system

Abstract

We provide the system. [Solution] Collection technology for collecting past supply data, environmental information, timing information, and sales promotion activity information, A forecasting technique that uses the data collected by the aforementioned collection technique to predict demand, An order generation technology that automatically generates an order plan based on the demand forecast using the aforementioned forecasting technology, An automated execution technology that executes the order plan generated by the order generation technology, User confirmation and adjustment technology that allows order plans to be confirmed and adjusted via the user terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional manual order processing, it has been difficult to effectively utilize sales data and external factors, and order errors and over-orders have frequently occurred. As a result, excessive inventory, shortages, and waste losses have occurred, reducing the efficiency of the business. Furthermore, it has been difficult to consider different demand patterns for each store, and overall optimization has not been achieved.

Means for Solving the Problems

[0005] This invention provides information gathering means for collecting past sales data, weather information, seasonal information, and promotional event information, and uses forecasting means to predict demand based on the collected data to perform accurate demand forecasting. Furthermore, it includes an automated execution means that automatically generates an order plan based on this forecast and automatically executes the optimized order plan, thereby preventing ordering errors and over-ordering and improving the efficiency of inventory management. Highly accurate ordering that takes into account the characteristics of stores and products enables efficient and rapid ordering.

[0006] "Information gathering means" refers to a function for acquiring past sales data, weather information, seasonal information, and promotional event information, and integrating and storing them in a database.

[0007] A "prediction tool" is a function that uses data collected by information gathering tools as input to execute generative AI or other algorithms to estimate future demand.

[0008] The "order generation means" is a function that determines the optimal order quantity and timing based on the output of the prediction means.

[0009] The "automatic execution means" is a function that automatically executes an order based on the order plan determined by the order generation means.

[0010] "Store or product characteristics" refer to the location and size of individual stores, as well as the characteristics and demand patterns of specific products. Considering these factors improves the accuracy of ordering.

[0011] A "user" refers to a human operator who checks the system's output and provides feedback as needed. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to an automated ordering system in which a server, terminal, and user cooperate to improve the efficiency of ordering. Specific embodiments thereof will be described below.

[0034] First, the server uses information gathering tools to acquire historical sales data, weather information, seasonal information, and promotional event information from various data sources. The data is integrated and centrally recorded in a database. The database records the characteristics of each store and product, enabling analysis based on this information.

[0035] Next, the server applies prediction methods and uses the collected data to forecast future demand. This prediction model utilizes AI technology to perform highly accurate demand forecasts based on pattern recognition within the data. The demand forecast results are then used in subsequent processes.

[0036] Furthermore, the server generates an optimal order plan based on the demand forecast results using an order generation mechanism. This plan is optimized considering the characteristics of each store and product. It also includes adjustments to order quantity and timing. The generated order plan is sent to the terminal in a format that the user can review and correct.

[0037] The terminal is equipped with an automated execution mechanism and electronically places orders with manufacturers and wholesalers based on order proposals confirmed by the user. This reduces errors caused by manual input and achieves efficient and accurate ordering.

[0038] As a concrete example, in a retail store, if the server predicts that high temperatures will continue using past ice cream sales data and the weather forecast for the weekend, the AI ​​model will determine that demand for soft drinks will increase. As a result, the server generates an order plan suggesting twice the normal order quantity, which the terminal receives. The user reviews the order plan and makes adjustments if necessary. After confirmation, the terminal automatically places the order.

[0039] A feedback loop is also included in this system; based on the sales results provided by the user, the server enhances the generated AI model and improves prediction accuracy. This cycle leads to increased efficiency in both inventory management and order management.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects historical sales data, weather information, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there.

[0043] Step 2:

[0044] The server preprocesses the data stored in the database, including imputing missing values ​​and correcting outliers. This formats the data so that it is suitable as input for the demand forecasting model.

[0045] Step 3:

[0046] The server applies a generative AI model as a prediction tool and performs demand forecasting based on pre-processed data. The forecast results include multiple demand scenarios that take various external factors into account.

[0047] Step 4:

[0048] The server uses the prediction results to create an optimal order generation method that takes into account the characteristics of the store and the product. This is where the order quantity and timing are optimized.

[0049] Step 5:

[0050] The terminal receives order plans from the server and presents the information through an interface that allows the user to review and adjust the plans. Users can modify the proposals based on their own insights into changing demand.

[0051] Step 6:

[0052] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. Specifically, the terminal electronically sends the order information to the manufacturer or wholesaler.

[0053] Step 7:

[0054] Users evaluate sales results and inventory status, and provide this information as feedback to the server via their terminals. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future demand forecasts.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In today's business environment, rapid and accurate inventory management and ordering are essential, with a particular challenge in responding quickly to fluctuations in demand. Furthermore, traditional manual ordering methods are prone to human error, making efficient ordering difficult. Improving the accuracy of demand forecasting and optimizing inventory management are crucial factors directly linked to increased profits. Therefore, there is a need for methods that enable more accurate demand forecasting and efficiently automate ordering.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting historical sales data, weather information, seasonal information, and promotional event information; means for integrating and storing the collected data; and means for applying a generated AI model using the integrated data to forecast demand. This makes it possible to perform highly accurate demand forecasting, automatically generate optimized order plans, and streamline ordering operations.

[0060] "Historical sales data" refers to records of sales of goods and services in previous periods, and serves as the basis for demand forecasting.

[0061] "Weather information" refers to information about weather conditions such as temperature, precipitation, and wind speed, and is one of the factors that influence demand.

[0062] "Seasonal information" refers to information that influences demand fluctuations associated with seasonal changes, and is data that is reflected in forecasting models for a specific season.

[0063] "Sales promotion event information" refers to information about sales promotion activities and events, and is data used to account for temporary fluctuations in demand.

[0064] "Information gathering means" refers to a method or apparatus for acquiring and integrating necessary information from various data sources.

[0065] "Means of integration" refers to a method or apparatus for aggregating acquired data in an appropriate format and storing it in a database.

[0066] "Means for applying generative AI models to predict demand" refers to a method or apparatus that utilizes artificial intelligence technology to accurately predict future demand from collected data.

[0067] "Means for optimizing and automatically generating order plans" refers to a method or apparatus that automatically creates an order plan by calculating the optimal order quantity and timing based on predicted demand.

[0068] A "terminal" is a device used to receive order plans sent from a server and for users to review and adjust them.

[0069] "Means of automatic execution" refers to a method or apparatus for electronically placing an order based on a confirmed order plan.

[0070] "Means of collecting feedback to improve prediction accuracy" refers to methods or devices for continuously improving the performance of a prediction model based on actual sales results.

[0071] This invention relates to a system for streamlining automated ordering, in which a server, terminals, and users cooperate to operate the entire system. The server is primarily responsible for collecting information, performing forecasts, and generating order plans, while the terminals provide an interface with the user and assist in managing the executed orders.

[0072] The server acquires historical sales data, weather information, seasonal information, and promotional event information from various data sources through information gathering means. This utilizes an integrated database system, such as a data management platform like PostgreSQL. The data is centrally recorded and integrated, enabling efficient analysis.

[0073] Furthermore, the server incorporates generative AI models to achieve highly accurate demand forecasting. Specifically, it can utilize machine learning libraries such as Python's scikit-learn and TENSORFLOW®. This allows it to predict future demand through pattern recognition within the data and generate optimized ordering plans. The ordering plans are adjusted according to the store and product, providing the optimal combination of order quantity and timing.

[0074] The terminal receives order plans sent from the server and provides a user interface for the user to review and adjust as needed. After reviewing and adjusting the order plan based on the provided information, the user places the order electronically using an automated execution mechanism. This minimizes ordering errors and enables fast and accurate ordering.

[0075] As a concrete example, in a retail store, if the server uses past beverage sales data and the weather forecast for the weekend to predict continued high temperatures, the generating AI model will determine that demand for beverages will increase. As a result, the server generates an order plan suggesting twice the normal order quantity and sends it to the terminal. The user reviews the order plan and makes any necessary changes, after which the terminal automatically places the order.

[0076] Examples of prompt statements include the following:

[0077] "Based on this weekend's weather forecast and data from the past three years, please forecast next week's beverage demand and calculate the optimal order quantity."

[0078] "Consider the impact of the next promotional event, update the predictive model using past promotional event data, and propose an ordering plan."

[0079] This system enables inventory optimization and streamlined order management, leading to improved business flexibility and responsiveness.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server acquires historical sales data, weather information, seasonal information, and promotional event information through various data collection methods. This data serves as input. The collected data undergoes integration processing and is stored in a PostgreSQL database. Specifically, it may extract data from various APIs, perform data cleansing and format conversion, and generate integrated data. As a result, an integrated database is output.

[0083] Step 2:

[0084] The server applies a generative AI model using integrated data to perform demand forecasting. The input here is data from an integrated database. In this process, machine learning libraries such as Python's scikit-learn and TensorFlow are used to extract features from the data and train the predictive model. Specific operations include creating a training dataset and executing the model training process. The output is a forecast of future demand.

[0085] Step 3:

[0086] The server optimizes and automatically generates an order plan based on demand forecast data. The input is the demand forecast result from step 2. At this stage, the optimization algorithm is executed, taking into account the characteristics of the products and the conditions of each store. Specifically, the data is manipulated using the Python Pandas library to calculate the optimal order quantity and timing. The output is the optimized order plan.

[0087] Step 4:

[0088] The server sends the generated order plan to the terminal. The input to this process is the order plan obtained in step 3. Specifically, the server sends the order data to the terminal using the HTTP protocol. The terminal receives the order plan and displays it as output.

[0089] Step 5:

[0090] The user reviews and adjusts the order plan sent via the terminal as needed. In this step, the user interacts with the order plan using a GUI on the terminal. The input is the order plan displayed in step 4, and the output is the order plan reviewed or adjusted by the user. Specific actions include making fine adjustments using sliders and text fields.

[0091] Step 6:

[0092] The terminal places an order using an automated execution mechanism based on the confirmed order plan. The input is the confirmed order plan from step 5. The order data is automatically transmitted to the supplier via the EDI (Electronic Data Interchange) system. The specific process involves electronically transmitting the order information using network communication, and the output confirms the completion of the order.

[0093] Step 7:

[0094] Users send sales results to the server as feedback. This input includes actual sales data. The server collects the sales results and continuously updates the generated AI model. This improves the model's prediction accuracy. Specifically, it requires periodically sending sales data to the server's API endpoint. The output provides data to improve the model's accuracy.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] There is a need to improve the efficiency of inventory management in logistics centers and to enable accurate ordering based on demand forecasts. Traditional methods have problems such as excess inventory and stockouts, making efficient operation difficult. Furthermore, manual ordering is prone to errors and is time-consuming, which leads to increased costs and workload.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes a data collection technology that collects past supply data, environmental information, timing information, and sales promotion activity information; a forecasting technology that predicts demand using the data collected by the data collection technology; an order generation technology that automatically generates an order plan based on the demand forecast by the forecasting technology; and a user confirmation and adjustment technology that allows the order plan to be confirmed and adjusted via a user terminal. This enables efficient inventory management at the logistics center and accurate ordering at the appropriate time.

[0100] "Data collection technology" refers to technologies for efficiently collecting historical supply data, environmental information, timing information, and sales promotion activity information.

[0101] "Predictive technology" is a technology that uses collected data to predict future demand with high accuracy.

[0102] "Order generation technology" is a technology that automatically generates order plans based on predicted demand.

[0103] "Automated execution technology" is a technology that quickly and accurately executes generated order plans.

[0104] "User confirmation and adjustment technology" is a technology that allows users to confirm and adjust order plans via their terminals as needed.

[0105] In this embodiment of the invention, the system consists of a server, a terminal, and a user. The server utilizes information gathering technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from various data sources. This enables the data to be integrated into a database and centrally managed. The server uses prediction technology to predict future demand with high accuracy based on the collected data. In this process, the server uses AI technology to perform pattern recognition within the data. Based on the predicted demand, order generation technology automatically generates an optimal order plan. This order plan adjusts the order quantity and timing, taking into account the characteristics of the facilities and products.

[0106] Users review the order plan sent from the server via their terminal and make adjustments as needed. The reviewed order plan is then automatically placed with the appropriate suppliers using automated execution technology. This reduces human error and ensures efficient and accurate ordering.

[0107] For example, if increased demand for logistics centers is predicted due to a large-scale event, the server calculates and proposes an appropriate order quantity. The user can then review this proposal via their terminal and automatically place the confirmed order. This helps prevent inventory shortages and excesses.

[0108] The generative AI model is strengthened through a feedback loop, and the server improves its prediction accuracy based on the sales results provided by the user. This cycle leads to more efficient inventory and order management.

[0109] Examples of prompts to input into a generative AI model:

[0110] Based on sales data from store A over the past year and the weather forecast for next week, predict the amount of inventory needed for the following week.

[0111] This system allows logistics centers to secure the right inventory at the right time, improving operational efficiency and flexibility.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server uses data collection technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from data sources. Input is raw data obtained from various data sources, and output is a record in an integrated database. In this process, ETL tools are used to centrally manage and format the data.

[0115] Step 2:

[0116] The server uses forecasting technology to predict future demand based on data recorded in the database. The input is integrated data, and the output is the result of the demand forecast. It uses a generative AI model and analyzes future trends to perform highly accurate demand forecasts through pattern recognition algorithms.

[0117] Step 3:

[0118] The server uses order generation technology to automatically generate an order plan based on demand forecast results. The input is the demand forecast result, and the output is a prototype of the order plan. Based on the algorithm, it optimizes order quantities and timing, taking into account the characteristics of the product and facility.

[0119] Step 4:

[0120] The user receives the order plan sent from the server via their terminal and reviews its contents. The input is the draft order plan sent from the server, and the output is the order plan reviewed by the user. At this stage, the user reviews the proposed content on their terminal and makes adjustments as needed.

[0121] Step 5:

[0122] The terminal uses automated execution technology to place orders with designated suppliers based on the confirmed order plan. The input is the order plan confirmed by the user, and the output is an order notification to the supplier. This process involves electronic data transmission to complete the order at the appropriate time.

[0123] Step 6:

[0124] The server utilizes feedback to collect information such as sales results and enhance the generated AI model. The input is actual supply and sales data after an order is placed, and the output is an improved predictive model. This step improves the accuracy of predictions, which can then be used for subsequent predictions and orders.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention combines an automated ordering system with a user emotion recognition function, enabling the server, terminal, and user to work together to optimize ordering. Details are described below.

[0127] In this embodiment, the server uses information gathering means to collect historical sales data, weather information, seasonal information, and promotional event information, and integrates it into a database. The collected data undergoes preprocessing and is input into a demand forecasting model by forecasting means. The generated demand forecast is used to create an order plan through order generation means.

[0128] In addition, an emotion engine is built into the device, which recognizes the user's emotional state from the feedback they input. This emotion engine can also analyze emotions from the user's facial expressions and voice. When the user's emotional state is detected, the emotion engine sends that data to a server.

[0129] The server collects user sentiment data and incorporates it into the demand forecasting model to improve forecast accuracy. Furthermore, based on the data from the sentiment engine, the server can suggest adjustments to the order plan created by the order generation system. When adjustments are presented, the user reviews them on their terminal and makes changes as needed.

[0130] As a concrete example, the server predicts that ice cream demand will increase next week based on past data and weather information for a particular store. When the user reviews their order plan, the emotion engine detects the user's anxiety. Based on this, the server suggests adjustments, such as reducing the order quantity. The final plan is decided by the user after considering these adjustments.

[0131] This process allows the system to recognize users' emotional responses, enabling more realistic and efficient ordering. As a result, businesses can achieve more flexible and adaptable inventory management.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server collects sales data, weather data, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there. This allows the system to assess demand based on the latest information.

[0135] Step 2:

[0136] The server preprocesses the collected data, removing outliers and normalizing the data. This prepares a dataset suitable for demand forecasting.

[0137] Step 3:

[0138] The server uses prediction tools to perform demand forecasting based on pre-processed data. AI models are used to calculate best-selling products and expected sales volumes.

[0139] Step 4:

[0140] An emotion engine runs on the device and recognizes the user's emotions through facial expression and voice analysis. For example, it analyzes the emotions a user expresses while looking at the display.

[0141] Step 5:

[0142] The device retrieves the user's emotional data from the emotion engine and sends it to the server. This prepares the system for the user's emotions to be reflected in the ordering process.

[0143] Step 6:

[0144] The server incorporates emotional data into demand forecast information and adjusts the forecasting model. This generates an order plan that takes emotional bias into account.

[0145] Step 7:

[0146] The server uses an order generation method that takes sentiment data into account to formulate the optimal order plan and sends it to the terminal. The user reviews the order plan on the terminal and makes adjustments as needed.

[0147] Step 8:

[0148] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. The system then sends the order details to the designated manufacturer or wholesaler for confirmation.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] Conventional automated ordering systems based demand forecasts on quantitative data such as past sales data and weather information. However, because they did not take into account user emotions or intuitive judgments, discrepancies sometimes arose between actual demand and forecasts. This resulted in problems such as inventory shortages or surpluses and lost sales opportunities.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes data acquisition means for collecting past sales information, weather information, seasonal information, and sales promotion event information; estimation means for estimating demand using the collected information; plan generation means for automatically formulating an order plan based on the estimated demand; sentiment analysis means for recognizing user sentiment information and reflecting the recognition results in the demand forecast; and integrated management means for integrating data processing for the entire system. This enables more accurate demand forecasting and flexible order planning that takes into account user sentiment and intuition.

[0154] "Data acquisition means" refers to devices or functions for collecting past sales information, weather information, seasonal information, and sales promotion event information.

[0155] An "estimation tool" refers to a device or function used to calculate or predict future demand based on collected information.

[0156] A "plan generation means" refers to a device or function that automatically creates an optimal ordering plan, taking estimated demand into consideration.

[0157] "Sentiment analysis tools" refer to devices or functions that recognize and analyze users' emotional information to reflect it in demand forecasting.

[0158] An "integrated management system" refers to a device or function for centrally managing and controlling data processing across the entire system.

[0159] The embodiments for carrying out the present invention are described below.

[0160] In this system, the server utilizes data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. The server uses high-performance database servers and cloud services, for example, to acquire weather data via external APIs and collect historical sales information from existing sales management systems. This allows the necessary information to be integrated into the database.

[0161] Next, the server processes the collected information using estimation methods and performs demand forecasting using a generative AI model. Here, TensorFlow and PyTorch are used as machine learning libraries to build a model for analyzing demand patterns.

[0162] Subsequently, the server uses a plan generation mechanism to automatically create an ordering plan based on estimated demand. This plans the appropriate order quantity and timing for the demand, enabling the system to achieve flexible inventory management.

[0163] Furthermore, the user's device acquires emotional information through emotion analysis. This process uses cameras and microphones to capture facial expressions and voice data, which are then analyzed by an emotion recognition AI model. The analyzed emotional data is sent to a server and incorporated into demand forecasts to improve their accuracy.

[0164] Ultimately, the server utilizes integrated management tools to centrally manage all data processing and sends the optimal order plan to the terminal. Users can then review the presented order plan and make modifications as needed.

[0165] As a concrete example, the server predicts that demand for ice cream will increase during the summer peak season based on past sales data and weather information for a particular store. When a terminal detects anxiety while the user is reviewing their order plan, the server suggests adjusting the order quantity to be more modest. This process allows businesses to respond more flexibly and adaptably.

[0166] An example of a prompt to input into the generating AI model is, "Propose an optimal order plan that takes into account user sentiment and sales forecast data." This prompt will allow the system to improve the order plan by incorporating user sentiment.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server uses data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. Specifically, it obtains weather information from an external API and receives sales data from the sales management system. In this step, the acquired data is integrated into a database and converted into a format for use in the next process. The input is data obtained from various sources, and the output is an integrated dataset.

[0170] Step 2:

[0171] The server uses estimation methods to predict future demand using the collected information. Here, a generative AI model is utilized, and TensorFlow or PyTorch is used to train it on past data patterns. The input is an integrated dataset, and the output is the predicted value from the demand forecasting model. In this step, the data is preprocessed and converted into the format required by the model.

[0172] Step 3:

[0173] The server uses a planning generation mechanism to create an optimal ordering plan based on demand forecasts. This planning process employs an algorithm that generates ordering suggestions for the predicted demand. The input is the demand forecast result, and the output is the details of the ordering plan. This step also considers inventory levels and supply chain information.

[0174] Step 4:

[0175] The device uses emotion analysis tools to recognize the user's emotions, collecting emotional information through facial expressions and voice. The device acquires data using a facial recognition camera and microphone, and analyzes it using emotion analysis AI. The input is the user's facial expressions and voice, and the output is the recognized emotional state.

[0176] Step 5:

[0177] The device sends the acquired sentiment information to the server. The server receives this data and incorporates it into the demand forecasting model to improve the accuracy of the forecast. The input is the user's sentiment information, and the output is a new forecast value from the improved demand forecasting model.

[0178] Step 6:

[0179] The server utilizes integrated management tools to generate proposed adjustments to the order plan and send them to the terminal. These adjustments take into account sentiment information and market trends. The input is the latest demand forecast and sentiment information, and the output is the adjusted order plan presented to the user.

[0180] Step 7:

[0181] The user reviews the displayed order plan via their terminal and makes modifications as needed. They then finalize the order details and send that information to the server. The input is the adjusted order plan, and the output is the confirmed order plan after user review. This ensures optimized ordering.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0184] Conventional automated ordering systems rely primarily on data-driven mathematical models for demand forecasting, making it difficult to reflect subjective user emotions and anxieties. This can lead to a lack of adaptability to actual sales conditions and market fluctuations, potentially resulting in excess or shortages of inventory. Furthermore, the loss of sales opportunities due to mismatches between supply and demand remains a challenge.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes information gathering means for collecting past sales data, environmental information, duration information, and sales promotion activity information; estimation means for predicting demand using the data collected by the information gathering means; plan generation means for automatically generating an order plan based on the demand forecast by the estimation means; sentiment analysis means for collecting and analyzing the user's sentiment information; sentiment adjustment means for adjusting the order plan based on the sentiment information analyzed by the sentiment analysis means; and automatic execution means for executing the adjusted order plan. This improves the accuracy of demand forecasting and enables flexible and adaptable inventory management that reflects sentiment information.

[0187] "Information gathering means" refers to technologies or devices for collecting past sales data, environmental information, duration information, and sales promotion activity information.

[0188] "Estimation methods" refer to algorithms and functions that utilize collected data to predict future demand.

[0189] "Plan generation means" refers to a technology or system that automatically creates an ordering plan based on demand forecasts obtained by estimation means.

[0190] "Emotional analysis means" refers to the functions of software or hardware used to collect and analyze user emotional information.

[0191] "Emotional adjustment means" refers to functions or methods for revising or adjusting ordering plans using emotional information obtained through emotional analysis means.

[0192] "Automated execution means" refers to automated processes or devices for executing planned orders.

[0193] The system for realizing this invention involves the collaborative operation of a server, terminals, and users. The server uses information gathering means to collect historical sales data, environmental information, duration information, and sales promotion activity information. Database software such as MySQL® or Firebase is used for data storage and management.

[0194] The collected data is analyzed by estimation tools, and future demand is predicted using demand forecasting models such as TensorFlow and PyTorch. The predicted data is then supplied to a planning generation tool to automatically create an order plan.

[0195] Meanwhile, the device's built-in emotion analysis system collects and analyzes the user's emotional information, specifically facial expressions and voice tone, in real time. This analysis utilizes the image recognition library OpenCV and the speech analysis API Google® Cloud Speech-to-Text. When a user uses the device to review a plan, their emotions are analyzed, and this data is sent to the server.

[0196] The server adjusts the order plan based on emotional information via an emotion adjustment mechanism. This function generates an order plan that reflects emotional information, enabling more appropriate ordering that is closer to the actual situation. Finally, the adjusted plan is executed by an automated execution mechanism. For example, if a weather forecast predicts an increase in beverage demand, an order plan is created based on that forecast. If the user experiences anxiety at that time, the plan is adjusted based on the emotional information.

[0197] An example of a prompt might be: "Based on today's customer traffic, sales forecast, and what I've told you, please suggest one option that seems best. If I look unsure or negative, please also consider alternative options."

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server collects historical sales data, environmental information, duration information, and sales promotion activity information using various data collection methods. Inputs are from diverse data sources (databases, web APIs, etc.), and output is an integrated dataset. This dataset is preprocessed to feed into a predictive model. Data processing includes imputation of missing values, data normalization, and aggregation on a time-unit basis.

[0201] Step 2:

[0202] The server analyzes collected datasets using estimation methods to predict future demand. The input is pre-processed integrated data, and the output is the demand forecast result. The data calculations utilize a machine learning model using TensorFlow, and parameter tuning is performed to improve prediction accuracy.

[0203] Step 3:

[0204] The server automatically generates an order plan based on demand forecasts using a plan generation mechanism. The input is the demand forecast result, and the output is the initial order plan. Specifically, a logic is executed to calculate the appropriate order quantity and timing based on the sales forecast.

[0205] Step 4:

[0206] The device's built-in emotion analysis system analyzes emotional information collected from the user in real time. Input is the user's facial expression images and audio data, and output is the analyzed emotional state. OpenCV is used to analyze facial expressions, and Google Cloud Speech-to-Text is used to evaluate the emotion of the audio.

[0207] Step 5:

[0208] The server adjusts the order plan based on the analyzed user's emotional information via an emotion adjustment mechanism. The input is the initial order plan and analyzed emotional data, and the output is the adjusted order plan. Specifically, an algorithm is applied that increases or decreases the order quantity based on the user's emotions.

[0209] Step 6:

[0210] The user reviews the adjusted order plan on their terminal and approves or modifies it as needed, performing a final check as necessary. The input is the adjusted order plan, and the output is the order plan finalized by the user. Specifically, the user reviews the details of the order plan via the user interface and reflects any changes.

[0211] Step 7:

[0212] The server executes orders based on the finalized order plan using automated execution mechanisms. The input is the finalized order plan, and the output is the execution result of that order. Specifically, it sends order commands to the execution system and monitors the status of their implementation.

[0213] 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.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] 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.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] 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.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0229] This invention relates to an automated ordering system in which a server, terminal, and user cooperate to improve the efficiency of ordering. Specific embodiments thereof will be described below.

[0230] First, the server uses information gathering tools to acquire historical sales data, weather information, seasonal information, and promotional event information from various data sources. The data is integrated and centrally recorded in a database. The database records the characteristics of each store and product, enabling analysis based on this information.

[0231] Next, the server applies prediction methods and uses the collected data to forecast future demand. This prediction model utilizes AI technology to perform highly accurate demand forecasts based on pattern recognition within the data. The demand forecast results are then used in subsequent processes.

[0232] Furthermore, the server generates an optimal order plan based on the demand forecast results using an order generation mechanism. This plan is optimized considering the characteristics of each store and product. It also includes adjustments to order quantity and timing. The generated order plan is sent to the terminal in a format that the user can review and correct.

[0233] The terminal is equipped with an automated execution mechanism and electronically places orders with manufacturers and wholesalers based on order proposals confirmed by the user. This reduces errors caused by manual input and achieves efficient and accurate ordering.

[0234] As a concrete example, in a retail store, if the server predicts that high temperatures will continue using past ice cream sales data and the weather forecast for the weekend, the AI ​​model will determine that demand for soft drinks will increase. As a result, the server generates an order plan suggesting twice the normal order quantity, which the terminal receives. The user reviews the order plan and makes adjustments if necessary. After confirmation, the terminal automatically places the order.

[0235] A feedback loop is also included in this system; based on the sales results provided by the user, the server enhances the generated AI model and improves prediction accuracy. This cycle leads to increased efficiency in both inventory management and order management.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server collects historical sales data, weather information, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there.

[0239] Step 2:

[0240] The server preprocesses the data stored in the database, including imputing missing values ​​and correcting outliers. This formats the data so that it is suitable as input for the demand forecasting model.

[0241] Step 3:

[0242] The server applies a generative AI model as a prediction tool and performs demand forecasting based on pre-processed data. The forecast results include multiple demand scenarios that take various external factors into account.

[0243] Step 4:

[0244] The server uses the prediction results to create an optimal order generation method that takes into account the characteristics of the store and the product. This is where the order quantity and timing are optimized.

[0245] Step 5:

[0246] The terminal receives order plans from the server and presents the information through an interface that allows the user to review and adjust the plans. Users can modify the proposals based on their own insights into changing demand.

[0247] Step 6:

[0248] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. Specifically, the terminal electronically sends the order information to the manufacturer or wholesaler.

[0249] Step 7:

[0250] Users evaluate sales results and inventory status, and provide this information as feedback to the server via their terminals. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future demand forecasts.

[0251] (Example 1)

[0252] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0253] In today's business environment, rapid and accurate inventory management and ordering are essential, with a particular challenge in responding quickly to fluctuations in demand. Furthermore, traditional manual ordering methods are prone to human error, making efficient ordering difficult. Improving the accuracy of demand forecasting and optimizing inventory management are crucial factors directly linked to increased profits. Therefore, there is a need for methods that enable more accurate demand forecasting and efficiently automate ordering.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for collecting historical sales data, weather information, seasonal information, and promotional event information; means for integrating and storing the collected data; and means for applying a generated AI model using the integrated data to forecast demand. This makes it possible to perform highly accurate demand forecasting, automatically generate optimized order plans, and streamline ordering operations.

[0256] "Historical sales data" refers to records of sales of goods and services in previous periods, and serves as the basis for demand forecasting.

[0257] "Weather information" refers to information about weather conditions such as temperature, precipitation, and wind speed, and is one of the factors that influence demand.

[0258] "Seasonal information" refers to information that influences demand fluctuations associated with seasonal changes, and is data that is reflected in forecasting models for a specific season.

[0259] "Sales promotion event information" refers to information about sales promotion activities and events, and is data used to account for temporary fluctuations in demand.

[0260] "Information gathering means" refers to a method or apparatus for acquiring and integrating necessary information from various data sources.

[0261] "Means of integration" refers to a method or apparatus for aggregating acquired data in an appropriate format and storing it in a database.

[0262] "Means for applying generative AI models to predict demand" refers to a method or apparatus that utilizes artificial intelligence technology to accurately predict future demand from collected data.

[0263] "Means for optimizing and automatically generating order plans" refers to a method or apparatus that automatically creates an order plan by calculating the optimal order quantity and timing based on predicted demand.

[0264] A "terminal" is a device used to receive order plans sent from a server and for users to review and adjust them.

[0265] "Means of automatic execution" refers to a method or apparatus for electronically placing an order based on a confirmed order plan.

[0266] "Means of collecting feedback to improve prediction accuracy" refers to methods or devices for continuously improving the performance of a prediction model based on actual sales results.

[0267] This invention relates to a system for streamlining automated ordering, in which a server, terminals, and users cooperate to operate the entire system. The server is primarily responsible for collecting information, performing forecasts, and generating order plans, while the terminals provide an interface with the user and assist in managing the executed orders.

[0268] The server acquires historical sales data, weather information, seasonal information, and promotional event information from various data sources through information gathering means. This utilizes an integrated database system, such as a data management platform like PostgreSQL. The data is centrally recorded and integrated, enabling efficient analysis.

[0269] Furthermore, the server incorporates generative AI models to achieve highly accurate demand forecasting. Specifically, it can utilize machine learning libraries such as Python's scikit-learn and TensorFlow. This allows it to predict future demand through pattern recognition within the data and generate optimized ordering plans. The ordering plans are tailored to each store and product, providing the optimal combination of order quantity and timing.

[0270] The terminal receives order plans sent from the server and provides a user interface for the user to review and adjust as needed. After reviewing and adjusting the order plan based on the provided information, the user places the order electronically using an automated execution mechanism. This minimizes ordering errors and enables fast and accurate ordering.

[0271] As a concrete example, in a retail store, if the server uses past beverage sales data and the weather forecast for the weekend to predict continued high temperatures, the generating AI model will determine that demand for beverages will increase. As a result, the server generates an order plan suggesting twice the normal order quantity and sends it to the terminal. The user reviews the order plan and makes any necessary changes, after which the terminal automatically places the order.

[0272] Examples of prompt statements include the following:

[0273] "Based on this weekend's weather forecast and data from the past three years, please forecast next week's beverage demand and calculate the optimal order quantity."

[0274] "Consider the impact of the next promotional event, update the predictive model using past promotional event data, and propose an ordering plan."

[0275] This system enables inventory optimization and streamlined order management, leading to improved business flexibility and responsiveness.

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The server acquires historical sales data, weather information, seasonal information, and promotional event information through various data collection methods. This data serves as input. The collected data undergoes integration processing and is stored in a PostgreSQL database. Specifically, it may extract data from various APIs, perform data cleansing and format conversion, and generate integrated data. As a result, an integrated database is output.

[0279] Step 2:

[0280] The server applies a generative AI model using integrated data to perform demand forecasting. The input here is data from an integrated database. In this process, machine learning libraries such as Python's scikit-learn and TensorFlow are used to extract features from the data and train the predictive model. Specific operations include creating a training dataset and executing the model training process. The output is a forecast of future demand.

[0281] Step 3:

[0282] The server optimizes and automatically generates an order plan based on demand prediction data. The input is the demand prediction result of Step 2. At this stage, an optimization algorithm is executed considering the characteristics of the products and the conditions of each store. Specifically, data is manipulated using the Pandas library in Python to calculate the optimal order quantity and timing. The output is the optimized order plan.

[0283] Step 4:

[0284] The server sends the generated order plan to the terminal. The input to this process is the order plan obtained in Step 3. The specific operation is to send the order data to the terminal using the HTTP protocol. The terminal receives the order plan and the plan is displayed as the output.

[0285] Step 5:

[0286] The user checks and adjusts the order plan sent via the terminal as needed. In this step, the user operates the order plan using the GUI on the terminal. The input is the order plan displayed in Step 4, and the output is the order plan confirmed or adjusted by the user. Specific operations include fine-tuning using sliders and text fields.

[0287] Step 6:

[0288] The terminal places an order using an automatic execution means based on the confirmed order plan. The input is the confirmed order plan of Step 5. Through the EDI (Electronic Data Interchange) system, the order data is automatically sent to the merchant. Specific processing includes electronically transmitting the order information using network communication, and the completion of the order is confirmed as the output.

[0289] Step 7: )

[0290] Users send sales results to the server as feedback. This input includes actual sales data. The server collects the sales results and continuously updates the generated AI model. This improves the model's prediction accuracy. Specifically, it requires periodically sending sales data to the server's API endpoint. The output provides data to improve the model's accuracy.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] There is a need to improve the efficiency of inventory management in logistics centers and to enable accurate ordering based on demand forecasts. Traditional methods have problems such as excess inventory and stockouts, making efficient operation difficult. Furthermore, manual ordering is prone to errors and is time-consuming, which leads to increased costs and workload.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes a data collection technology that collects past supply data, environmental information, timing information, and sales promotion activity information; a forecasting technology that predicts demand using the data collected by the data collection technology; an order generation technology that automatically generates an order plan based on the demand forecast by the forecasting technology; and a user confirmation and adjustment technology that allows the order plan to be confirmed and adjusted via a user terminal. This enables efficient inventory management at the logistics center and accurate ordering at the appropriate time.

[0296] "Data collection technology" refers to technologies for efficiently collecting historical supply data, environmental information, timing information, and sales promotion activity information.

[0297] "Predictive technology" is a technology that uses collected data to predict future demand with high accuracy.

[0298] "Order generation technology" is a technology that automatically generates order plans based on predicted demand.

[0299] "Automated execution technology" is a technology that quickly and accurately executes generated order plans.

[0300] "User confirmation and adjustment technology" is a technology that allows users to confirm and adjust order plans via their terminals as needed.

[0301] In this embodiment of the invention, the system consists of a server, a terminal, and a user. The server utilizes information gathering technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from various data sources. This enables the data to be integrated into a database and centrally managed. The server uses prediction technology to predict future demand with high accuracy based on the collected data. In this process, the server uses AI technology to perform pattern recognition within the data. Based on the predicted demand, order generation technology automatically generates an optimal order plan. This order plan adjusts the order quantity and timing, taking into account the characteristics of the facilities and products.

[0302] Users review the order plan sent from the server via their terminal and make adjustments as needed. The reviewed order plan is then automatically placed with the appropriate suppliers using automated execution technology. This reduces human error and ensures efficient and accurate ordering.

[0303] For example, if increased demand for logistics centers is predicted due to a large-scale event, the server calculates and proposes an appropriate order quantity. The user can then review this proposal via their terminal and automatically place the confirmed order. This helps prevent inventory shortages and excesses.

[0304] The generated AI model is enhanced through a feedback loop, and the server improves the prediction accuracy based on the sales results provided by the user. This cycle aims to streamline inventory management and order management.

[0305] Examples of prompt sentences input into the generated AI model:

[0306] Considering the past one-year sales data at Store A and the weather forecast for next week, please predict the required inventory quantity for the next week.

[0307] With this system, the logistics center can ensure appropriate inventory at the right time, improving the efficiency and flexibility of operations.

[0308] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0309] Step 1:

[0310] The server uses information collection technology to obtain past supply data, environmental information, timing information, and sales promotion activity information from data sources. The input is the raw data obtained from various data sources, and the output is the record in the integrated database. In this process, ETL tools are used to manage the data centrally and format it.

[0311] Step 2:

[0312] The server uses prediction technology to predict future demand based on the data recorded in the database. The input is the integrated data, and the output is the result of demand prediction. The generated AI model is used to perform high-precision demand prediction through a pattern recognition algorithm and analyze future trends.

[0313] Step 3:

[0314] The server uses order generation technology to automatically generate an order plan based on demand forecast results. The input is the demand forecast result, and the output is a prototype of the order plan. Based on the algorithm, it optimizes order quantities and timing, taking into account the characteristics of the product and facility.

[0315] Step 4:

[0316] The user receives the order plan sent from the server via their terminal and reviews its contents. The input is the draft order plan sent from the server, and the output is the order plan reviewed by the user. At this stage, the user reviews the proposed content on their terminal and makes adjustments as needed.

[0317] Step 5:

[0318] The terminal uses automated execution technology to place orders with designated suppliers based on the confirmed order plan. The input is the order plan confirmed by the user, and the output is an order notification to the supplier. This process involves electronic data transmission to complete the order at the appropriate time.

[0319] Step 6:

[0320] The server utilizes feedback to collect information such as sales results and enhance the generated AI model. The input is actual supply and sales data after an order is placed, and the output is an improved predictive model. This step improves the accuracy of predictions, which can then be used for subsequent predictions and orders.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] This invention combines an automated ordering system with a user emotion recognition function, enabling the server, terminal, and user to work together to optimize ordering. Details are described below.

[0323] In this embodiment, the server uses information gathering means to collect historical sales data, weather information, seasonal information, and promotional event information, and integrates it into a database. The collected data undergoes preprocessing and is input into a demand forecasting model by forecasting means. The generated demand forecast is used to create an order plan through order generation means.

[0324] In addition, an emotion engine is built into the device, which recognizes the user's emotional state from the feedback they input. This emotion engine can also analyze emotions from the user's facial expressions and voice. When the user's emotional state is detected, the emotion engine sends that data to a server.

[0325] The server collects user sentiment data and incorporates it into the demand forecasting model to improve forecast accuracy. Furthermore, based on the data from the sentiment engine, the server can suggest adjustments to the order plan created by the order generation system. When adjustments are presented, the user reviews them on their terminal and makes changes as needed.

[0326] As a concrete example, the server predicts that ice cream demand will increase next week based on past data and weather information for a particular store. When the user reviews their order plan, the emotion engine detects the user's anxiety. Based on this, the server suggests adjustments, such as reducing the order quantity. The final plan is decided by the user after considering these adjustments.

[0327] This process allows the system to recognize users' emotional responses, enabling more realistic and efficient ordering. As a result, businesses can achieve more flexible and adaptable inventory management.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The server collects sales data, weather data, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there. This allows the system to assess demand based on the latest information.

[0331] Step 2:

[0332] The server preprocesses the collected data, removing outliers and normalizing the data. This prepares a dataset suitable for demand forecasting.

[0333] Step 3:

[0334] The server uses prediction tools to perform demand forecasting based on pre-processed data. AI models are used to calculate best-selling products and expected sales volumes.

[0335] Step 4:

[0336] An emotion engine runs on the device and recognizes the user's emotions through facial expression and voice analysis. For example, it analyzes the emotions a user expresses while looking at the display.

[0337] Step 5:

[0338] The device retrieves the user's emotional data from the emotion engine and sends it to the server. This prepares the system for the user's emotions to be reflected in the ordering process.

[0339] Step 6:

[0340] The server incorporates emotional data into demand forecast information and adjusts the forecasting model. This generates an order plan that takes emotional bias into account.

[0341] Step 7:

[0342] The server uses an order generation method that takes sentiment data into account to formulate the optimal order plan and sends it to the terminal. The user reviews the order plan on the terminal and makes adjustments as needed.

[0343] Step 8:

[0344] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. The system then sends the order details to the designated manufacturer or wholesaler for confirmation.

[0345] (Example 2)

[0346] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0347] Conventional automated ordering systems based demand forecasts on quantitative data such as past sales data and weather information. However, because they did not take into account user emotions or intuitive judgments, discrepancies sometimes arose between actual demand and forecasts. This resulted in problems such as inventory shortages or surpluses and lost sales opportunities.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes data acquisition means for collecting past sales information, weather information, seasonal information, and sales promotion event information; estimation means for estimating demand using the collected information; plan generation means for automatically formulating an order plan based on the estimated demand; sentiment analysis means for recognizing user sentiment information and reflecting the recognition results in the demand forecast; and integrated management means for integrating data processing for the entire system. This enables more accurate demand forecasting and flexible order planning that takes into account user sentiment and intuition.

[0350] "Data acquisition means" refers to devices or functions for collecting past sales information, weather information, seasonal information, and sales promotion event information.

[0351] An "estimation tool" refers to a device or function used to calculate or predict future demand based on collected information.

[0352] A "plan generation means" refers to a device or function that automatically creates an optimal ordering plan, taking estimated demand into consideration.

[0353] "Sentiment analysis tools" refer to devices or functions that recognize and analyze users' emotional information to reflect it in demand forecasting.

[0354] An "integrated management system" refers to a device or function for centrally managing and controlling data processing across the entire system.

[0355] The embodiments for carrying out the present invention are described below.

[0356] In this system, the server utilizes data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. The server uses high-performance database servers and cloud services, for example, to acquire weather data via external APIs and collect historical sales information from existing sales management systems. This allows the necessary information to be integrated into the database.

[0357] Next, the server processes the collected information using estimation methods and performs demand forecasting using a generative AI model. Here, TensorFlow and PyTorch are used as machine learning libraries to build a model for analyzing demand patterns.

[0358] Subsequently, the server uses a plan generation mechanism to automatically create an ordering plan based on estimated demand. This plans the appropriate order quantity and timing for the demand, enabling the system to achieve flexible inventory management.

[0359] Furthermore, the user's device acquires emotional information through emotion analysis. This process uses cameras and microphones to capture facial expressions and voice data, which are then analyzed by an emotion recognition AI model. The analyzed emotional data is sent to a server and incorporated into demand forecasts to improve their accuracy.

[0360] Ultimately, the server utilizes integrated management tools to centrally manage all data processing and sends the optimal order plan to the terminal. Users can then review the presented order plan and make modifications as needed.

[0361] As a concrete example, the server predicts that demand for ice cream will increase during the summer peak season based on past sales data and weather information for a particular store. When a terminal detects anxiety while the user is reviewing their order plan, the server suggests adjusting the order quantity to be more modest. This process allows businesses to respond more flexibly and adaptably.

[0362] An example of a prompt to input into the generating AI model is, "Propose an optimal order plan that takes into account user sentiment and sales forecast data." This prompt will allow the system to improve the order plan by incorporating user sentiment.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The server uses data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. Specifically, it obtains weather information from an external API and receives sales data from the sales management system. In this step, the acquired data is integrated into a database and converted into a format for use in the next process. The input is data obtained from various sources, and the output is an integrated dataset.

[0366] Step 2:

[0367] The server uses estimation methods to predict future demand using the collected information. Here, a generative AI model is utilized, and TensorFlow or PyTorch is used to train it on past data patterns. The input is an integrated dataset, and the output is the predicted value from the demand forecasting model. In this step, the data is preprocessed and converted into the format required by the model.

[0368] Step 3:

[0369] The server uses a planning generation mechanism to create an optimal ordering plan based on demand forecasts. This planning process employs an algorithm that generates ordering suggestions for the predicted demand. The input is the demand forecast result, and the output is the details of the ordering plan. This step also considers inventory levels and supply chain information.

[0370] Step 4:

[0371] The device uses emotion analysis tools to recognize the user's emotions, collecting emotional information through facial expressions and voice. The device acquires data using a facial recognition camera and microphone, and analyzes it using emotion analysis AI. The input is the user's facial expressions and voice, and the output is the recognized emotional state.

[0372] Step 5:

[0373] The device sends the acquired sentiment information to the server. The server receives this data and incorporates it into the demand forecasting model to improve the accuracy of the forecast. The input is the user's sentiment information, and the output is a new forecast value from the improved demand forecasting model.

[0374] Step 6:

[0375] The server utilizes integrated management tools to generate proposed adjustments to the order plan and send them to the terminal. These adjustments take into account sentiment information and market trends. The input is the latest demand forecast and sentiment information, and the output is the adjusted order plan presented to the user.

[0376] Step 7:

[0377] The user reviews the displayed order plan via their terminal and makes modifications as needed. They then finalize the order details and send that information to the server. The input is the adjusted order plan, and the output is the confirmed order plan after user review. This ensures optimized ordering.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] Conventional automated ordering systems rely primarily on data-driven mathematical models for demand forecasting, making it difficult to reflect subjective user emotions and anxieties. This can lead to a lack of adaptability to actual sales conditions and market fluctuations, potentially resulting in excess or shortages of inventory. Furthermore, the loss of sales opportunities due to mismatches between supply and demand remains a challenge.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes information gathering means for collecting past sales data, environmental information, duration information, and sales promotion activity information; estimation means for predicting demand using the data collected by the information gathering means; plan generation means for automatically generating an order plan based on the demand forecast by the estimation means; sentiment analysis means for collecting and analyzing the user's sentiment information; sentiment adjustment means for adjusting the order plan based on the sentiment information analyzed by the sentiment analysis means; and automatic execution means for executing the adjusted order plan. This improves the accuracy of demand forecasting and enables flexible and adaptable inventory management that reflects sentiment information.

[0383] "Information gathering means" refers to technologies or devices for collecting past sales data, environmental information, duration information, and sales promotion activity information.

[0384] "Estimation methods" refer to algorithms and functions that utilize collected data to predict future demand.

[0385] "Plan generation means" refers to a technology or system that automatically creates an ordering plan based on demand forecasts obtained by estimation means.

[0386] "Emotional analysis means" refers to the functions of software or hardware used to collect and analyze user emotional information.

[0387] "Emotional adjustment means" refers to functions or methods for revising or adjusting ordering plans using emotional information obtained through emotional analysis means.

[0388] "Automated execution means" refers to automated processes or devices for executing planned orders.

[0389] The system for realizing this invention involves the collaborative operation of a server, terminals, and users. The server uses information gathering means to collect historical sales data, environmental information, duration information, and sales promotion activity information. Database software such as MySQL or Firebase is used for data storage and management.

[0390] The collected data is analyzed by estimation tools, and future demand is predicted using demand forecasting models such as TensorFlow and PyTorch. The predicted data is then supplied to a planning generation tool to automatically create an order plan.

[0391] Meanwhile, the device's built-in emotion analysis system collects and analyzes the user's emotional information, specifically facial expressions and voice tone, in real time. This analysis utilizes the image recognition library OpenCV and the speech analysis API Google Cloud Speech-to-Text. When a user uses the device to review a plan, their emotions are analyzed, and this data is sent to the server.

[0392] The server adjusts the order plan based on emotional information via an emotion adjustment mechanism. This function generates an order plan that reflects emotional information, enabling more appropriate ordering that is closer to the actual situation. Finally, the adjusted plan is executed by an automated execution mechanism. For example, if a weather forecast predicts an increase in beverage demand, an order plan is created based on that forecast. If the user experiences anxiety at that time, the plan is adjusted based on the emotional information.

[0393] An example of a prompt might be: "Based on today's customer traffic, sales forecast, and what I've told you, please suggest one option that seems best. If I look unsure or negative, please also consider alternative options."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server collects historical sales data, environmental information, duration information, and sales promotion activity information using various data collection methods. Inputs are from diverse data sources (databases, web APIs, etc.), and output is an integrated dataset. This dataset is preprocessed to feed into a predictive model. Data processing includes imputation of missing values, data normalization, and aggregation on a time-unit basis.

[0397] Step 2:

[0398] The server analyzes collected datasets using estimation methods to predict future demand. The input is pre-processed integrated data, and the output is the demand forecast result. The data calculations utilize a machine learning model using TensorFlow, and parameter tuning is performed to improve prediction accuracy.

[0399] Step 3:

[0400] The server automatically generates an order plan based on demand forecasts using a plan generation mechanism. The input is the demand forecast result, and the output is the initial order plan. Specifically, a logic is executed to calculate the appropriate order quantity and timing based on the sales forecast.

[0401] Step 4:

[0402] The device's built-in emotion analysis system analyzes emotional information collected from the user in real time. Input is the user's facial expression images and audio data, and output is the analyzed emotional state. OpenCV is used to analyze facial expressions, and Google Cloud Speech-to-Text is used to evaluate the emotion of the audio.

[0403] Step 5:

[0404] The server adjusts the order plan based on the analyzed user's emotional information via an emotion adjustment mechanism. The input is the initial order plan and analyzed emotional data, and the output is the adjusted order plan. Specifically, an algorithm is applied that increases or decreases the order quantity based on the user's emotions.

[0405] Step 6:

[0406] The user reviews the adjusted order plan on their terminal and approves or modifies it as needed, performing a final check as necessary. The input is the adjusted order plan, and the output is the order plan finalized by the user. Specifically, the user reviews the details of the order plan via the user interface and reflects any changes.

[0407] Step 7:

[0408] The server executes orders based on the finalized order plan using automated execution mechanisms. The input is the finalized order plan, and the output is the execution result of that order. Specifically, it sends order commands to the execution system and monitors the status of their implementation.

[0409] 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.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] 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.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] 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.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] 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.

[0420] 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.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention relates to an automated ordering system in which a server, terminal, and user cooperate to improve the efficiency of ordering. Specific embodiments thereof will be described below.

[0426] First, the server uses information gathering tools to acquire historical sales data, weather information, seasonal information, and promotional event information from various data sources. The data is integrated and centrally recorded in a database. The database records the characteristics of each store and product, enabling analysis based on this information.

[0427] Next, the server applies prediction methods and uses the collected data to forecast future demand. This prediction model utilizes AI technology to perform highly accurate demand forecasts based on pattern recognition within the data. The demand forecast results are then used in subsequent processes.

[0428] Furthermore, the server generates an optimal order plan based on the demand forecast results using an order generation mechanism. This plan is optimized considering the characteristics of each store and product. It also includes adjustments to order quantity and timing. The generated order plan is sent to the terminal in a format that the user can review and correct.

[0429] The terminal is equipped with an automated execution mechanism and electronically places orders with manufacturers and wholesalers based on order proposals confirmed by the user. This reduces errors caused by manual input and achieves efficient and accurate ordering.

[0430] As a concrete example, in a retail store, if the server predicts that high temperatures will continue using past ice cream sales data and the weather forecast for the weekend, the AI ​​model will determine that demand for soft drinks will increase. As a result, the server generates an order plan suggesting twice the normal order quantity, which the terminal receives. The user reviews the order plan and makes adjustments if necessary. After confirmation, the terminal automatically places the order.

[0431] A feedback loop is also included in this system; based on the sales results provided by the user, the server enhances the generated AI model and improves prediction accuracy. This cycle leads to increased efficiency in both inventory management and order management.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server collects historical sales data, weather information, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there.

[0435] Step 2:

[0436] The server preprocesses the data stored in the database, including imputing missing values ​​and correcting outliers. This formats the data so that it is suitable as input for the demand forecasting model.

[0437] Step 3:

[0438] The server applies a generative AI model as a prediction tool and performs demand forecasting based on pre-processed data. The forecast results include multiple demand scenarios that take various external factors into account.

[0439] Step 4:

[0440] The server uses the prediction results to create an optimal order generation method that takes into account the characteristics of the store and the product. This is where the order quantity and timing are optimized.

[0441] Step 5:

[0442] The terminal receives order plans from the server and presents the information through an interface that allows the user to review and adjust the plans. Users can modify the proposals based on their own insights into changing demand.

[0443] Step 6:

[0444] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. Specifically, the terminal electronically sends the order information to the manufacturer or wholesaler.

[0445] Step 7:

[0446] Users evaluate sales results and inventory status, and provide this information as feedback to the server via their terminals. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future demand forecasts.

[0447] (Example 1)

[0448] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] In today's business environment, rapid and accurate inventory management and ordering are essential, with a particular challenge in responding quickly to fluctuations in demand. Furthermore, traditional manual ordering methods are prone to human error, making efficient ordering difficult. Improving the accuracy of demand forecasting and optimizing inventory management are crucial factors directly linked to increased profits. Therefore, there is a need for methods that enable more accurate demand forecasting and efficiently automate ordering.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes means for collecting historical sales data, weather information, seasonal information, and promotional event information; means for integrating and storing the collected data; and means for applying a generated AI model using the integrated data to forecast demand. This makes it possible to perform highly accurate demand forecasting, automatically generate optimized order plans, and streamline ordering operations.

[0452] "Historical sales data" refers to records of sales of goods and services in previous periods, and serves as the basis for demand forecasting.

[0453] "Weather information" refers to information about weather conditions such as temperature, precipitation, and wind speed, and is one of the factors that influence demand.

[0454] "Seasonal information" refers to information that influences demand fluctuations associated with seasonal changes, and is data that is reflected in forecasting models for a specific season.

[0455] "Sales promotion event information" refers to information about sales promotion activities and events, and is data used to account for temporary fluctuations in demand.

[0456] "Information gathering means" refers to a method or apparatus for acquiring and integrating necessary information from various data sources.

[0457] "Means of integration" refers to a method or apparatus for aggregating acquired data in an appropriate format and storing it in a database.

[0458] "Means for applying generative AI models to predict demand" refers to a method or apparatus that utilizes artificial intelligence technology to accurately predict future demand from collected data.

[0459] "Means for optimizing and automatically generating order plans" refers to a method or apparatus that automatically creates an order plan by calculating the optimal order quantity and timing based on predicted demand.

[0460] A "terminal" is a device used to receive order plans sent from a server and for users to review and adjust them.

[0461] "Means of automatic execution" refers to a method or apparatus for electronically placing an order based on a confirmed order plan.

[0462] "Means of collecting feedback to improve prediction accuracy" refers to methods or devices for continuously improving the performance of a prediction model based on actual sales results.

[0463] This invention relates to a system for streamlining automated ordering, in which a server, terminals, and users cooperate to operate the entire system. The server is primarily responsible for collecting information, performing forecasts, and generating order plans, while the terminals provide an interface with the user and assist in managing the executed orders.

[0464] The server acquires historical sales data, weather information, seasonal information, and promotional event information from various data sources through information gathering means. This utilizes an integrated database system, such as a data management platform like PostgreSQL. The data is centrally recorded and integrated, enabling efficient analysis.

[0465] Furthermore, the server incorporates generative AI models to achieve highly accurate demand forecasting. Specifically, it can utilize machine learning libraries such as Python's scikit-learn and TensorFlow. This allows it to predict future demand through pattern recognition within the data and generate optimized ordering plans. The ordering plans are tailored to each store and product, providing the optimal combination of order quantity and timing.

[0466] The terminal receives order plans sent from the server and provides a user interface for the user to review and adjust as needed. After reviewing and adjusting the order plan based on the provided information, the user places the order electronically using an automated execution mechanism. This minimizes ordering errors and enables fast and accurate ordering.

[0467] As a concrete example, in a retail store, if the server uses past beverage sales data and the weather forecast for the weekend to predict continued high temperatures, the generating AI model will determine that demand for beverages will increase. As a result, the server generates an order plan suggesting twice the normal order quantity and sends it to the terminal. The user reviews the order plan and makes any necessary changes, after which the terminal automatically places the order.

[0468] Examples of prompt statements include the following:

[0469] "Based on this weekend's weather forecast and data from the past three years, please forecast next week's beverage demand and calculate the optimal order quantity."

[0470] "Consider the impact of the next promotional event, update the predictive model using past promotional event data, and propose an ordering plan."

[0471] This system enables inventory optimization and streamlined order management, leading to improved business flexibility and responsiveness.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The server acquires historical sales data, weather information, seasonal information, and promotional event information through various data collection methods. This data serves as input. The collected data undergoes integration processing and is stored in a PostgreSQL database. Specifically, it may extract data from various APIs, perform data cleansing and format conversion, and generate integrated data. As a result, an integrated database is output.

[0475] Step 2:

[0476] The server applies a generative AI model using integrated data to perform demand forecasting. The input here is data from an integrated database. In this process, machine learning libraries such as Python's scikit-learn and TensorFlow are used to extract features from the data and train the predictive model. Specific operations include creating a training dataset and executing the model training process. The output is a forecast of future demand.

[0477] Step 3:

[0478] The server optimizes and automatically generates an order plan based on demand forecast data. The input is the demand forecast result from step 2. At this stage, the optimization algorithm is executed, taking into account the characteristics of the products and the conditions of each store. Specifically, the data is manipulated using the Python Pandas library to calculate the optimal order quantity and timing. The output is the optimized order plan.

[0479] Step 4:

[0480] The server sends the generated order plan to the terminal. The input to this process is the order plan obtained in step 3. Specifically, the server sends the order data to the terminal using the HTTP protocol. The terminal receives the order plan and displays it as output.

[0481] Step 5:

[0482] The user reviews and adjusts the order plan sent via the terminal as needed. In this step, the user interacts with the order plan using a GUI on the terminal. The input is the order plan displayed in step 4, and the output is the order plan reviewed or adjusted by the user. Specific actions include making fine adjustments using sliders and text fields.

[0483] Step 6:

[0484] The terminal places an order using an automated execution mechanism based on the confirmed order plan. The input is the confirmed order plan from step 5. The order data is automatically transmitted to the supplier via the EDI (Electronic Data Interchange) system. The specific process involves electronically transmitting the order information using network communication, and the output confirms the completion of the order.

[0485] Step 7:

[0486] Users send sales results to the server as feedback. This input includes actual sales data. The server collects the sales results and continuously updates the generated AI model. This improves the model's prediction accuracy. Specifically, it requires periodically sending sales data to the server's API endpoint. The output provides data to improve the model's accuracy.

[0487] (Application Example 1)

[0488] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0489] There is a need to improve the efficiency of inventory management in logistics centers and to enable accurate ordering based on demand forecasts. Traditional methods have problems such as excess inventory and stockouts, making efficient operation difficult. Furthermore, manual ordering is prone to errors and is time-consuming, which leads to increased costs and workload.

[0490] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0491] In this invention, the server includes a data collection technology that collects past supply data, environmental information, timing information, and sales promotion activity information; a forecasting technology that predicts demand using the data collected by the data collection technology; an order generation technology that automatically generates an order plan based on the demand forecast by the forecasting technology; and a user confirmation and adjustment technology that allows the order plan to be confirmed and adjusted via a user terminal. This enables efficient inventory management at the logistics center and accurate ordering at the appropriate time.

[0492] "Data collection technology" refers to technologies for efficiently collecting historical supply data, environmental information, timing information, and sales promotion activity information.

[0493] "Predictive technology" is a technology that uses collected data to predict future demand with high accuracy.

[0494] "Order generation technology" is a technology that automatically generates order plans based on predicted demand.

[0495] "Automated execution technology" is a technology that quickly and accurately executes generated order plans.

[0496] "User confirmation and adjustment technology" is a technology that allows users to confirm and adjust order plans via their terminals as needed.

[0497] In this embodiment of the invention, the system consists of a server, a terminal, and a user. The server utilizes information gathering technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from various data sources. This enables the data to be integrated into a database and centrally managed. The server uses prediction technology to predict future demand with high accuracy based on the collected data. In this process, the server uses AI technology to perform pattern recognition within the data. Based on the predicted demand, order generation technology automatically generates an optimal order plan. This order plan adjusts the order quantity and timing, taking into account the characteristics of the facilities and products.

[0498] Users review the order plan sent from the server via their terminal and make adjustments as needed. The reviewed order plan is then automatically placed with the appropriate suppliers using automated execution technology. This reduces human error and ensures efficient and accurate ordering.

[0499] For example, if increased demand for logistics centers is predicted due to a large-scale event, the server calculates and proposes an appropriate order quantity. The user can then review this proposal via their terminal and automatically place the confirmed order. This helps prevent inventory shortages and excesses.

[0500] The generative AI model is strengthened through a feedback loop, and the server improves its prediction accuracy based on the sales results provided by the user. This cycle leads to more efficient inventory and order management.

[0501] Examples of prompts to input into a generative AI model:

[0502] Based on sales data from store A over the past year and the weather forecast for next week, predict the amount of inventory needed for the following week.

[0503] This system allows logistics centers to secure the right inventory at the right time, improving operational efficiency and flexibility.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] The server uses data collection technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from data sources. Input is raw data obtained from various data sources, and output is a record in an integrated database. In this process, ETL tools are used to centrally manage and format the data.

[0507] Step 2:

[0508] The server uses forecasting technology to predict future demand based on data recorded in the database. The input is integrated data, and the output is the result of the demand forecast. It uses a generative AI model and analyzes future trends to perform highly accurate demand forecasts through pattern recognition algorithms.

[0509] Step 3:

[0510] The server uses order generation technology to automatically generate an order plan based on demand forecast results. The input is the demand forecast result, and the output is a prototype of the order plan. Based on the algorithm, it optimizes order quantities and timing, taking into account the characteristics of the product and facility.

[0511] Step 4:

[0512] The user receives the order plan sent from the server via their terminal and reviews its contents. The input is the draft order plan sent from the server, and the output is the order plan reviewed by the user. At this stage, the user reviews the proposed content on their terminal and makes adjustments as needed.

[0513] Step 5:

[0514] The terminal uses automated execution technology to place orders with designated suppliers based on the confirmed order plan. The input is the order plan confirmed by the user, and the output is an order notification to the supplier. This process involves electronic data transmission to complete the order at the appropriate time.

[0515] Step 6:

[0516] The server utilizes feedback to collect information such as sales results and enhance the generated AI model. The input is actual supply and sales data after an order is placed, and the output is an improved predictive model. This step improves the accuracy of predictions, which can then be used for subsequent predictions and orders.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] This invention combines an automated ordering system with a user emotion recognition function, enabling the server, terminal, and user to work together to optimize ordering. Details are described below.

[0519] In this embodiment, the server uses information gathering means to collect historical sales data, weather information, seasonal information, and promotional event information, and integrates it into a database. The collected data undergoes preprocessing and is input into a demand forecasting model by forecasting means. The generated demand forecast is used to create an order plan through order generation means.

[0520] In addition, an emotion engine is built into the device, which recognizes the user's emotional state from the feedback they input. This emotion engine can also analyze emotions from the user's facial expressions and voice. When the user's emotional state is detected, the emotion engine sends that data to a server.

[0521] The server collects user sentiment data and incorporates it into the demand forecasting model to improve forecast accuracy. Furthermore, based on the data from the sentiment engine, the server can suggest adjustments to the order plan created by the order generation system. When adjustments are presented, the user reviews them on their terminal and makes changes as needed.

[0522] As a concrete example, the server predicts that ice cream demand will increase next week based on past data and weather information for a particular store. When the user reviews their order plan, the emotion engine detects the user's anxiety. Based on this, the server suggests adjustments, such as reducing the order quantity. The final plan is decided by the user after considering these adjustments.

[0523] This process allows the system to recognize users' emotional responses, enabling more realistic and efficient ordering. As a result, businesses can achieve more flexible and adaptable inventory management.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] The server collects sales data, weather data, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there. This allows the system to assess demand based on the latest information.

[0527] Step 2:

[0528] The server preprocesses the collected data, removing outliers and normalizing the data. This prepares a dataset suitable for demand forecasting.

[0529] Step 3:

[0530] The server uses prediction tools to perform demand forecasting based on pre-processed data. AI models are used to calculate best-selling products and expected sales volumes.

[0531] Step 4:

[0532] An emotion engine runs on the device and recognizes the user's emotions through facial expression and voice analysis. For example, it analyzes the emotions a user expresses while looking at the display.

[0533] Step 5:

[0534] The device retrieves the user's emotional data from the emotion engine and sends it to the server. This prepares the system for the user's emotions to be reflected in the ordering process.

[0535] Step 6:

[0536] The server incorporates emotional data into demand forecast information and adjusts the forecasting model. This generates an order plan that takes emotional bias into account.

[0537] Step 7:

[0538] The server uses an order generation method that takes sentiment data into account to formulate the optimal order plan and sends it to the terminal. The user reviews the order plan on the terminal and makes adjustments as needed.

[0539] Step 8:

[0540] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. The system then sends the order details to the designated manufacturer or wholesaler for confirmation.

[0541] (Example 2)

[0542] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0543] Conventional automated ordering systems based demand forecasts on quantitative data such as past sales data and weather information. However, because they did not take into account user emotions or intuitive judgments, discrepancies sometimes arose between actual demand and forecasts. This resulted in problems such as inventory shortages or surpluses and lost sales opportunities.

[0544] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0545] In this invention, the server includes data acquisition means for collecting past sales information, weather information, seasonal information, and sales promotion event information; estimation means for estimating demand using the collected information; plan generation means for automatically formulating an order plan based on the estimated demand; sentiment analysis means for recognizing user sentiment information and reflecting the recognition results in the demand forecast; and integrated management means for integrating data processing for the entire system. This enables more accurate demand forecasting and flexible order planning that takes into account user sentiment and intuition.

[0546] "Data acquisition means" refers to devices or functions for collecting past sales information, weather information, seasonal information, and sales promotion event information.

[0547] An "estimation tool" refers to a device or function used to calculate or predict future demand based on collected information.

[0548] A "plan generation means" refers to a device or function that automatically creates an optimal ordering plan, taking estimated demand into consideration.

[0549] "Sentiment analysis tools" refer to devices or functions that recognize and analyze users' emotional information to reflect it in demand forecasting.

[0550] An "integrated management system" refers to a device or function for centrally managing and controlling data processing across the entire system.

[0551] The embodiments for carrying out the present invention are described below.

[0552] In this system, the server utilizes data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. The server uses high-performance database servers and cloud services, for example, to acquire weather data via external APIs and collect historical sales information from existing sales management systems. This allows the necessary information to be integrated into the database.

[0553] Next, the server processes the collected information using estimation methods and performs demand forecasting using a generative AI model. Here, TensorFlow and PyTorch are used as machine learning libraries to build a model for analyzing demand patterns.

[0554] Subsequently, the server uses a plan generation mechanism to automatically create an ordering plan based on estimated demand. This plans the appropriate order quantity and timing for the demand, enabling the system to achieve flexible inventory management.

[0555] Furthermore, the user's device acquires emotional information through emotion analysis. This process uses cameras and microphones to capture facial expressions and voice data, which are then analyzed by an emotion recognition AI model. The analyzed emotional data is sent to a server and incorporated into demand forecasts to improve their accuracy.

[0556] Ultimately, the server utilizes integrated management tools to centrally manage all data processing and sends the optimal order plan to the terminal. Users can then review the presented order plan and make modifications as needed.

[0557] As a concrete example, the server predicts that demand for ice cream will increase during the summer peak season based on past sales data and weather information for a particular store. When a terminal detects anxiety while the user is reviewing their order plan, the server suggests adjusting the order quantity to be more modest. This process allows businesses to respond more flexibly and adaptably.

[0558] An example of a prompt to input into the generating AI model is, "Propose an optimal order plan that takes into account user sentiment and sales forecast data." This prompt will allow the system to improve the order plan by incorporating user sentiment.

[0559] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0560] Step 1:

[0561] The server uses data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. Specifically, it obtains weather information from an external API and receives sales data from the sales management system. In this step, the acquired data is integrated into a database and converted into a format for use in the next process. The input is data obtained from various sources, and the output is an integrated dataset.

[0562] Step 2:

[0563] The server uses estimation methods to predict future demand using the collected information. Here, a generative AI model is utilized, and TensorFlow or PyTorch is used to train it on past data patterns. The input is an integrated dataset, and the output is the predicted value from the demand forecasting model. In this step, the data is preprocessed and converted into the format required by the model.

[0564] Step 3:

[0565] The server uses a planning generation mechanism to create an optimal ordering plan based on demand forecasts. This planning process employs an algorithm that generates ordering suggestions for the predicted demand. The input is the demand forecast result, and the output is the details of the ordering plan. This step also considers inventory levels and supply chain information.

[0566] Step 4:

[0567] The device uses emotion analysis tools to recognize the user's emotions, collecting emotional information through facial expressions and voice. The device acquires data using a facial recognition camera and microphone, and analyzes it using emotion analysis AI. The input is the user's facial expressions and voice, and the output is the recognized emotional state.

[0568] Step 5:

[0569] The device sends the acquired sentiment information to the server. The server receives this data and incorporates it into the demand forecasting model to improve the accuracy of the forecast. The input is the user's sentiment information, and the output is a new forecast value from the improved demand forecasting model.

[0570] Step 6:

[0571] The server utilizes integrated management tools to generate proposed adjustments to the order plan and send them to the terminal. These adjustments take into account sentiment information and market trends. The input is the latest demand forecast and sentiment information, and the output is the adjusted order plan presented to the user.

[0572] Step 7:

[0573] The user reviews the displayed order plan via their terminal and makes modifications as needed. They then finalize the order details and send that information to the server. The input is the adjusted order plan, and the output is the confirmed order plan after user review. This ensures optimized ordering.

[0574] (Application Example 2)

[0575] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0576] Conventional automated ordering systems rely primarily on data-driven mathematical models for demand forecasting, making it difficult to reflect subjective user emotions and anxieties. This can lead to a lack of adaptability to actual sales conditions and market fluctuations, potentially resulting in excess or shortages of inventory. Furthermore, the loss of sales opportunities due to mismatches between supply and demand remains a challenge.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes information gathering means for collecting past sales data, environmental information, duration information, and sales promotion activity information; estimation means for predicting demand using the data collected by the information gathering means; plan generation means for automatically generating an order plan based on the demand forecast by the estimation means; sentiment analysis means for collecting and analyzing the user's sentiment information; sentiment adjustment means for adjusting the order plan based on the sentiment information analyzed by the sentiment analysis means; and automatic execution means for executing the adjusted order plan. This improves the accuracy of demand forecasting and enables flexible and adaptable inventory management that reflects sentiment information.

[0579] "Information gathering means" refers to technologies or devices for collecting past sales data, environmental information, duration information, and sales promotion activity information.

[0580] "Estimation methods" refer to algorithms and functions that utilize collected data to predict future demand.

[0581] "Plan generation means" refers to a technology or system that automatically creates an ordering plan based on demand forecasts obtained by estimation means.

[0582] "Emotional analysis means" refers to the functions of software or hardware used to collect and analyze user emotional information.

[0583] "Emotional adjustment means" refers to functions or methods for revising or adjusting ordering plans using emotional information obtained through emotional analysis means.

[0584] "Automated execution means" refers to automated processes or devices for executing planned orders.

[0585] The system for realizing this invention involves the collaborative operation of a server, terminals, and users. The server uses information gathering means to collect historical sales data, environmental information, duration information, and sales promotion activity information. Database software such as MySQL or Firebase is used for data storage and management.

[0586] The collected data is analyzed by estimation tools, and future demand is predicted using demand forecasting models such as TensorFlow and PyTorch. The predicted data is then supplied to a planning generation tool to automatically create an order plan.

[0587] Meanwhile, the device's built-in emotion analysis system collects and analyzes the user's emotional information, specifically facial expressions and voice tone, in real time. This analysis utilizes the image recognition library OpenCV and the speech analysis API Google Cloud Speech-to-Text. When a user uses the device to review a plan, their emotions are analyzed, and this data is sent to the server.

[0588] The server adjusts the order plan based on emotional information via an emotion adjustment mechanism. This function generates an order plan that reflects emotional information, enabling more appropriate ordering that is closer to the actual situation. Finally, the adjusted plan is executed by an automated execution mechanism. For example, if a weather forecast predicts an increase in beverage demand, an order plan is created based on that forecast. If the user experiences anxiety at that time, the plan is adjusted based on the emotional information.

[0589] An example of a prompt might be: "Based on today's customer traffic, sales forecast, and what I've told you, please suggest one option that seems best. If I look unsure or negative, please also consider alternative options."

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] The server collects historical sales data, environmental information, duration information, and sales promotion activity information using various data collection methods. Inputs are from diverse data sources (databases, web APIs, etc.), and output is an integrated dataset. This dataset is preprocessed to feed into a predictive model. Data processing includes imputation of missing values, data normalization, and aggregation on a time-unit basis.

[0593] Step 2:

[0594] The server analyzes collected datasets using estimation methods to predict future demand. The input is pre-processed integrated data, and the output is the demand forecast result. The data calculations utilize a machine learning model using TensorFlow, and parameter tuning is performed to improve prediction accuracy.

[0595] Step 3:

[0596] The server automatically generates an order plan based on demand forecasts using a plan generation mechanism. The input is the demand forecast result, and the output is the initial order plan. Specifically, a logic is executed to calculate the appropriate order quantity and timing based on the sales forecast.

[0597] Step 4:

[0598] The device's built-in emotion analysis system analyzes emotional information collected from the user in real time. Input is the user's facial expression images and audio data, and output is the analyzed emotional state. OpenCV is used to analyze facial expressions, and Google Cloud Speech-to-Text is used to evaluate the emotion of the audio.

[0599] Step 5:

[0600] The server adjusts the order plan based on the analyzed user's emotional information via an emotion adjustment mechanism. The input is the initial order plan and analyzed emotional data, and the output is the adjusted order plan. Specifically, an algorithm is applied that increases or decreases the order quantity based on the user's emotions.

[0601] Step 6:

[0602] The user reviews the adjusted order plan on their terminal and approves or modifies it as needed, performing a final check as necessary. The input is the adjusted order plan, and the output is the order plan finalized by the user. Specifically, the user reviews the details of the order plan via the user interface and reflects any changes.

[0603] Step 7:

[0604] The server executes orders based on the finalized order plan using automated execution mechanisms. The input is the finalized order plan, and the output is the execution result of that order. Specifically, it sends order commands to the execution system and monitors the status of their implementation.

[0605] 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.

[0606] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0607] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0608] [Fourth Embodiment]

[0609] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0610] 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.

[0611] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0612] 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.

[0613] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0614] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0615] 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.

[0616] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0617] 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.

[0618] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0619] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0620] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0621] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] This invention relates to an automated ordering system in which a server, terminal, and user cooperate to improve the efficiency of ordering. Specific embodiments thereof will be described below.

[0623] First, the server uses information gathering tools to acquire historical sales data, weather information, seasonal information, and promotional event information from various data sources. The data is integrated and centrally recorded in a database. The database records the characteristics of each store and product, enabling analysis based on this information.

[0624] Next, the server applies prediction methods and uses the collected data to forecast future demand. This prediction model utilizes AI technology to perform highly accurate demand forecasts based on pattern recognition within the data. The demand forecast results are then used in subsequent processes.

[0625] Furthermore, the server generates an optimal order plan based on the demand forecast results using an order generation mechanism. This plan is optimized considering the characteristics of each store and product. It also includes adjustments to order quantity and timing. The generated order plan is sent to the terminal in a format that the user can review and correct.

[0626] The terminal is equipped with an automated execution mechanism and electronically places orders with manufacturers and wholesalers based on order proposals confirmed by the user. This reduces errors caused by manual input and achieves efficient and accurate ordering.

[0627] As a concrete example, in a retail store, if the server predicts that high temperatures will continue using past ice cream sales data and the weather forecast for the weekend, the AI ​​model will determine that demand for soft drinks will increase. As a result, the server generates an order plan suggesting twice the normal order quantity, which the terminal receives. The user reviews the order plan and makes adjustments if necessary. After confirmation, the terminal automatically places the order.

[0628] A feedback loop is also included in this system; based on the sales results provided by the user, the server enhances the generated AI model and improves prediction accuracy. This cycle leads to increased efficiency in both inventory management and order management.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The server collects historical sales data, weather information, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there.

[0632] Step 2:

[0633] The server preprocesses the data stored in the database, including imputing missing values ​​and correcting outliers. This formats the data so that it is suitable as input for the demand forecasting model.

[0634] Step 3:

[0635] The server applies a generative AI model as a prediction tool and performs demand forecasting based on pre-processed data. The forecast results include multiple demand scenarios that take various external factors into account.

[0636] Step 4:

[0637] The server uses the prediction results to create an optimal order generation method that takes into account the characteristics of the store and the product. This is where the order quantity and timing are optimized.

[0638] Step 5:

[0639] The terminal receives order plans from the server and presents the information through an interface that allows the user to review and adjust the plans. Users can modify the proposals based on their own insights into changing demand.

[0640] Step 6:

[0641] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. Specifically, the terminal electronically sends the order information to the manufacturer or wholesaler.

[0642] Step 7:

[0643] Users evaluate sales results and inventory status, and provide this information as feedback to the server via their terminals. The server uses this feedback to retrain the AI ​​model and improve the accuracy of future demand forecasts.

[0644] (Example 1)

[0645] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] In today's business environment, rapid and accurate inventory management and ordering are essential, with a particular challenge in responding quickly to fluctuations in demand. Furthermore, traditional manual ordering methods are prone to human error, making efficient ordering difficult. Improving the accuracy of demand forecasting and optimizing inventory management are crucial factors directly linked to increased profits. Therefore, there is a need for methods that enable more accurate demand forecasting and efficiently automate ordering.

[0647] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0648] In this invention, the server includes means for collecting historical sales data, weather information, seasonal information, and promotional event information; means for integrating and storing the collected data; and means for applying a generated AI model using the integrated data to forecast demand. This makes it possible to perform highly accurate demand forecasting, automatically generate optimized order plans, and streamline ordering operations.

[0649] "Historical sales data" refers to records of sales of goods and services in previous periods, and serves as the basis for demand forecasting.

[0650] "Weather information" refers to information about weather conditions such as temperature, precipitation, and wind speed, and is one of the factors that influence demand.

[0651] "Seasonal information" refers to information that influences demand fluctuations associated with seasonal changes, and is data that is reflected in forecasting models for a specific season.

[0652] "Sales promotion event information" refers to information about sales promotion activities and events, and is data used to account for temporary fluctuations in demand.

[0653] "Information gathering means" refers to a method or apparatus for acquiring and integrating necessary information from various data sources.

[0654] "Means of integration" refers to a method or apparatus for aggregating acquired data in an appropriate format and storing it in a database.

[0655] "Means for applying generative AI models to predict demand" refers to a method or apparatus that utilizes artificial intelligence technology to accurately predict future demand from collected data.

[0656] "Means for optimizing and automatically generating order plans" refers to a method or apparatus that automatically creates an order plan by calculating the optimal order quantity and timing based on predicted demand.

[0657] A "terminal" is a device used to receive order plans sent from a server and for users to review and adjust them.

[0658] "Means of automatic execution" refers to a method or apparatus for electronically placing an order based on a confirmed order plan.

[0659] "Means of collecting feedback to improve prediction accuracy" refers to methods or devices for continuously improving the performance of a prediction model based on actual sales results.

[0660] This invention relates to a system for streamlining automated ordering, in which a server, terminals, and users cooperate to operate the entire system. The server is primarily responsible for collecting information, performing forecasts, and generating order plans, while the terminals provide an interface with the user and assist in managing the executed orders.

[0661] The server acquires historical sales data, weather information, seasonal information, and promotional event information from various data sources through information gathering means. This utilizes an integrated database system, such as a data management platform like PostgreSQL. The data is centrally recorded and integrated, enabling efficient analysis.

[0662] Furthermore, the server incorporates generative AI models to achieve highly accurate demand forecasting. Specifically, it can utilize machine learning libraries such as Python's scikit-learn and TensorFlow. This allows it to predict future demand through pattern recognition within the data and generate optimized ordering plans. The ordering plans are tailored to each store and product, providing the optimal combination of order quantity and timing.

[0663] The terminal receives order plans sent from the server and provides a user interface for the user to review and adjust as needed. After reviewing and adjusting the order plan based on the provided information, the user places the order electronically using an automated execution mechanism. This minimizes ordering errors and enables fast and accurate ordering.

[0664] As a concrete example, in a retail store, if the server uses past beverage sales data and the weather forecast for the weekend to predict continued high temperatures, the generating AI model will determine that demand for beverages will increase. As a result, the server generates an order plan suggesting twice the normal order quantity and sends it to the terminal. The user reviews the order plan and makes any necessary changes, after which the terminal automatically places the order.

[0665] Examples of prompt statements include the following:

[0666] "Based on this weekend's weather forecast and data from the past three years, please forecast next week's beverage demand and calculate the optimal order quantity."

[0667] "Consider the impact of the next promotional event, update the predictive model using past promotional event data, and propose an ordering plan."

[0668] This system enables inventory optimization and streamlined order management, leading to improved business flexibility and responsiveness.

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] The server acquires historical sales data, weather information, seasonal information, and promotional event information through various data collection methods. This data serves as input. The collected data undergoes integration processing and is stored in a PostgreSQL database. Specifically, it may extract data from various APIs, perform data cleansing and format conversion, and generate integrated data. As a result, an integrated database is output.

[0672] Step 2:

[0673] The server applies a generative AI model using integrated data to perform demand forecasting. The input here is data from an integrated database. In this process, machine learning libraries such as Python's scikit-learn and TensorFlow are used to extract features from the data and train the predictive model. Specific operations include creating a training dataset and executing the model training process. The output is a forecast of future demand.

[0674] Step 3:

[0675] The server optimizes and automatically generates an order plan based on demand forecast data. The input is the demand forecast result from step 2. At this stage, the optimization algorithm is executed, taking into account the characteristics of the products and the conditions of each store. Specifically, the data is manipulated using the Python Pandas library to calculate the optimal order quantity and timing. The output is the optimized order plan.

[0676] Step 4:

[0677] The server sends the generated order plan to the terminal. The input to this process is the order plan obtained in step 3. Specifically, the server sends the order data to the terminal using the HTTP protocol. The terminal receives the order plan and displays it as output.

[0678] Step 5:

[0679] The user reviews and adjusts the order plan sent via the terminal as needed. In this step, the user interacts with the order plan using a GUI on the terminal. The input is the order plan displayed in step 4, and the output is the order plan reviewed or adjusted by the user. Specific actions include making fine adjustments using sliders and text fields.

[0680] Step 6:

[0681] The terminal places an order using an automated execution mechanism based on the confirmed order plan. The input is the confirmed order plan from step 5. The order data is automatically transmitted to the supplier via the EDI (Electronic Data Interchange) system. The specific process involves electronically transmitting the order information using network communication, and the output confirms the completion of the order.

[0682] Step 7:

[0683] Users send sales results to the server as feedback. This input includes actual sales data. The server collects the sales results and continuously updates the generated AI model. This improves the model's prediction accuracy. Specifically, it requires periodically sending sales data to the server's API endpoint. The output provides data to improve the model's accuracy.

[0684] (Application Example 1)

[0685] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0686] There is a need to improve the efficiency of inventory management in logistics centers and to enable accurate ordering based on demand forecasts. Traditional methods have problems such as excess inventory and stockouts, making efficient operation difficult. Furthermore, manual ordering is prone to errors and is time-consuming, which leads to increased costs and workload.

[0687] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0688] In this invention, the server includes a data collection technology that collects past supply data, environmental information, timing information, and sales promotion activity information; a forecasting technology that predicts demand using the data collected by the data collection technology; an order generation technology that automatically generates an order plan based on the demand forecast by the forecasting technology; and a user confirmation and adjustment technology that allows the order plan to be confirmed and adjusted via a user terminal. This enables efficient inventory management at the logistics center and accurate ordering at the appropriate time.

[0689] "Data collection technology" refers to technologies for efficiently collecting historical supply data, environmental information, timing information, and sales promotion activity information.

[0690] "Predictive technology" is a technology that uses collected data to predict future demand with high accuracy.

[0691] "Order generation technology" is a technology that automatically generates order plans based on predicted demand.

[0692] "Automated execution technology" is a technology that quickly and accurately executes generated order plans.

[0693] "User confirmation and adjustment technology" is a technology that allows users to confirm and adjust order plans via their terminals as needed.

[0694] In this embodiment of the invention, the system consists of a server, a terminal, and a user. The server utilizes information gathering technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from various data sources. This enables the data to be integrated into a database and centrally managed. The server uses prediction technology to predict future demand with high accuracy based on the collected data. In this process, the server uses AI technology to perform pattern recognition within the data. Based on the predicted demand, order generation technology automatically generates an optimal order plan. This order plan adjusts the order quantity and timing, taking into account the characteristics of the facilities and products.

[0695] Users review the order plan sent from the server via their terminal and make adjustments as needed. The reviewed order plan is then automatically placed with the appropriate suppliers using automated execution technology. This reduces human error and ensures efficient and accurate ordering.

[0696] For example, if increased demand for logistics centers is predicted due to a large-scale event, the server calculates and proposes an appropriate order quantity. The user can then review this proposal via their terminal and automatically place the confirmed order. This helps prevent inventory shortages and excesses.

[0697] The generative AI model is strengthened through a feedback loop, and the server improves its prediction accuracy based on the sales results provided by the user. This cycle leads to more efficient inventory and order management.

[0698] Examples of prompts to input into a generative AI model:

[0699] Based on sales data from store A over the past year and the weather forecast for next week, predict the amount of inventory needed for the following week.

[0700] This system allows logistics centers to secure the right inventory at the right time, improving operational efficiency and flexibility.

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The server uses data collection technology to acquire historical supply data, environmental information, timing information, and sales promotion activity information from data sources. Input is raw data obtained from various data sources, and output is a record in an integrated database. In this process, ETL tools are used to centrally manage and format the data.

[0704] Step 2:

[0705] The server uses forecasting technology to predict future demand based on data recorded in the database. The input is integrated data, and the output is the result of the demand forecast. It uses a generative AI model and analyzes future trends to perform highly accurate demand forecasts through pattern recognition algorithms.

[0706] Step 3:

[0707] The server uses order generation technology to automatically generate an order plan based on demand forecast results. The input is the demand forecast result, and the output is a prototype of the order plan. Based on the algorithm, it optimizes order quantities and timing, taking into account the characteristics of the product and facility.

[0708] Step 4:

[0709] The user receives the order plan sent from the server via their terminal and reviews its contents. The input is the draft order plan sent from the server, and the output is the order plan reviewed by the user. At this stage, the user reviews the proposed content on their terminal and makes adjustments as needed.

[0710] Step 5:

[0711] The terminal uses automated execution technology to place orders with designated suppliers based on the confirmed order plan. The input is the order plan confirmed by the user, and the output is an order notification to the supplier. This process involves electronic data transmission to complete the order at the appropriate time.

[0712] Step 6:

[0713] The server utilizes feedback to collect information such as sales results and enhance the generated AI model. The input is actual supply and sales data after an order is placed, and the output is an improved predictive model. This step improves the accuracy of predictions, which can then be used for subsequent predictions and orders.

[0714] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0715] This invention combines an automated ordering system with a user emotion recognition function, enabling the server, terminal, and user to work together to optimize ordering. Details are described below.

[0716] In this embodiment, the server uses information gathering means to collect historical sales data, weather information, seasonal information, and promotional event information, and integrates it into a database. The collected data undergoes preprocessing and is input into a demand forecasting model by forecasting means. The generated demand forecast is used to create an order plan through order generation means.

[0717] In addition, an emotion engine is built into the device, which recognizes the user's emotional state from the feedback they input. This emotion engine can also analyze emotions from the user's facial expressions and voice. When the user's emotional state is detected, the emotion engine sends that data to a server.

[0718] The server collects user sentiment data and incorporates it into the demand forecasting model to improve forecast accuracy. Furthermore, based on the data from the sentiment engine, the server can suggest adjustments to the order plan created by the order generation system. When adjustments are presented, the user reviews them on their terminal and makes changes as needed.

[0719] As a concrete example, the server predicts that ice cream demand will increase next week based on past data and weather information for a particular store. When the user reviews their order plan, the emotion engine detects the user's anxiety. Based on this, the server suggests adjustments, such as reducing the order quantity. The final plan is decided by the user after considering these adjustments.

[0720] This process allows the system to recognize users' emotional responses, enabling more realistic and efficient ordering. As a result, businesses can achieve more flexible and adaptable inventory management.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The server collects sales data, weather data, seasonal information, and promotional event information from various data sources, integrates them into a database, and stores them there. This allows the system to assess demand based on the latest information.

[0724] Step 2:

[0725] The server preprocesses the collected data, removing outliers and normalizing the data. This prepares a dataset suitable for demand forecasting.

[0726] Step 3:

[0727] The server uses prediction tools to perform demand forecasting based on pre-processed data. AI models are used to calculate best-selling products and expected sales volumes.

[0728] Step 4:

[0729] An emotion engine runs on the device and recognizes the user's emotions through facial expression and voice analysis. For example, it analyzes the emotions a user expresses while looking at the display.

[0730] Step 5:

[0731] The device retrieves the user's emotional data from the emotion engine and sends it to the server. This prepares the system for the user's emotions to be reflected in the ordering process.

[0732] Step 6:

[0733] The server incorporates emotional data into demand forecast information and adjusts the forecasting model. This generates an order plan that takes emotional bias into account.

[0734] Step 7:

[0735] The server uses an order generation method that takes sentiment data into account to formulate the optimal order plan and sends it to the terminal. The user reviews the order plan on the terminal and makes adjustments as needed.

[0736] Step 8:

[0737] Based on the order plan confirmed by the user, the terminal executes the order using an automated mechanism. The system then sends the order details to the designated manufacturer or wholesaler for confirmation.

[0738] (Example 2)

[0739] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0740] Conventional automated ordering systems based demand forecasts on quantitative data such as past sales data and weather information. However, because they did not take into account user emotions or intuitive judgments, discrepancies sometimes arose between actual demand and forecasts. This resulted in problems such as inventory shortages or surpluses and lost sales opportunities.

[0741] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0742] In this invention, the server includes data acquisition means for collecting past sales information, weather information, seasonal information, and sales promotion event information; estimation means for estimating demand using the collected information; plan generation means for automatically formulating an order plan based on the estimated demand; sentiment analysis means for recognizing user sentiment information and reflecting the recognition results in the demand forecast; and integrated management means for integrating data processing for the entire system. This enables more accurate demand forecasting and flexible order planning that takes into account user sentiment and intuition.

[0743] "Data acquisition means" refers to devices or functions for collecting past sales information, weather information, seasonal information, and sales promotion event information.

[0744] An "estimation tool" refers to a device or function used to calculate or predict future demand based on collected information.

[0745] A "plan generation means" refers to a device or function that automatically creates an optimal ordering plan, taking estimated demand into consideration.

[0746] "Sentiment analysis tools" refer to devices or functions that recognize and analyze users' emotional information to reflect it in demand forecasting.

[0747] An "integrated management system" refers to a device or function for centrally managing and controlling data processing across the entire system.

[0748] The embodiments for carrying out the present invention are described below.

[0749] In this system, the server utilizes data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. The server uses high-performance database servers and cloud services, for example, to acquire weather data via external APIs and collect historical sales information from existing sales management systems. This allows the necessary information to be integrated into the database.

[0750] Next, the server processes the collected information using estimation methods and performs demand forecasting using a generative AI model. Here, TensorFlow and PyTorch are used as machine learning libraries to build a model for analyzing demand patterns.

[0751] Subsequently, the server uses a plan generation mechanism to automatically create an ordering plan based on estimated demand. This plans the appropriate order quantity and timing for the demand, enabling the system to achieve flexible inventory management.

[0752] Furthermore, the user's device acquires emotional information through emotion analysis. This process uses cameras and microphones to capture facial expressions and voice data, which are then analyzed by an emotion recognition AI model. The analyzed emotional data is sent to a server and incorporated into demand forecasts to improve their accuracy.

[0753] Ultimately, the server utilizes integrated management tools to centrally manage all data processing and sends the optimal order plan to the terminal. Users can then review the presented order plan and make modifications as needed.

[0754] As a concrete example, the server predicts that demand for ice cream will increase during the summer peak season based on past sales data and weather information for a particular store. When a terminal detects anxiety while the user is reviewing their order plan, the server suggests adjusting the order quantity to be more modest. This process allows businesses to respond more flexibly and adaptably.

[0755] An example of a prompt to input into the generating AI model is, "Propose an optimal order plan that takes into account user sentiment and sales forecast data." This prompt will allow the system to improve the order plan by incorporating user sentiment.

[0756] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0757] Step 1:

[0758] The server uses data acquisition methods to collect historical sales information, weather information, seasonal information, and sales promotion event information. Specifically, it obtains weather information from an external API and receives sales data from the sales management system. In this step, the acquired data is integrated into a database and converted into a format for use in the next process. The input is data obtained from various sources, and the output is an integrated dataset.

[0759] Step 2:

[0760] The server uses estimation methods to predict future demand using the collected information. Here, a generative AI model is utilized, and TensorFlow or PyTorch is used to train it on past data patterns. The input is an integrated dataset, and the output is the predicted value from the demand forecasting model. In this step, the data is preprocessed and converted into the format required by the model.

[0761] Step 3:

[0762] The server uses a planning generation mechanism to create an optimal ordering plan based on demand forecasts. This planning process employs an algorithm that generates ordering suggestions for the predicted demand. The input is the demand forecast result, and the output is the details of the ordering plan. This step also considers inventory levels and supply chain information.

[0763] Step 4:

[0764] The device uses emotion analysis tools to recognize the user's emotions, collecting emotional information through facial expressions and voice. The device acquires data using a facial recognition camera and microphone, and analyzes it using emotion analysis AI. The input is the user's facial expressions and voice, and the output is the recognized emotional state.

[0765] Step 5:

[0766] The device sends the acquired sentiment information to the server. The server receives this data and incorporates it into the demand forecasting model to improve the accuracy of the forecast. The input is the user's sentiment information, and the output is a new forecast value from the improved demand forecasting model.

[0767] Step 6:

[0768] The server utilizes integrated management tools to generate proposed adjustments to the order plan and send them to the terminal. These adjustments take into account sentiment information and market trends. The input is the latest demand forecast and sentiment information, and the output is the adjusted order plan presented to the user.

[0769] Step 7:

[0770] The user reviews the displayed order plan via their terminal and makes modifications as needed. They then finalize the order details and send that information to the server. The input is the adjusted order plan, and the output is the confirmed order plan after user review. This ensures optimized ordering.

[0771] (Application Example 2)

[0772] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] Conventional automated ordering systems rely primarily on data-driven mathematical models for demand forecasting, making it difficult to reflect subjective user emotions and anxieties. This can lead to a lack of adaptability to actual sales conditions and market fluctuations, potentially resulting in excess or shortages of inventory. Furthermore, the loss of sales opportunities due to mismatches between supply and demand remains a challenge.

[0774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0775] In this invention, the server includes information gathering means for collecting past sales data, environmental information, duration information, and sales promotion activity information; estimation means for predicting demand using the data collected by the information gathering means; plan generation means for automatically generating an order plan based on the demand forecast by the estimation means; sentiment analysis means for collecting and analyzing the user's sentiment information; sentiment adjustment means for adjusting the order plan based on the sentiment information analyzed by the sentiment analysis means; and automatic execution means for executing the adjusted order plan. This improves the accuracy of demand forecasting and enables flexible and adaptable inventory management that reflects sentiment information.

[0776] "Information gathering means" refers to technologies or devices for collecting past sales data, environmental information, duration information, and sales promotion activity information.

[0777] "Estimation methods" refer to algorithms and functions that utilize collected data to predict future demand.

[0778] "Plan generation means" refers to a technology or system that automatically creates an ordering plan based on demand forecasts obtained by estimation means.

[0779] "Emotional analysis means" refers to the functions of software or hardware used to collect and analyze user emotional information.

[0780] "Emotional adjustment means" refers to functions or methods for revising or adjusting ordering plans using emotional information obtained through emotional analysis means.

[0781] "Automated execution means" refers to automated processes or devices for executing planned orders.

[0782] The system for realizing this invention involves the collaborative operation of a server, terminals, and users. The server uses information gathering means to collect historical sales data, environmental information, duration information, and sales promotion activity information. Database software such as MySQL or Firebase is used for data storage and management.

[0783] The collected data is analyzed by estimation tools, and future demand is predicted using demand forecasting models such as TensorFlow and PyTorch. The predicted data is then supplied to a planning generation tool to automatically create an order plan.

[0784] Meanwhile, the device's built-in emotion analysis system collects and analyzes the user's emotional information, specifically facial expressions and voice tone, in real time. This analysis utilizes the image recognition library OpenCV and the speech analysis API Google Cloud Speech-to-Text. When a user uses the device to review a plan, their emotions are analyzed, and this data is sent to the server.

[0785] The server adjusts the order plan based on emotional information via an emotion adjustment mechanism. This function generates an order plan that reflects emotional information, enabling more appropriate ordering that is closer to the actual situation. Finally, the adjusted plan is executed by an automated execution mechanism. For example, if a weather forecast predicts an increase in beverage demand, an order plan is created based on that forecast. If the user experiences anxiety at that time, the plan is adjusted based on the emotional information.

[0786] An example of a prompt might be: "Based on today's customer traffic, sales forecast, and what I've told you, please suggest one option that seems best. If I look unsure or negative, please also consider alternative options."

[0787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0788] Step 1:

[0789] The server collects historical sales data, environmental information, duration information, and sales promotion activity information using various data collection methods. Inputs are from diverse data sources (databases, web APIs, etc.), and output is an integrated dataset. This dataset is preprocessed to feed into a predictive model. Data processing includes imputation of missing values, data normalization, and aggregation on a time-unit basis.

[0790] Step 2:

[0791] The server analyzes collected datasets using estimation methods to predict future demand. The input is pre-processed integrated data, and the output is the demand forecast result. The data calculations utilize a machine learning model using TensorFlow, and parameter tuning is performed to improve prediction accuracy.

[0792] Step 3:

[0793] The server automatically generates an order plan based on demand forecasts using a plan generation mechanism. The input is the demand forecast result, and the output is the initial order plan. Specifically, a logic is executed to calculate the appropriate order quantity and timing based on the sales forecast.

[0794] Step 4:

[0795] The device's built-in emotion analysis system analyzes emotional information collected from the user in real time. Input is the user's facial expression images and audio data, and output is the analyzed emotional state. OpenCV is used to analyze facial expressions, and Google Cloud Speech-to-Text is used to evaluate the emotion of the audio.

[0796] Step 5:

[0797] The server adjusts the order plan based on the analyzed user's emotional information via an emotion adjustment mechanism. The input is the initial order plan and analyzed emotional data, and the output is the adjusted order plan. Specifically, an algorithm is applied that increases or decreases the order quantity based on the user's emotions.

[0798] Step 6:

[0799] The user reviews the adjusted order plan on their terminal and approves or modifies it as needed, performing a final check as necessary. The input is the adjusted order plan, and the output is the order plan finalized by the user. Specifically, the user reviews the details of the order plan via the user interface and reflects any changes.

[0800] Step 7:

[0801] The server executes orders based on the finalized order plan using automated execution mechanisms. The input is the finalized order plan, and the output is the execution result of that order. Specifically, it sends order commands to the execution system and monitors the status of their implementation.

[0802] 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.

[0803] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0804] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0805] 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.

[0806] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0807] 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.

[0808] 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.

[0809] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0810] 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."

[0811] 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.

[0812] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0813] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0822] 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.

[0823] The following is further disclosed regarding the embodiments described above.

[0824] (Claim 1)

[0825] Information gathering means for collecting past sales data, weather information, seasonal information and promotional event information,

[0826] A forecasting means that uses the data collected by the aforementioned collection means to predict demand,

[0827] An order generation means that automatically generates an order plan based on the demand forecast by the forecasting means,

[0828] An automatic execution means for executing the order plan generated by the order generation means,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, wherein the order generation means adjusts the order quantity and timing of the order taking into consideration the characteristics of the store or product.

[0832] (Claim 3)

[0833] The system according to claim 1, wherein the automated execution means places an order based on an order plan confirmed by the user.

[0834] "Example 1"

[0835] (Claim 1)

[0836] A means of collecting past sales data, weather information, seasonal information, and promotional event information,

[0837] Means for integrating and storing the aforementioned collected data,

[0838] A means for applying a generative AI model using the aforementioned integrated data to predict demand,

[0839] A means for optimizing and automatically generating an order plan based on the aforementioned predicted demand,

[0840] A means of sending the generated order plan to the terminal and prompting the user for confirmation,

[0841] A means of automatically executing orders based on order plans confirmed and adjusted by the user,

[0842] A means for collecting sales results as feedback and improving the prediction accuracy of the generated AI model,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, wherein the ordering plan adjusts the order quantity and ordering timing taking into account the characteristics of the store or product.

[0846] (Claim 3)

[0847] The system according to claim 1, wherein the means for automatically executing an order places an order based on an order plan confirmed by the user.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] Collection technology for collecting past supply data, environmental information, timing information, and sales promotion activity information,

[0851] A forecasting technique that uses the data collected by the aforementioned collection technique to predict demand,

[0852] An order generation technology that automatically generates an order plan based on the demand forecast using the aforementioned forecasting technology,

[0853] An automated execution technology that executes the order plan generated by the order generation technology,

[0854] User confirmation and adjustment technology that allows order plans to be confirmed and adjusted via the user terminal,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, wherein the order generation technology adjusts the order quantity and order timing taking into consideration the characteristics of the facility or product.

[0858] (Claim 3)

[0859] The system according to claim 1, wherein the automated execution technology places an order based on an order plan confirmed and adjusted by the user.

[0860] "Example 2 of combining an emotion engine"

[0861] (Claim 1)

[0862] A data acquisition method for collecting past sales information, weather information, seasonal information, and sales promotion event information,

[0863] Estimation methods for estimating demand using collected information,

[0864] A plan generation means that automatically formulates an ordering plan based on estimated demand,

[0865] A sentiment analysis method that recognizes user sentiment information and reflects the recognition results in demand forecasting,

[0866] An integrated management means that integrates data processing across the entire system,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, wherein the plan generation means adjusts the order quantity and order timing taking into consideration the characteristics of a specific industry or product category.

[0870] (Claim 3)

[0871] The system according to claim 1, wherein the integrated management means processes an order based on an order plan revised by the user.

[0872] "Application example 2 when combining with an emotional engine"

[0873] (Claim 1)

[0874] Information gathering means for collecting past sales data, environmental information, duration information, and sales promotion activity information,

[0875] An estimation means for predicting demand using data collected by the aforementioned information gathering means,

[0876] A plan generation means that automatically generates an order plan based on the demand forecast by the estimation means,

[0877] A sentiment analysis means for collecting and analyzing the user's sentiment information,

[0878] An emotion adjustment means that adjusts the order plan based on the emotion information analyzed by the emotion analysis means,

[0879] Automatic execution means for executing the adjusted order plan,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, wherein the plan generation means adjusts the order quantity and order timing taking into account the characteristics of the facility or goods, and reflects the adjustments made by the emotion adjustment means.

[0883] (Claim 3)

[0884] The system according to claim 1, wherein the automated execution means places an order based on an order plan confirmed by the user. [Explanation of Symbols]

[0885] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Collection technology for collecting past supply data, environmental information, timing information, and sales promotion activity information, A forecasting technique that uses the data collected by the aforementioned collection technique to predict demand, An order generation technology that automatically generates an order plan based on the demand forecast using the aforementioned forecasting technology, An automated execution technology that executes the order plan generated by the order generation technology, User confirmation and adjustment technology that allows order plans to be confirmed and adjusted via the user terminal, A system that includes this.

2. The system according to claim 1, wherein the order generation technology adjusts the order quantity and order timing taking into consideration the characteristics of the facility or product.

3. The system according to claim 1, wherein the automated execution technology places an order based on an order plan confirmed and adjusted by the user.

Images