system

Abstract

The system according to this embodiment aims to accurately predict audience needs and determine appropriate SKUs. [Solution] The system according to the embodiment comprises an analysis unit, a history analysis unit, and a prediction unit. The analysis unit analyzes live video to collect audience reactions. The history analysis unit analyzes purchase history on e-commerce sites to identify popular goods. The prediction unit predicts needs and determines SKUs based on the information obtained by the analysis unit and the history analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to accurately grasp the needs of spectators in the sports business and determine appropriate SKUs.

[0005] The system according to the embodiment aims to accurately predict the needs of spectators and determine appropriate SKUs.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, a history analysis unit, and a prediction unit. The analysis unit analyzes relay video to collect the reactions of spectators. The history analysis unit analyzes the purchase history of an EC site to grasp popular goods. The prediction unit predicts needs and determines SKUs based on the information obtained by the analysis unit and the history analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can accurately predict audience needs and determine appropriate SKUs. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The sports business merchandise planning system according to an embodiment of the present invention is a system in which AI predicts needs and SKUs (stock management units) from broadcast footage and purchase history on e-commerce sites. First, the AI ​​analyzes the broadcast footage to collect information such as audience reactions and merchandise used by players. Next, it analyzes purchase history on e-commerce sites to understand which merchandise is popular. Based on this information, the AI ​​predicts the needs for sports business merchandise and determines the SKUs. For example, the AI ​​detects from the broadcast footage that audiences are reacting to a particular player's uniform and predicts that there is high demand for that player's uniform. It also identifies the popularity of a particular item from the purchase history on e-commerce sites and adjusts the SKUs to increase the inventory of that item. In this way, the AI ​​can efficiently plan sports business merchandise. As a result, the sports business merchandise planning system can efficiently plan team merchandise with a small number of people.

[0029] The sports business merchandise planning system according to this embodiment comprises an analysis unit, a history analysis unit, and a prediction unit. The analysis unit analyzes broadcast video to collect audience reactions. The analysis unit collects audience reactions using, for example, image analysis technology. The analysis unit can collect audience reactions such as applause, cheers, and facial expressions. For example, the analysis unit can analyze audience facial expressions in real time, identify emotions such as smiles and surprise, and collect reactions. The analysis unit can also analyze audience actions (e.g., standing up, applauding) and collect reactions based on those actions. Furthermore, the analysis unit can analyze audience gaze to identify which parts of the play or players they are paying attention to and collect reactions. The history analysis unit analyzes purchase history from e-commerce sites to identify popular merchandise. The history analysis unit analyzes purchase history using, for example, data mining technology. The history analysis unit can analyze purchase history such as purchase date and time, purchased items, and purchaser information. For example, the history analysis unit can use clustering technology to group purchase history and identify popular items. The history analysis unit can also use association analysis to identify related products from purchase history. Furthermore, the history analysis unit can use regression analysis to predict trends in popular items from purchase history. The forecasting unit predicts needs and determines SKUs based on the information obtained by the analysis and history analysis units. The forecasting unit predicts demand based on, for example, audience reactions and purchase history. For demand forecasting, the forecasting unit can use time series analysis, regression models, machine learning algorithms, etc. For example, the forecasting unit can use time series analysis to predict demand trends from past data. It can also use regression models to predict demand from audience reactions and purchase history. Furthermore, the forecasting unit can use machine learning algorithms to predict demand from audience reactions and purchase history. The forecasting unit adjusts SKUs based on the forecast. For example, the forecasting unit can change inventory levels, adjust order quantities, and change the product lineup. For example, the forecasting unit can change inventory levels based on demand forecasts and increase the inventory of popular items. Furthermore, the forecasting unit can adjust order quantities based on demand forecasts to prevent stockouts.Furthermore, the forecasting unit can also change the product lineup based on demand forecasts and provide products that meet demand. As a result, the sports business goods planning system according to this embodiment can efficiently plan sports business goods by analyzing broadcast video and purchase history from e-commerce sites, predicting needs, and determining SKUs.

[0030] The analysis unit analyzes the broadcast footage to collect audience reactions. For example, the analysis unit uses image analysis technology to collect audience reactions. Specifically, it can use facial recognition technology and motion recognition technology as image analysis technologies. By using facial recognition technology, it is possible to analyze the audience's facial expressions in real time and identify emotions such as smiles, surprise, and sadness. This makes it possible to understand what emotions the audience is feeling towards which plays or players. In addition, by using motion recognition technology, it is possible to analyze the audience's actions (for example, standing up, clapping, waving) and collect reactions based on those actions. Furthermore, by using eye-tracking technology, it is possible to analyze the audience's gaze and identify which parts of the play or players they are paying attention to. This makes it possible to understand which plays or players the audience is interested in. The analysis unit can combine these technologies to comprehensively analyze audience reactions and collect reactions in real time. Furthermore, the analysis unit can store the collected reaction data in a database and use it for subsequent analysis and prediction. This allows the analysis department to efficiently collect audience reactions and use them to plan sports business merchandise.

[0031] The History Analysis Department analyzes purchase history from e-commerce sites to identify popular items. For example, it uses data mining techniques to analyze purchase history. Specifically, it can analyze purchase date and time, purchased items, and buyer information. Data mining techniques such as clustering, association analysis, and regression analysis can be used. Clustering allows for grouping purchase history and identifying popular items within specific groups. For example, it can identify items that were purchased frequently within a specific period, indicating their popularity. Association analysis allows for identifying related products from purchase history. For example, it can analyze what other items users who purchased a particular item have purchased, identifying related products. Furthermore, regression analysis can predict trends in popular items from purchase history. For example, it can predict what items will be popular in the future based on past purchase data. The History Analysis Department combines these techniques to comprehensively analyze purchase history and identify popular items. Additionally, the History Analysis Department stores the analysis results in a database for use in subsequent predictions. This allows the history analysis department to efficiently analyze purchase history and use the data to plan sports business merchandise.

[0032] The forecasting unit predicts needs and determines SKUs based on information obtained by the analysis unit and the historical analysis unit. The forecasting unit predicts demand based on, for example, customer reactions and purchase history. Specifically, it can use time series analysis, regression models, and machine learning algorithms for demand forecasting. By using time series analysis, it is possible to predict demand trends from past data. For example, it is possible to predict future demand fluctuations based on past customer reaction data and purchase history data. Also, by using regression models, it is possible to predict demand from customer reactions and purchase history. For example, a regression model that predicts demand can be constructed using customer reaction data and purchase history data as input, and demand can be predicted using that model. Furthermore, by using machine learning algorithms, demand can be predicted from customer reactions and purchase history. For example, a machine learning model that predicts demand can be constructed using customer reaction data and purchase history data as input, and demand can be predicted using that model. The forecasting unit can combine these technologies to comprehensively predict demand and determine SKUs. Furthermore, based on the forecasting results, the forecasting unit can change inventory levels, adjust order quantities, change the product lineup, etc. For example, inventory levels can be adjusted based on demand forecasts, increasing the stock of popular items. Order quantities can also be adjusted based on demand forecasts to prevent stockouts. Furthermore, the product lineup can be modified based on demand forecasts to provide products that meet demand. This allows the forecasting department to efficiently predict demand and utilize this information in planning sports business merchandise.

[0033] The analysis unit can collect audience reactions using image analysis technology. For example, the analysis unit can analyze audience facial expressions in real time, identify emotions such as smiles and surprise, and collect reactions. The analysis unit can also analyze audience actions (e.g., standing up, applauding) and collect reactions based on those actions. The analysis unit can also analyze audience gaze to identify which parts of the play or players they are focusing on and collect reactions. This allows for high-precision collection of audience reactions using image analysis technology. Image analysis technology includes, but is not limited to, face recognition, motion analysis, and facial expression analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input audience facial expression data into a generating AI and have the generating AI perform facial expression analysis.

[0034] The history analysis unit can analyze purchase history using data mining techniques. For example, the history analysis unit can group purchase history and identify popular items using clustering techniques. The history analysis unit can also identify related products from purchase history using association analysis. Furthermore, the history analysis unit can predict trends in popular items from purchase history using regression analysis. This allows for a detailed analysis of purchase history using data mining techniques. Data mining techniques include, but are not limited to, clustering, association analysis, and regression analysis. Some or all of the above-described processes in the history analysis unit may be performed using, for example, AI, or not. For example, the history analysis unit can input purchase history data into a generating AI and have the generating AI perform data mining.

[0035] The forecasting unit can predict demand based on audience reactions and purchase history. For example, the forecasting unit can use time series analysis to predict demand trends from past data. The forecasting unit can also use regression models to predict demand from audience reactions and purchase history. Furthermore, the forecasting unit can use machine learning algorithms to predict demand from audience reactions and purchase history. This enables accurate demand forecasting by predicting demand based on audience reactions and purchase history. Demand forecasting includes, but is not limited to, time series analysis, regression models, and machine learning algorithms. Some or all of the above-described processes in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input audience reaction data and purchase history data into a generating AI and have the generating AI perform demand forecasting.

[0036] The forecasting unit can adjust SKUs based on forecasts. For example, the forecasting unit can change inventory levels, adjust order quantities, and change the product lineup. For example, the forecasting unit can change inventory levels based on demand forecasts to increase the stock of popular items. For example, the forecasting unit can also adjust order quantities based on demand forecasts to prevent stockouts. For example, the forecasting unit can change the product lineup based on demand forecasts to provide products that meet demand. This makes inventory management more efficient by adjusting SKUs based on forecasts. SKU adjustments include, but are not limited to, changing inventory levels, adjusting order quantities, and changing the product lineup. Some or all of the above processes in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input demand forecast data into a generating AI and have the generating AI perform SKU adjustments.

[0037] The analysis unit can analyze the actions and facial expressions of spectators in detail and collect their reactions when analyzing live broadcast footage. For example, the analysis unit can use AI to analyze spectators' facial expressions in real time, identify emotions such as smiles and surprise, and collect their reactions. The analysis unit can also use AI to analyze spectators' actions (e.g., standing up, applauding) and collect reactions based on those actions. The analysis unit can also use AI to analyze spectators' gaze, identify which parts of the play or players they are focusing on, and collect their reactions. This allows for accurate collection of reactions by analyzing spectators' actions and facial expressions in detail. The analysis of actions and facial expressions includes, but is not limited to, the type of action, changes in facial expression, and analysis algorithms. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input spectator action data and facial expression data into a generating AI and have the generating AI perform the analysis of actions and facial expressions.

[0038] The analysis unit can individually collect audience reactions to specific players or plays when analyzing broadcast footage. For example, the analysis unit can use AI to analyze audience reactions at the moment a specific player touches the ball and evaluate the player's popularity. The analysis unit can also use AI to analyze audience reactions to specific plays (e.g., goals or home runs) and evaluate the impact of those plays. The analysis unit can also use AI to analyze audience reactions to a specific player's performance and evaluate the player's brand value. This allows for the evaluation of popularity and impact by individually collecting audience reactions to specific players and plays. Identification of specific players and plays includes, but is not limited to, the player's name, the type of play, and the identification algorithm. Some or all of the above processing in the analysis unit may be performed using AI, or not. For example, the analysis unit can input data about specific players or plays into a generating AI and have the generating AI perform the reaction analysis.

[0039] The analysis unit can collect reactions while considering attribute information such as the age group and gender of the audience when analyzing the broadcast video. For example, the analysis unit can use AI to analyze the age group of the audience and prioritize collecting reactions from younger audiences. The analysis unit can also use AI to analyze the gender of the audience and prioritize collecting reactions from women. The analysis unit can also use AI to analyze the attribute information of the audience and prioritize collecting reactions from a specific attribute group. This allows for the priority collection of reactions from a specific attribute group by considering the attribute information of the audience. The attribute information collected includes, but is not limited to, age, gender, occupation, and hobbies. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audience attribute information into a generating AI and have the generating AI perform the analysis of the attribute information.

[0040] The analysis unit can collect reactions based on the location information of spectators when analyzing the broadcast video. For example, the analysis unit can use AI to analyze the seating positions of spectators and prioritize collecting reactions from specific areas. The analysis unit can also use AI to analyze the location information of spectators and prioritize collecting reactions from specific sections of the stadium. The analysis unit can also use AI to analyze the location information of spectators and prioritize collecting reactions from specific blocks. This allows for the priority collection of reactions from specific areas by collecting reactions based on the location information of spectators. Location information collection includes, but is not limited to, seating positions, area divisions, and GPS data. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input spectator location information into a generating AI and have the generating AI perform the analysis of the location information.

[0041] The history analysis unit can analyze a buyer's past purchase patterns in detail when analyzing purchase history. For example, the history analysis unit can use AI to analyze a buyer's past purchase history and identify frequently purchased product categories. The history analysis unit can also use AI to analyze a buyer's past purchase history and identify trends in purchase frequency and purchase amount. The history analysis unit can also use AI to analyze a buyer's past purchase history and identify purchase patterns associated with specific seasons or events. This allows for a detailed analysis of a buyer's past purchase patterns, thereby understanding their purchasing trends. The analysis of past purchase patterns includes, but is not limited to, purchase frequency, purchase timing, and types of purchased products. Some or all of the above-described processes in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input a buyer's past purchase data into a generating AI and have the generating AI perform the purchase pattern analysis.

[0042] The history analysis unit can individually analyze purchase history for specific periods or events when analyzing purchase history. For example, the history analysis unit can use AI to analyze purchase history for a specific period (e.g., during a sale) and identify popular products during that period. The history analysis unit can also use AI to analyze purchase history during a specific event (e.g., a sporting event) and identify the popularity of products related to that event. The history analysis unit can also use AI to analyze purchase history for a specific season (e.g., the Christmas season) and identify the demand for products related to that season. This allows for understanding fluctuations in demand by individually analyzing purchase history for specific periods or events. Examples of specific periods or events include, but are not limited to, sales periods, sporting events, and seasonal events. Some or all of the above processing in the history analysis unit may be performed using AI, or not. For example, the history analysis unit can input purchase data related to a specific period or event into a generating AI and have the generating AI perform the purchase history analysis.

[0043] The history analysis unit can perform analysis of purchase history while considering the purchaser's geographical location information. For example, the history analysis unit can use AI to analyze the purchaser's geographical location information and identify popular products in a particular region. The history analysis unit can also use AI to analyze the purchaser's geographical location information and identify differences in purchase patterns by region. The history analysis unit can also use AI to analyze the purchaser's geographical location information and identify demand trends by region. This allows for an understanding of regional demand by considering the purchaser's geographical location information. The collection of geographical location information includes, but is not limited to, addresses, regional codes, and GPS data. Some or all of the above-described processes in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input the purchaser's geographical location information into a generating AI and have the generating AI perform the analysis of the geographical location information.

[0044] The history analysis unit can analyze the purchaser's social media activity and identify relevant purchase history when analyzing purchase history. For example, the history analysis unit can use AI to analyze the purchaser's social media activity and identify products the purchaser has shown interest in. The history analysis unit can also use AI to analyze the purchaser's social media activity and identify products the purchaser has shared. The history analysis unit can also use AI to analyze the purchaser's social media activity and identify the purchase history of brands and products the purchaser follows. This allows for increased relevance of purchase history by analyzing the purchaser's social media activity. Social media activity analysis includes, but is not limited to, posts, likes, and follower counts. Some or all of the above processing in the history analysis unit may be performed using AI or not. For example, the history analysis unit can input the purchaser's social media data into a generating AI and have the generating AI perform the analysis of social media activity.

[0045] The forecasting unit can optimize its forecasting algorithm by referencing historical data when forecasting demand. For example, the forecasting unit can use AI to analyze historical sales data and optimize the demand forecasting algorithm. The forecasting unit can also use AI to analyze historical purchase history and optimize the demand forecasting algorithm. The forecasting unit can also use AI to analyze historical event data and optimize the demand forecasting algorithm. By optimizing the forecasting algorithm by referencing historical data, the accuracy of demand forecasting is improved. Examples of historical data to be referenced include, but are not limited to, sales data, customer data, and market data. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input historical data into a generating AI and have the generating AI perform the optimization of the forecasting algorithm.

[0046] The forecasting unit can forecast demand based on specific events or seasons. For example, the forecasting unit can use AI to forecast demand based on specific events (e.g., sporting events). The forecasting unit can also use AI to forecast demand based on specific seasons (e.g., Christmas season). The forecasting unit can also use AI to forecast demand based on specific periods (e.g., sales periods). This allows for responding to demand fluctuations by forecasting demand based on specific events or seasons. Examples of specific events or seasons include, but are not limited to, Christmas, summer holidays, and sporting events. Some or all of the above processing in the forecasting unit may be performed using AI or not. For example, the forecasting unit can input data about specific events or seasons into a generating AI and have the generating AI perform demand forecasting.

[0047] The forecasting unit can adjust SKUs while considering geographical demand distribution during demand forecasting. For example, the forecasting unit can use AI to analyze geographical demand distribution and adjust SKUs in specific regions. The forecasting unit can also use AI to analyze geographical demand distribution and adjust SKUs according to regional demand. The forecasting unit can also use AI to analyze geographical demand distribution and adjust SKUs according to regional differences in demand. This allows for addressing regional demand by adjusting SKUs while considering geographical demand distribution. Analysis of geographical demand distribution includes, but is not limited to, regional sales data, population distribution, and economic conditions. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or without AI. For example, the forecasting unit can input geographical demand distribution data into a generating AI and have the generating AI perform the SKU adjustments.

[0048] The forecasting unit can adjust SKUs by referencing relevant market data when forecasting demand. For example, the forecasting unit can use AI to analyze market data and adjust SKUs based on the demand forecast. The forecasting unit can also use AI to analyze competitor data and adjust SKUs based on the demand forecast. The forecasting unit can also use AI to analyze market trends and adjust SKUs based on the demand forecast. This improves the accuracy of demand forecasting by adjusting SKUs by referencing relevant market data. Examples of market data to refer to include, but are not limited to, competitor sales data, industry trends, and consumer survey data. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input market data into a generating AI and have the generating AI perform the SKU adjustment.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The analysis unit can analyze the tone and volume of audience voices when collecting audience reactions. For example, if the audience is cheering loudly, the volume of their cheers can be analyzed to collect reactions to specific players or plays. It can also analyze the tone of the audience's voices to identify whether they are excited or calm. Furthermore, it can analyze changes in the volume and tone of the audience's voices in real time to collect emotional changes as the game progresses. This allows for the collection of more detailed reaction data by analyzing the tone and volume of the audience's voices.

[0051] The purchase history analysis unit can analyze purchase history while taking into account customer reviews and feedback. For example, if a customer leaves a positive review for a product, the unit can rate the product's popularity highly. Conversely, if a customer leaves negative feedback, the unit can identify problems with the product and find areas for improvement. Furthermore, it can analyze the content of customer reviews and feedback to collect information about the product's quality and functionality. This allows for a more accurate analysis of purchase history by considering customer reviews and feedback.

[0052] The forecasting unit can predict demand by taking social media trends into account. For example, if a particular product is trending on social media, it can predict that demand for that product will increase. It can also analyze trends in social media hashtags and keywords to predict fluctuations in demand. Furthermore, it can analyze the content of posts by social media influencers and reflect their influence in the demand forecast. This allows for more accurate demand forecasting by considering social media trends.

[0053] The analysis unit can analyze the merchandise and clothing worn by spectators when collecting their reactions. For example, if a spectator is wearing a specific player's jersey, the popularity of that player can be evaluated. Similarly, if a spectator is carrying merchandise from a specific brand, the popularity of that brand can be evaluated. Furthermore, by analyzing the types and designs of merchandise and clothing worn by spectators, trends can be grasped. This allows for the collection of more detailed reaction data by analyzing the merchandise and clothing worn by spectators.

[0054] The purchase history analysis unit can analyze purchase history while considering the purchaser's lifestyle and preferences. For example, if a purchaser frequently buys outdoor equipment, the unit can suggest products that match that purchaser's lifestyle. Furthermore, if a purchaser buys products related to a specific sport, the unit can predict the demand for products related to that sport. In addition, it can analyze the purchase history of related products based on the purchaser's preferences to understand demand trends. This allows for a more accurate analysis of purchase history by considering the purchaser's lifestyle and preferences.

[0055] The following briefly describes the processing flow for example form 1.

[0056] Step 1: The analysis unit analyzes the live broadcast footage to collect audience reactions. The analysis unit uses image analysis technology to collect audience reactions and identify applause, cheers, facial expressions, etc. For example, it can analyze audience facial expressions in real time to identify emotions such as smiles and surprise. It can also analyze audience actions (standing up, applauding, etc.) and gaze to identify which parts of the play or players they are paying attention to. Step 2: The History Analysis Unit analyzes the purchase history of the e-commerce site to identify popular items. The History Analysis Unit uses data mining techniques to analyze purchase history, including purchase date and time, purchased items, and buyer information. For example, it uses clustering techniques to group purchase history and identify popular items. It can also use association analysis to identify related products and regression analysis to predict trends in popular items. Step 3: The forecasting unit predicts needs and determines SKUs based on information obtained by the analysis unit and the historical analysis unit. The forecasting unit predicts demand based on audience reactions and purchase history, using time series analysis, regression models, machine learning algorithms, etc. For example, it uses time series analysis to predict demand trends from past data and regression models and machine learning algorithms to predict demand from audience reactions and purchase history. Based on the forecast, it makes changes to inventory levels, adjusts order quantities, and changes to the product lineup.

[0057] (Example of form 2) The sports business merchandise planning system according to an embodiment of the present invention is a system in which AI predicts needs and SKUs (stock management units) from broadcast footage and purchase history on e-commerce sites. First, the AI ​​analyzes the broadcast footage to collect information such as audience reactions and merchandise used by players. Next, it analyzes purchase history on e-commerce sites to understand which merchandise is popular. Based on this information, the AI ​​predicts the needs for sports business merchandise and determines the SKUs. For example, the AI ​​detects from the broadcast footage that audiences are reacting to a particular player's uniform and predicts that there is high demand for that player's uniform. It also identifies the popularity of a particular item from the purchase history on e-commerce sites and adjusts the SKUs to increase the inventory of that item. In this way, the AI ​​can efficiently plan sports business merchandise. As a result, the sports business merchandise planning system can efficiently plan team merchandise with a small number of people.

[0058] The sports business merchandise planning system according to this embodiment comprises an analysis unit, a history analysis unit, and a prediction unit. The analysis unit analyzes broadcast video to collect audience reactions. The analysis unit collects audience reactions using, for example, image analysis technology. The analysis unit can collect audience reactions such as applause, cheers, and facial expressions. For example, the analysis unit can analyze audience facial expressions in real time, identify emotions such as smiles and surprise, and collect reactions. The analysis unit can also analyze audience actions (e.g., standing up, applauding) and collect reactions based on those actions. Furthermore, the analysis unit can analyze audience gaze to identify which parts of the play or players they are paying attention to and collect reactions. The history analysis unit analyzes purchase history from e-commerce sites to identify popular merchandise. The history analysis unit analyzes purchase history using, for example, data mining technology. The history analysis unit can analyze purchase history such as purchase date and time, purchased items, and purchaser information. For example, the history analysis unit can use clustering technology to group purchase history and identify popular items. The history analysis unit can also use association analysis to identify related products from purchase history. Furthermore, the history analysis unit can use regression analysis to predict trends in popular items from purchase history. The forecasting unit predicts needs and determines SKUs based on the information obtained by the analysis and history analysis units. The forecasting unit predicts demand based on, for example, audience reactions and purchase history. For demand forecasting, the forecasting unit can use time series analysis, regression models, machine learning algorithms, etc. For example, the forecasting unit can use time series analysis to predict demand trends from past data. It can also use regression models to predict demand from audience reactions and purchase history. Furthermore, the forecasting unit can use machine learning algorithms to predict demand from audience reactions and purchase history. The forecasting unit adjusts SKUs based on the forecast. For example, the forecasting unit can change inventory levels, adjust order quantities, and change the product lineup. For example, the forecasting unit can change inventory levels based on demand forecasts and increase the inventory of popular items. Furthermore, the forecasting unit can adjust order quantities based on demand forecasts to prevent stockouts.Furthermore, the forecasting unit can also change the product lineup based on demand forecasts and provide products that meet demand. As a result, the sports business goods planning system according to this embodiment can efficiently plan sports business goods by analyzing broadcast video and purchase history from e-commerce sites, predicting needs, and determining SKUs.

[0059] The analysis unit analyzes the broadcast footage to collect audience reactions. For example, the analysis unit uses image analysis technology to collect audience reactions. Specifically, it can use facial recognition technology and motion recognition technology as image analysis technologies. By using facial recognition technology, it is possible to analyze the audience's facial expressions in real time and identify emotions such as smiles, surprise, and sadness. This makes it possible to understand what emotions the audience is feeling towards which plays or players. In addition, by using motion recognition technology, it is possible to analyze the audience's actions (for example, standing up, clapping, waving) and collect reactions based on those actions. Furthermore, by using eye-tracking technology, it is possible to analyze the audience's gaze and identify which parts of the play or players they are paying attention to. This makes it possible to understand which plays or players the audience is interested in. The analysis unit can combine these technologies to comprehensively analyze audience reactions and collect reactions in real time. Furthermore, the analysis unit can store the collected reaction data in a database and use it for subsequent analysis and prediction. This allows the analysis department to efficiently collect audience reactions and use them to plan sports business merchandise.

[0060] The History Analysis Department analyzes purchase history from e-commerce sites to identify popular items. For example, it uses data mining techniques to analyze purchase history. Specifically, it can analyze purchase date and time, purchased items, and buyer information. Data mining techniques such as clustering, association analysis, and regression analysis can be used. Clustering allows for grouping purchase history and identifying popular items within specific groups. For example, it can identify items that were purchased frequently within a specific period, indicating their popularity. Association analysis allows for identifying related products from purchase history. For example, it can analyze what other items users who purchased a particular item have purchased, identifying related products. Furthermore, regression analysis can predict trends in popular items from purchase history. For example, it can predict what items will be popular in the future based on past purchase data. The History Analysis Department combines these techniques to comprehensively analyze purchase history and identify popular items. Additionally, the History Analysis Department stores the analysis results in a database for use in subsequent predictions. This allows the history analysis department to efficiently analyze purchase history and use the data to plan sports business merchandise.

[0061] The forecasting unit predicts needs and determines SKUs based on information obtained by the analysis unit and the historical analysis unit. The forecasting unit predicts demand based on, for example, customer reactions and purchase history. Specifically, it can use time series analysis, regression models, and machine learning algorithms for demand forecasting. By using time series analysis, it is possible to predict demand trends from past data. For example, it is possible to predict future demand fluctuations based on past customer reaction data and purchase history data. Also, by using regression models, it is possible to predict demand from customer reactions and purchase history. For example, a regression model that predicts demand can be constructed using customer reaction data and purchase history data as input, and demand can be predicted using that model. Furthermore, by using machine learning algorithms, demand can be predicted from customer reactions and purchase history. For example, a machine learning model that predicts demand can be constructed using customer reaction data and purchase history data as input, and demand can be predicted using that model. The forecasting unit can combine these technologies to comprehensively predict demand and determine SKUs. Furthermore, based on the forecasting results, the forecasting unit can change inventory levels, adjust order quantities, change the product lineup, etc. For example, inventory levels can be adjusted based on demand forecasts, increasing the stock of popular items. Order quantities can also be adjusted based on demand forecasts to prevent stockouts. Furthermore, the product lineup can be modified based on demand forecasts to provide products that meet demand. This allows the forecasting department to efficiently predict demand and utilize this information in planning sports business merchandise.

[0062] The analysis unit can collect audience reactions using image analysis technology. For example, the analysis unit can analyze audience facial expressions in real time, identify emotions such as smiles and surprise, and collect reactions. The analysis unit can also analyze audience actions (e.g., standing up, applauding) and collect reactions based on those actions. The analysis unit can also analyze audience gaze to identify which parts of the play or players they are focusing on and collect reactions. This allows for high-precision collection of audience reactions using image analysis technology. Image analysis technology includes, but is not limited to, face recognition, motion analysis, and facial expression analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input audience facial expression data into a generating AI and have the generating AI perform facial expression analysis.

[0063] The history analysis unit can analyze purchase history using data mining techniques. For example, the history analysis unit can group purchase history and identify popular items using clustering techniques. The history analysis unit can also identify related products from purchase history using association analysis. Furthermore, the history analysis unit can predict trends in popular items from purchase history using regression analysis. This allows for a detailed analysis of purchase history using data mining techniques. Data mining techniques include, but are not limited to, clustering, association analysis, and regression analysis. Some or all of the above-described processes in the history analysis unit may be performed using, for example, AI, or not. For example, the history analysis unit can input purchase history data into a generating AI and have the generating AI perform data mining.

[0064] The forecasting unit can predict demand based on audience reactions and purchase history. For example, the forecasting unit can use time series analysis to predict demand trends from past data. The forecasting unit can also use regression models to predict demand from audience reactions and purchase history. Furthermore, the forecasting unit can use machine learning algorithms to predict demand from audience reactions and purchase history. This enables accurate demand forecasting by predicting demand based on audience reactions and purchase history. Demand forecasting includes, but is not limited to, time series analysis, regression models, and machine learning algorithms. Some or all of the above-described processes in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input audience reaction data and purchase history data into a generating AI and have the generating AI perform demand forecasting.

[0065] The forecasting unit can adjust SKUs based on forecasts. For example, the forecasting unit can change inventory levels, adjust order quantities, and change the product lineup. For example, the forecasting unit can change inventory levels based on demand forecasts to increase the stock of popular items. For example, the forecasting unit can also adjust order quantities based on demand forecasts to prevent stockouts. For example, the forecasting unit can change the product lineup based on demand forecasts to provide products that meet demand. This makes inventory management more efficient by adjusting SKUs based on forecasts. SKU adjustments include, but are not limited to, changing inventory levels, adjusting order quantities, and changing the product lineup. Some or all of the above processes in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input demand forecast data into a generating AI and have the generating AI perform SKU adjustments.

[0066] The analysis unit can estimate the audience's emotions and adjust the method of collecting reactions based on the estimated audience emotions. For example, if the audience is excited, the AI ​​in the analysis unit can accurately analyze the degree of excitement and focus on collecting reactions to specific plays or players. For example, if the audience is bored, the AI ​​in the analysis unit can detect that emotion and identify which plays or players are not attracting the audience's attention. For example, if the audience is moved, the AI ​​in the analysis unit can analyze that emotion and collect factors that caused the emotion (e.g., specific actions of players or developments in the game). This allows for the collection of more accurate reaction data by adjusting the method of collecting reactions based on the audience's emotions. The estimation of audience emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AIs include, but are not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audience emotion data into a generating AI and have the generating AI perform emotion estimation.

[0067] The analysis unit can analyze the actions and facial expressions of spectators in detail and collect their reactions when analyzing live broadcast footage. For example, the analysis unit can use AI to analyze spectators' facial expressions in real time, identify emotions such as smiles and surprise, and collect their reactions. The analysis unit can also use AI to analyze spectators' actions (e.g., standing up, applauding) and collect reactions based on those actions. The analysis unit can also use AI to analyze spectators' gaze, identify which parts of the play or players they are focusing on, and collect their reactions. This allows for accurate collection of reactions by analyzing spectators' actions and facial expressions in detail. The analysis of actions and facial expressions includes, but is not limited to, the type of action, changes in facial expression, and analysis algorithms. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input spectator action data and facial expression data into a generating AI and have the generating AI perform the analysis of actions and facial expressions.

[0068] The analysis unit can individually collect audience reactions to specific players or plays when analyzing broadcast footage. For example, the analysis unit can use AI to analyze audience reactions at the moment a specific player touches the ball and evaluate the player's popularity. The analysis unit can also use AI to analyze audience reactions to specific plays (e.g., goals or home runs) and evaluate the impact of those plays. The analysis unit can also use AI to analyze audience reactions to a specific player's performance and evaluate the player's brand value. This allows for the evaluation of popularity and impact by individually collecting audience reactions to specific players and plays. Identification of specific players and plays includes, but is not limited to, the player's name, the type of play, and the identification algorithm. Some or all of the above processing in the analysis unit may be performed using AI, or not. For example, the analysis unit can input data about specific players or plays into a generating AI and have the generating AI perform the reaction analysis.

[0069] The analysis unit can estimate the audience's emotions and determine the priority of responses to collect based on the estimated audience emotions. For example, the analysis unit can use AI to analyze the audience's emotions and prioritize collecting responses with a high level of excitement. The analysis unit can also use AI to analyze the audience's emotions and prioritize collecting responses with a high level of emotional impact. The analysis unit can also use AI to analyze the audience's emotions and prioritize collecting negative responses. By determining the priority of responses based on the audience's emotions, important responses can be collected preferentially. The determination of response priority includes, but is not limited to, the intensity of emotion, the frequency of the response, and its importance. The estimation of audience emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input audience emotion data into a generating AI and have the generating AI perform emotion estimation.

[0070] The analysis unit can collect reactions while considering attribute information such as the age group and gender of the audience when analyzing the broadcast video. For example, the analysis unit can use AI to analyze the age group of the audience and prioritize collecting reactions from younger audiences. The analysis unit can also use AI to analyze the gender of the audience and prioritize collecting reactions from women. The analysis unit can also use AI to analyze the attribute information of the audience and prioritize collecting reactions from a specific attribute group. This allows for the priority collection of reactions from a specific attribute group by considering the attribute information of the audience. The attribute information collected includes, but is not limited to, age, gender, occupation, and hobbies. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audience attribute information into a generating AI and have the generating AI perform the analysis of the attribute information.

[0071] The analysis unit can collect reactions based on the location information of spectators when analyzing the broadcast video. For example, the analysis unit can use AI to analyze the seating positions of spectators and prioritize collecting reactions from specific areas. The analysis unit can also use AI to analyze the location information of spectators and prioritize collecting reactions from specific sections of the stadium. The analysis unit can also use AI to analyze the location information of spectators and prioritize collecting reactions from specific blocks. This allows for the priority collection of reactions from specific areas by collecting reactions based on the location information of spectators. Location information collection includes, but is not limited to, seating positions, area divisions, and GPS data. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input spectator location information into a generating AI and have the generating AI perform the analysis of the location information.

[0072] The history analysis unit can estimate the buyer's emotions and adjust the method of analyzing the purchase history based on the estimated emotions. For example, if the AI ​​analyzes the buyer's emotions and the emotions at the time of purchase are positive, the history analysis unit will prioritize the analysis of that purchase history. For example, if the AI ​​analyzes the buyer's emotions and the emotions at the time of purchase are negative, the history analysis unit can also analyze that purchase history in detail. For example, if the AI ​​analyzes the buyer's emotions and the emotions at the time of purchase are neutral, the history analysis unit can also analyze that purchase history in a standard manner. By adjusting the method of analyzing the purchase history based on the buyer's emotions, more accurate analysis becomes possible. The estimation of the buyer's emotions is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the history analysis unit may be performed using AI, for example, or without using AI. For example, the history analysis unit can input the buyer's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0073] The history analysis unit can analyze a buyer's past purchase patterns in detail when analyzing purchase history. For example, the history analysis unit can use AI to analyze a buyer's past purchase history and identify frequently purchased product categories. The history analysis unit can also use AI to analyze a buyer's past purchase history and identify trends in purchase frequency and purchase amount. The history analysis unit can also use AI to analyze a buyer's past purchase history and identify purchase patterns associated with specific seasons or events. This allows for a detailed analysis of a buyer's past purchase patterns, thereby understanding their purchasing trends. The analysis of past purchase patterns includes, but is not limited to, purchase frequency, purchase timing, and types of purchased products. Some or all of the above-described processes in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input a buyer's past purchase data into a generating AI and have the generating AI perform the purchase pattern analysis.

[0074] The history analysis unit can individually analyze purchase history for specific periods or events when analyzing purchase history. For example, the history analysis unit can use AI to analyze purchase history for a specific period (e.g., during a sale) and identify popular products during that period. The history analysis unit can also use AI to analyze purchase history during a specific event (e.g., a sporting event) and identify the popularity of products related to that event. The history analysis unit can also use AI to analyze purchase history for a specific season (e.g., the Christmas season) and identify the demand for products related to that season. This allows for understanding fluctuations in demand by individually analyzing purchase history for specific periods or events. Examples of specific periods or events include, but are not limited to, sales periods, sporting events, and seasonal events. Some or all of the above processing in the history analysis unit may be performed using AI, or not. For example, the history analysis unit can input purchase data related to a specific period or event into a generating AI and have the generating AI perform the purchase history analysis.

[0075] The history analysis unit can estimate the buyer's emotions and determine the priority of purchase history to analyze based on the estimated buyer's emotions. For example, the history analysis unit can use AI to analyze the buyer's emotions and prioritize the analysis of purchase history of items purchased with positive emotions. For example, the history analysis unit can use AI to analyze the buyer's emotions and perform a detailed analysis of purchase history of items purchased with negative emotions. For example, the history analysis unit can use AI to analyze the buyer's emotions and perform a standard analysis of purchase history of items purchased with neutral emotions. This allows for the prioritization of important purchase history by determining the priority of purchase history based on the buyer's emotions. The determination of purchase history priority includes, but is not limited to, purchase amount, purchase frequency, and the importance of purchased items. The estimation of buyer's emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input the buyer's emotional data into a generating AI and have the generating AI perform emotional estimation.

[0076] The history analysis unit can perform analysis of purchase history while considering the purchaser's geographical location information. For example, the history analysis unit can use AI to analyze the purchaser's geographical location information and identify popular products in a particular region. The history analysis unit can also use AI to analyze the purchaser's geographical location information and identify differences in purchase patterns by region. The history analysis unit can also use AI to analyze the purchaser's geographical location information and identify demand trends by region. This allows for an understanding of regional demand by considering the purchaser's geographical location information. The collection of geographical location information includes, but is not limited to, addresses, regional codes, and GPS data. Some or all of the above-described processes in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input the purchaser's geographical location information into a generating AI and have the generating AI perform the analysis of the geographical location information.

[0077] The history analysis unit can analyze the purchaser's social media activity and identify relevant purchase history when analyzing purchase history. For example, the history analysis unit can use AI to analyze the purchaser's social media activity and identify products the purchaser has shown interest in. The history analysis unit can also use AI to analyze the purchaser's social media activity and identify products the purchaser has shared. The history analysis unit can also use AI to analyze the purchaser's social media activity and identify the purchase history of brands and products the purchaser follows. This allows for increased relevance of purchase history by analyzing the purchaser's social media activity. Social media activity analysis includes, but is not limited to, posts, likes, and follower counts. Some or all of the above processing in the history analysis unit may be performed using AI or not. For example, the history analysis unit can input the purchaser's social media data into a generating AI and have the generating AI perform the analysis of social media activity.

[0078] The forecasting unit can estimate the emotions of the audience and buyers and adjust the demand forecasting method based on the estimated emotions. For example, the forecasting unit can use AI to analyze the emotions of the audience and, if the level of excitement is high, make a demand forecast based on that emotion. The forecasting unit can also use AI to analyze the emotions of buyers and predict the demand for products purchased with positive emotions. The forecasting unit can also use AI to analyze the emotions of the audience and buyers and predict the demand for products purchased with negative emotions. By adjusting the demand forecasting method based on the emotions of the audience and buyers, more accurate demand forecasting becomes possible. Adjustments to the demand forecasting method include, but are not limited to, changing the forecasting algorithm or changing the target of the forecast. The estimation of the emotions of the audience and buyers is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input emotional data from audiences and buyers into the generating AI, which can then adjust the demand forecast.

[0079] The forecasting unit can optimize its forecasting algorithm by referencing historical data when forecasting demand. For example, the forecasting unit can use AI to analyze historical sales data and optimize the demand forecasting algorithm. The forecasting unit can also use AI to analyze historical purchase history and optimize the demand forecasting algorithm. The forecasting unit can also use AI to analyze historical event data and optimize the demand forecasting algorithm. By optimizing the forecasting algorithm by referencing historical data, the accuracy of demand forecasting is improved. Examples of historical data to be referenced include, but are not limited to, sales data, customer data, and market data. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input historical data into a generating AI and have the generating AI perform the optimization of the forecasting algorithm.

[0080] The forecasting unit can forecast demand based on specific events or seasons. For example, the forecasting unit can use AI to forecast demand based on specific events (e.g., sporting events). The forecasting unit can also use AI to forecast demand based on specific seasons (e.g., Christmas season). The forecasting unit can also use AI to forecast demand based on specific periods (e.g., sales periods). This allows for responding to demand fluctuations by forecasting demand based on specific events or seasons. Examples of specific events or seasons include, but are not limited to, Christmas, summer holidays, and sporting events. Some or all of the above processing in the forecasting unit may be performed using AI or not. For example, the forecasting unit can input data about specific events or seasons into a generating AI and have the generating AI perform demand forecasting.

[0081] The prediction unit can estimate the emotions of the audience or buyers and determine how to adjust SKUs based on the estimated emotions. For example, the prediction unit can use AI to analyze the emotions of the audience and adjust SKUs based on the level of excitement if it is high. The prediction unit can also use AI to analyze the emotions of buyers and adjust the SKUs of products purchased with positive emotions. The prediction unit can also use AI to analyze the emotions of the audience or buyers and adjust the SKUs of products purchased with negative emotions. This optimizes inventory management by determining how to adjust SKUs based on the emotions of the audience or buyers. The determination of how to adjust SKUs includes, but is not limited to, changing inventory levels, adjusting order quantities, or changing the product lineup. The estimation of audience or buyer emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using, for example, AI or not using AI. For example, the prediction unit can input emotional data from audiences and buyers into a generating AI, and have the generating AI perform adjustments to the SKUs.

[0082] The forecasting unit can adjust SKUs while considering geographical demand distribution during demand forecasting. For example, the forecasting unit can use AI to analyze geographical demand distribution and adjust SKUs in specific regions. The forecasting unit can also use AI to analyze geographical demand distribution and adjust SKUs according to regional demand. The forecasting unit can also use AI to analyze geographical demand distribution and adjust SKUs according to regional differences in demand. This allows for addressing regional demand by adjusting SKUs while considering geographical demand distribution. Analysis of geographical demand distribution includes, but is not limited to, regional sales data, population distribution, and economic conditions. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or without AI. For example, the forecasting unit can input geographical demand distribution data into a generating AI and have the generating AI perform the SKU adjustments.

[0083] The forecasting unit can adjust SKUs by referencing relevant market data when forecasting demand. For example, the forecasting unit can use AI to analyze market data and adjust SKUs based on the demand forecast. The forecasting unit can also use AI to analyze competitor data and adjust SKUs based on the demand forecast. The forecasting unit can also use AI to analyze market trends and adjust SKUs based on the demand forecast. This improves the accuracy of demand forecasting by adjusting SKUs by referencing relevant market data. Examples of market data to refer to include, but are not limited to, competitor sales data, industry trends, and consumer survey data. Some or all of the above processing in the forecasting unit may be performed using, for example, AI, or not using AI. For example, the forecasting unit can input market data into a generating AI and have the generating AI perform the SKU adjustment.

[0084] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0085] The analysis unit can analyze the tone and volume of audience voices when collecting audience reactions. For example, if the audience is cheering loudly, the volume of their cheers can be analyzed to collect reactions to specific players or plays. It can also analyze the tone of the audience's voices to identify whether they are excited or calm. Furthermore, it can analyze changes in the volume and tone of the audience's voices in real time to collect emotional changes as the game progresses. This allows for the collection of more detailed reaction data by analyzing the tone and volume of the audience's voices.

[0086] The purchase history analysis unit can analyze purchase history while taking into account customer reviews and feedback. For example, if a customer leaves a positive review for a product, the unit can rate the product's popularity highly. Conversely, if a customer leaves negative feedback, the unit can identify problems with the product and find areas for improvement. Furthermore, it can analyze the content of customer reviews and feedback to collect information about the product's quality and functionality. This allows for a more accurate analysis of purchase history by considering customer reviews and feedback.

[0087] The forecasting unit can predict demand by taking social media trends into account. For example, if a particular product is trending on social media, it can predict that demand for that product will increase. It can also analyze trends in social media hashtags and keywords to predict fluctuations in demand. Furthermore, it can analyze the content of posts by social media influencers and reflect their influence in the demand forecast. This allows for more accurate demand forecasting by considering social media trends.

[0088] The analysis unit can analyze the merchandise and clothing worn by spectators when collecting their reactions. For example, if a spectator is wearing a specific player's jersey, the popularity of that player can be evaluated. Similarly, if a spectator is carrying merchandise from a specific brand, the popularity of that brand can be evaluated. Furthermore, by analyzing the types and designs of merchandise and clothing worn by spectators, trends can be grasped. This allows for the collection of more detailed reaction data by analyzing the merchandise and clothing worn by spectators.

[0089] The purchase history analysis unit can analyze purchase history while considering the purchaser's lifestyle and preferences. For example, if a purchaser frequently buys outdoor equipment, the unit can suggest products that match that purchaser's lifestyle. Furthermore, if a purchaser buys products related to a specific sport, the unit can predict the demand for products related to that sport. In addition, it can analyze the purchase history of related products based on the purchaser's preferences to understand demand trends. This allows for a more accurate analysis of purchase history by considering the purchaser's lifestyle and preferences.

[0090] The analysis unit can estimate the audience's emotions and adjust the method of collecting reactions based on those estimated emotions. For example, if the audience is excited, the AI ​​can analyze their level of excitement with high accuracy and focus on collecting reactions to specific plays or players. If the audience is bored, the AI ​​can detect their emotions and identify which plays or players are not capturing their attention. If the audience is moved, the AI ​​can analyze their emotions and collect the factors that caused the emotion (e.g., specific actions by players or the course of the game). By adjusting the method of collecting reactions based on the audience's emotions, more accurate reaction data can be collected.

[0091] The history analysis unit can estimate the buyer's emotions and adjust the purchase history analysis method based on the estimated emotions. For example, if the AI ​​analyzes the buyer's emotions and the emotions at the time of purchase are positive, it will prioritize the analysis of that purchase history. If the emotions at the time of purchase are negative, it can also analyze that purchase history in detail. If the emotions at the time of purchase are neutral, it can also analyze that purchase history in a standard manner. By adjusting the purchase history analysis method based on the buyer's emotions, more accurate analysis becomes possible.

[0092] The forecasting unit can estimate the emotions of audience members and buyers, and adjust the demand forecasting method based on the estimated emotions. For example, if the AI ​​analyzes the emotions of audience members and indicates a high level of excitement, it can make a demand forecast based on those emotions. It can also analyze the emotions of buyers and predict the demand for products purchased with positive emotions. It can also analyze the emotions of audience members and buyers and predict the demand for products purchased with negative emotions. By adjusting the demand forecasting method based on the emotions of audience members and buyers, more accurate demand forecasting becomes possible.

[0093] The prediction unit can estimate the emotions of audience members and buyers, and determine how to adjust SKUs based on those estimated emotions. For example, if the AI ​​analyzes the emotions of audience members and they are highly excited, it will adjust SKUs based on those emotions. It can also analyze the emotions of buyers and adjust the SKUs of products purchased with positive emotions. It can also analyze the emotions of audience members and buyers and adjust the SKUs of products purchased with negative emotions. This optimizes inventory management by determining how to adjust SKUs based on the emotions of audience members and buyers.

[0094] The analysis unit can estimate the audience's emotions and determine the priority of responses to collect based on those estimated emotions. For example, the AI ​​can analyze the audience's emotions and prioritize collecting responses that indicate high levels of excitement. It can also prioritize collecting responses that indicate high levels of emotional impact. It can also prioritize collecting negative responses. In this way, by prioritizing responses based on the audience's emotions, important responses can be collected preferentially.

[0095] The following briefly describes the processing flow for example form 2.

[0096] Step 1: The analysis unit analyzes the live broadcast footage to collect audience reactions. The analysis unit uses image analysis technology to collect audience reactions and identify applause, cheers, facial expressions, etc. For example, it can analyze audience facial expressions in real time to identify emotions such as smiles and surprise. It can also analyze audience actions (standing up, applauding, etc.) and gaze to identify which parts of the play or players they are paying attention to. Step 2: The History Analysis Unit analyzes the purchase history of the e-commerce site to identify popular items. The History Analysis Unit uses data mining techniques to analyze purchase history, including purchase date and time, purchased items, and buyer information. For example, it uses clustering techniques to group purchase history and identify popular items. It can also use association analysis to identify related products and regression analysis to predict trends in popular items. Step 3: The forecasting unit predicts needs and determines SKUs based on information obtained by the analysis unit and the historical analysis unit. The forecasting unit predicts demand based on audience reactions and purchase history, using time series analysis, regression models, machine learning algorithms, etc. For example, it uses time series analysis to predict demand trends from past data and regression models and machine learning algorithms to predict demand from audience reactions and purchase history. Based on the forecast, it makes changes to inventory levels, adjusts order quantities, and changes to the product lineup.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0099] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0100] Each of the multiple elements described above, including the analysis unit, history analysis unit, and prediction unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit collects audience reactions using the camera 42 of the smart device 14 and analyzes them using the control unit 46A. The history analysis unit analyzes the purchase history of the e-commerce site using the specific processing unit 290 of the data processing unit 12. The prediction unit predicts demand based on audience reactions and purchase history using the specific processing unit 290 of the data processing unit 12 and determines SKUs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0101] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0102] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0107] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0108] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0109] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0110] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0111] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the analysis unit, history analysis unit, and prediction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit collects audience reactions using the camera 42 of the smart glasses 214 and analyzes them using the control unit 46A. The history analysis unit analyzes the purchase history of the e-commerce site using the specific processing unit 290 of the data processing unit 12. The prediction unit predicts demand based on audience reactions and purchase history using the specific processing unit 290 of the data processing unit 12 and determines SKUs. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0117] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0118] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the analysis unit, history analysis unit, and prediction unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit collects audience reactions using the camera 42 of the headset terminal 314 and analyzes them using the control unit 46A. The history analysis unit analyzes the purchase history of the e-commerce site using the specific processing unit 290 of the data processing unit 12. The prediction unit predicts demand based on audience reactions and purchase history using the specific processing unit 290 of the data processing unit 12 and determines SKUs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0134] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0141] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the analysis unit, history analysis unit, and prediction unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit collects audience reactions using the camera 42 of the robot 414 and analyzes them using the control unit 46A. The history analysis unit analyzes the purchase history of the e-commerce site using, for example, the specific processing unit 290 of the data processing unit 12. The prediction unit predicts demand based on audience reactions and purchase history using, for example, the specific processing unit 290 of the data processing unit 12 and determines SKUs. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0150] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0152] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0153] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0154] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0158] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0159] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0160] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0161] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0162] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0163] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0165] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0166] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0167] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0168] (Note 1) The analysis unit analyzes the live broadcast footage and collects audience reactions, The History Analysis Department analyzes purchase history on e-commerce sites to identify popular items, The system includes a prediction unit that predicts needs and determines SKUs based on information obtained by the analysis unit and the history analysis unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Use image analysis technology to collect audience reactions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The history analysis unit, Analyze purchase history using data mining techniques. The system described in Appendix 1, characterized by the features described herein. (Note 4) The prediction unit, Predicting demand based on audience reactions and purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 5) The prediction unit, Adjust SKUs based on predictions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, We estimate the audience's emotions and adjust the method of collecting responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, During the analysis of the live broadcast footage, the movements and facial expressions of the audience are analyzed in detail to collect their reactions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing broadcast footage, individual audience reactions to specific players or plays are collected. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the audience's emotions and determines the priority of responses to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing live broadcast footage, the system collects reactions while considering demographic information such as the age group and gender of the audience. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing live broadcast footage, reactions are collected based on the location information of the audience. The system described in Appendix 1, characterized by the features described herein. (Note 12) The history analysis unit, We estimate the buyer's emotions and adjust the purchase history analysis method based on the estimated buyer's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The history analysis unit, When analyzing purchase history, the past purchase patterns of the buyer are analyzed in detail. The system described in Appendix 1, characterized by the features described herein. (Note 14) The history analysis unit, When analyzing purchase history, it is possible to analyze purchase history individually for specific periods or events. The system described in Appendix 1, characterized by the features described herein. (Note 15) The history analysis unit, It estimates the buyer's emotions and determines the priority of purchase history to analyze based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The history analysis unit, When analyzing purchase history, the analysis takes into account the buyer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The history analysis unit, When analyzing purchase history, the social media activity of the buyer is analyzed to identify relevant purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 18) The prediction unit, We estimate the emotions of audiences and buyers, and adjust demand forecasting methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The prediction unit, When forecasting demand, we optimize the forecasting algorithm by referring to historical data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The prediction unit, When forecasting demand, forecast demand based on specific events or seasons. The system described in Appendix 1, characterized by the features described herein. (Note 21) The prediction unit, We estimate the emotions of the audience and buyers, and determine how to adjust SKUs based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The prediction unit, When forecasting demand, adjust SKUs to take geographical demand distribution into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The prediction unit, When forecasting demand, adjust SKUs by referring to relevant market data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the live broadcast footage and collects audience reactions, The History Analysis Department analyzes purchase history on e-commerce sites to identify popular items, The system includes a prediction unit that predicts needs and determines SKUs based on information obtained by the analysis unit and the history analysis unit. A system characterized by the following features.

2. The aforementioned analysis unit, Use image analysis technology to collect audience reactions. The system according to feature 1.

3. The history analysis unit, Analyze purchase history using data mining techniques. The system according to feature 1.

4. The prediction unit, Predicting demand based on audience reactions and purchase history. The system according to feature 1.

5. The prediction unit, Adjust SKUs based on predictions. The system according to feature 1.

6. The aforementioned analysis unit, We estimate the audience's emotions and adjust the method of collecting responses based on those estimated emotions. The system according to feature 1.

7. The aforementioned analysis unit, During the analysis of the live broadcast footage, the movements and facial expressions of the audience are analyzed in detail to collect their reactions. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing broadcast footage, individual audience reactions to specific players or plays are collected. The system according to feature 1.

Images