system

Abstract

The system according to this embodiment aims to compensate for the shortage of sales crew and improve the closing rate. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, a closing unit, a registration unit, and a training unit. The collection unit collects information on plans and services of other companies and the company itself. The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of excellent sales crews. The generation unit generates an AI with advanced sales skills based on the sales pitches learned by the analysis unit. The closing unit performs closing on customers who have been approached and seated by a crew member, using the sales AI generated by the generation unit and installed at the store counter. The registration unit handles everything from the closing unit's decision-making to registration. The training unit trains the crew members using the sales AI.

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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there are problems such as the training of sales staff not keeping up, the shortage of excellent staff, and the occurrence of outsourcing costs.

[0005] The system according to the embodiment aims to compensate for the shortage of sales staff and improve the closing rate.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a closing unit, a registration unit, and a training unit. The collection unit collects information on plans and services of other companies and the company itself. The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of excellent sales crews. The generation unit generates an AI with advanced sales skills based on the sales pitches learned by the analysis unit. The closing unit closes the deal for customers who have been approached and seated by a crew member, using the sales AI generated by the generation unit and installed at the store counter. The registration unit handles everything from the closing unit's decision-making process to registration. The training unit provides training for the crew members using the sales AI. [Effects of the Invention]

[0007] The system according to this embodiment can compensate for a shortage of sales crew and improve the closing rate. [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 signed 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 including 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 support system according to an embodiment of the present invention is a system that uses generative AI to generate the strongest sales crew in order to solve problems in the sales field. This sales support system generates an AI with the strongest sales skills by inputting information on plans and services of other companies and the company itself into the generative AI and having it learn the sales pitches of excellent sales crews. The generated sales AI is installed at the store counter and performs closing on customers that the crew has approached and seated, handling everything from the decision to close the deal to registration. Furthermore, the strongest sales AI conducts training for the crew to improve their skills. For example, the sales support system inputs information on plans and services of other companies and the company itself into the generative AI. At this time, it collects the latest information on plans and services and has the generative AI learn from it. For example, by inputting new pricing plans and campaign information into the generative AI, the generative AI can grasp the latest information and generate the optimal sales pitch. Next, the generative AI learns the sales pitches of excellent sales crews. Specifically, it collects sales pitch data from past excellent sales crews and has the generative AI learn from it. As a result, the generative AI can generate an AI with the strongest sales skills. For example, by training the AI ​​with high-converting sales pitches and pitches tailored to customer needs, it can generate optimal sales pitches. The generated sales AI is then installed at the store counter. The sales AI then closes the deal with customers who are approached and seated by the crew. Specifically, it listens to the customer's needs and proposes the most suitable plan and service. For example, if a customer wants to buy a new smartphone, the sales AI will make the best proposal based on the latest pricing plans and campaign information. This allows for a smooth process from decision-making to registration. Furthermore, the top-performing sales AI conducts training for the crew. Specifically, the sales AI teaches the crew tips for sales pitches and the latest plan information. This helps to improve the crew's skills. For example, by teaching new crew members tips for high-converting sales pitches, the crew's closing rate can be improved. This system allows for the mass production of top-performing sales AIs with the same skills, thus compensating for the shortage of crew members.Furthermore, it can reduce the cost of outsourced closers during events. In addition, having a highly effective AI handle closing significantly improves the closing rate and leads to an increase in the number of deals acquired. The strongest sales AI can train the crew, allowing them to transfer the AI's skills to the crew. As a result, the sales support system can solve challenges in the sales field, compensate for crew shortages, and improve the closing rate.

[0029] The sales support system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a closing unit, a registration unit, and a training unit. The collection unit collects information on plans and services of other companies and the company itself. For example, the collection unit can collect the latest pricing plans and campaign information. The collection unit can also collect information such as customer satisfaction and feature information. For example, the collection unit automatically collects information from the internet and stores it in a database. The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of excellent sales crews. For example, the analysis unit can analyze the sales pitch data of past excellent sales crews and learn the optimal sales pitch. For example, the analysis unit analyzes and learns sales pitches with high closing rates and high customer satisfaction. The generation unit generates an AI with the strongest sales skills based on the sales pitches learned by the analysis unit. For example, the generation unit can generate an AI with the strongest sales skills using the generated AI. For example, the generation unit generates sales pitches with high closing rates and sales pitches tailored to customer needs using the generated AI. The closing unit is where the sales AI generated by the generation unit is installed at the store counter, and the crew approaches and closes the deal with customers who have been approached and seated. The closing unit can, for example, listen to the customer's needs and propose the most suitable plan or service. For example, if a customer wants to buy a new smartphone, the closing unit will make the best proposal based on the latest pricing plans and campaign information. The registration unit handles everything from the closing unit's decision to registration. The registration unit can, for example, create contracts and register customer information. For example, after the decision to close a deal, the registration unit quickly creates a contract and registers customer information. The training unit uses the sales AI to train the crew. The training unit can, for example, teach the crew tips for sales pitches and the latest plan information. For example, the training unit teaches new crew members tips for sales pitches that lead to higher closing rates. As a result, the sales support system according to this embodiment can solve problems in the sales field, compensate for crew shortages, and improve the closing rate.

[0030] The data collection unit collects information about plans and services of other companies and its own company. For example, it can collect the latest pricing plans and campaign information. It can also collect information such as customer satisfaction and feature information. Specifically, the data collection unit automatically collects information from the internet and stores it in a database. This includes using web scraping technology to obtain the latest pricing plans and campaign information from other companies' websites, social media, forums, etc. Furthermore, it collects data on customer satisfaction from customer review sites and survey results, and also collects information on product and service features. The data collection unit centrally manages this data and can share it with other departments as needed. For example, the collected data is stored in a cloud-based database and made accessible to the analysis and generation units. The data collection unit can also adjust the frequency and accuracy of data collection, allowing for flexible responses to specific situations and conditions. This enables the data collection unit to collect data efficiently and effectively, improving the overall system performance. In addition, the data collection unit can verify and clean the collected data to ensure data quality. For example, it can remove duplicate data and correct inaccurate data to provide reliable data. This allows the data collection unit to provide accurate and up-to-date information, maximizing the effectiveness of the sales support system.

[0031] The analysis unit analyzes the information collected by the data collection unit and learns the sales pitches of top-performing sales crews. For example, the analysis unit can analyze past sales pitch data from successful sales crews and learn optimal sales pitches. Specifically, the analysis unit analyzes and learns sales pitches with high conversion rates and high customer satisfaction. It utilizes AI-based natural language processing technology to extract effective phrases and speaking patterns from the sales pitch data. For example, it can identify commonalities in high-converting sales pitches and create optimal sales pitch scripts based on them. It also analyzes customer reactions and feedback to learn what kind of pitches customers prefer. Based on this data, the analysis unit can identify areas for improvement in the sales pitches used by sales crews and provide more effective pitches. Furthermore, the analysis unit can utilize past sales and customer data to perform trend analysis and predictive analysis. For example, it can analyze sales trends in specific periods or regions to formulate future sales strategies. In addition, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data and issue warnings early. This allows the analysis unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0032] The generation unit generates AI with the strongest sales skills based on the dialogue learned by the analysis unit. For example, the generation unit can generate AI with the strongest sales skills using the generated AI. Specifically, the generated AI generates dialogue with a high conversion rate and dialogue tailored to customer needs. The generated AI utilizes natural language generation technology to generate optimal dialogue while simulating conversations with customers. For example, if a customer wants to buy a new smartphone, the generated AI will generate dialogue that proposes the best plan and service based on the customer's needs and budget. Furthermore, the generated AI can flexibly change the dialogue in response to customer reactions, enabling more effective conversations. The generation unit can introduce these generated AIs to sales sites and improve the sales skills of the crew by having them use them. In addition, the generation unit can continuously evaluate and improve the performance of the generated AI. For example, it can monitor the effectiveness of the generated AI's dialogue and adjust the AI's algorithm based on data on conversion rates and customer satisfaction. This allows the generation unit to always provide highly accurate dialogue based on the latest information, maximizing the effectiveness of the sales support system.

[0033] The closing unit utilizes a sales AI generated by the generation unit, which is installed at the store counter. A crew member then engages with the customer and performs the closing process. For example, the closing unit can listen to the customer's needs and propose the most suitable plan or service. Specifically, if a customer wants to purchase a new smartphone, the closing unit will provide the best recommendation based on the latest pricing plans and campaign information. The sales AI can quickly and accurately answer customer questions and concerns, building trust. Furthermore, the closing unit can monitor customer reactions in real time and adjust the conversation as needed. For instance, if a customer shows interest in a particular feature, it can provide detailed information about that feature to increase their purchase intent. Additionally, the closing unit can provide personalized recommendations based on the customer's purchase history and preferences. This allows the closing unit to propose the most suitable plan or service to the customer, improving the closing rate.

[0034] The Registration Department handles everything from contract decision-making to registration by the Closing Department. The Registration Department can, for example, create contracts and register customer information. Specifically, after a contract decision is made, the Registration Department quickly creates contracts and registers customer information. Contract creation is done using templates, automatically inputting necessary information for accurate and rapid creation. Furthermore, customer information registration involves saving customer personal information and contract details in a database and sharing it with other departments. This allows the Registration Department to efficiently handle post-contract procedures and provide prompt service to customers. In addition, the Registration Department can review and revise contract details. For example, if a customer requests changes to the contract details, the Registration Department can respond quickly and revise the contract. The Registration Department can also monitor the progress of contracts and follow up as needed. This allows the Registration Department to provide high-quality service to customers and improve customer satisfaction.

[0035] The training department uses sales AI to conduct training for crew members. For example, the training department can teach crew members sales techniques and the latest plan information. Specifically, the training department teaches new crew members sales techniques that lead to higher closing rates. The sales AI imparts effective sales techniques to crew members based on sales data from past top-performing sales crew members. For example, it teaches them how to ask questions to elicit customer needs and how to adjust their sales pitch based on customer responses. The training department also provides crew members with the latest pricing plans and campaign information, ensuring they always conduct sales pitches based on the most up-to-date information. Furthermore, the training department can evaluate crew members' skills and create individualized training plans. For example, it can identify skills that need improvement based on crew members' closing rates and customer satisfaction data and provide individualized training plans. This allows the training department to continuously improve crew members' skills and maximize the effectiveness of the sales support system.

[0036] The data collection unit can collect information on the latest plans and services. For example, it can collect information on new product releases. For example, it can also collect information on price revisions. For example, it can also collect information on campaigns. This allows the unit to always provide the latest plans and services by collecting the latest information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can collect information using an AI model that automatically collects information from the internet and stores it in a database.

[0037] The analysis unit can analyze the sales talk data of past successful sales crews and learn the optimal sales talk. For example, the analysis unit can analyze and learn sales talk with a high closing rate. The analysis unit can also analyze and learn sales talk with a high customer satisfaction rate. The analysis unit can also analyze and learn sales talk tailored to customer needs. In this way, by learning from past successful sales talk data, the optimal sales talk can be generated. 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 learn sales talk using an AI model that takes past sales talk data as input and outputs the optimal sales talk.

[0038] The generation unit can generate AI with advanced sales skills using generative AI. For example, the generation unit can generate high-converting sales pitches using generative AI. The generation unit can also generate sales pitches tailored to customer needs using generative AI. The generation unit can also generate sales pitches that result in high customer satisfaction using generative AI. In this way, by using generative AI, it is possible to generate AI with the strongest sales skills. The generative AI generates sales pitches using machine learning algorithms, for example. The generative AI learns from a large amount of sales pitch data and generates optimal sales pitches, for example. The generative AI generates sales pitches using natural language processing technology, for example. Some or all of the above processes in the generation unit are performed using generative AI. For example, the generation unit can generate sales pitches using a generative AI model that takes past sales pitch data as input and outputs optimal sales pitches.

[0039] The closing department can listen to the customer's needs and propose the most suitable plan and service. For example, if a customer wants to purchase a new smartphone, the closing department can make the best proposal based on the latest pricing plans and campaign information. For example, if a customer wants to subscribe to an internet service, the closing department can also propose the best plan. For example, if a customer is considering an insurance product, the closing department can also propose the best insurance plan. This makes it possible to make the best proposal tailored to the customer's needs. Some or all of the above processes in the closing department may be performed using AI, for example, or not. For example, the closing department can make proposals using an AI model that takes the customer's needs as input and outputs the best plan and service.

[0040] The registration unit can streamline the process from contract decision-making to registration. For example, the registration unit can automate the creation of contracts. For example, the registration unit can automate the registration of customer information. For example, the registration unit can simplify the required documents. This streamlines the process from contract decision-making to registration, enabling efficient registration. Some or all of the processes described above in the registration unit may be performed using AI, for example, or not. For example, the registration unit can perform registration using an AI model that automates the process after contract decision-making.

[0041] The training department can teach crew members sales techniques and the latest plan information. For example, the training department can teach new crew members sales techniques that lead to higher closing rates. The training department can also provide crew members with the latest pricing plans and campaign information. The training department can also teach crew members sales techniques that lead to higher customer satisfaction. This helps to improve the skills of the crew. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes sales techniques and the latest plan information as input and conducts effective training for crew members.

[0042] The data collection unit can track the change history of plans and services of other companies and its own company, thereby improving the accuracy of the information it collects. For example, the data collection unit can analyze past plan change history and prioritize the collection of plans that change frequently. The data collection unit can also track service change history and keep the latest service information constantly updated. For example, the data collection unit can refer to the plan change history of other companies to understand the trends of competitors. This improves the accuracy of the information collected by tracking change history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can collect information using an AI model that takes plan and service change history as input and improves the accuracy of the information collected.

[0043] The data collection unit can analyze competitors' marketing strategies and expand the scope of information it collects. For example, it can analyze competitors' advertising campaigns and collect relevant information. It can also investigate competitors' sales strategies and broaden the scope of information it collects. It can also understand competitors' market trends and optimize the information it collects. This allows it to expand the scope of information collected by analyzing competitors' marketing strategies. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes competitors' marketing data as input and expands the scope of information it collects.

[0044] The data collection unit can prioritize the collection of highly relevant information by considering the user's geographical location during data collection. For example, the data collection unit can collect region-specific plan and service information based on the user's current location. The data collection unit can also prioritize the collection of relevant information by referring to the user's travel history. The data collection unit can also collect the most relevant information by considering the user's geographical location. This allows for the priority collection of highly relevant information by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes the user's geographical location data as input and outputs highly relevant information.

[0045] The data collection unit can analyze social media trends and collect the latest plans and service information during data collection. For example, the data collection unit can analyze social media trends in real time and collect relevant information. For example, the data collection unit can track popular hashtags and collect the latest plans and service information. For example, the data collection unit can analyze user posts on social media and collect trend-based information. In this way, by analyzing social media trends, the latest plans and service information can be collected. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes social media data as input and analyzes trends to collect information.

[0046] The analysis unit can analyze past sales data and extract optimal sales talk patterns. For example, the analysis unit can extract sales talk patterns with high conversion rates based on past sales data. The analysis unit can also analyze sales data and extract sales talk patterns tailored to customer needs. For example, the analysis unit can analyze sales data and identify effective sales talk patterns. This allows for the extraction of optimal sales talk patterns by analyzing past sales data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can extract sales talk patterns using an AI model that takes past sales data as input and outputs optimal sales talk patterns.

[0047] The analysis unit can evaluate the effectiveness of a sales pitch by considering the customer's purchase history during analysis. For example, the analysis unit evaluates the effectiveness of a sales pitch based on the customer's purchase history. The analysis unit can also evaluate the effectiveness of a sales pitch tailored to the customer's needs by referring to the purchase history. The analysis unit can also optimize the effectiveness of a sales pitch by analyzing the customer's past purchase history. This allows for the evaluation of the effectiveness of a sales pitch by considering the customer's purchase history. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can evaluate the effectiveness of a sales pitch using an AI model that takes customer purchase history data as input and outputs the effectiveness of the sales pitch.

[0048] The analysis unit can optimize the talk patterns by considering the customer's demographic information during analysis. For example, the analysis unit can optimize talk patterns to match the customer's age group. The analysis unit can also adjust talk patterns based on the customer's gender. The analysis unit can also optimize talk patterns by considering the customer's regional information. In this way, the talk patterns can be optimized by considering the customer's demographic information. 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 optimize talk patterns using an AI model that takes customer demographic data as input and outputs talk patterns.

[0049] The analysis unit can compare the effectiveness of a sales pitch by referring to the sales data of competitors during the analysis. For example, the analysis unit can compare the effectiveness of a sales pitch based on the sales data of competitors. The analysis unit can also, for example, analyze the sales strategies of competitors and evaluate the effectiveness of a sales pitch. The analysis unit can also, for example, refer to the sales data of competitors and optimize the effectiveness of a sales pitch. This allows for the comparison of the effectiveness of a sales pitch by referring to the sales data of competitors. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can compare the effectiveness of a sales pitch by using an AI model that takes competitor sales data as input and outputs the effectiveness of a sales pitch.

[0050] The generation unit can generate an AI with optimal sales skills by referring to past success stories during the generation process. For example, the generation unit can generate an AI with high closing rate skills based on past success stories. The generation unit can also generate an AI with skills tailored to customer needs by referring to success stories. For example, the generation unit can analyze past success stories and generate an AI with optimal sales skills. In this way, an AI with optimal sales skills can be generated by referring to past success stories. Some or all of the above processes in the generation unit are performed using the generation AI. For example, the generation unit can generate an AI using a generation AI model that takes past success story data as input and outputs an AI with optimal sales skills.

[0051] The generation unit can generate new sales AI by combining sales skills from different industries during the generation process. For example, the generation unit can generate a unique sales AI by combining sales skills from different industries. The generation unit can also generate an AI with new sales skills by referring to successful case studies from different industries. For example, the generation unit can analyze sales data from different industries and generate an AI with the optimal skills. This allows for the generation of unique sales AI by combining sales skills from different industries. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate AI using a generation AI model that takes sales data from different industries as input and outputs an AI that combines skills.

[0052] The generation unit can generate region-specific sales AI by referencing sales data from different regions during the generation process. For example, the generation unit can generate region-specific sales AI based on sales data from different regions. The generation unit can also analyze sales trends for each region and generate AI with optimal skills. For example, the generation unit can generate region-specific sales AI by referencing successful case studies from different regions. In this way, region-specific sales AI can be generated by referencing sales data from different regions. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate AI using a generation AI model that takes sales data from different regions as input and outputs region-specific AI.

[0053] The generation unit can generate a multilingual sales AI by combining sales skills in different languages ​​during the generation process. For example, the generation unit can generate a multilingual sales AI by combining sales skills in different languages. The generation unit can also generate an AI with the optimal skills by referring to successful multilingual case studies. The generation unit can also generate a multilingual sales AI by analyzing sales data in different languages. In this way, a multilingual sales AI can be generated by combining sales skills in different languages. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate an AI using a generation AI model that takes sales data in different languages ​​as input and outputs a multilingual AI.

[0054] The closing unit can make optimal proposals by referring to the customer's purchase history at the time of closing. For example, the closing unit can propose the most suitable plan or service based on the customer's past purchase history. The closing unit can also make proposals tailored to the customer's needs by referring to the purchase history. The closing unit can also analyze the customer's past purchase history and make the most effective proposals. This makes it possible to make optimal proposals by referring to the customer's purchase history. Some or all of the above processes in the closing unit may be performed using AI, for example, or not using AI. For example, the closing unit can make proposals using an AI model that takes customer purchase history data as input and outputs the optimal proposal.

[0055] The closing unit can adjust the proposal content in real time by reflecting customer feedback during the closing process. For example, the closing unit can collect customer feedback in real time and adjust the proposal content. For example, the closing unit can make proposals tailored to customer needs based on the feedback. For example, the closing unit can analyze real-time feedback and make the optimal proposal. This makes it possible to make more effective proposals by reflecting customer feedback in real time. Some or all of the above processes in the closing unit may be performed using AI, for example, or not using AI. For example, the closing unit can make proposals using an AI model that takes customer feedback data as input and adjusts the proposal content.

[0056] The closing unit can make optimal proposals at the time of closing, taking into account the customer's geographical location information. For example, the closing unit can propose region-specific plans and services based on the customer's current location. The closing unit can also refer to geographical location information and make proposals tailored to the customer's needs. The closing unit can also make optimal proposals by taking into account the customer's geographical location information. This makes it possible to make optimal proposals by taking into account the customer's geographical location information. Some or all of the above processing in the closing unit may be performed using AI, for example, or without using AI. For example, the closing unit can make proposals using an AI model that takes the customer's geographical location data as input and outputs optimal proposals.

[0057] The closing department can analyze the customer's social media activity and customize the proposal at the time of closing. For example, the closing department can analyze the customer's social media activity and make relevant proposals. For example, the closing department can make proposals tailored to the customer's needs based on social media posts. For example, the closing department can refer to the customer's social media activity and make optimal proposals. In this way, the proposal can be customized by analyzing the customer's social media activity. Some or all of the above processes in the closing department may be performed using AI, for example, or not using AI. For example, the closing department can use an AI model that takes the customer's social media data as input and customizes the proposal to make proposals.

[0058] The registration unit can select the optimal registration method by referring to the customer's past registration history during registration. For example, the registration unit can propose the optimal registration method based on the customer's past registration history. For example, the registration unit can also refer to the registration history and provide a registration method tailored to the customer's needs. For example, the registration unit can analyze the customer's past registration history and select the most effective registration method. This allows the optimal registration method to be selected by referring to the customer's past registration history. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can select a registration method using an AI model that takes customer registration history data as input and outputs the optimal registration method.

[0059] The registration unit can adjust registration content in real time by reflecting customer feedback during registration. For example, the registration unit can collect customer feedback in real time and adjust registration content. For example, the registration unit can also provide registration content tailored to customer needs based on feedback. For example, the registration unit can analyze real-time feedback and provide optimal registration content. This makes more effective registration possible by reflecting customer feedback in real time. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can perform registration using an AI model that takes customer feedback data as input and adjusts registration content.

[0060] The registration unit can select the optimal registration method at the time of registration, taking into account the customer's geographical location information. For example, the registration unit can provide a region-specific registration method based on the customer's current location. For example, the registration unit can also refer to geographical location information and provide a registration method tailored to the customer's needs. For example, the registration unit can select the optimal registration method by taking the customer's geographical location information into account. This allows for the selection of the optimal registration method by considering the customer's geographical location information. Some or all of the above-described processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can select a registration method using an AI model that takes the customer's geographical location data as input and outputs the optimal registration method.

[0061] The registration unit can analyze the customer's social media activity and customize the registration content during registration. For example, the registration unit can analyze the customer's social media activity and provide relevant registration content. For example, the registration unit can also provide registration content tailored to the customer's needs based on social media posts. For example, the registration unit can refer to the customer's social media activity and provide optimal registration content. This allows for customization of registration content by analyzing the customer's social media activity. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can use an AI model that takes the customer's social media data as input and customizes the registration content to perform registration.

[0062] The training department can select the optimal training method by referring to past training data during training sessions. For example, the training department can propose the optimal training method based on past training data. The training department can also provide effective training methods by referring to training data. For example, the training department can analyze past training data and select the most effective training method. This allows for the selection of the optimal training method by referring to past training data. Some or all of the above processes in the training department may be performed using AI, for example, or without AI. For example, the training department can conduct training using an AI model that takes past training data as input and outputs the optimal training method.

[0063] The training department can create new training programs by combining training data from different industries during training sessions. For example, the training department can create unique training programs by combining training data from different industries. The training department can also provide new training programs by referring to successful case studies from different industries. The training department can also create optimal training programs by analyzing training data from different industries. This allows for the creation of unique training programs by combining training data from different industries. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes training data from different industries as input and creates training programs.

[0064] The training department can create region-specific training programs by referencing training data from different regions during training sessions. For example, the training department can create region-specific training programs based on training data from different regions. The training department can also analyze training trends in each region and provide optimal training programs. For example, the training department can create region-specific training programs by referencing successful case studies from different regions. This allows for the creation of region-specific training programs by referencing training data from different regions. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes training data from different regions as input and creates region-specific training programs.

[0065] The training department can create multilingual training programs by combining training data from different languages ​​during training sessions. For example, the training department can combine training data from different languages ​​to create multilingual training programs. The training department can also refer to successful multilingual case studies to provide optimal training programs. For example, the training department can analyze training data from different languages ​​to create multilingual training programs. This allows for the creation of multilingual training programs by combining training data from different languages. Some or all of the above processes in the training department may be performed using AI, or not. For example, the training department can conduct training using an AI model that takes training data from different languages ​​as input and creates multilingual training programs.

[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 sales support system can also include a purchase history analysis unit that analyzes the customer's purchase history. This unit analyzes the customer's preferences and purchasing patterns based on their past purchase history. For example, it can analyze the types and frequency of products a customer has purchased in the past to understand their preferences. It can also identify products that customers tend to purchase during specific seasons or events. Furthermore, it can analyze reviews and ratings of products a customer has purchased in the past to understand their satisfaction level. This allows the sales support system to provide more personalized suggestions based on the customer's purchase history.

[0068] The sales support system can also include a social media analytics unit that analyzes customers' social media activity. This unit analyzes customers' posts and activities on social media to understand their interests and concerns. For example, it can analyze accounts customers follow and groups they participate in to identify their hobbies and interests. It can also analyze the content and comments customers post to understand their emotions and opinions. Furthermore, it can analyze articles and videos customers share to identify topics they are interested in. This allows the sales support system to make more appropriate suggestions based on customers' social media activity.

[0069] The sales support system can also be equipped with a geographic information analysis unit that utilizes the customer's geographic location information. This unit provides region-specific information based on the customer's current location and travel history. For example, it can suggest specific stores or services in the area where the customer is currently located. Furthermore, it can analyze places the customer has visited in the past and areas they frequently visit to understand their behavioral patterns. It can also provide information on services and promotions available to the customer while they are on the move. This allows the sales support system to make more relevant suggestions based on the customer's geographic location information.

[0070] The sales support system can also include a feedback analysis unit that collects and analyzes customer feedback in real time. The feedback analysis unit collects and analyzes customer feedback in real time. For example, it can collect customer reviews and ratings to understand customer satisfaction. It can also analyze customer comments and opinions to identify customer needs and requests. Furthermore, based on customer feedback, the feedback analysis unit can identify areas for improvement in services and products. This allows the sales support system to make more effective suggestions based on customer feedback.

[0071] The sales support system can also include a campaign provision unit that provides personalized campaigns based on the customer's purchase history. The campaign provision unit analyzes the customer's past purchase history and proposes the most suitable campaigns. For example, based on the types and frequency of products the customer has purchased in the past, the campaign provision unit can propose discount campaigns for related products. It can also identify products that customers tend to purchase during specific seasons or events and provide campaigns tailored to those times. Furthermore, based on the customer's purchase history, the campaign provision unit can propose campaigns for new products that the customer might be interested in. This allows the sales support system to provide more effective campaigns based on the customer's purchase history.

[0072] The sales support system can also include a recommendation unit that provides recommendation functions based on the customer's purchase history. The recommendation unit analyzes the customer's past purchase history and proposes the most suitable products and services. For example, the recommendation unit can suggest related products based on the types and frequency of products the customer has purchased in the past. It can also identify products that customers tend to purchase during specific seasons or events and make suggestions tailored to those times. Furthermore, the recommendation unit can suggest new products that the customer might be interested in, based on their purchase history. As a result, the sales support system can provide more effective recommendations based on the customer's purchase history.

[0073] The sales support system can also include an after-sales service department that provides after-sales services based on the customer's purchase history. The after-sales service department analyzes the customer's past purchase history and proposes the most suitable after-sales service. For example, the after-sales service department can propose maintenance and repair services for products the customer has previously purchased. Furthermore, the after-sales service department can also provide follow-up services after a customer has purchased a specific product. In addition, based on the customer's purchase history, the after-sales service department can propose after-sales services that the customer might be interested in. This allows the sales support system to provide more effective after-sales services based on the customer's purchase history.

[0074] The following briefly describes the processing flow for example form 1.

[0075] Step 1: The data collection unit collects information about other companies' and its own plans and services. For example, it automatically collects the latest pricing plans and promotional information, customer satisfaction ratings, and feature information from the internet and stores them in a database. Step 2: The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of top-performing sales crews. For example, it analyzes past sales pitch data from top-performing sales crews to learn pitches that have a high closing rate and high customer satisfaction. Step 3: The generation unit generates an AI with the strongest sales skills based on the talk learned by the analysis unit. For example, the generation AI is used to generate talks with a high conversion rate or talks tailored to customer needs. Step 4: In the closing section, the sales AI generated by the generation section is installed at the store counter, and the crew closes the deal with customers who have been approached and seated. For example, they listen to the customer's needs and propose the most suitable plan or service. Step 5: The registration department handles everything from contract decision-making to registration by the closing department. For example, they quickly create contracts and register customer information. Step 6: The training department uses the sales AI to conduct training for the crew. For example, it teaches the crew tips on sales techniques and the latest plan information.

[0076] (Example of form 2) The sales support system according to an embodiment of the present invention is a system that uses generative AI to generate the strongest sales crew in order to solve problems in the sales field. This sales support system generates an AI with the strongest sales skills by inputting information on plans and services of other companies and the company itself into the generative AI and having it learn the sales pitches of excellent sales crews. The generated sales AI is installed at the store counter and performs closing on customers that the crew has approached and seated, handling everything from the decision to close the deal to registration. Furthermore, the strongest sales AI conducts training for the crew to improve their skills. For example, the sales support system inputs information on plans and services of other companies and the company itself into the generative AI. At this time, it collects the latest information on plans and services and has the generative AI learn from it. For example, by inputting new pricing plans and campaign information into the generative AI, the generative AI can grasp the latest information and generate the optimal sales pitch. Next, the generative AI learns the sales pitches of excellent sales crews. Specifically, it collects sales pitch data from past excellent sales crews and has the generative AI learn from it. As a result, the generative AI can generate an AI with the strongest sales skills. For example, by training the AI ​​with high-converting sales pitches and pitches tailored to customer needs, it can generate optimal sales pitches. The generated sales AI is then installed at the store counter. The sales AI then closes the deal with customers who are approached and seated by the crew. Specifically, it listens to the customer's needs and proposes the most suitable plan and service. For example, if a customer wants to buy a new smartphone, the sales AI will make the best proposal based on the latest pricing plans and campaign information. This allows for a smooth process from decision-making to registration. Furthermore, the top-performing sales AI conducts training for the crew. Specifically, the sales AI teaches the crew tips for sales pitches and the latest plan information. This helps to improve the crew's skills. For example, by teaching new crew members tips for high-converting sales pitches, the crew's closing rate can be improved. This system allows for the mass production of top-performing sales AIs with the same skills, thus compensating for the shortage of crew members.Furthermore, it can reduce the cost of outsourced closers during events. In addition, having a highly effective AI handle closing significantly improves the closing rate and leads to an increase in the number of deals acquired. The strongest sales AI can train the crew, allowing them to transfer the AI's skills to the crew. As a result, the sales support system can solve challenges in the sales field, compensate for crew shortages, and improve the closing rate.

[0077] The sales support system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a closing unit, a registration unit, and a training unit. The collection unit collects information on plans and services of other companies and the company itself. For example, the collection unit can collect the latest pricing plans and campaign information. The collection unit can also collect information such as customer satisfaction and feature information. For example, the collection unit automatically collects information from the internet and stores it in a database. The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of excellent sales crews. For example, the analysis unit can analyze the sales pitch data of past excellent sales crews and learn the optimal sales pitch. For example, the analysis unit analyzes and learns sales pitches with high closing rates and high customer satisfaction. The generation unit generates an AI with the strongest sales skills based on the sales pitches learned by the analysis unit. For example, the generation unit can generate an AI with the strongest sales skills using the generated AI. For example, the generation unit generates sales pitches with high closing rates and sales pitches tailored to customer needs using the generated AI. The closing unit is where the sales AI generated by the generation unit is installed at the store counter, and the crew approaches and closes the deal with customers who have been approached and seated. The closing unit can, for example, listen to the customer's needs and propose the most suitable plan or service. For example, if a customer wants to buy a new smartphone, the closing unit will make the best proposal based on the latest pricing plans and campaign information. The registration unit handles everything from the closing unit's decision to registration. The registration unit can, for example, create contracts and register customer information. For example, after the decision to close a deal, the registration unit quickly creates a contract and registers customer information. The training unit uses the sales AI to train the crew. The training unit can, for example, teach the crew tips for sales pitches and the latest plan information. For example, the training unit teaches new crew members tips for sales pitches that lead to higher closing rates. As a result, the sales support system according to this embodiment can solve problems in the sales field, compensate for crew shortages, and improve the closing rate.

[0078] The data collection unit collects information about plans and services of other companies and its own company. For example, it can collect the latest pricing plans and campaign information. It can also collect information such as customer satisfaction and feature information. Specifically, the data collection unit automatically collects information from the internet and stores it in a database. This includes using web scraping technology to obtain the latest pricing plans and campaign information from other companies' websites, social media, forums, etc. Furthermore, it collects data on customer satisfaction from customer review sites and survey results, and also collects information on product and service features. The data collection unit centrally manages this data and can share it with other departments as needed. For example, the collected data is stored in a cloud-based database and made accessible to the analysis and generation units. The data collection unit can also adjust the frequency and accuracy of data collection, allowing for flexible responses to specific situations and conditions. This enables the data collection unit to collect data efficiently and effectively, improving the overall system performance. In addition, the data collection unit can verify and clean the collected data to ensure data quality. For example, it can remove duplicate data and correct inaccurate data to provide reliable data. This allows the data collection unit to provide accurate and up-to-date information, maximizing the effectiveness of the sales support system.

[0079] The analysis unit analyzes the information collected by the data collection unit and learns the sales pitches of top-performing sales crews. For example, the analysis unit can analyze past sales pitch data from successful sales crews and learn optimal sales pitches. Specifically, the analysis unit analyzes and learns sales pitches with high conversion rates and high customer satisfaction. It utilizes AI-based natural language processing technology to extract effective phrases and speaking patterns from the sales pitch data. For example, it can identify commonalities in high-converting sales pitches and create optimal sales pitch scripts based on them. It also analyzes customer reactions and feedback to learn what kind of pitches customers prefer. Based on this data, the analysis unit can identify areas for improvement in the sales pitches used by sales crews and provide more effective pitches. Furthermore, the analysis unit can utilize past sales and customer data to perform trend analysis and predictive analysis. For example, it can analyze sales trends in specific periods or regions to formulate future sales strategies. In addition, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data and issue warnings early. This allows the analysis unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0080] The generation unit generates AI with the strongest sales skills based on the dialogue learned by the analysis unit. For example, the generation unit can generate AI with the strongest sales skills using the generated AI. Specifically, the generated AI generates dialogue with a high conversion rate and dialogue tailored to customer needs. The generated AI utilizes natural language generation technology to generate optimal dialogue while simulating conversations with customers. For example, if a customer wants to buy a new smartphone, the generated AI will generate dialogue that proposes the best plan and service based on the customer's needs and budget. Furthermore, the generated AI can flexibly change the dialogue in response to customer reactions, enabling more effective conversations. The generation unit can introduce these generated AIs to sales sites and improve the sales skills of the crew by having them use them. In addition, the generation unit can continuously evaluate and improve the performance of the generated AI. For example, it can monitor the effectiveness of the generated AI's dialogue and adjust the AI's algorithm based on data on conversion rates and customer satisfaction. This allows the generation unit to always provide highly accurate dialogue based on the latest information, maximizing the effectiveness of the sales support system.

[0081] The closing unit utilizes a sales AI generated by the generation unit, which is installed at the store counter. A crew member then engages with the customer and performs the closing process. For example, the closing unit can listen to the customer's needs and propose the most suitable plan or service. Specifically, if a customer wants to purchase a new smartphone, the closing unit will provide the best recommendation based on the latest pricing plans and campaign information. The sales AI can quickly and accurately answer customer questions and concerns, building trust. Furthermore, the closing unit can monitor customer reactions in real time and adjust the conversation as needed. For instance, if a customer shows interest in a particular feature, it can provide detailed information about that feature to increase their purchase intent. Additionally, the closing unit can provide personalized recommendations based on the customer's purchase history and preferences. This allows the closing unit to propose the most suitable plan or service to the customer, improving the closing rate.

[0082] The Registration Department handles everything from contract decision-making to registration by the Closing Department. The Registration Department can, for example, create contracts and register customer information. Specifically, after a contract decision is made, the Registration Department quickly creates contracts and registers customer information. Contract creation is done using templates, automatically inputting necessary information for accurate and rapid creation. Furthermore, customer information registration involves saving customer personal information and contract details in a database and sharing it with other departments. This allows the Registration Department to efficiently handle post-contract procedures and provide prompt service to customers. In addition, the Registration Department can review and revise contract details. For example, if a customer requests changes to the contract details, the Registration Department can respond quickly and revise the contract. The Registration Department can also monitor the progress of contracts and follow up as needed. This allows the Registration Department to provide high-quality service to customers and improve customer satisfaction.

[0083] The training department uses sales AI to conduct training for crew members. For example, the training department can teach crew members sales techniques and the latest plan information. Specifically, the training department teaches new crew members sales techniques that lead to higher closing rates. The sales AI imparts effective sales techniques to crew members based on sales data from past top-performing sales crew members. For example, it teaches them how to ask questions to elicit customer needs and how to adjust their sales pitch based on customer responses. The training department also provides crew members with the latest pricing plans and campaign information, ensuring they always conduct sales pitches based on the most up-to-date information. Furthermore, the training department can evaluate crew members' skills and create individualized training plans. For example, it can identify skills that need improvement based on crew members' closing rates and customer satisfaction data and provide individualized training plans. This allows the training department to continuously improve crew members' skills and maximize the effectiveness of the sales support system.

[0084] The data collection unit can collect information on the latest plans and services. For example, it can collect information on new product releases. For example, it can also collect information on price revisions. For example, it can also collect information on campaigns. This allows the unit to always provide the latest plans and services by collecting the latest information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can collect information using an AI model that automatically collects information from the internet and stores it in a database.

[0085] The analysis unit can analyze the sales talk data of past successful sales crews and learn the optimal sales talk. For example, the analysis unit can analyze and learn sales talk with a high closing rate. The analysis unit can also analyze and learn sales talk with a high customer satisfaction rate. The analysis unit can also analyze and learn sales talk tailored to customer needs. In this way, by learning from past successful sales talk data, the optimal sales talk can be generated. 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 learn sales talk using an AI model that takes past sales talk data as input and outputs the optimal sales talk.

[0086] The generation unit can generate AI with advanced sales skills using generative AI. For example, the generation unit can generate high-converting sales pitches using generative AI. The generation unit can also generate sales pitches tailored to customer needs using generative AI. The generation unit can also generate sales pitches that result in high customer satisfaction using generative AI. In this way, by using generative AI, it is possible to generate AI with the strongest sales skills. The generative AI generates sales pitches using machine learning algorithms, for example. The generative AI learns from a large amount of sales pitch data and generates optimal sales pitches, for example. The generative AI generates sales pitches using natural language processing technology, for example. Some or all of the above processes in the generation unit are performed using generative AI. For example, the generation unit can generate sales pitches using a generative AI model that takes past sales pitch data as input and outputs optimal sales pitches.

[0087] The closing department can listen to the customer's needs and propose the most suitable plan and service. For example, if a customer wants to purchase a new smartphone, the closing department can make the best proposal based on the latest pricing plans and campaign information. For example, if a customer wants to subscribe to an internet service, the closing department can also propose the best plan. For example, if a customer is considering an insurance product, the closing department can also propose the best insurance plan. This makes it possible to make the best proposal tailored to the customer's needs. Some or all of the above processes in the closing department may be performed using AI, for example, or not. For example, the closing department can make proposals using an AI model that takes the customer's needs as input and outputs the best plan and service.

[0088] The registration unit can streamline the process from contract decision-making to registration. For example, the registration unit can automate the creation of contracts. For example, the registration unit can automate the registration of customer information. For example, the registration unit can simplify the required documents. This streamlines the process from contract decision-making to registration, enabling efficient registration. Some or all of the processes described above in the registration unit may be performed using AI, for example, or not. For example, the registration unit can perform registration using an AI model that automates the process after contract decision-making.

[0089] The training department can teach crew members sales techniques and the latest plan information. For example, the training department can teach new crew members sales techniques that lead to higher closing rates. The training department can also provide crew members with the latest pricing plans and campaign information. The training department can also teach crew members sales techniques that lead to higher customer satisfaction. This helps to improve the skills of the crew. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes sales techniques and the latest plan information as input and conducts effective training for crew members.

[0090] The data collection unit can estimate the user's emotions and adjust the timing of information collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of information collection and collect information at times when the user is relaxed. For example, if the user is relaxed, the data collection unit can increase the frequency of information collection and collect more detailed information. For example, if the user is in a hurry, the data collection unit can quickly collect the necessary information and provide it in a timely manner. This allows for more effective information collection by adjusting the timing of information collection 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 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 data collection unit may be performed using AI, or not using AI. For example, the data collection unit can adjust the timing of information collection using an AI model that takes user emotion data as input and outputs the timing of information collection.

[0091] The data collection unit can track the change history of plans and services of other companies and its own company, thereby improving the accuracy of the information it collects. For example, the data collection unit can analyze past plan change history and prioritize the collection of plans that change frequently. The data collection unit can also track service change history and keep the latest service information constantly updated. For example, the data collection unit can refer to the plan change history of other companies to understand the trends of competitors. This improves the accuracy of the information collected by tracking change history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can collect information using an AI model that takes plan and service change history as input and improves the accuracy of the information collected.

[0092] The data collection unit can analyze competitors' marketing strategies and expand the scope of information it collects. For example, it can analyze competitors' advertising campaigns and collect relevant information. It can also investigate competitors' sales strategies and broaden the scope of information it collects. It can also understand competitors' market trends and optimize the information it collects. This allows it to expand the scope of information collected by analyzing competitors' marketing strategies. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes competitors' marketing data as input and expands the scope of information it collects.

[0093] The data collection unit can estimate the user's emotions and determine the priority of information to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will prioritize collecting important information. For example, if the user is relaxed, the data collection unit may prioritize collecting detailed information. For example, if the user is in a hurry, the data collection unit may prioritize collecting information that is needed quickly. This allows for more effective information collection by prioritizing information according to the user's emotions. 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 data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can determine the priority of information using an AI model that takes user emotion data as input and outputs the priority of information.

[0094] The data collection unit can prioritize the collection of highly relevant information by considering the user's geographical location during data collection. For example, the data collection unit can collect region-specific plan and service information based on the user's current location. The data collection unit can also prioritize the collection of relevant information by referring to the user's travel history. The data collection unit can also collect the most relevant information by considering the user's geographical location. This allows for the priority collection of highly relevant information by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes the user's geographical location data as input and outputs highly relevant information.

[0095] The data collection unit can analyze social media trends and collect the latest plans and service information during data collection. For example, the data collection unit can analyze social media trends in real time and collect relevant information. For example, the data collection unit can track popular hashtags and collect the latest plans and service information. For example, the data collection unit can analyze user posts on social media and collect trend-based information. In this way, by analyzing social media trends, the latest plans and service information can be collected. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes social media data as input and analyzes trends to collect information.

[0096] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide deep insights. For example, if the user is in a hurry, the analysis unit can perform a rapid analysis and provide concise results. For example, if the user is stressed, the analysis unit can perform a simple analysis and provide easy-to-understand results. This allows for more effective analysis by adjusting the analysis method according to the user's emotions. 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 analysis method using an AI model that takes user emotion data as input and outputs an analysis method.

[0097] The analysis unit can analyze past sales data and extract optimal sales talk patterns. For example, the analysis unit can extract sales talk patterns with high conversion rates based on past sales data. The analysis unit can also analyze sales data and extract sales talk patterns tailored to customer needs. For example, the analysis unit can analyze sales data and identify effective sales talk patterns. This allows for the extraction of optimal sales talk patterns by analyzing past sales data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can extract sales talk patterns using an AI model that takes past sales data as input and outputs optimal sales talk patterns.

[0098] The analysis unit can evaluate the effectiveness of a sales pitch by considering the customer's purchase history during analysis. For example, the analysis unit evaluates the effectiveness of a sales pitch based on the customer's purchase history. The analysis unit can also evaluate the effectiveness of a sales pitch tailored to the customer's needs by referring to the purchase history. The analysis unit can also optimize the effectiveness of a sales pitch by analyzing the customer's past purchase history. This allows for the evaluation of the effectiveness of a sales pitch by considering the customer's purchase history. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can evaluate the effectiveness of a sales pitch using an AI model that takes customer purchase history data as input and outputs the effectiveness of the sales pitch.

[0099] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the analysis unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the analysis unit can also provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, a more effective display becomes possible. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can adjust the display method of the analysis results using an AI model that takes user emotion data as input and outputs a display method.

[0100] The analysis unit can optimize the talk patterns by considering the customer's demographic information during analysis. For example, the analysis unit can optimize talk patterns to match the customer's age group. The analysis unit can also adjust talk patterns based on the customer's gender. The analysis unit can also optimize talk patterns by considering the customer's regional information. In this way, the talk patterns can be optimized by considering the customer's demographic information. 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 optimize talk patterns using an AI model that takes customer demographic data as input and outputs talk patterns.

[0101] The analysis unit can compare the effectiveness of a sales pitch by referring to the sales data of competitors during the analysis. For example, the analysis unit can compare the effectiveness of a sales pitch based on the sales data of competitors. The analysis unit can also, for example, analyze the sales strategies of competitors and evaluate the effectiveness of a sales pitch. The analysis unit can also, for example, refer to the sales data of competitors and optimize the effectiveness of a sales pitch. This allows for the comparison of the effectiveness of a sales pitch by referring to the sales data of competitors. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can compare the effectiveness of a sales pitch by using an AI model that takes competitor sales data as input and outputs the effectiveness of a sales pitch.

[0102] The generation unit can estimate the user's emotions and adjust the skills of the AI ​​it generates based on those estimated emotions. For example, if the user is relaxed, the generation unit can generate an AI with skills that include detailed explanations. If the user is in a hurry, the generation unit can also generate an AI with skills that allow for quick responses. If the user is stressed, the generation unit can also generate an AI with simple and easy-to-understand skills. By adjusting the AI's skills according to the user's emotions, a more effective AI can be generated. 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-described processes in the generation unit are performed using a generation AI. For example, the generation unit can adjust the AI's skills using a generation AI model that takes user emotion data as input and outputs an AI with adjusted skills.

[0103] The generation unit can generate an AI with optimal sales skills by referring to past success stories during the generation process. For example, the generation unit can generate an AI with high closing rate skills based on past success stories. The generation unit can also generate an AI with skills tailored to customer needs by referring to success stories. For example, the generation unit can analyze past success stories and generate an AI with optimal sales skills. In this way, an AI with optimal sales skills can be generated by referring to past success stories. Some or all of the above processes in the generation unit are performed using the generation AI. For example, the generation unit can generate an AI using a generation AI model that takes past success story data as input and outputs an AI with optimal sales skills.

[0104] The generation unit can generate new sales AI by combining sales skills from different industries during the generation process. For example, the generation unit can generate a unique sales AI by combining sales skills from different industries. The generation unit can also generate an AI with new sales skills by referring to successful case studies from different industries. For example, the generation unit can analyze sales data from different industries and generate an AI with the optimal skills. This allows for the generation of unique sales AI by combining sales skills from different industries. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate AI using a generation AI model that takes sales data from different industries as input and outputs an AI that combines skills.

[0105] The generation unit can estimate the user's emotions and determine the priority of the AI ​​to generate based on the estimated user emotions. For example, if the user is in a hurry, the generation unit will prioritize generating an AI that can respond quickly. For example, if the user is relaxed, the generation unit may prioritize generating an AI that includes detailed explanations. For example, if the user is stressed, the generation unit may prioritize generating a simple and easy-to-understand AI. In this way, by determining the priority of the AI ​​according to the user's emotions, a more effective AI can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can determine the priority of the AI ​​using a generation AI model that takes user emotion data as input and outputs an AI with determined priorities.

[0106] The generation unit can generate region-specific sales AI by referencing sales data from different regions during the generation process. For example, the generation unit can generate region-specific sales AI based on sales data from different regions. The generation unit can also analyze sales trends for each region and generate AI with optimal skills. For example, the generation unit can generate region-specific sales AI by referencing successful case studies from different regions. In this way, region-specific sales AI can be generated by referencing sales data from different regions. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate AI using a generation AI model that takes sales data from different regions as input and outputs region-specific AI.

[0107] The generation unit can generate a multilingual sales AI by combining sales skills in different languages ​​during the generation process. For example, the generation unit can generate a multilingual sales AI by combining sales skills in different languages. The generation unit can also generate an AI with the optimal skills by referring to successful multilingual case studies. The generation unit can also generate a multilingual sales AI by analyzing sales data in different languages. In this way, a multilingual sales AI can be generated by combining sales skills in different languages. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit can generate an AI using a generation AI model that takes sales data in different languages ​​as input and outputs a multilingual AI.

[0108] The closing unit can estimate the user's emotions and adjust the closing method based on the estimated emotions. For example, if the user is relaxed, the closing unit may perform a closing that includes a detailed explanation. If the user is in a hurry, the closing unit may perform a quick closing. If the user is stressed, the closing unit may perform a simple and easy-to-understand closing. By adjusting the closing method according to the user's emotions, more effective closing becomes possible. 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 closing unit may be performed using AI, or not using AI. For example, the closing unit can adjust the closing method using an AI model that takes user emotion data as input and outputs a closing method.

[0109] The closing unit can make optimal proposals by referring to the customer's purchase history at the time of closing. For example, the closing unit can propose the most suitable plan or service based on the customer's past purchase history. The closing unit can also make proposals tailored to the customer's needs by referring to the purchase history. The closing unit can also analyze the customer's past purchase history and make the most effective proposals. This makes it possible to make optimal proposals by referring to the customer's purchase history. Some or all of the above processes in the closing unit may be performed using AI, for example, or not using AI. For example, the closing unit can make proposals using an AI model that takes customer purchase history data as input and outputs the optimal proposal.

[0110] The closing unit can adjust the proposal content in real time by reflecting customer feedback during the closing process. For example, the closing unit can collect customer feedback in real time and adjust the proposal content. For example, the closing unit can make proposals tailored to customer needs based on the feedback. For example, the closing unit can analyze real-time feedback and make the optimal proposal. This makes it possible to make more effective proposals by reflecting customer feedback in real time. Some or all of the above processes in the closing unit may be performed using AI, for example, or not using AI. For example, the closing unit can make proposals using an AI model that takes customer feedback data as input and adjusts the proposal content.

[0111] The closing unit can estimate the user's emotions and determine closing priorities based on those emotions. For example, if the user is in a hurry, the closing unit will close the deal quickly. If the user is relaxed, the closing unit may also provide a detailed explanation. If the user is stressed, the closing unit may also provide a simple and easy-to-understand closing. This allows for more effective closing by determining closing priorities 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 include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the closing unit may be performed using AI or not. For example, the closing unit can determine priorities using an AI model that takes user emotion data as input and outputs closing priorities.

[0112] The closing unit can make optimal proposals at the time of closing, taking into account the customer's geographical location information. For example, the closing unit can propose region-specific plans and services based on the customer's current location. The closing unit can also refer to geographical location information and make proposals tailored to the customer's needs. The closing unit can also make optimal proposals by taking into account the customer's geographical location information. This makes it possible to make optimal proposals by taking into account the customer's geographical location information. Some or all of the above processing in the closing unit may be performed using AI, for example, or without using AI. For example, the closing unit can make proposals using an AI model that takes the customer's geographical location data as input and outputs optimal proposals.

[0113] The closing department can analyze the customer's social media activity and customize the proposal at the time of closing. For example, the closing department can analyze the customer's social media activity and make relevant proposals. For example, the closing department can make proposals tailored to the customer's needs based on social media posts. For example, the closing department can refer to the customer's social media activity and make optimal proposals. In this way, the proposal can be customized by analyzing the customer's social media activity. Some or all of the above processes in the closing department may be performed using AI, for example, or not using AI. For example, the closing department can use an AI model that takes the customer's social media data as input and customizes the proposal to make proposals.

[0114] The registration unit can estimate the user's emotions and adjust the registration method based on the estimated emotions. For example, if the user is relaxed, the registration unit can provide a registration method that includes detailed explanations. For example, if the user is in a hurry, the registration unit can also provide a method for quick registration. For example, if the user is stressed, the registration unit can also provide a simple and easy-to-understand registration method. This allows for more effective registration by adjusting the registration method 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 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 registration unit may be performed using AI or not. For example, the registration unit can adjust the registration method using an AI model that takes user emotion data as input and outputs a registration method.

[0115] The registration unit can select the optimal registration method by referring to the customer's past registration history during registration. For example, the registration unit can propose the optimal registration method based on the customer's past registration history. For example, the registration unit can also refer to the registration history and provide a registration method tailored to the customer's needs. For example, the registration unit can analyze the customer's past registration history and select the most effective registration method. This allows the optimal registration method to be selected by referring to the customer's past registration history. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can select a registration method using an AI model that takes customer registration history data as input and outputs the optimal registration method.

[0116] The registration unit can adjust registration content in real time by reflecting customer feedback during registration. For example, the registration unit can collect customer feedback in real time and adjust registration content. For example, the registration unit can also provide registration content tailored to customer needs based on feedback. For example, the registration unit can analyze real-time feedback and provide optimal registration content. This makes more effective registration possible by reflecting customer feedback in real time. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can perform registration using an AI model that takes customer feedback data as input and adjusts registration content.

[0117] The registration unit can estimate the user's emotions and determine registration priorities based on the estimated emotions. For example, if the user is in a hurry, the registration unit can provide a quick registration method. For example, if the user is relaxed, the registration unit can provide a registration method that includes detailed explanations. For example, if the user is stressed, the registration unit can provide a simple and easy-to-understand registration method. This allows for more effective registration by determining registration priorities 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 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 registration unit may be performed using AI or not. For example, the registration unit can determine priorities using an AI model that takes user emotion data as input and outputs registration priorities.

[0118] The registration unit can select the optimal registration method at the time of registration, taking into account the customer's geographical location information. For example, the registration unit can provide a region-specific registration method based on the customer's current location. For example, the registration unit can also refer to geographical location information and provide a registration method tailored to the customer's needs. For example, the registration unit can select the optimal registration method by taking the customer's geographical location information into account. This allows for the selection of the optimal registration method by considering the customer's geographical location information. Some or all of the above-described processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can select a registration method using an AI model that takes the customer's geographical location data as input and outputs the optimal registration method.

[0119] The registration unit can analyze the customer's social media activity and customize the registration content during registration. For example, the registration unit can analyze the customer's social media activity and provide relevant registration content. For example, the registration unit can also provide registration content tailored to the customer's needs based on social media posts. For example, the registration unit can refer to the customer's social media activity and provide optimal registration content. This allows for customization of registration content by analyzing the customer's social media activity. Some or all of the above processes in the registration unit may be performed using AI, for example, or without AI. For example, the registration unit can use an AI model that takes the customer's social media data as input and customizes the registration content to perform registration.

[0120] The training department can estimate the user's emotions and adjust the training content based on those emotions. For example, if the user is relaxed, the training department can provide training content that includes detailed explanations. If the user is in a hurry, the training department can also provide training content that allows for quick learning. If the user is stressed, the training department can also provide training content that is simple and easy to understand. By adjusting the training content according to the user's emotions, more effective training becomes possible. 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 training department may be performed using AI, or not. For example, the training department can conduct training using an AI model that takes user emotion data as input and adjusts the training content.

[0121] The training department can select the optimal training method by referring to past training data during training sessions. For example, the training department can propose the optimal training method based on past training data. The training department can also provide effective training methods by referring to training data. For example, the training department can analyze past training data and select the most effective training method. This allows for the selection of the optimal training method by referring to past training data. Some or all of the above processes in the training department may be performed using AI, for example, or without AI. For example, the training department can conduct training using an AI model that takes past training data as input and outputs the optimal training method.

[0122] The training department can create new training programs by combining training data from different industries during training sessions. For example, the training department can create unique training programs by combining training data from different industries. The training department can also provide new training programs by referring to successful case studies from different industries. The training department can also create optimal training programs by analyzing training data from different industries. This allows for the creation of unique training programs by combining training data from different industries. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes training data from different industries as input and creates training programs.

[0123] The training department can estimate the user's emotions and determine training priorities based on those emotions. For example, if the user is in a hurry, the training department can prioritize training content that can be learned quickly. If the user is relaxed, the training department can also prioritize training content that includes detailed explanations. If the user is stressed, the training department can also prioritize training content that is simple and easy to understand. This allows for more effective training by prioritizing training 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the training department may be performed using AI or not. For example, the training department can determine priorities using an AI model that takes user emotion data as input and outputs training priorities.

[0124] The training department can create region-specific training programs by referencing training data from different regions during training sessions. For example, the training department can create region-specific training programs based on training data from different regions. The training department can also analyze training trends in each region and provide optimal training programs. For example, the training department can create region-specific training programs by referencing successful case studies from different regions. This allows for the creation of region-specific training programs by referencing training data from different regions. Some or all of the above processes in the training department may be performed using AI, for example, or not. For example, the training department can conduct training using an AI model that takes training data from different regions as input and creates region-specific training programs.

[0125] The training department can create multilingual training programs by combining training data from different languages ​​during training sessions. For example, the training department can combine training data from different languages ​​to create multilingual training programs. The training department can also refer to successful multilingual case studies to provide optimal training programs. For example, the training department can analyze training data from different languages ​​to create multilingual training programs. This allows for the creation of multilingual training programs by combining training data from different languages. Some or all of the above processes in the training department may be performed using AI, or not. For example, the training department can conduct training using an AI model that takes training data from different languages ​​as input and creates multilingual training programs.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] The sales support system can also include a purchase history analysis unit that analyzes the customer's purchase history. This unit analyzes the customer's preferences and purchasing patterns based on their past purchase history. For example, it can analyze the types and frequency of products a customer has purchased in the past to understand their preferences. It can also identify products that customers tend to purchase during specific seasons or events. Furthermore, it can analyze reviews and ratings of products a customer has purchased in the past to understand their satisfaction level. This allows the sales support system to provide more personalized suggestions based on the customer's purchase history.

[0128] The sales support system can also include a social media analytics unit that analyzes customers' social media activity. This unit analyzes customers' posts and activities on social media to understand their interests and concerns. For example, it can analyze accounts customers follow and groups they participate in to identify their hobbies and interests. It can also analyze the content and comments customers post to understand their emotions and opinions. Furthermore, it can analyze articles and videos customers share to identify topics they are interested in. This allows the sales support system to make more appropriate suggestions based on customers' social media activity.

[0129] The sales support system can also be equipped with a geographic information analysis unit that utilizes the customer's geographic location information. This unit provides region-specific information based on the customer's current location and travel history. For example, it can suggest specific stores or services in the area where the customer is currently located. Furthermore, it can analyze places the customer has visited in the past and areas they frequently visit to understand their behavioral patterns. It can also provide information on services and promotions available to the customer while they are on the move. This allows the sales support system to make more relevant suggestions based on the customer's geographic location information.

[0130] The sales support system can also include a feedback analysis unit that collects and analyzes customer feedback in real time. The feedback analysis unit collects and analyzes customer feedback in real time. For example, it can collect customer reviews and ratings to understand customer satisfaction. It can also analyze customer comments and opinions to identify customer needs and requests. Furthermore, based on customer feedback, the feedback analysis unit can identify areas for improvement in services and products. This allows the sales support system to make more effective suggestions based on customer feedback.

[0131] The sales support system may also include an emotion analysis unit that estimates the customer's emotions and adjusts the proposal content based on the estimated emotions. The emotion analysis unit estimates emotions from the customer's facial expressions, tone of voice, text content, etc. For example, if the customer is relaxed, the emotion analysis unit can make a proposal that includes detailed explanations. If the customer is in a hurry, the emotion analysis unit can also make a proposal that can be addressed quickly. Furthermore, if the customer is stressed, the emotion analysis unit can make a simple and easy-to-understand proposal. In this way, the sales support system can make more effective proposals according to the customer's emotions.

[0132] The sales support system can also include a campaign provision unit that provides personalized campaigns based on the customer's purchase history. The campaign provision unit analyzes the customer's past purchase history and proposes the most suitable campaigns. For example, based on the types and frequency of products the customer has purchased in the past, the campaign provision unit can propose discount campaigns for related products. It can also identify products that customers tend to purchase during specific seasons or events and provide campaigns tailored to those times. Furthermore, based on the customer's purchase history, the campaign provision unit can propose campaigns for new products that the customer might be interested in. This allows the sales support system to provide more effective campaigns based on the customer's purchase history.

[0133] The sales support system can also include an Emotional Training Department that estimates customer emotions and adjusts training content based on those estimates. The Emotional Training Department estimates the crew's emotions and adjusts the pace and content of the training accordingly. For example, if the crew is relaxed, the Emotional Training Department can conduct training with detailed explanations. If the crew is in a hurry, the Emotional Training Department can conduct training that allows for quick learning. Furthermore, if the crew is stressed, the Emotional Training Department can conduct training that is simple and easy to understand. This allows the sales support system to conduct more effective training according to the crew's emotions.

[0134] The sales support system can also include a recommendation unit that provides recommendation functions based on the customer's purchase history. The recommendation unit analyzes the customer's past purchase history and proposes the most suitable products and services. For example, the recommendation unit can suggest related products based on the types and frequency of products the customer has purchased in the past. It can also identify products that customers tend to purchase during specific seasons or events and make suggestions tailored to those times. Furthermore, the recommendation unit can suggest new products that the customer might be interested in, based on their purchase history. As a result, the sales support system can provide more effective recommendations based on the customer's purchase history.

[0135] The sales support system may also include an emotional closing unit that estimates the customer's emotions and adjusts the closing method based on those emotions. The emotional closing unit estimates the customer's emotions and adjusts the progress and content of the closing. For example, if the customer is relaxed, the emotional closing unit can perform a closing that includes detailed explanations. If the customer is in a hurry, the emotional closing unit can perform a quick closing. Furthermore, if the customer is stressed, the emotional closing unit can perform a simple and easy-to-understand closing. This allows the sales support system to perform more effective closings according to the customer's emotions.

[0136] The sales support system can also include an after-sales service department that provides after-sales services based on the customer's purchase history. The after-sales service department analyzes the customer's past purchase history and proposes the most suitable after-sales service. For example, the after-sales service department can propose maintenance and repair services for products the customer has previously purchased. Furthermore, the after-sales service department can also provide follow-up services after a customer has purchased a specific product. In addition, based on the customer's purchase history, the after-sales service department can propose after-sales services that the customer might be interested in. This allows the sales support system to provide more effective after-sales services based on the customer's purchase history.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The data collection unit collects information about other companies' and its own plans and services. For example, it automatically collects the latest pricing plans and promotional information, customer satisfaction ratings, and feature information from the internet and stores them in a database. Step 2: The analysis unit analyzes the information collected by the collection unit and learns the sales pitches of top-performing sales crews. For example, it analyzes past sales pitch data from top-performing sales crews to learn pitches that have a high closing rate and high customer satisfaction. Step 3: The generation unit generates an AI with the strongest sales skills based on the talk learned by the analysis unit. For example, the generation AI is used to generate talks with a high conversion rate or talks tailored to customer needs. Step 4: In the closing section, the sales AI generated by the generation section is installed at the store counter, and the crew closes the deal with customers who have been approached and seated. For example, they listen to the customer's needs and propose the most suitable plan or service. Step 5: The registration department handles everything from contract decision-making to registration by the closing department. For example, they quickly create contracts and register customer information. Step 6: The training department uses the sales AI to conduct training for the crew. For example, it teaches the crew tips on sales techniques and the latest plan information.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, closing unit, registration unit, and training unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects information using the camera 42 and microphone 38B of the smart device 14 and analyzes it by 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 and analyzes the collected information. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates an AI with the strongest sales skills. The closing unit is implemented by, for example, the control unit 46A of the smart device 14 and closes the deal with the customer at the store counter. The registration unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and handles everything from the decision to close the deal to registration. The training unit is implemented by, for example, the control unit 46A of the smart device 14 and conducts training for the crew. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, closing unit, registration unit, and training unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects information using the camera 42 and microphone 238 of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected information. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates an AI with the strongest sales skills. The closing unit is implemented, for example, by the control unit 46A of the smart glasses 214 and closes the deal with the customer at the store counter. The registration unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and handles everything from the decision to close the deal to registration. The training unit is implemented, for example, by the control unit 46A of the smart glasses 214 and conducts training for the crew. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, closing unit, registration unit, and training unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects information using the camera 42 and microphone 238 of the headset terminal 314 and analyzes it by 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 and analyzes the collected information. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates an AI with the strongest sales skills. The closing unit is implemented by, for example, the control unit 46A of the headset terminal 314 and closes the deal with the customer at the store counter. The registration unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and handles everything from the decision to close the deal to registration. The training unit is implemented by, for example, the control unit 46A of the headset terminal 314 and conducts training for the crew. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.).

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, closing unit, registration unit, and training unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects information using the camera 42 and microphone 238 of the robot 414 and analyzes it by 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 and analyzes the collected information. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates an AI with the strongest sales skills. The closing unit is implemented by, for example, the control unit 46A of the robot 414 and closes the deal with the customer at the store counter. The registration unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and handles everything from the decision to close the deal to registration. The training unit is implemented by, for example, the control unit 46A of the robot 414 and conducts training for the crew. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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."

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] (Note 1) A collection department that collects information on plans and services of other companies and its own company, The analysis unit analyzes the information collected by the aforementioned collection unit and learns the sales techniques of excellent sales crew members, A generation unit generates an AI with advanced sales skills based on the speech learned by the analysis unit, The sales AI generated by the aforementioned generation unit is installed on the store counter, and the closing unit is used by a crew member to close the deal with customers who have been approached and seated. The closing unit handles everything from contract decision-making to registration, and the registration unit handles everything from contract decision-making to registration. The aforementioned sales AI includes a training department that conducts training for the crew. A system characterized by the following features. (Note 2) The aforementioned collection unit is Gather information on the latest plans and services. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, By analyzing the sales pitch data of past top-performing sales crews, the system learns the optimal sales pitch. The system described in Appendix 1, characterized by the features described herein. (Note 4) The system according to Appendix 1, characterized in that the generation unit generates an AI with advanced sales skills using the generation AI. (Note 5) The closing section is, We listen to our customers' needs and propose the most suitable plans and services. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned registration unit is To ensure a smooth process from contract decision to registration. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned training department, I teach the crew tips on how to talk and the latest plan information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of information collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is Track the change history of plans and services of other companies and our own, and improve the accuracy of the information we collect. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When gathering information, analyze the marketing strategies of competitors and expand the scope of information collected. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is It estimates the user's emotions and prioritizes the information to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting information, the system prioritizes collecting highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When gathering information, we analyze social media trends and collect the latest plans and service information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Analyze past sales data to extract the optimal sales pitch patterns. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the effectiveness of the talk is evaluated by considering the customer's purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the conversation patterns are optimized by considering the customer's demographic information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, compare the effectiveness of your pitch by referring to sales data from competitors. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is Estimate user emotions and adjust AI skills that are generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During the generation process, the system references past success stories to generate an AI with the optimal sales skills. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During the generation process, a new sales AI is created by combining sales skills from different industries. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is It estimates the user's emotions and determines the priority of AI generated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the system references sales data from different regions to generate region-specific sales AI. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is During generation, combine sales skills in different languages ​​to create a multilingual sales AI. The system described in Appendix 1, characterized by the features described herein. (Note 26) The closing section is, It estimates the user's emotions and adjusts the closing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The closing section is, At closing time, we refer to the customer's purchase history to make the most suitable proposal. The system described in Appendix 1, characterized by the features described herein. (Note 28) The closing section is, During the closing process, we adjust the proposal based on real-time customer feedback. The system described in Appendix 1, characterized by the features described herein. (Note 29) The closing section is, The system estimates the user's emotions and determines closing priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The closing section is, When closing a deal, we make the best proposal by taking the customer's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 31) The closing section is, At the closing stage, analyze the customer's social media activity to customize the proposal. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned registration unit is The system estimates the user's emotions and adjusts the registration process based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned registration unit is During registration, the system will refer to the customer's past registration history to select the most suitable registration method. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned registration unit is During registration, we adjust the registration details by incorporating customer feedback in real time. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned registration unit is The system estimates user sentiment and determines registration priority based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned registration unit is During registration, the system selects the most suitable registration method, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned registration unit is During registration, the system analyzes the customer's social media activity to customize their registration details. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned training department, The system estimates the user's emotions and adjusts the training content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned training department, During training, the optimal training method is selected by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned training department, During training, we combine training data from different industries to create new training programs. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned training department, The system estimates user emotions and prioritizes training based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned training department, During training, create region-specific training programs by referencing training data from different regions. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned training department, During training, combine training data in different languages ​​to create a multilingual training program. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0211] 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 collection department that collects information on plans and services of other companies and its own company, The analysis unit analyzes the information collected by the aforementioned collection unit and learns the sales techniques of excellent sales crew members, A generation unit generates an AI with advanced sales skills based on the speech learned by the analysis unit, The sales AI generated by the aforementioned generation unit is installed on the store counter, and a closing unit is used to close the deal with customers who are approached and seated by a crew member. The aforementioned closing unit handles everything from contract decision-making to registration, and the registration unit also handles the process. The aforementioned sales AI includes a training department that conducts training for the crew. A system characterized by the following features.

2. The aforementioned collection unit is Gather information on the latest plans and services. The system according to feature 1.

3. The aforementioned analysis unit, By analyzing the sales pitch data of past top-performing sales crews, the system learns the optimal sales pitch. The system according to feature 1.

4. The system according to claim 1, characterized in that the generation unit generates an AI with advanced sales skills using the generation AI.

5. The closing section is, We listen to our customers' needs and propose the most suitable plans and services. The system according to feature 1.

6. The aforementioned registration unit is To ensure a smooth process from contract decision to registration. The system according to feature 1.

7. The aforementioned training department, I teach the crew tips on how to talk and the latest plan information. The system according to feature 1.

8. The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of information collection based on the estimated user emotions. The system according to feature 1.

Images