System

Abstract

To provide a system that automatizes a sales talk taking advantage of big data and improves the quality of selling.SOLUTION: A system according to an embodiment of the present invention comprises a collection unit, an analysis unit, a generation unit, and a sales unit. The collection unit collects big data related to commodities. The analysis unit analyzes the big data collected by the collection unit. The generation unit generates a talk script on the basis of analysis results obtained by the analysis unit. The sales unit conducts selling by utilizing the talk script generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has not fully utilized big data in the sales industry to automate sales talks, and there is room for improvement.

[0005] The system according to the embodiment aims to utilize big data to automate sales talk and improve the quality of sales. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a sales unit. The collection unit collects big data related to products. The analysis unit analyzes the big data collected by the collection unit. The generation unit generates a talk script based on the analysis result obtained by the analysis unit. The sales unit performs sales using the talk script generated by the generation unit. Effect of the Invention

[0007] The system according to the embodiment can utilize big data to automate sales talk and improve the quality of sales. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The sales system according to the embodiment of the present invention is a system that collects big data on products and talks in the same way as a top salesman. This sales system aims to automate and unmanned sellers and maintain the quality of sales in this day and age when the seller population is decreasing. Specifically, it is composed of the following steps. First, big data on products is collected. Big data includes past sales data, customer feedback, product reviews, information on competing products, etc. This data is input into the generation AI. Next, the generation AI analyzes the collected big data and generates a talk script of a top salesman. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on them. For example, it includes phrases to attract customers' interest in a specific product and persuasive words to encourage purchases. The generated talk script is sent to a sales robot or vending system. This allows the sales robot or vending system to talk in the same way as a top salesman and effectively appeal to customers about the product. For example, a sales robot in a store can explain the product to customers and answer their questions. This mechanism makes it possible to realize automation and unmanned sales without deteriorating the quality of sales, even if the seller population decreases. For example, even in unmanned stores, customers can receive the same sales pitch as a top salesman, which increases their motivation to purchase. Furthermore, sales robots and vending systems can operate 24 hours a day, so they can always provide high-quality sales pitches without being restricted by business hours. This allows the sales system to analyze big data about products, generate sales scripts similar to those of a top salesman, and make sales.

[0029] The sales system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a sales unit. The collection unit collects big data related to products. The big data related to products includes, for example, past sales data, customer feedback, product reviews, information on competing products, and the like, but is not limited to such examples. For example, the collection unit acquires past sales data from a database, and collects customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from an online platform, and collect information on competing products from market research data. The analysis unit analyzes the big data collected by the collection unit. The analysis unit extracts useful information from the big data, for example, using data mining technology. The analysis unit can also analyze data patterns and extract data for generating talk scripts, using machine learning algorithms. For example, the analysis unit extracts patterns of successful sales talks from past sales data, and analyzes customer reactions from customer feedback. The generation unit generates talk scripts based on the analysis results obtained by the analysis unit. The generation unit generates talk scripts for top salesmen, for example, using a generation AI. The generation AI learns from past successful sales talks and customer reactions, and creates an optimal talk script based on the learned information. For example, the generation AI generates phrases to attract customers' interest in a particular product and persuasive words to encourage purchases. The sales department uses the talk script generated by the generation department to make sales. The sales department transmits the talk script to, for example, a sales robot or a vending system, which explains the product to customers and answers their questions. The sales department operates 24 hours a day, and can always provide high-quality sales talks. As a result, the sales system according to the embodiment can analyze big data related to products, generate talk scripts similar to those of a top salesman, and make sales.

[0030] The collection unit collects big data related to the product. The big data related to the product includes, for example, past sales data, customer feedback, product reviews, information on competing products, and the like, but is not limited to such examples. For example, the collection unit acquires past sales data from a database, and collects customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from an online platform, and collect information on competing products from market research data. Specifically, the past sales data includes the sales volume, sales period, price fluctuation, seasonal sales trends, and the like of each product. These data are automatically acquired from the company's internal database or cloud storage. Customer feedback is collected from questionnaire surveys, review sites, comments on social media, and the like, and analyzed using text mining technology. Product reviews are acquired from online shopping sites and specialized review sites using scraping technology, and evaluations and opinions are extracted using natural language processing technology. Information on competing products is collected from market research reports, published sales data, and competitors' websites, and is used for competitive analysis. This allows the collection unit to collect comprehensive data from a wide range of information sources and build a data set that serves as the basis of a sales strategy. Furthermore, the data collection department can flexibly set the frequency of data collection and the timing of updates, making it possible to obtain the latest information in real time. This allows the data collection department to always grasp the latest market trends and customer needs, enabling them to respond quickly.

[0031] The analysis unit analyzes the big data collected by the collection unit. The analysis unit extracts useful information from the big data, for example, using data mining technology. The analysis unit can also use a machine learning algorithm to analyze data patterns and extract data for generating talk scripts. Specifically, the data mining technology is used to analyze sales trends and seasonal fluctuations from past sales data, and identify factors behind successful sales campaigns. The machine learning algorithm, for example, uses a clustering method to identify customer segments and derive optimal sales strategies for each segment. In addition, natural language processing technology is used to perform sentiment analysis from customer feedback and product reviews, and extract customer satisfaction and dissatisfaction. Furthermore, the analysis unit analyzes information on competing products, identifies the strengths and weaknesses of competitors, and clarifies the differentiation points of the company's products. As a result, the analysis unit can analyze the collected big data from multiple angles and provide useful information necessary for planning a sales strategy. The analysis unit is required to analyze data in real time and provide results quickly, so it utilizes high-performance computing resources and distributed processing technology. The analysis results are displayed as graphs and charts using visualization tools and presented in an intuitive and easy-to-understand format, allowing the analysis department to support data-based decision-making and maximize the effectiveness of sales activities.

[0032] The generation unit generates a talk script based on the analysis results obtained by the analysis unit. The generation unit generates a talk script of a top salesman, for example, using a generation AI. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on them. Specifically, the generation AI uses natural language generation technology to generate phrases to attract customers' attention and persuasive words to encourage purchases. For example, to attract customers' interest in a specific product, it generates phrases that emphasize the features and advantages of the product, and to encourage purchases, it creates persuasive messages including limited offers and discount information. The generation AI learns past sales data and customer feedback, and builds a model to predict customer reactions. This allows the generation unit to generate customized talk scripts tailored to the needs and interests of customers. Furthermore, the generation unit evaluates the quality of the generated talk script and makes corrections and improvements as necessary. For example, the generated talk script is tested in an actual sales scenario, customer reactions are collected as feedback, and the generation AI model is retrained. This allows the generation unit to always provide high-quality talk scripts and maximize the effectiveness of sales activities.

[0033] The sales department uses the talk script generated by the generation department to make sales. The sales department, for example, sends the talk script to a sales robot or a vending system, which explains the product to the customer and answers questions. Specifically, the sales robot explains the features and advantages of the product to the customer based on the generated talk script, and provides a persuasive message to encourage the purchase. The vending system uses an online chatbot or a voice assistant to quickly and accurately answer the customer's questions and support the purchase procedure. The sales department operates 24 hours a day and can always provide high-quality sales talk. This allows the customer to obtain product information at any time and make a purchase decision quickly. Furthermore, the sales department collects customer feedback and uses it to improve the talk script. For example, by analyzing the customer's reactions and questions and reviewing the content and expression of the talk script, it is possible to provide a more effective sales talk. In addition, the sales department integrates multiple sales channels to provide a consistent customer experience. For example, the same talk script can be used in different channels, such as an online store, a physical store, and a mobile app, and the customer can obtain consistent information regardless of which channel they use. This allows the sales department to improve customer satisfaction and maximize the effectiveness of sales activities.

[0034] The collection unit can collect past sales data, customer feedback, product reviews, and information on competing products. For example, the collection unit can acquire past sales data from a database and collect customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from online platforms and collect information on competing products from market research data. This allows the collection unit to collect a variety of data, enabling more accurate analysis. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past sales data into AI, which then collects and organizes the data.

[0035] The analysis unit can analyze the collected big data and extract data for generating a talk script for a top salesman. The analysis unit can extract useful information from the big data, for example, using data mining technology. The analysis unit can also analyze patterns of data and extract data for generating a talk script, using a machine learning algorithm. For example, the analysis unit can extract patterns of successful sales talks from past sales data and analyze customer reactions from customer feedback. In this way, the analysis unit can extract data, and the generation unit can generate an optimal talk script. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input the collected big data to AI, and the AI ​​can analyze and extract the data.

[0036] The generation unit can learn past successful sales talks and customer reactions, and generate a talk script based on the same. The generation unit generates a talk script of a top salesman, for example, using a generation AI. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on the same. For example, the generation AI generates phrases to attract the customer's interest in a specific product and persuasive words to encourage purchases. This makes it possible to generate an effective talk script based on the data learned by the generation unit. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs past successful sales talks and customer reactions into the generation AI, and the generation AI generates a talk script.

[0037] The sales department can use the generated talk script to explain the product to the customer and answer questions. The sales department can send the talk script to a sales robot or a vending system, for example, to explain the product to the customer and answer questions. The sales department can use the generated talk script to explain the product's features, advantages, usage, etc. to the customer. The sales department can also answer customer questions through the use of FAQs or real-time chat support. This allows the sales department to effectively explain the product to the customer by using the talk script. Some or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the generated talk script into AI, which then explains the product to the customer.

[0038] The sales department operates 24 hours a day and can provide sales talk at all times. For example, the sales department operates a sales robot or an automatic vending system 24 hours a day to provide high-quality sales talk without being restricted by business hours. The sales department can respond to customers on a 24-hour basis by using a shift system or an automatic response system. As a result, the sales department operates 24 hours a day and can provide high-quality sales talk without being restricted by business hours. Some or all of the above-mentioned processing in the sales department may be performed using, for example, AI, or may be performed without using AI. For example, the sales department inputs the information of an automatic response system that operates 24 hours a day into AI, and the AI ​​responds to customers.

[0039] The collection unit can preferentially collect data related to seasons and events from among past sales data. For example, the collection unit preferentially collects sales data of Christmas-related products during the Christmas season. The collection unit can also preferentially collect sales data of summer-limited products during the summer. Furthermore, the collection unit can also preferentially collect sales data of school supplies during the back-to-school season. This allows for a more effective sales strategy to be developed by preferentially collecting data related to a specific season or event. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs past sales data into AI, which then preferentially collects data related to seasons and events.

[0040] The collection unit can filter data based on the customer's purchase history and preferences when collecting data. For example, the collection unit preferentially collects data on products that the customer has purchased in the past. The collection unit can also filter and collect data on related products based on the customer's preferences. Furthermore, the collection unit can preferentially collect data on a specific brand from the customer's purchase history. This makes it possible to collect more personalized data by filtering data based on the customer's purchase history and preferences. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit inputs the customer's purchase history data into AI, which filters the data.

[0041] The collection unit can collect data by incorporating trend information from social media at the time of collection. For example, the collection unit preferentially collects data on currently trending products. The collection unit can also collect data on products that are trending on social media. Furthermore, the collection unit can collect data on products related to trending hashtags. This makes it possible to collect data based on the latest trends by incorporating trend information from social media. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs trend information from social media into AI, which then collects data based on the trend information.

[0042] The collection unit can collect data for each region based on geographical sales data at the time of collection. The collection unit, for example, collects data on products that are popular in a particular region. The collection unit can also collect data taking into account sales trends for each region. Furthermore, the collection unit can also collect customer feedback for each region. This makes it possible to develop a sales strategy for each region by taking into account the geographical sales data. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs geographical sales data into AI, which then collects data for each region.

[0043] During the analysis, the analysis unit can extract patterns of past successful sales talks and reflect them in the analysis. For example, the analysis unit can extract phrases of past successful sales talks and reflect them in the analysis. The analysis unit can also analyze patterns of successful sales talks and reflect them in the talk script. Furthermore, the analysis unit can analyze customer reactions to successful sales talks and reflect them in the talk script. In this way, by extracting patterns of past successful sales talks, a more effective talk script can be generated. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit inputs data of past successful sales talks into AI, which extracts patterns and reflects them in the analysis.

[0044] During the analysis, the analysis unit can analyze the sales strategy of the competing product and use it to generate a talk script. For example, the analysis unit analyzes the sales strategy of the competing product and reflects it in the talk script. The analysis unit can also analyze a successful sales talk of the competing product and reflect it in the talk script. Furthermore, the analysis unit can analyze customer reactions to the competing product and reflect it in the talk script. In this way, a more effective talk script can be generated by analyzing the sales strategy of the competing product. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit inputs sales strategy data of the competing product to AI, which analyzes the data and uses it to generate a talk script.

[0045] The analysis unit can incorporate customer feedback in real time during analysis and perform analysis. The analysis unit, for example, reflects the customer's real-time feedback in the analysis. The analysis unit can also collect customer feedback in real time and reflect it in the analysis. Furthermore, the analysis unit can analyze customer feedback in real time and reflect it in the talk script. This enables more effective analysis by incorporating customer feedback in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs customer's real-time feedback data into AI, which analyzes the data and reflects it in the talk script.

[0046] The analysis unit can adjust the analysis method for each different product category during analysis. For example, the analysis unit applies a different analysis method for each product category. The analysis unit can also analyze by focusing on different data for each product category. Furthermore, the analysis unit can apply a different analysis algorithm for each product category. This enables more effective analysis by customizing the analysis method for each product category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs data for each product category into AI, and the AI ​​adjusts the analysis method.

[0047] The generation unit can generate a talk script for a specific customer demographic at the time of generation. The generation unit generates, for example, a casual talk script for younger generations. The generation unit can also generate a polite talk script for older people. Furthermore, the generation unit can generate a professional talk script for business people. This allows for more effective sales by generating an optimal talk script for a specific customer demographic. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on a specific customer demographic into the generation AI, which then generates a talk script.

[0048] The generation unit can optimize the talk script based on past customer reaction data at the time of generation. The generation unit generates an optimal talk script based on, for example, past customer reaction data. The generation unit can also analyze customer reaction data and reflect it in the talk script. Furthermore, the generation unit can adjust the expression method of the talk script based on the customer reaction data. This enables a more effective sales talk by optimizing the talk script based on past customer reaction data. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs past customer reaction data into the generation AI, which then optimizes the talk script.

[0049] The generation unit can generate talk scripts corresponding to different sales channels at the time of generation. The generation unit generates a text-based talk script for online sales, for example. The generation unit can also generate a voice-based talk script for offline sales. Furthermore, the generation unit can generate a talk script compatible with online chat. This enables more effective sales by generating talk scripts corresponding to different sales channels. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data of different sales channels into the generation AI, which generates the talk script.

[0050] At the time of generation, the generation unit can generate a talk script that matches a promotion or campaign. For example, the generation unit generates a talk script for a Christmas campaign. The generation unit can also generate a talk script for a summer sale. Furthermore, the generation unit can generate a talk script for a new product launch campaign. This enables more effective sales by generating a talk script that matches a specific promotion or campaign. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on a promotion or campaign into the generation AI, which generates a talk script.

[0051] At the time of sale, the sales department can make personalized talk by referring to the customer's past purchase history. For example, the sales department can make talk about related products based on information about products purchased by the customer in the past. The sales department can also suggest personalized recommended products by referring to the customer's purchase history. Furthermore, the sales department can make talk about a specific brand based on the customer's purchase history. This allows for more personalized sales talk by referring to the customer's past purchase history. Some or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the customer's purchase history data into AI, and the AI ​​makes personalized talk.

[0052] The sales department can analyze the real-time reaction of the customer at the time of sale and dynamically change the content of the talk. For example, if the customer shows interest, the sales department provides detailed information about the product. In addition, if the customer has questions, the sales department can immediately talk to answer the questions. Furthermore, if the customer is unsure about the purchase, the sales department can also talk persuasively to encourage the purchase. This allows for more effective sales talk by analyzing the real-time reaction of the customer. Some or all of the above-mentioned processing in the sales department may be performed using, for example, AI, or may be performed without using AI. For example, the sales department inputs the real-time reaction data of the customer into AI, and the AI ​​dynamically changes the content of the talk.

[0053] The sales department can make a region-specific talk by taking into account the geographical information of the customer at the time of sale. For example, the sales department makes a talk about a product that is popular in a particular region. The sales department can also make a talk by taking into account sales trends for each region. Furthermore, the sales department can make a talk based on customer feedback for each region. This makes it possible to make a sales talk that is region-specific by taking into account the geographical information of the customer. A part or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the geographical information of the customer into AI, and the AI ​​makes a region-specific talk.

[0054] The sales department can analyze the social media activity of the customer at the time of sale and hold a related talk. For example, the sales department holds a talk about a product in which the customer showed interest on social media. The sales department can also hold a personalized talk based on the social media activity of the customer. Furthermore, the sales department can hold a talk based on the customer's feedback on social media. In this way, a more personalized sales talk is possible by analyzing the social media activity of the customer. A part or all of the above-mentioned processing in the sales department may be performed using, for example, an AI, or may be performed without using an AI. For example, the sales department inputs the social media activity data of the customer into an AI, and the AI ​​holds a related talk.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The sales system may further include a history analysis unit that analyzes the purchasing history of customers. The history analysis unit analyzes data on products purchased in the past by customers to identify the customer's preferences and purchasing patterns. For example, it may identify product categories and brands that customers frequently purchase, and generate personalized talk scripts based on that information. The history analysis unit may also analyze reviews and feedback on products purchased in the past by customers to ascertain the customer's satisfaction levels and dissatisfaction points. This allows for more effective sales strategies to be developed based on the customer's purchasing history.

[0057] The collection unit can further collect social media activities of the customer. For example, the collection unit can collect products and comments shared by the customer on social media to understand the customer's interests and concerns. The collection unit can also collect trend information on social media to collect data based on the latest trends. The collection unit can also collect the number of followers and engagement rate of the customer on social media to evaluate the influence of the customer. This enables more effective data collection based on social media activities.

[0058] The analysis unit can further integrate and analyze data from different data sources. For example, data from online shopping sites, sales data from physical stores, and data from social media can be integrated to perform comprehensive analysis. The analysis unit can also compare data from different data sources to find correlations. Furthermore, the analysis unit can predict customer purchasing behavior and trends using data from different data sources. In this way, more accurate analysis is possible by integrating different data sources.

[0059] The generation unit can further generate a talk script by incorporating a customer's real-time reaction. For example, if a customer shows interest in a product, a talk script including detailed information about the product is generated. Also, if a customer has a question, a talk script that answers the question can be generated. Furthermore, if a customer is unsure about a purchase, a persuasive talk script to encourage the purchase can be generated. This makes it possible to generate more effective talk scripts based on the customer's real-time reaction.

[0060] The sales department can further consider the geographical information of the customer when making a sales pitch. For example, the sales department can make a pitch about products that are popular in a particular region. The sales department can also consider sales trends in each region when making a pitch. The sales department can also make a pitch based on customer feedback in each region. This makes it possible to make sales pitches specific to each region by considering the geographical information of the customer.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The collection unit collects big data related to the product. The big data related to the product includes past sales data, customer feedback, product reviews, information on competing products, and the like. For example, the collection unit obtains past sales data from a database and collects customer feedback from surveys and review sites. It is also possible to obtain product reviews from an online platform and collect information on competing products from market research data. Step 2: The analysis unit analyzes the big data collected by the collection unit. The analysis unit uses data mining techniques to extract useful information from the big data and uses machine learning algorithms to analyze patterns in the data. For example, it extracts patterns of successful sales pitches from past sales data and analyzes customer responses from customer feedback. Step 3: The generation unit generates a talk script based on the analysis results obtained by the analysis unit. The generation unit uses a generation AI to generate a talk script for a top salesman. The generation AI learns from past successful sales talks and customer responses, and creates an optimal talk script based on that. For example, it generates phrases to attract a customer's interest in a particular product and persuasive words to encourage a purchase. Step 4: The sales department uses the talk script generated by the generation department to make a sale. The sales department sends the talk script to the sales robot or vending system, explains the product to the customer, and answers any questions. The sales department operates 24 hours a day, and can always provide high-quality sales talks.

[0063] (Example 2) The sales system according to the embodiment of the present invention is a system that collects big data on products and talks in the same way as a top salesman. This sales system aims to automate and unmanned sellers and maintain the quality of sales in this day and age when the seller population is decreasing. Specifically, it is composed of the following steps. First, big data on products is collected. Big data includes past sales data, customer feedback, product reviews, information on competing products, etc. This data is input into the generation AI. Next, the generation AI analyzes the collected big data and generates a talk script of a top salesman. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on them. For example, it includes phrases to attract customers' interest in a specific product and persuasive words to encourage purchases. The generated talk script is sent to a sales robot or vending system. This allows the sales robot or vending system to talk in the same way as a top salesman and effectively appeal to customers about the product. For example, a sales robot in a store can explain the product to customers and answer their questions. This mechanism makes it possible to realize automation and unmanned sales without deteriorating the quality of sales, even if the seller population decreases. For example, even in unmanned stores, customers can receive the same sales pitch as a top salesman, which increases their motivation to purchase. Furthermore, sales robots and vending systems can operate 24 hours a day, so they can always provide high-quality sales pitches without being restricted by business hours. This allows the sales system to analyze big data about products, generate sales scripts similar to those of a top salesman, and make sales.

[0064] The sales system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a sales unit. The collection unit collects big data related to products. The big data related to products includes, for example, past sales data, customer feedback, product reviews, information on competing products, and the like, but is not limited to such examples. For example, the collection unit acquires past sales data from a database, and collects customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from an online platform, and collect information on competing products from market research data. The analysis unit analyzes the big data collected by the collection unit. The analysis unit extracts useful information from the big data, for example, using data mining technology. The analysis unit can also analyze data patterns and extract data for generating talk scripts, using machine learning algorithms. For example, the analysis unit extracts patterns of successful sales talks from past sales data, and analyzes customer reactions from customer feedback. The generation unit generates talk scripts based on the analysis results obtained by the analysis unit. The generation unit generates talk scripts for top salesmen, for example, using a generation AI. The generation AI learns from past successful sales talks and customer reactions, and creates an optimal talk script based on the learned information. For example, the generation AI generates phrases to attract customers' interest in a particular product and persuasive words to encourage purchases. The sales department uses the talk script generated by the generation department to make sales. The sales department transmits the talk script to, for example, a sales robot or a vending system, which explains the product to customers and answers their questions. The sales department operates 24 hours a day, and can always provide high-quality sales talks. As a result, the sales system according to the embodiment can analyze big data related to products, generate talk scripts similar to those of a top salesman, and make sales.

[0065] The collection unit collects big data related to the product. The big data related to the product includes, for example, past sales data, customer feedback, product reviews, information on competing products, and the like, but is not limited to such examples. For example, the collection unit acquires past sales data from a database, and collects customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from an online platform, and collect information on competing products from market research data. Specifically, the past sales data includes the sales volume, sales period, price fluctuation, seasonal sales trends, and the like of each product. These data are automatically acquired from the company's internal database or cloud storage. Customer feedback is collected from questionnaire surveys, review sites, comments on social media, and the like, and analyzed using text mining technology. Product reviews are acquired from online shopping sites and specialized review sites using scraping technology, and evaluations and opinions are extracted using natural language processing technology. Information on competing products is collected from market research reports, published sales data, and competitors' websites, and is used for competitive analysis. This allows the collection unit to collect comprehensive data from a wide range of information sources and build a data set that serves as the basis of a sales strategy. Furthermore, the data collection department can flexibly set the frequency of data collection and the timing of updates, making it possible to obtain the latest information in real time. This allows the data collection department to always grasp the latest market trends and customer needs, enabling them to respond quickly.

[0066] The analysis unit analyzes the big data collected by the collection unit. The analysis unit extracts useful information from the big data, for example, using data mining technology. The analysis unit can also use a machine learning algorithm to analyze data patterns and extract data for generating talk scripts. Specifically, the data mining technology is used to analyze sales trends and seasonal fluctuations from past sales data, and identify factors behind successful sales campaigns. The machine learning algorithm, for example, uses a clustering method to identify customer segments and derive optimal sales strategies for each segment. In addition, natural language processing technology is used to perform sentiment analysis from customer feedback and product reviews, and extract customer satisfaction and dissatisfaction. Furthermore, the analysis unit analyzes information on competing products, identifies the strengths and weaknesses of competitors, and clarifies the differentiation points of the company's products. As a result, the analysis unit can analyze the collected big data from multiple angles and provide useful information necessary for planning a sales strategy. The analysis unit is required to analyze data in real time and provide results quickly, so it utilizes high-performance computing resources and distributed processing technology. The analysis results are displayed as graphs and charts using visualization tools and presented in an intuitive and easy-to-understand format, allowing the analysis department to support data-based decision-making and maximize the effectiveness of sales activities.

[0067] The generation unit generates a talk script based on the analysis results obtained by the analysis unit. The generation unit generates a talk script of a top salesman, for example, using a generation AI. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on them. Specifically, the generation AI uses natural language generation technology to generate phrases to attract customers' attention and persuasive words to encourage purchases. For example, to attract customers' interest in a specific product, it generates phrases that emphasize the features and advantages of the product, and to encourage purchases, it creates persuasive messages including limited offers and discount information. The generation AI learns past sales data and customer feedback, and builds a model to predict customer reactions. This allows the generation unit to generate customized talk scripts tailored to the needs and interests of customers. Furthermore, the generation unit evaluates the quality of the generated talk script and makes corrections and improvements as necessary. For example, the generated talk script is tested in an actual sales scenario, customer reactions are collected as feedback, and the generation AI model is retrained. This allows the generation unit to always provide high-quality talk scripts and maximize the effectiveness of sales activities.

[0068] The sales department uses the talk script generated by the generation department to make sales. The sales department, for example, sends the talk script to a sales robot or a vending system, which explains the product to the customer and answers questions. Specifically, the sales robot explains the features and advantages of the product to the customer based on the generated talk script, and provides a persuasive message to encourage the purchase. The vending system uses an online chatbot or a voice assistant to quickly and accurately answer the customer's questions and support the purchase procedure. The sales department operates 24 hours a day and can always provide high-quality sales talk. This allows the customer to obtain product information at any time and make a purchase decision quickly. Furthermore, the sales department collects customer feedback and uses it to improve the talk script. For example, by analyzing the customer's reactions and questions and reviewing the content and expression of the talk script, it is possible to provide a more effective sales talk. In addition, the sales department integrates multiple sales channels to provide a consistent customer experience. For example, the same talk script can be used in different channels, such as an online store, a physical store, and a mobile app, and the customer can obtain consistent information regardless of which channel they use. This allows the sales department to improve customer satisfaction and maximize the effectiveness of sales activities.

[0069] The collection unit can collect past sales data, customer feedback, product reviews, and information on competing products. For example, the collection unit can acquire past sales data from a database and collect customer feedback from questionnaires and review sites. The collection unit can also acquire product reviews from online platforms and collect information on competing products from market research data. This allows the collection unit to collect a variety of data, enabling more accurate analysis. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past sales data into AI, which then collects and organizes the data.

[0070] The analysis unit can analyze the collected big data and extract data for generating a talk script for a top salesman. The analysis unit can extract useful information from the big data, for example, using data mining technology. The analysis unit can also analyze patterns of data and extract data for generating a talk script, using a machine learning algorithm. For example, the analysis unit can extract patterns of successful sales talks from past sales data and analyze customer reactions from customer feedback. In this way, the analysis unit can extract data, and the generation unit can generate an optimal talk script. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input the collected big data to AI, and the AI ​​can analyze and extract the data.

[0071] The generation unit can learn past successful sales talks and customer reactions, and generate a talk script based on the same. The generation unit generates a talk script of a top salesman, for example, using a generation AI. The generation AI learns past successful sales talks and customer reactions, and creates an optimal talk script based on the same. For example, the generation AI generates phrases to attract the customer's interest in a specific product and persuasive words to encourage purchases. This makes it possible to generate an effective talk script based on the data learned by the generation unit. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs past successful sales talks and customer reactions into the generation AI, and the generation AI generates a talk script.

[0072] The sales department can use the generated talk script to explain the product to the customer and answer questions. The sales department can send the talk script to a sales robot or a vending system, for example, to explain the product to the customer and answer questions. The sales department can use the generated talk script to explain the product's features, advantages, usage, etc. to the customer. The sales department can also answer customer questions through the use of FAQs or real-time chat support. This allows the sales department to effectively explain the product to the customer by using the talk script. Some or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the generated talk script into AI, which then explains the product to the customer.

[0073] The sales department operates 24 hours a day and can provide sales talk at all times. For example, the sales department operates a sales robot or an automatic vending system 24 hours a day to provide high-quality sales talk without being restricted by business hours. The sales department can respond to customers on a 24-hour basis by using a shift system or an automatic response system. As a result, the sales department operates 24 hours a day and can provide high-quality sales talk without being restricted by business hours. Some or all of the above-mentioned processing in the sales department may be performed using, for example, AI, or may be performed without using AI. For example, the sales department inputs the information of an automatic response system that operates 24 hours a day into AI, and the AI ​​responds to customers.

[0074] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. For example, when the user is excited, the collection unit preferentially collects positive customer feedback. In addition, when the user is anxious, the collection unit can also preferentially collect information on competing products. Furthermore, when the user is relaxed, the collection unit can evenly collect past sales data. This enables more effective data collection by determining the priority of data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit inputs the user's emotion data into the generation AI, and the generation AI determines the priority of the data.

[0075] The collection unit can preferentially collect data related to seasons and events from among past sales data. For example, the collection unit preferentially collects sales data of Christmas-related products during the Christmas season. The collection unit can also preferentially collect sales data of summer-limited products during the summer. Furthermore, the collection unit can also preferentially collect sales data of school supplies during the back-to-school season. This allows for a more effective sales strategy to be developed by preferentially collecting data related to a specific season or event. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs past sales data into AI, which then preferentially collects data related to seasons and events.

[0076] The collection unit can filter data based on the customer's purchase history and preferences when collecting data. For example, the collection unit preferentially collects data on products that the customer has purchased in the past. The collection unit can also filter and collect data on related products based on the customer's preferences. Furthermore, the collection unit can preferentially collect data on a specific brand from the customer's purchase history. This makes it possible to collect more personalized data by filtering data based on the customer's purchase history and preferences. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit inputs the customer's purchase history data into AI, which filters the data.

[0077] The collection unit can estimate the user's emotion and adjust the range of data to be collected based on the estimated user's emotion. For example, when the user is excited, the collection unit collects a wide range of data. In addition, when the user is anxious, the collection unit can also collect specific data. Furthermore, when the user is relaxed, the collection unit can collect balanced data. This allows more effective data collection by adjusting the range of data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit inputs the user's emotion data into the generation AI, and the generation AI adjusts the range of data.

[0078] The collection unit can collect data by incorporating trend information from social media at the time of collection. For example, the collection unit preferentially collects data on currently trending products. The collection unit can also collect data on products that are trending on social media. Furthermore, the collection unit can collect data on products related to trending hashtags. This makes it possible to collect data based on the latest trends by incorporating trend information from social media. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs trend information from social media into AI, which then collects data based on the trend information.

[0079] The collection unit can collect data for each region based on geographical sales data at the time of collection. The collection unit, for example, collects data on products that are popular in a particular region. The collection unit can also collect data taking into account sales trends for each region. Furthermore, the collection unit can also collect customer feedback for each region. This makes it possible to develop a sales strategy for each region by taking into account the geographical sales data. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs geographical sales data into AI, which then collects data for each region.

[0080] The analysis unit can estimate the user's emotion and adjust the analysis algorithm based on the estimated user's emotion. For example, when the user is excited, the analysis unit analyzes by emphasizing positive data. In addition, when the user is feeling anxious, the analysis unit can also analyze by emphasizing data for reducing risks. Furthermore, when the user is relaxed, the analysis unit can also analyze by emphasizing balanced data. This allows for more effective analysis by adjusting the analysis algorithm based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit inputs the user's emotion data to the generation AI, and the generation AI adjusts the analysis algorithm.

[0081] During the analysis, the analysis unit can extract patterns of past successful sales talks and reflect them in the analysis. For example, the analysis unit can extract phrases of past successful sales talks and reflect them in the analysis. The analysis unit can also analyze patterns of successful sales talks and reflect them in the talk script. Furthermore, the analysis unit can analyze customer reactions to successful sales talks and reflect them in the talk script. In this way, by extracting patterns of past successful sales talks, a more effective talk script can be generated. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit inputs data of past successful sales talks into AI, which extracts patterns and reflects them in the analysis.

[0082] During the analysis, the analysis unit can analyze the sales strategy of the competing product and use it to generate a talk script. For example, the analysis unit analyzes the sales strategy of the competing product and reflects it in the talk script. The analysis unit can also analyze a successful sales talk of the competing product and reflect it in the talk script. Furthermore, the analysis unit can analyze customer reactions to the competing product and reflect it in the talk script. In this way, a more effective talk script can be generated by analyzing the sales strategy of the competing product. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit inputs sales strategy data of the competing product to AI, which analyzes the data and uses it to generate a talk script.

[0083] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, when the user is excited, the analysis unit highlights and displays a positive analysis result. In addition, when the user is anxious, the analysis unit can also highlight and display an analysis result for reducing risk. Furthermore, when the user is relaxed, the analysis unit can display a balanced analysis result. This makes it possible to provide information more effectively by adjusting the display method of the analysis result based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit inputs the user's emotion data to the generation AI, and the generation AI adjusts the display method of the analysis result.

[0084] The analysis unit can incorporate customer feedback in real time during analysis and perform analysis. The analysis unit, for example, reflects the customer's real-time feedback in the analysis. The analysis unit can also collect customer feedback in real time and reflect it in the analysis. Furthermore, the analysis unit can analyze customer feedback in real time and reflect it in the talk script. This enables more effective analysis by incorporating customer feedback in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs customer's real-time feedback data into AI, which analyzes the data and reflects it in the talk script.

[0085] The analysis unit can adjust the analysis method for each different product category during analysis. For example, the analysis unit applies a different analysis method for each product category. The analysis unit can also analyze by focusing on different data for each product category. Furthermore, the analysis unit can apply a different analysis algorithm for each product category. This enables more effective analysis by customizing the analysis method for each product category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs data for each product category into AI, and the AI ​​adjusts the analysis method.

[0086] The generation unit can estimate the user's emotion and adjust the expression method of the talk script based on the estimated user's emotion. For example, when the user is excited, the generation unit uses an energetic expression. Also, when the user is anxious, the generation unit can use an expression that gives a sense of security. Furthermore, when the user is relaxed, the generation unit can use a calm expression. This allows for a more effective sales talk by adjusting the expression method of the talk script based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs the user's emotion data into the generation AI, and the generation AI adjusts the expression method of the talk script.

[0087] The generation unit can generate a talk script for a specific customer demographic at the time of generation. The generation unit generates, for example, a casual talk script for younger generations. The generation unit can also generate a polite talk script for older people. Furthermore, the generation unit can generate a professional talk script for business people. This allows for more effective sales by generating an optimal talk script for a specific customer demographic. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on a specific customer demographic into the generation AI, which then generates a talk script.

[0088] The generation unit can optimize the talk script based on past customer reaction data at the time of generation. The generation unit generates an optimal talk script based on, for example, past customer reaction data. The generation unit can also analyze customer reaction data and reflect it in the talk script. Furthermore, the generation unit can adjust the expression method of the talk script based on the customer reaction data. This enables a more effective sales talk by optimizing the talk script based on past customer reaction data. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs past customer reaction data into the generation AI, which then optimizes the talk script.

[0089] The generation unit can estimate the user's emotion and adjust the length of the talk script based on the estimated user's emotion. For example, when the user is excited, the generation unit generates a short and to the point talk script. Also, when the user is anxious, the generation unit can generate a talk script including detailed explanations. Furthermore, when the user is relaxed, the generation unit can generate a balanced talk script. This allows for a more effective sales talk by adjusting the length of the talk script based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs the user's emotion data into the generation AI, and the generation AI adjusts the length of the talk script.

[0090] The generation unit can generate talk scripts corresponding to different sales channels at the time of generation. The generation unit generates a text-based talk script for online sales, for example. The generation unit can also generate a voice-based talk script for offline sales. Furthermore, the generation unit can generate a talk script compatible with online chat. This enables more effective sales by generating talk scripts corresponding to different sales channels. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data of different sales channels into the generation AI, which generates the talk script.

[0091] At the time of generation, the generation unit can generate a talk script that matches a promotion or campaign. For example, the generation unit generates a talk script for a Christmas campaign. The generation unit can also generate a talk script for a summer sale. Furthermore, the generation unit can generate a talk script for a new product launch campaign. This enables more effective sales by generating a talk script that matches a specific promotion or campaign. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on a promotion or campaign into the generation AI, which generates a talk script.

[0092] The sales department can estimate the user's emotion and adjust the timing of the sales talk based on the estimated user's emotion. For example, if the user is excited, the sales department immediately starts the sales talk. Also, if the user is feeling anxious, the sales department can first talk to relax the user. Furthermore, if the user is relaxed, the sales department can start the sales talk at an appropriate timing. This allows for more effective sales by adjusting the timing of the sales talk based on the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sales department may be performed, for example, using an AI, or may be performed without using an AI. For example, the sales department inputs the user's emotion data into the generation AI, and the generation AI adjusts the timing of the sales talk.

[0093] At the time of sale, the sales department can make personalized talk by referring to the customer's past purchase history. For example, the sales department can make talk about related products based on information about products purchased by the customer in the past. The sales department can also suggest personalized recommended products by referring to the customer's purchase history. Furthermore, the sales department can make talk about a specific brand based on the customer's purchase history. This allows for more personalized sales talk by referring to the customer's past purchase history. Some or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the customer's purchase history data into AI, and the AI ​​makes personalized talk.

[0094] The sales department can analyze the real-time reaction of the customer at the time of sale and dynamically change the content of the talk. For example, if the customer shows interest, the sales department provides detailed information about the product. In addition, if the customer has questions, the sales department can immediately talk to answer the questions. Furthermore, if the customer is unsure about the purchase, the sales department can also talk persuasively to encourage the purchase. This allows for more effective sales talk by analyzing the real-time reaction of the customer. Some or all of the above-mentioned processing in the sales department may be performed using, for example, AI, or may be performed without using AI. For example, the sales department inputs the real-time reaction data of the customer into AI, and the AI ​​dynamically changes the content of the talk.

[0095] The sales department can estimate the user's emotions and adjust the content of the sales talk based on the estimated user's emotions. For example, if the user is excited, the sales department can give energetic talk. Also, if the user is feeling anxious, the sales department can give reassuring talk. Furthermore, if the user is relaxed, the sales department can give calm talk. This allows for more effective sales by adjusting the content of the sales talk based on the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sales department may be performed, for example, using an AI, or may be performed without using an AI. For example, the sales department inputs the user's emotion data into the generation AI, and the generation AI adjusts the content of the sales talk.

[0096] The sales department can make a region-specific talk by taking into account the geographical information of the customer at the time of sale. For example, the sales department makes a talk about a product that is popular in a particular region. The sales department can also make a talk by taking into account sales trends for each region. Furthermore, the sales department can make a talk based on customer feedback for each region. This makes it possible to make a sales talk that is region-specific by taking into account the geographical information of the customer. A part or all of the above-mentioned processing in the sales department may be performed, for example, using AI, or may be performed without using AI. For example, the sales department inputs the geographical information of the customer into AI, and the AI ​​makes a region-specific talk.

[0097] The sales department can analyze the social media activity of the customer at the time of sale and hold a related talk. For example, the sales department holds a talk about a product in which the customer showed interest on social media. The sales department can also hold a personalized talk based on the social media activity of the customer. Furthermore, the sales department can hold a talk based on the customer's feedback on social media. In this way, a more personalized sales talk is possible by analyzing the social media activity of the customer. A part or all of the above-mentioned processing in the sales department may be performed using, for example, an AI, or may be performed without using an AI. For example, the sales department inputs the social media activity data of the customer into an AI, and the AI ​​holds a related talk.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The sales system may further include a history analysis unit that analyzes the purchasing history of customers. The history analysis unit analyzes data on products purchased in the past by customers to identify the customer's preferences and purchasing patterns. For example, it may identify product categories and brands that customers frequently purchase, and generate personalized talk scripts based on that information. The history analysis unit may also analyze reviews and feedback on products purchased in the past by customers to ascertain the customer's satisfaction levels and dissatisfaction points. This allows for more effective sales strategies to be developed based on the customer's purchasing history.

[0100] The collection unit can further collect social media activities of the customer. For example, the collection unit can collect products and comments shared by the customer on social media to understand the customer's interests and concerns. The collection unit can also collect trend information on social media to collect data based on the latest trends. The collection unit can also collect the number of followers and engagement rate of the customer on social media to evaluate the influence of the customer. This enables more effective data collection based on social media activities.

[0101] The analysis unit can further integrate and analyze data from different data sources. For example, data from online shopping sites, sales data from physical stores, and data from social media can be integrated to perform comprehensive analysis. The analysis unit can also compare data from different data sources to find correlations. Furthermore, the analysis unit can predict customer purchasing behavior and trends using data from different data sources. In this way, more accurate analysis is possible by integrating different data sources.

[0102] The generation unit can further generate a talk script by incorporating a customer's real-time reaction. For example, if a customer shows interest in a product, a talk script including detailed information about the product is generated. Also, if a customer has a question, a talk script that answers the question can be generated. Furthermore, if a customer is unsure about a purchase, a persuasive talk script to encourage the purchase can be generated. This makes it possible to generate more effective talk scripts based on the customer's real-time reaction.

[0103] The sales department can further consider the geographical information of the customer when making a sales pitch. For example, the sales department can make a pitch about products that are popular in a particular region. The sales department can also consider sales trends in each region when making a pitch. The sales department can also make a pitch based on customer feedback in each region. This makes it possible to make sales pitches specific to each region by considering the geographical information of the customer.

[0104] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user's emotions. For example, if the user is excited, positive customer feedback can be collected with priority. Also, if the user is feeling anxious, information on competing products can be collected with priority. Furthermore, if the user is relaxed, past sales data can be collected evenly. Thus, by determining the priority of data based on the user's emotions, more effective data collection is possible.

[0105] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user's emotions. For example, if the user is excited, the analysis can be weighted toward positive data. If the user is anxious, the analysis can be weighted toward data for reducing risks. Furthermore, if the user is relaxed, the analysis can be weighted toward balanced data. This allows for more effective analysis by adjusting the analysis algorithm based on the user's emotions.

[0106] The generation unit can estimate the user's emotions and adjust the way the talk script is expressed based on the estimated user's emotions. For example, if the user is excited, an energetic expression can be used. If the user is anxious, an expression that gives a sense of security can be used. Furthermore, if the user is relaxed, a calm expression can be used. In this way, by adjusting the way the talk script is expressed based on the user's emotions, a more effective sales talk can be achieved.

[0107] The sales department can estimate the user's emotions and adjust the timing of the sales talk based on the estimated user's emotions. For example, if the user is excited, the sales talk can be started immediately. Also, if the user is feeling anxious, the sales department can first start talking to relax the user. Furthermore, if the user is relaxed, the sales talk can be started at an appropriate time. In this way, more effective sales can be achieved by adjusting the timing of the sales talk based on the user's emotions.

[0108] The sales department can estimate the user's emotions and adjust the content of the sales talk based on the estimated user's emotions. For example, if the user is excited, the sales department can deliver energetic talk. If the user is anxious, the sales department can deliver reassuring talk. If the user is relaxed, the sales department can deliver calm talk. This allows for more effective sales by adjusting the content of the sales talk based on the user's emotions.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The collection unit collects big data related to the product. The big data related to the product includes past sales data, customer feedback, product reviews, information on competing products, and the like. For example, the collection unit obtains past sales data from a database and collects customer feedback from surveys and review sites. It is also possible to obtain product reviews from an online platform and collect information on competing products from market research data. Step 2: The analysis unit analyzes the big data collected by the collection unit. The analysis unit uses data mining techniques to extract useful information from the big data and uses machine learning algorithms to analyze patterns in the data. For example, it extracts patterns of successful sales pitches from past sales data and analyzes customer responses from customer feedback. Step 3: The generation unit generates a talk script based on the analysis results obtained by the analysis unit. The generation unit uses a generation AI to generate a talk script for a top salesman. The generation AI learns from past successful sales talks and customer responses, and creates an optimal talk script based on that. For example, it generates phrases to attract a customer's interest in a particular product and persuasive words to encourage a purchase. Step 4: The sales department uses the talk script generated by the generation department to make a sale. The sales department sends the talk script to the sales robot or vending system, explains the product to the customer, and answers any questions. The sales department operates 24 hours a day, and can always provide high-quality sales talks.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and sales unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects big data related to products using the camera 42 and the communication I / F 44 of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected big data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a talk script based on the analysis result. The sales unit is realized, for example, by the control unit 46A of the smart device 14, and sells using the generated talk script. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and sales unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects big data related to the product using the camera 42 and the communication I / F 44 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected big data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a talk script based on the analysis result. The sales unit is realized, for example, by the control unit 46A of the smart glasses 214, and sells using the generated talk script. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and sales unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects big data related to the product using the camera 42 and the communication I / F 44 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected big data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a talk script based on the analysis result. The sales unit is realized, for example, by the control unit 46A of the headset type terminal 314, and sells using the generated talk script. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and sales unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects big data related to the product using the camera 42 and the communication I / F 44 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected big data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a talk script based on the analysis result. The sales unit is realized, for example, by the control unit 46A of the robot 414, and sells using the generated talk script. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be 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). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A collection unit that collects big data regarding products; An analysis unit that analyzes the big data collected by the collection unit; a generation unit that generates a talk script based on the analysis result obtained by the analysis unit; A sales department that performs sales using the talk script generated by the generation unit. A system characterized by: (Appendix 2) The collecting unit includes: Collect past sales data, customer feedback, product reviews, and competitor information 2. The system of claim 1, (Appendix 3) The analysis unit is Analyze the collected big data and extract data to generate talk scripts for top salesmen 2. The system of claim 1, (Appendix 4) The generation unit is Generate sales scripts based on past successful sales pitches and customer responses 2. The system of claim 1, (Appendix 5) The sales department: Use the generated talk script to explain the product to customers and answer their questions 2. The system of claim 1, (Appendix 6) The sales department: 24-hour operation, always providing sales pitch 2. The system of claim 1, (Appendix 7) The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 8) The collecting unit includes: Prioritize collection of seasonal and event-related data from past sales data 2. The system of claim 1, (Appendix 9) The collecting unit includes: At the time of collection, filter the data based on the customer's purchasing history and preferences 2. The system of claim 1, (Appendix 10) The collecting unit includes: Infer user emotions and adjust the range of data to be collected based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The collecting unit includes: At the time of collection, incorporate social media trend information to collect data. 2. The system of claim 1, (Appendix 12) The collecting unit includes: At the time of collection, collect data by region based on geographic sales data 2. The system of claim 1, (Appendix 13) The analysis unit is Infer user sentiment and adjust analysis algorithms based on the inferred user sentiment 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, patterns of past successful sales talks are extracted and reflected in the analysis. 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, the sales strategies of competing products are analyzed to help generate talk scripts. 2. The system of claim 1, (Appendix 16) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, customer feedback is incorporated in real time. 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, adjust the analysis method for different product categories 2. The system of claim 1, (Appendix 19) The generation unit is Estimate the user's emotions and adjust the way the talk script is expressed based on the estimated user's emotions 2. The system of claim 1, (Appendix 20) The generation unit is Generate a talk script for a specific customer group at generation time 2. The system of claim 1, (Appendix 21) The generation unit is When generating a talk script, optimize it based on past customer response data. 2. The system of claim 1, (Appendix 22) The generation unit is The system estimates the user's emotions and adjusts the length of the talk script based on the estimated user emotions. 2. The system of claim 1, (Appendix 23) The generation unit is Generate talk scripts for different sales channels at generation time 2. The system of claim 1, (Appendix 24) The generation unit is Generate talk scripts tailored to promotions and campaigns at the time of generation 2. The system of claim 1, (Appendix 25) The sales department: Infer user emotions and adjust the timing of sales pitches based on the inferred user emotions 2. The system of claim 1, (Appendix 26) The sales department: At the point of sale, provide a personalized conversation with customers by referencing their past purchase history 2. The system of claim 1, (Appendix 27) The sales department: When selling, analyze real-time customer responses and dynamically change conversation content 2. The system of claim 1, (Appendix 28) The sales department: Infer user emotions and adjust sales pitches based on the inferred emotions 2. The system of claim 1, (Appendix 29) The sales department: At the point of sale, consider the customer's geographic location for a localized conversation 2. The system of claim 1, (Appendix 30) The sales department: Analyze your customers' social media activity and deliver relevant conversations at the point of sale 2. The system of claim 1, [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects big data regarding products; An analysis unit that analyzes the big data collected by the collection unit; a generation unit that generates a talk script based on the analysis result obtained by the analysis unit; A sales department that uses the talk script generated by the generation unit to make sales. A system characterized by:

2. The collecting unit includes: Collect past sales data, customer feedback, product reviews, and competitor information 2. The system of claim 1 .

3. The analysis unit is Analyzing the big data collected by the collection unit and extracting data for generating talk scripts for top salesmen 2. The system of claim 1 .

4. The generation unit is Generate sales scripts based on past successful sales pitches and customer responses 2. The system of claim 1 .

5. The sales department: Using the talk script generated by the generation unit, the device explains the product to the customer and answers their questions.

2. The system of claim 1 .

6. The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1 .

7. The collecting unit includes: Prioritize collection of seasonal and event-related data from past sales data 2. The system of claim 1 .

8. The collecting unit includes: At the time of collection, filter the data based on the customer's purchasing history and preferences 2. The system of claim 1 .

Images