. For example, the estimation unit may prioritize generating estimates for older products. For example, the estimation unit may adjust the priority of estimates in stages according to the submission date. This enables efficient estimate creation by determining the priority of estimates based on the submission date of the products. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can determine the priority using an AI model that takes product submission date data as input and outputs the priority of estimates.

[0053] The estimation unit can adjust the order of estimates based on the relevance of the products when generating estimates. For example, the estimation unit can prioritize generating estimates for highly relevant products. For example, the estimation unit can postpone generating estimates for less relevant products. For example, the estimation unit can adjust the order of estimates in stages according to relevance. This allows for efficient estimate creation by adjusting the order of estimates based on the relevance of the products. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the order using an AI model that takes product relevance data as input and outputs the order of estimates.

[0054] The analysis unit can predict current behavior by referring to past customer behavior data during analysis. For example, the analysis unit can predict a customer's next purchase behavior based on past purchase history. For example, the analysis unit can predict a customer's next visit behavior based on past access history. For example, the analysis unit can predict a customer's next inquiry behavior based on past inquiry history. In this way, current behavior can be predicted by referring to past customer behavior data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can predict behavior using an AI model that takes past customer behavior data as input and predicts current behavior.

[0055] The analysis department can apply different analytical methods to each customer category during analysis. For example, the analysis department can apply corporate-oriented analytical methods to corporate customers. For example, the analysis department can apply individual-oriented analytical methods to individual customers. For example, the analysis department can apply industry-specific analytical methods to customers in a particular industry. By applying different analytical methods to each customer category, more appropriate analysis becomes possible. Some or all of the above processing in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can apply analytical methods using an AI model that takes customer category data as input and outputs analytical methods.

[0056] The analysis department can analyze changes in customer behavior based on the timing of customer submissions. For example, the analysis department can analyze changes in customer behavior based on data from recent submission dates. For example, the analysis department can analyze changes in customer behavior based on data from older submission dates. For example, the analysis department can adjust the analysis of changes in behavior in stages according to the submission date. This makes it possible to perform more appropriate analysis by analyzing changes in behavior based on the timing of customer submissions. Some or all of the above processes in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can use an AI model that analyzes changes in behavior, taking customer submission date data as input, to analyze the changes.

[0057] The analysis unit can analyze customer behavior by referring to relevant market data during analysis. For example, the analysis unit analyzes customer behavior based on relevant market data. For example, the analysis unit predicts the customer's next actions based on relevant market data. For example, the analysis unit analyzes customer behavior patterns based on relevant market data. This makes it possible to perform more appropriate behavioral analysis by referring to relevant market data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can analyze behavior using an AI model that takes relevant market data as input and analyzes behavior.

[0058] The research department can predict the current competitive situation by referring to past competitive data during the research process. For example, the research department predicts the current competitive situation based on past competitive data. For example, the research department predicts the next actions of competitors based on past competitive data. For example, the research department analyzes the behavioral patterns of competitors based on past competitive data. This allows the current competitive situation to be predicted by referring to past competitive data. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can predict the situation using an AI model that takes past competitive data as input and predicts the current competitive situation.

[0059] The research department can apply different research methods to each competitor category during the research process. For example, the research department can apply industry-specific research methods to competitors in a particular industry. For example, the research department can apply region-specific research methods to competitors in a particular region. For example, the research department can apply scale-specific research methods to competitors of a particular size. By applying different research methods to each competitor category, a more appropriate research becomes possible. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can apply research methods using an AI model that takes competitor category data as input and outputs research methods.

[0060] The research department can analyze changes in the competitive landscape based on the submission timing of competitors during the research process. For example, the research department can analyze changes in the competitive landscape based on recent submission data. For example, the research department can analyze changes in the competitive landscape based on older submission data. For example, the research department can adjust the analysis of changes in the landscape in stages according to the submission timing. This allows for a more appropriate research by analyzing changes in the competitive landscape based on the submission timing of competitors. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can use an AI model that analyzes changes in the competitive landscape, taking competitor submission timing data as input, to analyze the changes.

[0061] The research department can analyze the competitive landscape by referring to relevant market data of competitors during the research process. For example, the research department can analyze the competitive landscape based on relevant market data of competitors. For example, the research department can predict the next actions of competitors based on relevant market data of competitors. For example, the research department can analyze the behavioral patterns of competitors based on relevant market data of competitors. This allows for a more appropriate analysis of the competitive landscape by referring to relevant market data of competitors. Some or all of the above processes performed by the research department may be carried out using AI, for example, or not. For example, the research department can analyze the situation using an AI model that takes relevant market data of competitors as input and analyzes the competitive landscape.

[0062] The question-and-answer section can predict the current business negotiation by referring to past business negotiation data when creating anticipated questions and answers. For example, the question-and-answer section predicts questions in the current business negotiation based on past business negotiation data. For example, the question-and-answer section predicts answers in the current business negotiation based on past business negotiation data. For example, the question-and-answer section predicts question-and-answer patterns in the current business negotiation based on past business negotiation data. In this way, the current business negotiation can be predicted by referring to past business negotiation data. Some or all of the above processing in the question-and-answer section may be performed using AI, for example, or without using AI. For example, the question-and-answer section can predict a business negotiation using an AI model that takes past business negotiation data as input and predicts the current business negotiation.

[0063] The Q&A unit can apply different Q&A methods to each category of business negotiation when creating anticipated questions and answers. For example, the Q&A unit can apply a product-specific Q&A method to a product-related business negotiation. For example, the Q&A unit can apply a service-specific Q&A method to a service-related business negotiation. For example, the Q&A unit can apply a technology-specific Q&A method to a technology-related business negotiation. By applying different Q&A methods to each category of business negotiation, more appropriate questions and answers become possible. Some or all of the above processing in the Q&A unit may be performed using AI, for example, or without AI. For example, the Q&A unit can apply a method using an AI model that takes business negotiation category data as input and outputs a Q&A method.

[0064] The Q&A section can determine the priority of questions and answers based on the submission date of the business opportunity when creating anticipated questions and answers. For example, the Q&A section may prioritize generating questions and answers for recently submitted business opportunities. For example, the Q&A section may prioritize generating questions and answers for older business opportunities. For example, the Q&A section may adjust the priority of questions and answers in stages according to the submission date. This enables efficient question and answer creation by determining the priority of questions and answers based on the submission date of the business opportunity. Some or all of the above processing in the Q&A section may be performed using AI, for example, or without AI. For example, the Q&A section can determine the priority using an AI model that takes business opportunity submission date data as input and outputs the priority of questions and answers.

[0065] The Q&A unit can create anticipated questions and answers by referring to relevant market data for the business negotiation. For example, the Q&A unit creates questions and answers based on relevant market data for the business negotiation. For example, the Q&A unit predicts questions for the next business negotiation based on relevant market data for the business negotiation. For example, the Q&A unit predicts answers for the next business negotiation based on relevant market data for the business negotiation. This ensures that more appropriate questions and answers are provided by referring to relevant market data for the business negotiation. Some or all of the above processing in the Q&A unit may be performed using AI, for example, or without AI. For example, the Q&A unit can create questions and answers using an AI model that takes relevant market data for the business negotiation as input.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The generation unit can analyze past customer list generation history and select the optimal generation method. For example, the generation unit can select a generation method with a high success rate from past generation history and apply it. For example, the generation unit can find the optimal generation method under specific conditions and use it. The generation unit can also, for example, try out new generation methods and find the optimal one. In this way, the optimal generation method can be selected by analyzing past generation history. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can select a generation method using an AI model that takes past generation history data as input and outputs the optimal generation method.

[0068] The reply unit can adjust the level of detail in its replies based on the importance of the inquiry. For example, it can generate detailed replies for high-importance inquiries, or concise replies for low-importance inquiries. For example, it can adjust the level of detail in its replies in stages according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in replies based on the importance of the inquiry. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust the level of detail using an AI model that takes inquiry importance data as input and outputs the level of detail in the replies.

[0069] The estimation unit can adjust the level of detail in an estimate based on the importance of the product when generating an estimate. For example, the estimation unit generates a detailed estimate for high-importance products. For example, the estimation unit generates a concise estimate for low-importance products. For example, the estimation unit adjusts the level of detail in an estimate in stages according to importance. This makes it possible to create estimates efficiently by adjusting the level of detail in an estimate based on the importance of the product. Some or all of the above processes in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the level of detail using an AI model that takes product importance data as input and outputs the level of detail in the estimate.

[0070] The analysis unit can predict current behavior by referring to past customer behavior data during analysis. For example, the analysis unit can predict a customer's next purchase behavior based on past purchase history. For example, the analysis unit can predict a customer's next visit behavior based on past access history. For example, the analysis unit can predict a customer's next inquiry behavior based on past inquiry history. In this way, current behavior can be predicted by referring to past customer behavior data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can predict behavior using an AI model that takes past customer behavior data as input and predicts current behavior.

[0071] The research department can predict the current competitive situation by referring to past competitive data during the research process. For example, the research department predicts the current competitive situation based on past competitive data. For example, the research department predicts the next actions of competitors based on past competitive data. For example, the research department analyzes the behavioral patterns of competitors based on past competitive data. This allows the current competitive situation to be predicted by referring to past competitive data. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can predict the situation using an AI model that takes past competitive data as input and predicts the current competitive situation.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The generation unit automatically generates a list of new customers. The generation unit automatically generates a list of new customers based on conditions such as industry, region, relevant keywords, and sales volume. For example, if you are looking for new IT-related customers in a specific region, the AI ​​will automatically generate a list of companies that meet the criteria. It can also list customers specializing in a specific industry or companies with a specific sales volume. Step 2: The reply unit automatically responds to inquiries based on the list generated by the generation unit. The reply unit automatically creates appropriate replies and follow-up emails in response to customer inquiries. For example, if a question about a product comes in, the AI ​​generates the best response based on past inquiry history. Furthermore, it can automatically create follow-up emails and customize the response content according to the content of the inquiry. Step 3: The Quotation Department automatically generates a quotation based on the response received by the Reply Department. The Quotation Department automatically generates quotations from the price list of products and services. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quotation. Furthermore, it can automatically create quotations for specific services and automatically adjust the quotation content in accordance with price list updates. Step 4: The analytics department analyzes customer behavior based on the estimates generated by the estimation department. The analytics department creates marketing strategies from purchase history and access history. For example, for customers who frequently purchase a particular product, the AI ​​can suggest the most suitable promotions for that customer. Furthermore, based on the customer's access history, it is possible to identify products they are interested in and analyze their behavior patterns to predict future behavior. Step 5: The Research Department conducts competitive analysis based on the results analyzed by the Analysis Department. The Research Department analyzes the differentiating points of its own products and services. For example, AI analyzes the advantages of its own products compared to those of competitors and generates a report. Furthermore, it can also analyze the pricing strategies and marketing measures of competitors. Step 6: The Q&A unit creates anticipated questions and answers based on the information obtained by the research unit. The Q&A unit creates anticipated questions and answers before direct negotiations with customers. For example, based on past negotiation data, the AI ​​generates common questions and answers and provides them to sales representatives. Furthermore, it can automatically create questions and answers and negotiation scenarios for specific products.

[0074] (Example of form 2) The sales activity automation system according to an embodiment of the present invention is a tool that automates sales activities and preserves internal know-how in industries where the changes are rapid and product descriptions are difficult (such as IT companies, retail industries, and real estate industries). This sales activity automation system has a function to automatically generate new customer lists based on conditions such as industry, region, related keywords, and sales volume. For example, when searching for new IT-related customers in a specific region, the AI ​​automatically generates a list of companies that meet the conditions. It also has a function to automatically create appropriate reply and follow-up emails in response to customer inquiries. For example, when a question about a product comes in, the AI ​​generates the optimal reply based on past inquiry history. Furthermore, it has a function to automatically generate quotations from product and service price lists. For example, when multiple products are selected, the AI ​​automatically calculates the total amount and generates a quotation. Furthermore, it has a customer behavior analysis function to create marketing strategies from purchase history and access history. For example, for customers who frequently purchase a particular product, the AI ​​proposes the most suitable promotion for that customer. Furthermore, it has a competitive analysis function to analyze the differentiating points of the company's products and services. For example, the AI ​​analyzes the advantages of the company's products compared to those of competitors and creates a report. Furthermore, it includes a function to create anticipated questions and answers before direct negotiations with customers. For example, based on past negotiation data, the AI ​​generates frequently asked questions and their answers and provides them to sales representatives. These functions aim to improve operational efficiency, understand customer needs, and realize optimal proposals by utilizing advanced technology and artificial intelligence. It identifies areas where customers are likely to have questions and provides information to facilitate smooth communication. As a result, the sales activity automation system automates sales activities and allows for the retention of internal know-how.

[0075] The automated sales activity system according to this embodiment comprises a generation unit, a reply unit, a quotation unit, an analysis unit, a research unit, and a question and answer unit. The generation unit automatically generates a list of new customers. The generation unit automatically generates a list of new customers based on conditions such as industry, region, relevant keywords, and sales volume. For example, if the generation unit is looking for new IT-related customers in a specific region, the AI ​​automatically generates a list of companies that meet the conditions. The generation unit can also generate a list of customers specializing in a specific industry. The generation unit can also list companies with a specific sales volume. The reply unit automatically replies to inquiries based on the list generated by the generation unit. The reply unit automatically creates appropriate reply and follow-up emails in response to customer inquiries. For example, if the reply unit receives a question about a product, the AI ​​generates the optimal reply based on past inquiry history. The reply unit can also automatically create follow-up emails. The reply unit can also customize the reply content according to the content of the inquiry. The quotation unit automatically generates quotations based on the content of the replies received by the reply unit. The Quotation Department automatically generates quotes from price lists for products and services. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quote. The Quotation Department can also automatically create quotes for specific services. The Quotation Department can also automatically adjust quote content in response to price list updates. The Analytics Department analyzes customer behavior based on the quotes generated by the Quotation Department. The Analytics Department creates marketing strategies from purchase history and access history. For example, the AI ​​in the Analytics Department suggests the most suitable promotions for customers who frequently purchase a particular product. The Analytics Department can also identify products of interest based on customer access history. The Analytics Department can also analyze customer behavior patterns and predict future behavior. The Research Department conducts competitive research based on the results analyzed by the Analytics Department. The Research Department analyzes the differentiating points of its own products and services. For example, the Research Department uses AI to analyze the advantages of its own products compared to those of competitors and creates a report.The research department can, for example, analyze the pricing strategies of competitors. The research department can, for example, analyze the marketing strategies of competitors. The question and answer department creates anticipated questions and answers based on the information obtained by the research department. The question and answer department creates anticipated questions and answers before direct negotiations with customers. For example, the question and answer department uses AI to generate frequently asked questions and answers based on past negotiation data and provides them to sales representatives. The question and answer department can also, for example, automatically generate questions and answers about specific products. The question and answer department can also, for example, automatically create negotiation scenarios. As a result, the sales activity automation system according to this embodiment can automate sales activities and retain internal know-how.

[0076] The generation unit automatically generates new customer lists. For example, it automatically generates new customer lists based on conditions such as industry, region, relevant keywords, and sales volume. Specifically, the generation unit collects data from publicly available databases and company information websites on the internet, and the AI ​​analyzes this data to list companies that meet the criteria. For example, when searching for new IT-related customers in a specific region, the AI ​​scans the company database for that region and extracts companies containing IT-related keywords. Furthermore, the AI ​​considers information such as the company's sales volume and number of employees, and adds the company that best fits the criteria to the list. The generation unit can also generate customer lists specialized for specific industries. For example, when generating a customer list specialized in the manufacturing industry, the AI ​​extracts companies based on manufacturing-related keywords and industry codes and creates a list. It can also list companies with a specific sales volume. For example, when targeting companies with annual sales of 100 million yen or more, the AI ​​analyzes the companies' financial data and adds companies that meet the criteria to the list. This allows the generation unit to efficiently and accurately generate new customer lists necessary for sales activities. Furthermore, the generation unit can periodically update the generated lists to reflect new information. For example, if a company's industry or sales volume changes, the AI ​​automatically updates the list to provide the latest information. This allows the generation unit to always provide new customer lists based on the most up-to-date information, improving the efficiency of sales activities.

[0077] The reply unit automatically responds to inquiries based on lists generated by the generation unit. For example, the reply unit automatically creates appropriate reply and follow-up emails in response to customer inquiries. Specifically, the AI ​​analyzes past inquiry history and FAQ databases to generate the optimal reply content. For example, if a question about a product is received, the AI ​​automatically generates an appropriate answer based on similar past inquiries. Furthermore, the reply unit can also automatically create follow-up emails. For example, after a certain period has elapsed since the initial inquiry, it can automatically send a follow-up email to maintain customer interest. The reply unit can also customize reply content according to the content of the inquiry. For example, if a customer shows interest in a particular product, it can generate a reply that includes information and promotions related to that product. This allows the reply unit to quickly provide appropriate replies that meet customer needs and improve customer satisfaction. Furthermore, the reply unit can analyze the effectiveness of the reply content and continuously improve it. For example, it can analyze the open rate and click-through rate of reply emails to identify effective reply content. This allows the reply unit to always provide optimal replies and maximize the effectiveness of sales activities.

[0078] The Quotation Department automatically generates quotations based on the responses received by the Reply Department. For example, the Quotation Department automatically generates quotations from product and service price lists. Specifically, the AI ​​refers to a price database of products and services and creates a quotation that meets the customer's needs. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quotation. The Quotation Department can also automatically create quotations for specific services. For example, when creating a quotation for a customized service, the AI ​​analyzes the content and scope of the service and calculates an appropriate price. Furthermore, the Quotation Department can automatically adjust the quotation content in response to price list updates. For example, if the price list is changed, the AI ​​automatically reflects the new prices and provides the latest quotation. This allows the Quotation Department to always provide accurate and up-to-date quotations quickly and gain customer trust. In addition, the Quotation Department can manage the history of quotations and optimize future quotations based on past quotation data. For example, it can analyze past quotation data to identify the optimal pricing under specific conditions. This allows the Quotation Department to create quotations efficiently and effectively and improve the results of sales activities.

[0079] The analytics department analyzes customer behavior based on estimates generated by the estimation department. For example, the analytics department creates marketing strategies from purchase history and website access history. Specifically, AI analyzes customer purchase history and website access data to identify customer interests. For instance, the AI ​​suggests the most suitable promotions for customers who frequently purchase a particular product. Furthermore, the analytics department can identify products of interest based on customer access history. For example, it provides information and promotions related to a product to customers who frequently visit a specific product page. The analytics department can also analyze customer behavior patterns and predict future behavior. For example, based on past purchase and access history, it predicts which products a customer is most likely to purchase next and provides promotions at the appropriate time. This allows the analytics department to accurately understand customer needs and implement effective marketing strategies. Additionally, the analytics department can segment customers and suggest optimal strategies for specific segments. For example, it can offer premium services and benefits to customers who frequently purchase expensive products. This allows the analytics department to improve customer satisfaction and increase repeat customers.

[0080] The research department conducts competitive analysis based on the results analyzed by the analysis department. For example, the research department analyzes the differentiating points of its own products and services. Specifically, AI collects product information and marketing strategies of competitors and compares them with its own products. For example, AI analyzes the advantages of its own products compared to those of competitors and creates a report. Furthermore, the research department can also analyze the pricing strategies of competitors. For example, it collects pricing data from competitors and analyzes price fluctuations and trends with AI. This provides information to optimize its own pricing strategy. The research department can also analyze the marketing strategies of competitors. For example, it collects advertising campaigns and promotional activities from competitors and analyzes their effectiveness with AI. This provides insights to improve its own marketing strategies. In addition, the research department can monitor the trends of new products and services from competitors and respond quickly. For example, if a competitor announces a new product, AI collects that information and reflects it in its own product development and marketing strategy. This allows the research department to always understand the competitive environment and support quick and appropriate responses.

[0081] The Q&A unit creates anticipated questions and answers based on information obtained by the research unit. For example, the Q&A unit creates anticipated questions and answers before direct negotiations with customers. Specifically, the AI ​​analyzes past negotiation data and competitor information to generate common questions and their answers. For example, if questions about a particular product are anticipated, the AI ​​generates answers that include detailed information and benefits about that product. Furthermore, the Q&A unit can also automatically create negotiation scenarios. For example, the AI ​​generates a scenario that includes the flow of the negotiation and key points, and provides it to the sales representative. This allows the sales representative to prepare in advance and conduct effective negotiations. The Q&A unit can also create customized anticipated questions and answers for specific customers. For example, it generates optimal questions and answers based on the customer's industry and past transaction history. This allows the sales representative to respond appropriately to the customer's needs. Furthermore, the Q&A unit can collect feedback after negotiations and continuously improve the accuracy of the anticipated questions and answers. For example, based on post-negotiation feedback, the AI ​​reviews the answers and scenarios and incorporates them into the next negotiation. This allows the Q&A section to consistently provide highly accurate anticipated questions and answers based on the latest information, thereby improving the results of sales activities.

[0082] The generation unit can automatically generate new customer lists based on conditions such as industry, region, relevant keywords, and sales volume. For example, if the generation unit is looking for new IT-related customers in a specific region, the AI ​​will automatically generate a list of companies that meet the conditions. The generation unit can also generate customer lists specialized in specific industries. The generation unit can also list companies with a specific sales volume. This enables efficient sales activities by automatically generating new customer lists based on conditions. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can automatically generate new customer lists using an AI model that takes conditions such as industry, region, relevant keywords, and sales volume as input and outputs new customer lists.

[0083] The reply function can automatically generate appropriate replies and follow-up emails in response to customer inquiries. For example, if a product-related question is received, the AI ​​will generate the optimal reply based on past inquiry history. The reply function can also automatically generate follow-up emails. The reply function can also customize the reply content according to the content of the inquiry. This enables a quick response by automatically generating appropriate replies and follow-up emails. Some or all of the above processes in the reply function may be performed using AI, or not. For example, the reply function can automatically generate replies using an AI model that takes customer inquiries as input and outputs appropriate reply content.

[0084] The estimation unit can automatically generate estimates from price lists of products and services. For example, if multiple products are selected, the AI ​​will automatically calculate the total price and generate an estimate. The estimation unit can also automatically create estimates for specific services. The estimation unit can also automatically adjust the estimate content in response to price list updates. This enables rapid estimate creation by automatically generating estimates from price lists of products and services. Some or all of the above processes in the estimation unit may be performed using AI, or not. For example, the estimation unit can automatically generate estimates using an AI model that takes a price list of products and services as input and outputs an estimate.

[0085] The analytics department can create marketing strategies from purchase history and access history. For example, the analytics department can use AI to suggest the most suitable promotions to customers who frequently purchase a particular product. The analytics department can also identify products of interest based on customer access history. The analytics department can also analyze customer behavior patterns and predict future behavior. This allows for proposals tailored to customer needs by creating marketing strategies from purchase history and access history. Some or all of the above processes in the analytics department may be performed using AI, or not. For example, the analytics department can create marketing strategies using an AI model that takes purchase history and access history as input and outputs marketing strategies.

[0086] The research department can analyze the differentiating points of its own products and services. For example, the research department can use AI to analyze the advantages of its own products compared to those of competitors and create a report. The research department can also analyze the pricing strategies of competitors. The research department can also analyze the marketing strategies of competitors. By analyzing the differentiating points of its own products and services, it becomes possible to differentiate itself from competitors. Some or all of the above processes in the research department may be performed using AI, or not. For example, the research department can analyze differentiating points using an AI model that takes competitor product information as input and outputs the advantages of its own products.

[0087] The Q&A unit can create anticipated questions and answers before direct negotiations with customers. For example, the Q&A unit uses AI to generate frequently asked questions and their answers based on past negotiation data and provides them to sales representatives. The Q&A unit can also automatically generate questions and answers about specific products. The Q&A unit can also automatically create negotiation scenarios. This allows for more efficient preparation for negotiations by creating anticipated questions and answers before direct negotiations with customers. Some or all of the above processes in the Q&A unit may be performed using AI, or not. For example, the Q&A unit can create anticipated questions and answers using an AI model that takes past negotiation data as input and outputs anticipated questions and answers.

[0088] The generation unit can estimate the user's emotions and adjust the timing of new customer list generation based on the estimated user emotions. For example, if the user is stressed, the generation unit may delay list generation and wait until the user is relaxed. For example, if the user is relaxed, the generation unit may immediately generate and provide the list to the user. For example, if the user is in a hurry, the generation unit may quickly generate the list and notify the user. This reduces user stress by adjusting the timing of new customer list generation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can adjust the generation timing using an AI model that takes user emotion data as input and outputs the generation timing.

[0089] The generation unit can analyze past customer list generation history and select the optimal generation method. For example, the generation unit can select a generation method with a high success rate from past generation history and apply it. For example, the generation unit can find the optimal generation method under specific conditions and use it. The generation unit can also, for example, try out new generation methods and find the optimal one. In this way, the optimal generation method can be selected by analyzing past generation history. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can select a generation method using an AI model that takes past generation history data as input and outputs the optimal generation method.

[0090] The generation unit can filter new customer lists based on the user's current business situation and areas of interest. For example, the generation unit can analyze the user's business situation and include highly relevant customers in the list. For example, the generation unit can consider the user's areas of interest and prioritize listing customers in specific industries or regions. For example, the generation unit can include customers with a specific sales volume in the list based on the user's current business needs. This allows for the generation of highly relevant customer lists by filtering based on the user's business situation and areas of interest. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform filtering using an AI model that takes data on the user's business situation and areas of interest as input and outputs a filtered customer list.

[0091] The generation unit can estimate the user's emotions and determine the priority of the customer list to be generated based on the estimated user emotions. For example, if the user is stressed, the generation unit will prioritize generating a list of less important customers. For example, if the user is relaxed, the generation unit will prioritize generating a list of highly important customers. For example, if the user is in a hurry, the generation unit will prioritize generating a list of customers that require immediate attention. This enables efficient sales activities by prioritizing the customer list according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can determine the priority using an AI model that takes user emotion data as input and outputs the priority of the customer list.

[0092] The generation unit can prioritize listing highly relevant customers by considering the user's geographical location when generating a new customer list. For example, the generation unit can prioritize listing nearby customers based on the user's current location. For example, the generation unit can prioritize listing customers within the user's business area by considering the user's business area. For example, the generation unit can prioritize listing easily accessible customers based on the user's travel range. In this way, by considering the user's geographical location, highly relevant customers can be prioritized. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform listing using an AI model that takes the user's geographical location information as input and outputs a list of highly relevant customers.

[0093] The generation unit can analyze a user's social media activity and list relevant customers when generating a new customer list. For example, the generation unit can list relevant customers based on the user's social media followers. For example, the generation unit can analyze the content of a user's social media posts and list customers in areas of interest. For example, the generation unit can list customers with whom the user has a close relationship based on their social media interactions. In this way, relevant customers can be listed by analyzing the user's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can perform listing using an AI model that takes user social media activity data as input and outputs a list of relevant customers.

[0094] The reply unit can estimate the user's emotions and adjust the way it expresses its reply based on those emotions. For example, if the user is stressed, the reply unit will generate a concise and clear reply. If the user is relaxed, the reply unit will generate a detailed and polite reply. If the user is in a hurry, the reply unit will generate a quick and to-the-point reply. This allows for more appropriate replies by adjusting the way the reply is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust its expression using an AI model that takes user emotion data as input and outputs a way to express the reply.

[0095] The reply unit can adjust the level of detail in its replies based on the importance of the inquiry. For example, it can generate detailed replies for high-importance inquiries, or concise replies for low-importance inquiries. For example, it can adjust the level of detail in its replies in stages according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in replies based on the importance of the inquiry. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust the level of detail using an AI model that takes inquiry importance data as input and outputs the level of detail in the replies.

[0096] The reply unit can apply different reply algorithms depending on the category of the inquiry when sending a reply. For example, the reply unit can apply a product-specific reply algorithm to a product-related inquiry, a service-specific reply algorithm to a service-related inquiry, and a technical-specific reply algorithm to a technical inquiry. By applying different reply algorithms depending on the category of the inquiry, more appropriate replies can be provided. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can apply an algorithm using an AI model that takes inquiry category data as input and outputs a reply algorithm.

[0097] The reply unit can estimate the user's emotions and adjust the length of the reply based on the estimated emotions. For example, if the user is stressed, the reply unit will generate a short, to-the-point reply. If the user is relaxed, the reply unit will generate a longer reply with detailed explanations. If the user is in a hurry, the reply unit will generate a quick and concise reply. By adjusting the length of the reply according to the user's emotions, more appropriate replies can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reply unit may be performed using AI or not. For example, the reply unit can adjust the length using an AI model that takes user emotion data as input and outputs the length of the reply.

[0098] The reply unit can determine the priority of replies based on when the inquiry was submitted. For example, the reply unit may prioritize replies to recently submitted inquiries. For example, the reply unit may prioritize replies to older inquiries. For example, the reply unit may adjust the priority of replies in stages according to the submission date. This enables efficient handling by determining the priority of replies based on when the inquiry was submitted. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can determine the priority using an AI model that takes inquiry submission date data as input and outputs the priority of replies.

[0099] The reply unit can adjust the order of replies based on the relevance of the inquiries. For example, the reply unit may prioritize replies to highly relevant inquiries. For example, the reply unit may postpone replies to less relevant inquiries. For example, the reply unit may adjust the order of replies in stages according to relevance. This allows for efficient responses by adjusting the order of replies based on the relevance of the inquiries. Some or all of the above processing in the reply unit may be performed using AI, for example, or without AI. For example, the reply unit can adjust the order using an AI model that takes inquiry relevance data as input and outputs the order of replies.

[0100] The estimation unit can estimate the user's emotions and adjust the way the estimate is presented based on the estimated emotions. For example, if the user is stressed, the estimation unit will generate a concise and clear estimate. If the user is relaxed, the estimation unit will generate a detailed and thorough estimate. If the user is in a hurry, the estimation unit will generate a quick and to-the-point estimate. By adjusting the way the estimate is presented according to the user's emotions, a more appropriate estimate can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the estimation unit may be performed using AI, or not using AI. For example, the estimation unit can adjust the presentation using an AI model that takes user emotion data as input and outputs the way the estimate is presented.

[0101] The estimation unit can adjust the level of detail in an estimate based on the importance of the product when generating an estimate. For example, the estimation unit generates a detailed estimate for high-importance products. For example, the estimation unit generates a concise estimate for low-importance products. For example, the estimation unit adjusts the level of detail in an estimate in stages according to importance. This makes it possible to create estimates efficiently by adjusting the level of detail in an estimate based on the importance of the product. Some or all of the above processes in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the level of detail using an AI model that takes product importance data as input and outputs the level of detail in the estimate.

[0102] The estimation unit can apply different estimation algorithms depending on the product category when generating estimates. For example, the estimation unit can apply a product-specific estimation algorithm to product estimates, a service-specific estimation algorithm to service estimates, and a technical-specific estimation algorithm to technical estimates. By applying different estimation algorithms depending on the product category, more accurate estimates can be obtained. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can apply an algorithm using an AI model that takes product category data as input and outputs an estimation algorithm.

[0103] The estimation unit can estimate the user's emotions and adjust the length of the estimate based on the estimated emotions. For example, if the user is stressed, the estimation unit will generate a short, to-the-point estimate. If the user is relaxed, the estimation unit will generate a longer estimate with detailed explanations. If the user is in a hurry, the estimation unit will generate a quick and concise estimate. By adjusting the length of the estimate according to the user's emotions, a more appropriate estimate can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the estimation unit may be performed using AI or not. For example, the estimation unit can adjust the length using an AI model that takes user emotion data as input and outputs the length of the estimate.

[0104] The estimation unit can determine the priority of estimates based on the submission date of the products when generating estimates. For example, the estimation unit may prioritize generating estimates for recently submitted products. For example, the estimation unit may prioritize generating estimates for older products. For example, the estimation unit may adjust the priority of estimates in stages according to the submission date. This enables efficient estimate creation by determining the priority of estimates based on the submission date of the products. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can determine the priority using an AI model that takes product submission date data as input and outputs the priority of estimates.

[0105] The estimation unit can adjust the order of estimates based on the relevance of the products when generating estimates. For example, the estimation unit can prioritize generating estimates for highly relevant products. For example, the estimation unit can postpone generating estimates for less relevant products. For example, the estimation unit can adjust the order of estimates in stages according to relevance. This allows for efficient estimate creation by adjusting the order of estimates based on the relevance of the products. Some or all of the above processing in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the order using an AI model that takes product relevance data as input and outputs the order of estimates.

[0106] The analysis unit can estimate the user's emotions and adjust the display method of the analysis based on the estimated user emotions. For example, if the user is stressed, the analysis unit provides a concise and highly visible display method. For example, if the user is relaxed, the analysis unit provides a display method that includes detailed information. For example, if the user is in a hurry, the analysis unit provides a display method that gets straight to the point. By adjusting the display method of the analysis according to the user's emotions, more appropriate analysis results are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can adjust the display method using an AI model that takes user emotion data as input and outputs an analysis display method.

[0107] The analysis unit can predict current behavior by referring to past customer behavior data during analysis. For example, the analysis unit can predict a customer's next purchase behavior based on past purchase history. For example, the analysis unit can predict a customer's next visit behavior based on past access history. For example, the analysis unit can predict a customer's next inquiry behavior based on past inquiry history. In this way, current behavior can be predicted by referring to past customer behavior data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can predict behavior using an AI model that takes past customer behavior data as input and predicts current behavior.

[0108] The analysis department can apply different analytical methods to each customer category during analysis. For example, the analysis department can apply corporate-oriented analytical methods to corporate customers. For example, the analysis department can apply individual-oriented analytical methods to individual customers. For example, the analysis department can apply industry-specific analytical methods to customers in a particular industry. By applying different analytical methods to each customer category, more appropriate analysis becomes possible. Some or all of the above processing in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can apply analytical methods using an AI model that takes customer category data as input and outputs analytical methods.

[0109] The analysis unit can estimate the user's emotions and adjust the importance of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit will prioritize displaying analysis results of low importance. For example, if the user is relaxed, the analysis unit will prioritize displaying analysis results of high importance. For example, if the user is in a hurry, the analysis unit will prioritize displaying analysis results that require immediate attention. In this way, by adjusting the importance of the analysis according to the user's emotions, more appropriate analysis results are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can adjust the importance using an AI model that takes user emotion data as input and outputs the importance of the analysis.

[0110] The analysis department can analyze changes in customer behavior based on the timing of customer submissions. For example, the analysis department can analyze changes in customer behavior based on data from recent submission dates. For example, the analysis department can analyze changes in customer behavior based on data from older submission dates. For example, the analysis department can adjust the analysis of changes in behavior in stages according to the submission date. This makes it possible to perform more appropriate analysis by analyzing changes in behavior based on the timing of customer submissions. Some or all of the above processes in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can use an AI model that analyzes changes in behavior, taking customer submission date data as input, to analyze the changes.

[0111] The analysis unit can analyze customer behavior by referring to relevant market data during analysis. For example, the analysis unit analyzes customer behavior based on relevant market data. For example, the analysis unit predicts the customer's next actions based on relevant market data. For example, the analysis unit analyzes customer behavior patterns based on relevant market data. This makes it possible to perform more appropriate behavioral analysis by referring to relevant market data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can analyze behavior using an AI model that takes relevant market data as input and analyzes behavior.

[0112] The research unit can estimate the user's emotions and adjust the way the survey is displayed based on the estimated emotions. For example, if the user is stressed, the research unit provides a concise and highly visible display. For example, if the user is relaxed, the research unit provides a display that includes detailed information. For example, if the user is in a hurry, the research unit provides a display that gets straight to the point. By adjusting the way the survey is displayed according to the user's emotions, more appropriate survey results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can adjust the display using an AI model that takes user emotion data as input and outputs the way the survey is displayed.

[0113] The research department can predict the current competitive situation by referring to past competitive data during the research process. For example, the research department predicts the current competitive situation based on past competitive data. For example, the research department predicts the next actions of competitors based on past competitive data. For example, the research department analyzes the behavioral patterns of competitors based on past competitive data. This allows the current competitive situation to be predicted by referring to past competitive data. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can predict the situation using an AI model that takes past competitive data as input and predicts the current competitive situation.

[0114] The research department can apply different research methods to each competitor category during the research process. For example, the research department can apply industry-specific research methods to competitors in a particular industry. For example, the research department can apply region-specific research methods to competitors in a particular region. For example, the research department can apply scale-specific research methods to competitors of a particular size. By applying different research methods to each competitor category, a more appropriate research becomes possible. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can apply research methods using an AI model that takes competitor category data as input and outputs research methods.

[0115] The research unit can estimate the user's emotions and adjust the importance of the survey based on the estimated emotions. For example, if the user is stressed, the research unit will prioritize displaying less important survey results. For example, if the user is relaxed, the research unit will prioritize displaying more important survey results. For example, if the user is in a hurry, the research unit will prioritize displaying survey results that require immediate attention. By adjusting the importance of the survey according to the user's emotions, more appropriate survey results are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can adjust the importance using an AI model that takes user emotion data as input and outputs the importance of the survey.

[0116] The research department can analyze changes in the competitive landscape based on the submission timing of competitors during the research process. For example, the research department can analyze changes in the competitive landscape based on recent submission data. For example, the research department can analyze changes in the competitive landscape based on older submission data. For example, the research department can adjust the analysis of changes in the landscape in stages according to the submission timing. This allows for a more appropriate research by analyzing changes in the competitive landscape based on the submission timing of competitors. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can use an AI model that analyzes changes in the competitive landscape, taking competitor submission timing data as input, to analyze the changes.

[0117] The research department can analyze the competitive landscape by referring to relevant market data of competitors during the research process. For example, the research department can analyze the competitive landscape based on relevant market data of competitors. For example, the research department can predict the next actions of competitors based on relevant market data of competitors. For example, the research department can analyze the behavioral patterns of competitors based on relevant market data of competitors. This allows for a more appropriate analysis of the competitive landscape by referring to relevant market data of competitors. Some or all of the above processes performed by the research department may be carried out using AI, for example, or not. For example, the research department can analyze the situation using an AI model that takes relevant market data of competitors as input and analyzes the competitive landscape.

[0118] The question-and-answer unit can estimate the user's emotions and adjust the expression of anticipated questions and answers based on the estimated emotions. For example, if the user is stressed, the question-and-answer unit generates concise and clear questions and answers. For example, if the user is relaxed, the question-and-answer unit generates detailed and polite questions and answers. For example, if the user is in a hurry, the question-and-answer unit generates quick and to-the-point questions and answers. In this way, by adjusting the expression of anticipated questions and answers according to the user's emotions, more appropriate questions and answers are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the question-and-answer unit may be performed using AI, for example, or without AI. For example, the question-and-answer unit can adjust the expression using an AI model that takes user emotion data as input and outputs the expression of anticipated questions and answers.

[0119] The question-and-answer section can predict the current business negotiation by referring to past business negotiation data when creating anticipated questions and answers. For example, the question-and-answer section predicts questions in the current business negotiation based on past business negotiation data. For example, the question-and-answer section predicts answers in the current business negotiation based on past business negotiation data. For example, the question-and-answer section predicts question-and-answer patterns in the current business negotiation based on past business negotiation data. In this way, the current business negotiation can be predicted by referring to past business negotiation data. Some or all of the above processing in the question-and-answer section may be performed using AI, for example, or without using AI. For example, the question-and-answer section can predict a business negotiation using an AI model that takes past business negotiation data as input and predicts the current business negotiation.

[0120] The Q&A unit can apply different Q&A methods to each category of business negotiation when creating anticipated questions and answers. For example, the Q&A unit can apply a product-specific Q&A method to a product-related business negotiation. For example, the Q&A unit can apply a service-specific Q&A method to a service-related business negotiation. For example, the Q&A unit can apply a technology-specific Q&A method to a technology-related business negotiation. By applying different Q&A methods to each category of business negotiation, more appropriate questions and answers become possible. Some or all of the above processing in the Q&A unit may be performed using AI, for example, or without AI. For example, the Q&A unit can apply a method using an AI model that takes business negotiation category data as input and outputs a Q&A method.

[0121] The question-and-answer unit can estimate the user's emotions and adjust the importance of anticipated questions and answers based on the estimated emotions. For example, if the user is stressed, the question-and-answer unit will prioritize generating questions and answers of low importance. For example, if the user is relaxed, the question-and-answer unit will prioritize generating questions and answers of high importance. For example, if the user is in a hurry, the question-and-answer unit will prioritize generating questions and answers that require a quick response. By adjusting the importance of anticipated questions and answers according to the user's emotions, more appropriate questions and answers are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the question-and-answer unit may be performed using AI, for example, or without AI. For example, the question-and-answer unit can adjust the importance using an AI model that takes user emotion data as input and outputs the importance of anticipated questions and answers.

[0122] The Q&A section can determine the priority of questions and answers based on the submission date of the business opportunity when creating anticipated questions and answers. For example, the Q&A section may prioritize generating questions and answers for recently submitted business opportunities. For example, the Q&A section may prioritize generating questions and answers for older business opportunities. For example, the Q&A section may adjust the priority of questions and answers in stages according to the submission date. This enables efficient question and answer creation by determining the priority of questions and answers based on the submission date of the business opportunity. Some or all of the above processing in the Q&A section may be performed using AI, for example, or without AI. For example, the Q&A section can determine the priority using an AI model that takes business opportunity submission date data as input and outputs the priority of questions and answers.

[0123] The Q&A unit can create anticipated questions and answers by referring to relevant market data for the business negotiation. For example, the Q&A unit creates questions and answers based on relevant market data for the business negotiation. For example, the Q&A unit predicts questions for the next business negotiation based on relevant market data for the business negotiation. For example, the Q&A unit predicts answers for the next business negotiation based on relevant market data for the business negotiation. This ensures that more appropriate questions and answers are provided by referring to relevant market data for the business negotiation. Some or all of the above processing in the Q&A unit may be performed using AI, for example, or without AI. For example, the Q&A unit can create questions and answers using an AI model that takes relevant market data for the business negotiation as input.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The generation unit can estimate the user's emotions and adjust the timing of new customer list generation based on the estimated user emotions. For example, if the user is stressed, the generation unit may delay list generation and wait until the user is relaxed. For example, if the user is relaxed, the generation unit may immediately generate and provide the list to the user. For example, if the user is in a hurry, the generation unit may quickly generate the list and notify the user. This reduces user stress by adjusting the timing of new customer list generation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can adjust the generation timing using an AI model that takes user emotion data as input and outputs the generation timing.

[0126] The reply unit can estimate the user's emotions and adjust the way it expresses its reply based on those emotions. For example, if the user is stressed, the reply unit will generate a concise and clear reply. If the user is relaxed, the reply unit will generate a detailed and polite reply. If the user is in a hurry, the reply unit will generate a quick and to-the-point reply. This allows for more appropriate replies by adjusting the way the reply is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust its expression using an AI model that takes user emotion data as input and outputs a way to express the reply.

[0127] The estimation unit can estimate the user's emotions and adjust the way the estimate is presented based on the estimated emotions. For example, if the user is stressed, the estimation unit will generate a concise and clear estimate. If the user is relaxed, the estimation unit will generate a detailed and thorough estimate. If the user is in a hurry, the estimation unit will generate a quick and to-the-point estimate. By adjusting the way the estimate is presented according to the user's emotions, a more appropriate estimate can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the estimation unit may be performed using AI, or not using AI. For example, the estimation unit can adjust the presentation using an AI model that takes user emotion data as input and outputs the way the estimate is presented.

[0128] The analysis unit can estimate the user's emotions and adjust the display method of the analysis based on the estimated user emotions. For example, if the user is stressed, the analysis unit provides a concise and highly visible display method. For example, if the user is relaxed, the analysis unit provides a display method that includes detailed information. For example, if the user is in a hurry, the analysis unit provides a display method that gets straight to the point. By adjusting the display method of the analysis according to the user's emotions, more appropriate analysis results are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can adjust the display method using an AI model that takes user emotion data as input and outputs an analysis display method.

[0129] The research unit can estimate the user's emotions and adjust the way the survey is displayed based on the estimated emotions. For example, if the user is stressed, the research unit provides a concise and highly visible display. For example, if the user is relaxed, the research unit provides a display that includes detailed information. For example, if the user is in a hurry, the research unit provides a display that gets straight to the point. By adjusting the way the survey is displayed according to the user's emotions, more appropriate survey results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can adjust the display using an AI model that takes user emotion data as input and outputs the way the survey is displayed.

[0130] The generation unit can analyze past customer list generation history and select the optimal generation method. For example, the generation unit can select a generation method with a high success rate from past generation history and apply it. For example, the generation unit can find the optimal generation method under specific conditions and use it. The generation unit can also, for example, try out new generation methods and find the optimal one. In this way, the optimal generation method can be selected by analyzing past generation history. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can select a generation method using an AI model that takes past generation history data as input and outputs the optimal generation method.

[0131] The reply unit can adjust the level of detail in its replies based on the importance of the inquiry. For example, it can generate detailed replies for high-importance inquiries, or concise replies for low-importance inquiries. For example, it can adjust the level of detail in its replies in stages according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in replies based on the importance of the inquiry. Some or all of the above processing in the reply unit may be performed using AI, or not. For example, the reply unit can adjust the level of detail using an AI model that takes inquiry importance data as input and outputs the level of detail in the replies.

[0132] The estimation unit can adjust the level of detail in an estimate based on the importance of the product when generating an estimate. For example, the estimation unit generates a detailed estimate for high-importance products. For example, the estimation unit generates a concise estimate for low-importance products. For example, the estimation unit adjusts the level of detail in an estimate in stages according to importance. This makes it possible to create estimates efficiently by adjusting the level of detail in an estimate based on the importance of the product. Some or all of the above processes in the estimation unit may be performed using AI, for example, or without AI. For example, the estimation unit can adjust the level of detail using an AI model that takes product importance data as input and outputs the level of detail in the estimate.

[0133] The analysis unit can predict current behavior by referring to past customer behavior data during analysis. For example, the analysis unit can predict a customer's next purchase behavior based on past purchase history. For example, the analysis unit can predict a customer's next visit behavior based on past access history. For example, the analysis unit can predict a customer's next inquiry behavior based on past inquiry history. In this way, current behavior can be predicted by referring to past customer behavior data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can predict behavior using an AI model that takes past customer behavior data as input and predicts current behavior.

[0134] The research department can predict the current competitive situation by referring to past competitive data during the research process. For example, the research department predicts the current competitive situation based on past competitive data. For example, the research department predicts the next actions of competitors based on past competitive data. For example, the research department analyzes the behavioral patterns of competitors based on past competitive data. This allows the current competitive situation to be predicted by referring to past competitive data. Some or all of the above processes in the research department may be performed using AI, for example, or without AI. For example, the research department can predict the situation using an AI model that takes past competitive data as input and predicts the current competitive situation.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The generation unit automatically generates a list of new customers. The generation unit automatically generates a list of new customers based on conditions such as industry, region, relevant keywords, and sales volume. For example, if you are looking for new IT-related customers in a specific region, the AI ​​will automatically generate a list of companies that meet the criteria. It can also list customers specializing in a specific industry or companies with a specific sales volume. Step 2: The reply unit automatically responds to inquiries based on the list generated by the generation unit. The reply unit automatically creates appropriate replies and follow-up emails in response to customer inquiries. For example, if a question about a product comes in, the AI ​​generates the best response based on past inquiry history. Furthermore, it can automatically create follow-up emails and customize the response content according to the content of the inquiry. Step 3: The Quotation Department automatically generates a quotation based on the response received by the Reply Department. The Quotation Department automatically generates quotations from the price list of products and services. For example, if multiple products are selected, the AI ​​automatically calculates the total price and generates a quotation. Furthermore, it can automatically create quotations for specific services and automatically adjust the quotation content in accordance with price list updates. Step 4: The analytics department analyzes customer behavior based on the estimates generated by the estimation department. The analytics department creates marketing strategies from purchase history and access history. For example, for customers who frequently purchase a particular product, the AI ​​can suggest the most suitable promotions for that customer. Furthermore, based on the customer's access history, it is possible to identify products they are interested in and analyze their behavior patterns to predict future behavior. Step 5: The Research Department conducts competitive analysis based on the results analyzed by the Analysis Department. The Research Department analyzes the differentiating points of its own products and services. For example, AI analyzes the advantages of its own products compared to those of competitors and generates a report. Furthermore, it can also analyze the pricing strategies and marketing measures of competitors. Step 6: The Q&A unit creates anticipated questions and answers based on the information obtained by the research unit. The Q&A unit creates anticipated questions and answers before direct negotiations with customers. For example, based on past negotiation data, the AI ​​generates common questions and answers and provides them to sales representatives. Furthermore, it can automatically create questions and answers and negotiation scenarios for specific products.

[0137] 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.

[0138] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the generation unit, reply unit, estimation unit, analysis unit, investigation unit, and Q&A unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The reply unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The estimation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12. The investigation unit is implemented by the specific processing unit 290 of the data processing unit 12. The Q&A unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0144] 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.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0146] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the generation unit, reply unit, estimation unit, analysis unit, investigation unit, and question-and-answer unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The reply unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The estimation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The investigation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The question-and-answer unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0160] 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.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0162] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] 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.

[0164] 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.

[0165] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the generation unit, reply unit, estimation unit, analysis unit, investigation unit, and question-and-answer unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The reply unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The estimation unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The investigation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The question-and-answer unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0176] 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.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0178] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] 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.

[0180] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] 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.

[0182] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] 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.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the generation unit, reply unit, estimation unit, analysis unit, investigation unit, and question-and-answer unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The reply unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The estimation unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The investigation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The question-and-answer unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0190] 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.

[0191] Figure 9 shows the 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.

[0192] 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.

[0193] 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.

[0194] 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, and motorcycles, 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 based, for example, 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.

[0195] 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."

[0196] 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.

[0197] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] 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 other things 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.

[0207] 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.

[0208] (Note 1) A generation unit that automatically generates a list of new customers, A reply unit that automatically responds to inquiries based on the list generated by the generation unit, An estimation unit that automatically generates an estimate based on the content of the reply sent by the aforementioned reply unit, An analysis unit analyzes customer behavior based on the estimates generated by the estimation unit, Based on the results of the analysis conducted by the aforementioned analysis department, the research department conducts competitive analysis, The system includes a question and answer unit that creates anticipated questions and answers based on information obtained by the aforementioned investigation unit. A system characterized by the following features. (Note 2) The generating unit is Automatically generate new customer lists based on criteria such as industry, region, relevant keywords, and sales volume. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned reply section is, Automatically generates appropriate replies and follow-up emails in response to customer inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 4) The estimation unit said above, Automatically generate quotes from product and service price lists. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit is Create marketing strategies based on purchase history and access history. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned investigation department, Analyze the differentiating points of your company's products and services. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned question and answer section is, Create anticipated questions and answers to prepare for direct negotiations with customers. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is It estimates user sentiment and adjusts the timing of new customer list generation based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The generating unit is Analyze past customer list generation history and select the optimal generation method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is When generating a new customer list, filter it based on the user's current business situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is It estimates user sentiment and determines the priority of customer lists generated based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is When generating a new customer list, the system prioritizes listing highly relevant customers by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating a new customer list, the system analyzes users' social media activity and lists relevant customers. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reply section is, It estimates the user's emotions and adjusts the way it expresses its replies based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reply section is, When replying, adjust the level of detail in the response based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reply section is, When replying, apply different reply algorithms depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned reply section is, It estimates the user's emotions and adjusts the length of the reply based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned reply section is, When responding, we will prioritize replies based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reply section is, When replying, we adjust the order of replies based on the relevance of the inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 20) The estimation unit said above, It estimates the user's emotions and adjusts how the estimate is presented based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The estimation unit said above, When generating an estimate, adjust the level of detail in the estimate based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 22) The estimation unit said above, When generating quotes, different quote algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The estimation unit said above, It estimates the user's sentiment and adjusts the length of the estimate based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The estimation unit said above, When generating quotes, we prioritize quotes based on when the products are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The estimation unit said above, When generating quotes, adjust the order of quotes based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit is During analysis, past customer behavior data is used to predict current behavior. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned analysis unit is During analysis, different analytical methods are applied to each customer category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned analysis unit is We estimate the user's emotions and adjust the importance of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned analysis unit is During the analysis, we analyze changes in customer behavior based on when they submitted their submissions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit is During analysis, we refer to relevant market data of customers to analyze their behavior. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned investigation department, We estimate the user's sentiment and adjust how the survey is displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned investigation department, During the survey, we refer to past competitive data to predict the current competitive landscape. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned investigation department, During the survey, different research methodologies are applied to each category of competitors. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned investigation department, We estimate user sentiment and adjust the importance of the survey based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned investigation department, During the investigation, we analyze changes in the competitive landscape based on the timing of competitor submissions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned investigation department, During the survey, we analyze the competitive landscape by referring to relevant market data of competitors. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned question and answer section is, The system estimates the user's emotions and adjusts the wording of anticipated questions and answers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned question and answer section is, When creating anticipated questions and answers, we refer to past sales negotiation data to predict the current sales negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned question and answer section is, When creating anticipated questions and answers, apply different question-and-answer methods for each category of business negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned question and answer section is, The system estimates the user's emotions and adjusts the importance of anticipated questions and answers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned question and answer section is, When creating anticipated questions and answers, prioritize them based on the timing of submitting the sales proposal. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned question and answer section is, When creating anticipated questions and answers, refer to relevant market data for the business negotiation. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A generation unit that automatically generates a list of new customers, A reply unit that automatically responds to inquiries based on the list generated by the generation unit, An estimation unit that automatically generates an estimate based on the content of the reply sent by the aforementioned reply unit, An analysis unit analyzes customer behavior based on the estimates generated by the estimation unit, Based on the results of the analysis conducted by the aforementioned analysis department, the research department conducts competitive analysis, The system includes a question and answer unit that creates anticipated questions and answers based on information obtained by the aforementioned investigation unit. A system characterized by the following features.

2. The generating unit is Automatically generate new customer lists based on criteria such as industry, region, relevant keywords, and sales volume. The system according to feature 1.

3. The aforementioned reply section is, Automatically generates appropriate replies and follow-up emails in response to customer inquiries. The system according to feature 1.

4. The estimation unit said above, Automatically generate quotes from product and service price lists. The system according to feature 1.

5. The aforementioned analysis unit is Create marketing strategies based on purchase history and access history. The system according to feature 1.

6. The aforementioned investigation department, Analyze the differentiating points of your company's products and services. The system according to feature 1.

7. The aforementioned question and answer section is, Create anticipated questions and answers to prepare for direct negotiations with customers. The system according to feature 1.

8. The generating unit is It estimates user sentiment and adjusts the timing of new customer list generation based on the estimated user sentiment. The system according to feature 1.

9. The generating unit is Analyze past customer list generation history and select the optimal generation method. The system according to feature 1.

10. The generating unit is When generating a new customer list, filter it based on the user's current business situation and areas of interest. The system according to feature 1.

Images