System

Abstract

A system is provided.SOLUTION: The system includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for pre-processing the collected data, means for analyzing the pre-processed data and predicting demand, means for analyzing competitor prices, means for calculating optimal room rates based on the prediction results and competitive analysis, means for applying pricing rules based on the calculated rates to determine a final price, means for communicating the final price information, and means for providing a user interface and displaying pricing and reasons therefor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Traditional hotel pricing strategies often missed revenue opportunities because they could not adapt to factors such as market trends, guest behavior, and local events. Furthermore, manually collecting and analyzing this data was time-consuming and labor-intensive, making it difficult to respond in real time. Therefore, solving these issues was necessary to maximize hotel occupancy rates and revenue. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. The system includes means for collecting market trend data, guest behavior data, and local event information. It also includes means for preprocessing this data and forecasting demand using a machine learning model, as well as means for analyzing competitors' prices. It also includes means for calculating optimal room rates based on the forecast results and the results of the competitor analysis, and for applying pricing rules to these prices to determine the final price. It also provides means for notifying the user of the final price information and displaying the pricing and the reasons for it through a user interface. This realizes a system that can maximize hotel occupancy rates and profits.

[0006] "Market Trends Data" means information regarding market fluctuations, such as average room rates, booking rates, and seasonal trends, in a hotel location.

[0007] "Guest Behavior Data" refers to information regarding guest behavior, such as past reservation data, cancellation rates, and customer demographic information.

[0008] "Local event information" refers to information about upcoming local events obtained from local governments and event organizing organizations.

[0009] "Preprocessing" refers to the process of removing missing values ​​and outliers from collected data and standardizing the data format.

[0010] "Demand forecasting" refers to the process of predicting future hotel demand based on market trend data, guest behavior data, and local event information.

[0011] "Competitive analysis" refers to the process of researching and analyzing the pricing of nearby competing hotels and comparing it with your hotel's rates.

[0012] "Pricing Rules" means the rules that apply to the calculated room rate based on the hotel's policies and specific restrictions (such as lowest price guarantees, special discounts, etc.).

[0013] "User interface" refers to the screens and functions provided for users to check and operate the system results. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The system of the present invention is an AI-based platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component.

[0036] Program Overview

[0037] The program of the present invention collects information on market trends, guest behavior, and local events in real time, and uses this data to forecast demand and calculate optimal room rates. The results are then notified to users, maximizing hotel occupancy rates and revenue.

[0038] Program processing

[0039] 1. Data Collection

[0040] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[0041] 2. Data analysis

[0042] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[0043] Server: Predicts demand from pre-processed data using machine learning models that are trained based on historical data and market trends.

[0044] 3. Price optimization

[0045] Server: Analyze competitor pricing and gather information to compare with your hotel's prices.

[0046] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis, taking into account the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.).

[0047] 4. Notification of Results

[0048] Server: Sends optimized pricing information to the hotel's PMS (Property Management System), and notifies connected reservation systems and front desk terminals.

[0049] 5. User Interface

[0050] Users can view optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model to weight specific factors.

[0051] Specific examples

[0052] Responses during periods of increased reservations

[0053] 1. Data Collection:

[0054] Server: Collects information about next week's major music festivals from an external API.

[0055] 2. Data Analysis:

[0056] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[0057] 3. Price optimization:

[0058] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[0059] Server: Based on the demand forecast results, increase the room rate by 30%.

[0060] 4. Notification of Results:

[0061] Server: Sends updated pricing information to the PMS and reflects it on the device.

[0062] 5. User Interface:

[0063] Users: View the dashboard to see the reason for the price adjustment (increased demand due to a music festival) and its impact.

[0064] Off-season response

[0065] 1. Data Collection:

[0066] Server: Checks current reservation status data and whether there are any upcoming major events.

[0067] 2. Data Analysis:

[0068] Server: Predicts a drop in demand based on data from similar periods in the past.

[0069] 3. Price optimization:

[0070] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[0071] Server: Based on forecasted demand, we will reduce room rates by 20% and add special offers packages.

[0072] 4. Notification of Results:

[0073] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[0074] 5. User Interface:

[0075] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed.

[0076] In this way, the system of the present invention uses AI to collect and analyze data in real time and set optimal prices, thereby maximizing hotel occupancy rates and profits.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] Data collection:

[0080] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[0081] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[0082] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[0083] Step 2:

[0084] Data preprocessing:

[0085] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0086] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0087] Step 3:

[0088] Demand forecast:

[0089] Server: Using the pre-processed data, machine learning algorithms (e.g., time series forecasting models or multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0090] Step 4:

[0091] Competitive analysis:

[0092] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0093] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[0094] Step 5:

[0095] Price Optimization:

[0096] Server: Calculates optimal room rates based on demand forecasts and competitive analysis, using algorithms designed to maximize hotel occupancy and profits.

[0097] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[0098] Step 6:

[0099] Notification of results:

[0100] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0101] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0102] Step 7:

[0103] User Interface:

[0104] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0105] Users: Use the ability to customize the forecast model settings to weight specific factors, which will take effect immediately and affect the next forecast.

[0106] Example 1

[0107] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0108] In the hotel industry, optimizing room rates and maximizing revenue are important challenges. However, current methods often involve manual data collection and analysis, making it difficult to quickly respond to fluctuations in demand or competitor pricing trends. This often results in missed revenue opportunities and makes it difficult to set optimal prices. Furthermore, data preprocessing and machine learning model adjustments require specialized knowledge, making them difficult for average users to use. To solve these issues, a system is needed that can collect and analyze a variety of data in real time and quickly propose prices.

[0109] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0110] In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for preprocessing the collected data, means for analyzing the preprocessed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal room rates based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated rates and determining final prices, means for notifying final price information, means for providing a user interface and displaying pricing settings and reasons for them, means for forecasting demand using a machine learning model and customizing model parameters, and means for collecting data using an external API. This enables accurate data collection and analysis in real time, enabling prompt and optimal room rate setting.

[0111] "Market trend data" is information that shows overall market movements, such as market trends, price fluctuations, and consumer preferences.

[0112] "Guest behavior data" refers to information that indicates the behavioral patterns of guests, such as their reservation status, cancellation history, frequency of stay, and length of stay.

[0113] "Local event information" is event information related to a particular area, such as concerts, festivals, and sporting events held in that area.

[0114] "Means for preprocessing collected data" refers to techniques for removing missing values ​​and outliers from collected data and standardizing the data format.

[0115] "Means for analyzing preprocessed data and forecasting demand" refers to technology for forecasting future demand using preprocessed data, and employs machine learning models, etc.

[0116] "Means to analyze competitors' prices" refers to the technology of collecting and analyzing the pricing of other hotels in the same market.

[0117] "Means for calculating optimal room rates based on forecast results and competitive analysis" refers to a technology for calculating optimal room rates based on the results of demand forecasts and the results of competitor price analysis.

[0118] "Means for determining the final price by applying pricing rules based on the calculated rate" refers to a technology that applies the hotel's policies and restrictions to the calculated rate to determine the final price.

[0119] The "means for notifying final price information" is a technology for transmitting the determined final price to the hotel's management system or reservation system.

[0120] The "means for providing a user interface and displaying pricing and the reasons therefor" refers to a technique for providing an interface for a user to check pricing and the reasons therefor.

[0121] "Means for forecasting demand using a machine learning model and customizing the model parameters" is a technology that uses a machine learning model to forecast demand and allows users to adjust the parameters of the model.

[0122] "Means of collecting data using external APIs" refers to technology that uses APIs to obtain data from external systems and services.

[0123] The system of the present invention is an AI-powered platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component. The server uses external APIs to collect market trend data, guest behavior data, and local event information. The server preprocesses the collected data and uses a machine learning model to predict demand. Based on this prediction, the server analyzes competitors' prices and calculates the optimal room rate. The server then sends the optimized pricing information to a property management system (PMS), which then notifies the connected reservation system and front desk terminal. Users can view the optimized pricing and the reasons for it, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the predictive model and assign weights to specific factors.

[0124] Hardware and software used

[0125] Server: The server is responsible for a series of processes such as data collection, preprocessing, analysis, price calculation, and notification. It uses Python and its libraries (pandas, scikit-learn, etc.) and uses HTTP requests to communicate with external APIs.

[0126] Terminals: Terminals used at the front desk or reservation system are designed to display optimized pricing information in real time, often with a browser-based interface.

[0127] User Interface: A browser-based dashboard allows users to see pricing and why, with specific graphical representations and numerical details, and often uses a front-end framework such as React or Vue.js.

[0128] Specific examples

[0129] Responses during periods of increased reservations

[0130] 1. The server collects information about large music festivals scheduled for next week from an external API.

[0131] 2. The server uses a machine learning model to predict a surge in demand based on historical data from the festival period.

[0132] 3. The server compares competitors' prices with the hotel's regular rates and increases the room rate by 30% based on the demand forecast results.

[0133] 4. The server sends the updated fee information to the PMS and reflects it on the terminal.

[0134] 5. The user sees the reason for the price adjustment (increased demand due to a music festival) and its impact on the dashboard.

[0135] Off-season response

[0136] 1. The server checks the current reservation status data and checks that there are no upcoming major events.

[0137] 2. The server predicts a drop in demand based on data from similar periods in the past.

[0138] 3. The server analyzes the pricing of competing hotels and compares it with the hotel's regular price.

[0139] 4. The server reduces the room rate by 20% and adds a special offer package based on demand forecasts.

[0140] 5. The server sends the adjusted price and benefit information to the PMS, which then reflects it on the terminal.

[0141] 6. User can check the reason for the pricing (low demand) through the dashboard and customize settings as needed.

[0142] In this way, the system of the present invention maximizes hotel occupancy rates and revenue by utilizing external APIs to collect data in real time and forecasting demand using machine learning models. Furthermore, users can view the system's pricing process and its background through a dashboard, enhancing reliability and transparency.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] System program processing flow

[0145] Step 1: Data collection

[0146] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information.

[0147] Specific operation: The server calls "MarketDataAPI" or "EventInfoAPI" and periodically obtains the data returned in JSON format.

[0148] Inputs: Market trend data, guest behavior data, local event information

[0149] Output: Raw collected data (JSON format)

[0150] Step 2: Data Preprocessing

[0151] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[0152] Specific operation: The server uses Python's pandas library, removes missing values ​​using DataFrame.dropna(), and unifies the date and time format using pd.to_datetime().

[0153] Input: Raw data collected

[0154] Output: Preprocessed data

[0155] Step 3: Demand forecast

[0156] Server: Uses pre-processed data to predict demand using machine learning models.

[0157] Specific operation: The server uses scikit-learn's LinearRegression model, learns from past data using the fit method, and performs demand forecasting using the predict method.

[0158] Input: Preprocessed data

[0159] Output: Demand forecast results

[0160] Step 4: Price optimization

[0161] Server: Collects competitor pricing information and compares it with the hotel's own rates. Then, based on the demand forecast and competitor pricing analysis results, calculates the optimal room rate taking into account specific constraints.

[0162] Specific operation: The server calls the "CompetitorPriceAPI" to obtain competitor price data in JSON format. It then uses Python to integrate the demand data and competitor prices to calculate the optimal price.

[0163] Input: Demand forecast results, competitor price data

[0164] Output: Calculated optimal room price

[0165] Step 5: Notification of results

[0166] Server: Sends optimized pricing information to the PMS and notifies connected reservation systems and front desk terminals.

[0167] What happens: The server sends the new price information to the PMS API endpoint using an HTTP POST request.

[0168] Input: Calculated best room price

[0169] Output: New price information reflected in PMS and terminal

[0170] Step 6: User Interface

[0171] Users: View optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model.

[0172] What it does: A user logs in and accesses the dashboard via a browser, where they can view data in charts and tables and adjust forecast parameters using sliders.

[0173] Input: Parameter settings entered by the user

[0174] Output: Display of updated forecast results and pricing information

[0175] In this way, the system performs specific data processing and calculations at each step, ultimately providing the user with the optimal pricing and the reasons for it.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] The challenge is to maximize the operational efficiency of taxi services using autonomous vehicles and optimize the utilization rate and revenue of taxis in operation. To achieve this, it is necessary to accurately predict demand for market trends, traffic conditions, and specific events, which fluctuate in real time, and set appropriate prices. However, current technology does not yet have a system that can efficiently collect and analyze these factors and automatically optimize prices. This makes it difficult to respond to fluctuations in demand and maximize revenue.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0180] In this invention, the server includes means for collecting market trend data, means for collecting traffic condition data, means for collecting specific event information, means for collecting operation condition data, means for pre-processing the collected data, means for analyzing the pre-processed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal fares based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated fares to determine final prices, means for notifying final price information, and means for providing a user interface and displaying pricing settings and reasons for them, thereby optimizing operation management and pricing settings of autonomous taxi services in real time and maximizing profits.

[0181] "Market trend data" is information used to understand market conditions and fluctuations. This includes data on economic indicators, consumer behavior, price fluctuations, etc.

[0182] "Traffic condition data" refers to information related to road congestion and traffic flow, including traffic jams, accidents, and traffic light status.

[0183] "Specific event information" refers to information about events that take place at specific dates, times, and locations. This refers to information about events that affect demand, such as concerts, sporting events, and local festivals.

[0184] "Operation status data" refers to information about the current operating status, location, speed, etc. of an autonomous vehicle. This data is used to understand the real-time status of the vehicle while it is in operation.

[0185] "Preprocessing" is the process of removing missing values ​​and outliers from collected data and preparing the data in a format that is easy to analyze.

[0186] "Demand forecasting" refers to predicting future demand based on past data and current conditions. This is done using machine learning and statistical models.

[0187] "Competitive analysis" refers to researching and comparatively analyzing the pricing and service content of competitors, which can be used to help develop your own pricing strategy.

[0188] "Pricing rules" refer to pre-determined pricing rules and standards that are used to calculate optimal prices based on demand and competitive conditions.

[0189] "User interface" refers to the display and controls that allow a user to interact with a system, including graphical interfaces and dashboards.

[0190] "Notification" refers to the process by which the system communicates calculation results and updated information to relevant parties. This includes push notifications on smartphones and emails.

[0191] The system of the present invention is a technology for optimizing the operation management and pricing of autonomous taxi services. The system is implemented by components including a server, a terminal, and a user.

[0192] server

[0193] The server collects market trend data, traffic data, specific event information, and operational status data in real time using external APIs. This data is updated periodically and pre-processed on the server. This pre-processing includes removing missing values ​​and outliers and standardizing the data format.

[0194] The server then uses a machine learning model to predict demand based on the pre-processed data. This model is trained based on past data and market trends. Based on the results of the demand forecast, the server analyzes competitors' prices and calculates the optimal taxi fare. This takes into account not only the demand forecast results and the results of the competitor analysis, but also specific pricing rules and constraints.

[0195] Terminal

[0196] The terminal refers to the smartphone used by taxi drivers and passengers. The optimal fare calculated by the server is sent to the terminal via push notification or app notification. This allows drivers and passengers to check the latest price in real time. The terminal's user interface also displays detailed information such as the reasons for the price setting, predicted demand, and competitor trends.

[0197] User

[0198] Users include system administrators, taxi drivers, and service users. Through the dashboard, users can check pricing and the reasons for it, the latest demand forecast, and competitor trends. They can also customize the parameters of the forecasting model and assign weights to specific factors. Furthermore, users can send feedback to the server to further customize the forecasting model.

[0199] Specific examples

[0200] Consider the following scenario: If information collected from an external API indicates that a large rock festival will be held in a city next week, the server uses this information to predict a surge in demand. Using data from past similar events, the server increases pricing by 25% over normal rates. This information is sent to drivers' and passengers' smartphones, and the dashboard displays the reason for the price adjustment as "Increased demand due to rock festival."

[0201] Prompt Sentence Examples

[0202] "Please forecast demand during the rock festival based on market trends, traffic conditions, and event information for the next two weeks, and set the optimal taxi fares. Please also take into account past data."

[0203] As described above, the system of the present invention can maximize the utilization rate and revenue of autonomous taxi services by collecting and analyzing data in real time and providing optimal pricing.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1: Data collection

[0206] The server uses external APIs to collect market trend data, traffic situation data, specific event information, and operation status data. This data is obtained in real time and updated periodically. Specifically, it makes API calls, standardizes the data format, and saves it in a database. The input is raw data obtained from the API, and the output is standardized data required for preprocessing.

[0207] Step 2: Data Preprocessing

[0208] The server performs preprocessing on the collected data. This preprocessing includes removing missing values ​​and outliers and standardizing the data format. Specifically, it uses a data cleaning algorithm to filter out inappropriate data. The input is the collected raw data, and the output is clean data that can be analyzed.

[0209] Step 3: Demand forecast

[0210] The server uses a machine learning model on the preprocessed data to forecast demand. The model used is a generative AI model trained based on past data and market trends. Specifically, clean data is input into the model to generate forecast results that predict future demand. The input is clean data, and the output is predicted demand data.

[0211] Step 4: Competitive analysis

[0212] The server collects competitors' pricing information and performs price analysis based on the collected information. Specifically, it obtains competitors' pricing data from an external API and compares it with the company's own prediction results. The input is competitors' pricing data, and the output is competitor comparison data.

[0213] Step 5: Price optimization

[0214] The server calculates the optimal fare based on the demand forecast and competitive analysis results. This calculation takes into account not only the demand forecast and competitive analysis results, but also specific pricing rules and constraints. Specifically, it uses a fare calculation algorithm to calculate the optimal price. The inputs are the demand forecast and competitive comparison data, and the output is the optimized fare data.

[0215] Step 6: Price Notification

[0216] The server sends the optimized fare data to the terminal and notifies the driver and passenger through push notifications or app notifications. Specifically, a notification server is used to deliver price information to the driver's and passenger's smartphones in real time. The input is the optimized fare data, and the output is the notification sent to the driver and passenger.

[0217] Step 7: Provide a user interface

[0218] The terminal displays detailed information such as the reasons for pricing, forecasted demand, and competitor trends on a user interface. Specifically, it provides the user with the necessary information via a dashboard, allowing them to change settings and send feedback. The input is notification data from the server, and the output is the user's operation interface.

[0219] Step 8: Feedback and Model Customization

[0220] Users send feedback to the system, and the server customizes the predictive model based on that feedback. Specifically, the server analyzes the user's feedback and adjusts the parameters of the machine learning model. The input is the user's feedback, and the output is a customized predictive model.

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] The system of the present invention combines an AI-based platform for optimizing hotel pricing and revenue management with an emotion engine that recognizes user emotions. The system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[0223] Program Overview

[0224] The program of the present invention collects market trends, guest behavior, local event information, and user sentiment in real time, and uses this data to forecast demand and calculate optimal room rates. It also evaluates user sentiment and incorporates the results into forecasting models and pricing. The results are then communicated to users, maximizing hotel occupancy and revenue.

[0225] Program processing

[0226] 1. Data Collection

[0227] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[0228] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[0229] 2. Data Preprocessing

[0230] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0231] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0232] 3. Demand forecasting

[0233] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0234] 4. Price optimization

[0235] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0236] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis results. The server also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses displeasure, the server adjusts the rate by reducing it.

[0237] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[0238] 5. Notification of Results

[0239] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0240] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0241] 6. User Interface

[0242] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0243] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[0244] Specific examples

[0245] Responses during periods of increased reservations

[0246] 1. Data Collection:

[0247] Server: Collects information about next week's major music festivals from an external API.

[0248] Server: Uses an emotion engine to collect user emotion data, for example, to ensure that users are sending a lot of positive feedback.

[0249] 2. Data Preprocessing:

[0250] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[0251] 3. Demand forecasting:

[0252] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[0253] 4. Price Optimization:

[0254] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[0255] Server: Based on the demand forecast results, increase the room rate by 30%. Also, consider the positive sentiment of users and add special offers.

[0256] 5. Notification of Results:

[0257] Server: Sends updated pricing information to the PMS and reflects it on the device.

[0258] 6. User Interface:

[0259] Users: See the reason for the price adjustment (increased demand due to music festivals) and its impact in the dashboard, along with feedback from the sentiment engine.

[0260] Off-season response

[0261] 1. Data Collection:

[0262] Server: Checks current reservation status data and whether there are any upcoming major events.

[0263] Server: Use the emotion engine to collect user emotion data. Check for a high number of negative feedbacks.

[0264] 2. Data Preprocessing:

[0265] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[0266] 3. Demand forecasting:

[0267] Server: Predicts a drop in demand based on data from similar periods in the past.

[0268] 4. Price Optimization:

[0269] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[0270] Server: Based on demand forecasts, reduce room rates by 20%, add rewards packages, and consider campaigns to alleviate negative sentiment.

[0271] 5. Notification of Results:

[0272] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[0273] 6. User Interface:

[0274] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed. Feedback from the sentiment engine is also displayed.

[0275] In this way, the system of the present invention uses an emotion engine to evaluate user emotions, collects and analyzes data in real time using AI, and sets optimal prices, thereby maximizing hotel occupancy rates and profits.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] Data collection:

[0279] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[0280] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[0281] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[0282] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[0283] Step 2:

[0284] Data preprocessing:

[0285] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0286] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0287] Step 3:

[0288] Demand forecast:

[0289] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0290] Step 4:

[0291] Competitive analysis:

[0292] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0293] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[0294] Step 5:

[0295] Price Optimization:

[0296] Server: Calculates optimal room rates based on demand forecasts and competitive analysis results, using algorithms aimed at maximizing hotel occupancy and profits.

[0297] Server: The server applies the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.) to the calculated optimal price. It also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses dissatisfaction, the server may adjust the price by lowering it.

[0298] Step 6:

[0299] Notification of results:

[0300] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0301] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0302] Step 7:

[0303] User Interface:

[0304] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0305] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[0306] Example 2

[0307] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] Traditional hotel pricing and revenue management systems are primarily based on market trends, competitive analysis, and guest behavior, but do not take into account user sentiment and immediate feedback, which can result in inadequate pricing, customer satisfaction, and maximum revenue.

[0309] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for collecting user emotion data, means for preprocessing the collected data, means for analyzing the preprocessed data and emotion data and forecasting demand, means for collecting and analyzing competitors' price information, means for calculating optimal room rates based on the forecast results, competitive analysis, and emotion data, means for applying pricing rules based on the calculated rates to determine final prices, means for notifying the hotel management system of the final price information, and means for providing a dashboard and displaying pricing settings, reasons for the settings, and emotion feedback. This enables optimal pricing, demand forecasting, and competitive analysis that take user emotions into account, thereby improving customer satisfaction and maximizing profits.

[0310] "Market trend data" refers to information that indicates changes and trends in market supply and demand, and primarily includes economic data and industry trends.

[0311] "Guest Behavior Data" means information including a guest's past booking history, behavioral patterns during their stay, as well as customer preferences and feedback.

[0312] "Local Event Information" is data about events and occasions taking place in a particular area, including festivals, concerts, sporting events, etc.

[0313] "User emotion data" refers to information collected from users' emotions and feedback while using the system, including emotional expressions expressed through facial expressions, voice, and text input.

[0314] "Preprocessing" refers to a series of processes for preparing collected data in an analyzable format, including filling in missing values, standardizing formats, and removing outliers.

[0315] A "machine learning algorithm" is a mathematical or statistical model that learns patterns and rules from data and predicts future data. Examples include time series prediction models and multivariate regression models.

[0316] "Competitive analysis" is a method for evaluating, analyzing, and comparing competitors' pricing and market strategies, and uses web scraping technology and API integration.

[0317] "Pricing rules" are internal regulations and external constraints regarding hotel pricing, including rules such as lowest price guarantees and special discounts.

[0318] "Notification" is a means of sending optimized price information to hotel management systems and terminals in real time to inform relevant parties.

[0319] A "dashboard" is part of the system's user interface and is a screen for visually displaying information such as pricing, demand forecasts, competitive situations, and emotional feedback.

[0320] This invention is a system for optimizing hotel pricing and revenue management, specifically combining an AI-based platform with an emotion engine that recognizes user emotions. This system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[0321] Hardware and software used

[0322] Server: Data collection, preprocessing, predictive model building, price optimization, and notifications. Uses libraries and frameworks such as Python, Scikit-learn, BeautifulSoup, and Selenium.

[0323] Emotion engine: Recognizes emotions by analyzing user feedback, facial expressions, and voice data. Specific examples include models using machine learning and deep learning.

[0324] Terminals: Computers used at front desks or administrative locations receive notifications of new pricing information and display dashboards.

[0325] User Interface: Provides a dashboard displaying pricing, demand forecasts, competitive information, and sentiment feedback.

[0326] Data collection

[0327] The server uses external APIs to collect market trend data, guest behavior data, and local event information. For example, it obtains information from tourist association APIs, social media data, and travel booking sites. This data is updated hourly.

[0328] The server uses an emotion engine to collect emotional data in real time from feedback, facial expressions, and voice data while the user is using the system. For example, data can be obtained through feedback input at the front desk or conversations with a chatbot.

[0329] Data Preprocessing

[0330] The server performs pre-processing on the collected data to remove missing values ​​and outliers. For example, it uses a data cleaning tool to detect, delete, or impute abnormal values.

[0331] The server unifies all data formats, converting different data formats (JSON, CSV, XML, etc.) into a uniform format and integrating them into a single database.

[0332] Demand forecasting

[0333] The server uses the preprocessed data and sentiment data to apply machine learning algorithms (e.g., Scikit-learn time series forecasting models and multivariate regression models) to forecast demand.

[0334] For example, historical data can be used to predict increased demand during specific events.

[0335] Price Optimization

[0336] The server uses web scraping techniques and API integration to obtain pricing information from other hotels to obtain competitor pricing, using tools such as BeautifulSoup and Selenium.

[0337] The system calculates optimal room rates based on demand forecasts and competitive analysis. For example, it raises rates during periods of high demand and lowers rates during periods of low demand. It also adjusts rates by taking into account user feedback.

[0338] The hotel's policies and specific constraints (such as lowest price guarantees and special discounts) are applied to the calculated best price to arrive at the final room price.

[0339] Notification of results

[0340] The server sends the optimized pricing information to the hotel management system, which updates the information in real time using API integration.

[0341] Terminals (front desk or administrator terminals) will receive notifications of the new pricing and will display pop-ups or alerts.

[0342] User Interface

[0343] Users access a dashboard to view optimized pricing and why, demand forecasts, competitor activity, and sentiment feedback. The dashboard is updated in real time, allowing for quick action.

[0344] Users can customize the settings of the predictive model, weighting certain factors, and see feedback from the sentiment engine.

[0345] Specific examples

[0346] Responses during periods of increased reservations

[0347] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[0348] Off-season response

[0349] For example, the server collects current reservation status and event information and uses the sentiment engine to determine that a large amount of negative feedback has been collected. The server then performs data preprocessing and predicts a decline in demand based on data from similar periods in the past. The server then analyzes the prices of competing hotels, reduces room rates by 20%, and adds special offers packages. It also considers campaigns to alleviate negative sentiment. The optimized prices and special offers are sent to the PMS and reflected on the device. Users can use the dashboard to determine the reasons for pricing and customize settings, and also check sentiment feedback.

[0350] Example prompts to input to the generative AI model

[0351] "How can I forecast demand and optimize pricing during festivals?"

[0352] "Please explain how to best adjust prices if demand drops during the off-season."

[0353] "Describe the effectiveness of using user sentiment data to set hotel prices."

[0354] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0355] Step 1: Data collection

[0356] The server uses external APIs to collect market trend data, guest behavior data, and local event information, specifically from tourism association APIs, social media data, and travel booking sites.

[0357] Inputs: Market trend data from external APIs, guest behavior data, and local event information.

[0358] Output: Collected market trend data, guest behavior data, and local event information.

[0359] What it does: Executes an API call, retrieves data, and saves it to the database.

[0360] Step 2: Collecting emotion data

[0361] The server uses an emotion engine to collect emotion data from feedback input by the user while using the system, as well as facial expressions and voice data during operation.

[0362] Input: Feedback, facial expression data, and audio data.

[0363] Output: Emotion data.

[0364] How it works: Activates the emotion engine and generates emotion data in real time by analyzing feedback, facial expressions, and voice data.

[0365] Step 3: Data Preprocessing

[0366] The server pre-processes all collected data to remove missing values ​​and outliers, for example, by using Excel's data cleaning tools to detect and remove outliers.

[0367] Inputs: Collected market trend data, guest behavior data, local event information, and sentiment data.

[0368] Output: The preprocessed dataset.

[0369] Operation: Imputes missing values, removes outliers, and standardizes data formats.

[0370] Step 4: Demand forecast

[0371] The server uses the preprocessed data and sentiment data to apply machine learning algorithms to predict future demand. Specifically, it uses Python libraries (e.g., Scikit-learn) to build time series forecasting models and multivariate regression models and executes the forecasting models.

[0372] Input: Preprocessed dataset, sentiment data.

[0373] Output: Demand forecast results.

[0374] How it works: Trains machine learning models and performs forecasting to calculate future demand.

[0375] Step 5: Price optimization

[0376] The server uses web scraping technology and API integration to gather current information on competitors' pricing. Specifically, it uses tools such as BeautifulSoup and Selenium to obtain pricing information.

[0377] Inputs: Competitor pricing information, demand forecast results, sentiment data.

[0378] Output: Optimized room rates.

[0379] Operation: Obtains price information, calculates optimal prices by combining demand forecasts and competitive analysis, and adjusts prices based on user sentiment.

[0380] Step 6: Applying Pricing Rules

[0381] The server applies the hotel's policies and specific constraints (such as best price guarantees or special discounts) to the calculated best price to determine the final room price.

[0382] Input: Optimized room rates, hotel policies and constraints information.

[0383] Output: Final room price.

[0384] How it works: Rules like lowest price guarantees and special discounts are applied to determine the final price.

[0385] Step 7: Notification of results

[0386] The server sends the optimized pricing information to the hotel management system (PMS), which updates the information in real time using API integration.

[0387] Input: Final room rate.

[0388] Output: Fee information notified to PMS.

[0389] Operation: Connects to PMS via API and sends pricing information.

[0390] Step 8: User Interface

[0391] Users access a dashboard to see optimized pricing and why, the latest demand forecast, competitor activity, and sentiment feedback.

[0392] Input: Data on the dashboard.

[0393] Output: The information confirmed by the user.

[0394] What it does: Displays information visually using graphs and charts and allows users to customize settings.

[0395] Specific examples

[0396] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[0397] Example prompts to input to a generative AI model:

[0398] "How can I forecast demand and optimize pricing during festivals?"

[0399] "Please explain how to best adjust prices if demand drops during the off-season."

[0400] "Describe the effectiveness of using user sentiment data to set hotel prices."

[0401] (Application example 2)

[0402] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0403] Conventional pricing systems rely on data based on market trends and competitive analysis, which means they have a problem of not being able to reflect user emotions and behavior. In particular, it is difficult to quickly respond to fluctuations in consumer behavior and the market, which can result in lost sales opportunities and excess inventory. Furthermore, it is difficult to set optimal prices solely through competitor price analysis, so pricing that responds to consumer needs and emotions is required.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting consumer behavior data, means for collecting related event information, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand, means for analyzing the prices of competing companies, means for calculating optimal product prices based on the prediction results and competitive analysis, means for applying pricing rules based on the calculated prices to determine final prices, means for notifying final price information, means for providing a user interface and displaying price settings and the reasons for them, means for acquiring user emotion data using an emotion engine and reflecting this in price settings, means for performing demand forecasting using a machine learning algorithm, and means for adjusting prices based on specific events and feedback. This enables optimal price setting in response to consumer emotions and market trends.

[0405] "Market trend data" refers to information related to overall market trends, such as supply and demand in the market, price fluctuations, and consumer purchasing behavior.

[0406] "Consumer behavior data" refers to information about consumer behavior, such as the actions and trends consumers take when purchasing products, their purchasing history, and their search history.

[0407] "Related event information" is information about specific events, campaigns, sales, festivals, etc. that affect the market and consumption.

[0408] "Preprocessing" is a process that improves the quality of collected data by removing missing values ​​and outliers and standardizing the data format.

[0409] "Demand forecasting" is the process of predicting future demand based on market trend data, consumer behavior data, etc.

[0410] "Competitor price analysis" is the process of collecting competitors' product prices and analyzing that data to use as a reference when setting your own product prices.

[0411] "Pricing rules" are rules or restrictions that apply to set prices, such as lowest price guarantees or special discounts.

[0412] "Notification" is the act of notifying users and systems of the final calculated price information in real time.

[0413] The "user interface" is an interface for providing and displaying optimized pricing, the reasons for it, analysis results, emotion engine feedback, etc. to the user.

[0414] The "emotion engine" is a system that acquires and analyzes emotional data from the user's facial expressions, voice, etc.

[0415] A "machine learning algorithm" is a calculation method or model used to forecast demand and optimize prices based on collected data.

[0416] "Feedback" refers to opinions, impressions, and information about usability collected from system users.

[0417] The present invention is a system for optimizing pricing and revenue management on an online shopping site. This system is realized by components including a server, a terminal, and a user.

[0418] System Configuration

[0419] 1. Server:

[0420] It plays a central role in collecting, preprocessing, and analyzing various types of data.

[0421] Collect market trend data, consumer behavior data, relevant event information, and competitor pricing data.

[0422] The emotion engine collects user emotion data.

[0423] This data is preprocessed and demand forecasts are made using machine learning algorithms.

[0424] Calculate the optimal product price based on the forecast results and competitive analysis, and determine the final price in accordance with pricing rules.

[0425] It has the function of notifying the final price information.

[0426] 2. Terminal:

[0427] It provides a dashboard for users to see pricing and why, the latest demand forecasts, and competitor activity.

[0428] It can be accessed from various devices such as mobile devices and PCs.

[0429] 3. User:

[0430] Provides emotion data collected by the emotion engine.

[0431] Review pricing information provided by the system and provide feedback if necessary.

[0432] Processing Details

[0433] Data collection

[0434] The server uses external APIs to collect market trend data, consumer behavior data, and related event information in real time, and also uses web scraping technology to obtain competitor pricing information.

[0435] The emotion engine uses the camera and microphone on the user's smartphone to collect emotional data from facial expressions and voice.

[0436] Data Preprocessing

[0437] The server performs preprocessing of the collected data, removing missing values ​​and outliers and standardizing the data format to improve data quality.

[0438] Demand forecasting

[0439] The server applies machine learning algorithms (e.g., LSTM models or multivariate regression models) based on the preprocessed data to predict future demand.

[0440] Price Optimization

[0441] The server calculates the optimal product price based on the prediction results and the competitive analysis results, taking into account the user's emotional evaluation results obtained by the emotion engine.

[0442] Pricing rules will be applied to determine the final price.

[0443] Notification of results

[0444] The server notifies the user interface of the optimized pricing information in real time.

[0445] Specific examples

[0446] Seasonal sale pricing

[0447] 1. Data Collection:

[0448] The server collects market trend data for Black Friday.

[0449] The emotion engine confirmed that users frequently displayed excited facial expressions while using the app.

[0450] 2. Data Preprocessing:

[0451] The server preprocesses the collected data and removes missing values ​​and outliers.

[0452] 3. Demand forecasting:

[0453] The server uses historical data from Black Friday to predict a surge in demand.

[0454] 4. Price Optimization:

[0455] The server collects competitor pricing information and offers a 20% discount.

[0456] Consider sentiment data and provide special offers to users.

[0457] 5. Notification of Results:

[0458] The server sends the updated price information to the online shopping site's system.

[0459] 6. User Interface:

[0460] Users can see the reason behind the new price (Black Friday sale) and see the sentiment engine feedback.

[0461] Prompt Sentence Examples

[0462] "Predict demand and set prices for Black Friday"

[0463] "Adjust prices for products with many negative reviews"

[0464] In this way, by utilizing an emotion engine and machine learning algorithms, it is possible to create a system that enables optimal pricing in response to user emotions and market trends.

[0465] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0466] Step 1: Data collection

[0467] The server uses external APIs to collect market trend data, consumer behavior data, and related event information. The server retrieves data in JSON format from the external APIs. It also uses web scraping technology to collect pricing information from competitors. Furthermore, the emotion engine uses the smartphone's camera and microphone to collect emotion data in real time from the user's facial expressions and voice. The inputs are market trend data, consumer behavior data, related event information, and emotion data, and the output is an integrated set of these data.

[0468] Step 2: Data Preprocessing

[0469] The server preprocesses the data collected in step 1, specifically removing missing values ​​and outliers and standardizing the data format (e.g., normalizing numerical data and encoding categorical data). The input is the data collected in step 1, and the output is a preprocessed, consistent dataset.

[0470] Step 3: Demand forecast

[0471] The server uses the preprocessed data to apply machine learning algorithms (e.g., LSTM models, time series forecasting models) to predict future demand. The server trains the model based on past data and performs demand forecasts based on new data. The input is the preprocessed data, and the output is the future demand forecast.

[0472] Step 4: Price optimization

[0473] The server calculates the optimal product price based on the demand forecast results and competitive analysis results. It also takes into account the user's emotional data from the emotion engine, adjusting the price if the user expresses displeasure, for example. It applies pricing rules to determine the final price. The inputs are the demand forecast results, competitive analysis results, and emotional data, and the output is the optimized product price.

[0474] Step 5: Notification of results

[0475] The server reflects the optimized price information in the online shopping site's pricing system. Specifically, it updates the price information using an API and notifies users of the price change via in-app notifications or push notifications. The input is the optimized price information, and the output is the updated price information and a notification to the user.

[0476] Step 6: User Interface

[0477] Users can check pricing and its reasons, demand forecast results, and competitive analysis data in real time through the provided dashboard. Users can also check feedback from the sentiment engine and send feedback as needed. The input is the notified price information and analysis data, and the output is the display on the dashboard and feedback from users.

[0478] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0479] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0480] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0481] [Second embodiment]

[0482] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0483] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0484] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0485] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0486] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0487] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0488] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0489] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0490] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0491] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0492] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0493] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0494] The system of the present invention is an AI-based platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component.

[0495] Program Overview

[0496] The program of the present invention collects information on market trends, guest behavior, and local events in real time, and uses this data to forecast demand and calculate optimal room rates. The results are then notified to users, maximizing hotel occupancy rates and revenue.

[0497] Program processing

[0498] 1. Data Collection

[0499] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[0500] 2. Data analysis

[0501] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[0502] Server: Predicts demand from pre-processed data using machine learning models that are trained based on historical data and market trends.

[0503] 3. Price optimization

[0504] Server: Analyze competitor pricing and gather information to compare with your hotel's prices.

[0505] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis, taking into account the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.).

[0506] 4. Notification of Results

[0507] Server: Sends optimized pricing information to the hotel's PMS (Property Management System), and notifies connected reservation systems and front desk terminals.

[0508] 5. User Interface

[0509] Users can view optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model to weight specific factors.

[0510] Specific examples

[0511] Responses during periods of increased reservations

[0512] 1. Data Collection:

[0513] Server: Collects information about next week's major music festivals from an external API.

[0514] 2. Data Analysis:

[0515] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[0516] 3. Price optimization:

[0517] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[0518] Server: Based on the demand forecast results, increase the room rate by 30%.

[0519] 4. Notification of Results:

[0520] Server: Sends updated pricing information to the PMS and reflects it on the device.

[0521] 5. User Interface:

[0522] Users: View the dashboard to see the reason for the price adjustment (increased demand due to a music festival) and its impact.

[0523] Off-season response

[0524] 1. Data Collection:

[0525] Server: Checks current reservation status data and whether there are any upcoming major events.

[0526] 2. Data Analysis:

[0527] Server: Predicts a drop in demand based on data from similar periods in the past.

[0528] 3. Price optimization:

[0529] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[0530] Server: Based on forecasted demand, we will reduce room rates by 20% and add special offers packages.

[0531] 4. Notification of Results:

[0532] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[0533] 5. User Interface:

[0534] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed.

[0535] In this way, the system of the present invention uses AI to collect and analyze data in real time and set optimal prices, thereby maximizing hotel occupancy rates and profits.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] Data collection:

[0539] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[0540] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[0541] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[0542] Step 2:

[0543] Data preprocessing:

[0544] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0545] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0546] Step 3:

[0547] Demand forecast:

[0548] Server: Using the pre-processed data, machine learning algorithms (e.g., time series forecasting models or multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0549] Step 4:

[0550] Competitive analysis:

[0551] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0552] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[0553] Step 5:

[0554] Price Optimization:

[0555] Server: Calculates optimal room rates based on demand forecasts and competitive analysis, using algorithms designed to maximize hotel occupancy and profits.

[0556] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[0557] Step 6:

[0558] Notification of results:

[0559] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0560] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0561] Step 7:

[0562] User Interface:

[0563] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0564] Users: Use the ability to customize the forecast model settings to weight specific factors, which will take effect immediately and affect the next forecast.

[0565] Example 1

[0566] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] In the hotel industry, optimizing room rates and maximizing revenue are important challenges. However, current methods often involve manual data collection and analysis, making it difficult to quickly respond to fluctuations in demand or competitor pricing trends. This often results in missed revenue opportunities and makes it difficult to set optimal prices. Furthermore, data preprocessing and machine learning model adjustments require specialized knowledge, making them difficult for average users to use. To solve these issues, a system is needed that can collect and analyze a variety of data in real time and quickly propose prices.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0569] In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for preprocessing the collected data, means for analyzing the preprocessed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal room rates based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated rates and determining final prices, means for notifying final price information, means for providing a user interface and displaying pricing settings and reasons for them, means for forecasting demand using a machine learning model and customizing model parameters, and means for collecting data using an external API. This enables accurate data collection and analysis in real time, enabling prompt and optimal room rate setting.

[0570] "Market trend data" is information that shows overall market movements, such as market trends, price fluctuations, and consumer preferences.

[0571] "Guest behavior data" refers to information that indicates the behavioral patterns of guests, such as their reservation status, cancellation history, frequency of stay, and length of stay.

[0572] "Local event information" is event information related to a particular area, such as concerts, festivals, and sporting events held in that area.

[0573] "Means for preprocessing collected data" refers to techniques for removing missing values ​​and outliers from collected data and standardizing the data format.

[0574] "Means for analyzing preprocessed data and forecasting demand" refers to technology for forecasting future demand using preprocessed data, and employs machine learning models, etc.

[0575] "Means to analyze competitors' prices" refers to the technology of collecting and analyzing the pricing of other hotels in the same market.

[0576] "Means for calculating optimal room rates based on forecast results and competitive analysis" refers to a technology for calculating optimal room rates based on the results of demand forecasts and the results of competitor price analysis.

[0577] "Means for determining the final price by applying pricing rules based on the calculated rate" refers to a technology that applies the hotel's policies and restrictions to the calculated rate to determine the final price.

[0578] The "means for notifying final price information" is a technology for transmitting the determined final price to the hotel's management system or reservation system.

[0579] The "means for providing a user interface and displaying pricing and the reasons therefor" refers to a technique for providing an interface for a user to check pricing and the reasons therefor.

[0580] "Means for forecasting demand using a machine learning model and customizing the model parameters" is a technology that uses a machine learning model to forecast demand and allows users to adjust the parameters of the model.

[0581] "Means of collecting data using external APIs" refers to technology that uses APIs to obtain data from external systems and services.

[0582] The system of the present invention is an AI-powered platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component. The server uses external APIs to collect market trend data, guest behavior data, and local event information. The server preprocesses the collected data and uses a machine learning model to predict demand. Based on this prediction, the server analyzes competitors' prices and calculates the optimal room rate. The server then sends the optimized pricing information to a property management system (PMS), which then notifies the connected reservation system and front desk terminal. Users can view the optimized pricing and the reasons for it, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the predictive model and assign weights to specific factors.

[0583] Hardware and software used

[0584] Server: The server is responsible for a series of processes such as data collection, preprocessing, analysis, price calculation, and notification. It uses Python and its libraries (pandas, scikit-learn, etc.) and uses HTTP requests to communicate with external APIs.

[0585] Terminals: Terminals used at the front desk or reservation system are designed to display optimized pricing information in real time, often with a browser-based interface.

[0586] User Interface: A browser-based dashboard allows users to see pricing and why, with specific graphical representations and numerical details, and often uses a front-end framework such as React or Vue.js.

[0587] Specific examples

[0588] Responses during periods of increased reservations

[0589] 1. The server collects information about large music festivals scheduled for next week from an external API.

[0590] 2. The server uses a machine learning model to predict a surge in demand based on historical data from the festival period.

[0591] 3. The server compares competitors' prices with the hotel's regular rates and increases the room rate by 30% based on the demand forecast results.

[0592] 4. The server sends the updated fee information to the PMS and reflects it on the terminal.

[0593] 5. The user sees the reason for the price adjustment (increased demand due to a music festival) and its impact on the dashboard.

[0594] Off-season response

[0595] 1. The server checks the current reservation status data and checks that there are no upcoming major events.

[0596] 2. The server predicts a drop in demand based on data from similar periods in the past.

[0597] 3. The server analyzes the pricing of competing hotels and compares it with the hotel's regular price.

[0598] 4. The server reduces the room rate by 20% and adds a special offer package based on demand forecasts.

[0599] 5. The server sends the adjusted price and benefit information to the PMS, which then reflects it on the terminal.

[0600] 6. User can check the reason for the pricing (low demand) through the dashboard and customize settings as needed.

[0601] In this way, the system of the present invention maximizes hotel occupancy rates and revenue by utilizing external APIs to collect data in real time and forecasting demand using machine learning models. Furthermore, users can view the system's pricing process and its background through a dashboard, enhancing reliability and transparency.

[0602] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0603] System program processing flow

[0604] Step 1: Data collection

[0605] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information.

[0606] Specific operation: The server calls "MarketDataAPI" or "EventInfoAPI" and periodically obtains the data returned in JSON format.

[0607] Inputs: Market trend data, guest behavior data, local event information

[0608] Output: Raw collected data (JSON format)

[0609] Step 2: Data Preprocessing

[0610] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[0611] Specific operation: The server uses Python's pandas library, removes missing values ​​using DataFrame.dropna(), and unifies the date and time format using pd.to_datetime().

[0612] Input: Raw data collected

[0613] Output: Preprocessed data

[0614] Step 3: Demand forecast

[0615] Server: Uses pre-processed data to predict demand using machine learning models.

[0616] Specific operation: The server uses scikit-learn's LinearRegression model, learns from past data using the fit method, and performs demand forecasting using the predict method.

[0617] Input: Preprocessed data

[0618] Output: Demand forecast results

[0619] Step 4: Price optimization

[0620] Server: Collects competitor pricing information and compares it with the hotel's own rates. Then, based on the demand forecast and competitor pricing analysis results, calculates the optimal room rate taking into account specific constraints.

[0621] Specific operation: The server calls the "CompetitorPriceAPI" to obtain competitor price data in JSON format. It then uses Python to integrate the demand data and competitor prices to calculate the optimal price.

[0622] Input: Demand forecast results, competitor price data

[0623] Output: Calculated optimal room price

[0624] Step 5: Notification of results

[0625] Server: Sends optimized pricing information to the PMS and notifies connected reservation systems and front desk terminals.

[0626] What happens: The server sends the new price information to the PMS API endpoint using an HTTP POST request.

[0627] Input: Calculated best room price

[0628] Output: New price information reflected in PMS and terminal

[0629] Step 6: User Interface

[0630] Users: View optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model.

[0631] What it does: A user logs in and accesses the dashboard via a browser, where they can view data in charts and tables and adjust forecast parameters using sliders.

[0632] Input: Parameter settings entered by the user

[0633] Output: Display of updated forecast results and pricing information

[0634] In this way, the system performs specific data processing and calculations at each step, ultimately providing the user with the optimal pricing and the reasons for it.

[0635] (Application example 1)

[0636] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] The challenge is to maximize the operational efficiency of taxi services using autonomous vehicles and optimize the utilization rate and revenue of taxis in operation. To achieve this, it is necessary to accurately predict demand for market trends, traffic conditions, and specific events, which fluctuate in real time, and set appropriate prices. However, current technology does not yet have a system that can efficiently collect and analyze these factors and automatically optimize prices. This makes it difficult to respond to fluctuations in demand and maximize revenue.

[0638] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0639] In this invention, the server includes means for collecting market trend data, means for collecting traffic condition data, means for collecting specific event information, means for collecting operation condition data, means for pre-processing the collected data, means for analyzing the pre-processed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal fares based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated fares to determine final prices, means for notifying final price information, and means for providing a user interface and displaying pricing settings and reasons for them, thereby optimizing operation management and pricing settings of autonomous taxi services in real time and maximizing profits.

[0640] "Market trend data" is information used to understand market conditions and fluctuations. This includes data on economic indicators, consumer behavior, price fluctuations, etc.

[0641] "Traffic condition data" refers to information related to road congestion and traffic flow, including traffic jams, accidents, and traffic light status.

[0642] "Specific event information" refers to information about events that take place at specific dates, times, and locations. This refers to information about events that affect demand, such as concerts, sporting events, and local festivals.

[0643] "Operation status data" refers to information about the current operating status, location, speed, etc. of an autonomous vehicle. This data is used to understand the real-time status of the vehicle while it is in operation.

[0644] "Preprocessing" is the process of removing missing values ​​and outliers from collected data and preparing the data in a format that is easy to analyze.

[0645] "Demand forecasting" refers to predicting future demand based on past data and current conditions. This is done using machine learning and statistical models.

[0646] "Competitive analysis" refers to researching and comparatively analyzing the pricing and service content of competitors, which can be used to help develop your own pricing strategy.

[0647] "Pricing rules" refer to pre-determined pricing rules and standards that are used to calculate optimal prices based on demand and competitive conditions.

[0648] "User interface" refers to the display and controls that allow a user to interact with a system, including graphical interfaces and dashboards.

[0649] "Notification" refers to the process by which the system communicates calculation results and updated information to relevant parties. This includes push notifications on smartphones and emails.

[0650] The system of the present invention is a technology for optimizing the operation management and pricing of autonomous taxi services. The system is implemented by components including a server, a terminal, and a user.

[0651] server

[0652] The server collects market trend data, traffic data, specific event information, and operational status data in real time using external APIs. This data is updated periodically and pre-processed on the server. This pre-processing includes removing missing values ​​and outliers and standardizing the data format.

[0653] The server then uses a machine learning model to predict demand based on the pre-processed data. This model is trained based on past data and market trends. Based on the results of the demand forecast, the server analyzes competitors' prices and calculates the optimal taxi fare. This takes into account not only the demand forecast results and the results of the competitor analysis, but also specific pricing rules and constraints.

[0654] Terminal

[0655] The terminal refers to the smartphone used by taxi drivers and passengers. The optimal fare calculated by the server is sent to the terminal via push notification or app notification. This allows drivers and passengers to check the latest price in real time. The terminal's user interface also displays detailed information such as the reasons for the price setting, predicted demand, and competitor trends.

[0656] User

[0657] Users include system administrators, taxi drivers, and service users. Through the dashboard, users can check pricing and the reasons for it, the latest demand forecast, and competitor trends. They can also customize the parameters of the forecasting model and assign weights to specific factors. Furthermore, users can send feedback to the server to further customize the forecasting model.

[0658] Specific examples

[0659] Consider the following scenario: If information collected from an external API indicates that a large rock festival will be held in a city next week, the server uses this information to predict a surge in demand. Using data from past similar events, the server increases pricing by 25% over normal rates. This information is sent to drivers' and passengers' smartphones, and the dashboard displays the reason for the price adjustment as "Increased demand due to rock festival."

[0660] Prompt Sentence Examples

[0661] "Please forecast demand during the rock festival based on market trends, traffic conditions, and event information for the next two weeks, and set the optimal taxi fares. Please also take into account past data."

[0662] As described above, the system of the present invention can maximize the utilization rate and revenue of autonomous taxi services by collecting and analyzing data in real time and providing optimal pricing.

[0663] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0664] Step 1: Data collection

[0665] The server uses external APIs to collect market trend data, traffic situation data, specific event information, and operation status data. This data is obtained in real time and updated periodically. Specifically, it makes API calls, standardizes the data format, and saves it in a database. The input is raw data obtained from the API, and the output is standardized data required for preprocessing.

[0666] Step 2: Data Preprocessing

[0667] The server performs preprocessing on the collected data. This preprocessing includes removing missing values ​​and outliers and standardizing the data format. Specifically, it uses a data cleaning algorithm to filter out inappropriate data. The input is the collected raw data, and the output is clean data that can be analyzed.

[0668] Step 3: Demand forecast

[0669] The server uses a machine learning model on the preprocessed data to forecast demand. The model used is a generative AI model trained based on past data and market trends. Specifically, clean data is input into the model to generate forecast results that predict future demand. The input is clean data, and the output is predicted demand data.

[0670] Step 4: Competitive analysis

[0671] The server collects competitors' pricing information and performs price analysis based on the collected information. Specifically, it obtains competitors' pricing data from an external API and compares it with the company's own prediction results. The input is competitors' pricing data, and the output is competitor comparison data.

[0672] Step 5: Price optimization

[0673] The server calculates the optimal fare based on the demand forecast and competitive analysis results. This calculation takes into account not only the demand forecast and competitive analysis results, but also specific pricing rules and constraints. Specifically, it uses a fare calculation algorithm to calculate the optimal price. The inputs are the demand forecast and competitive comparison data, and the output is the optimized fare data.

[0674] Step 6: Price Notification

[0675] The server sends the optimized fare data to the terminal and notifies the driver and passenger through push notifications or app notifications. Specifically, a notification server is used to deliver price information to the driver's and passenger's smartphones in real time. The input is the optimized fare data, and the output is the notification sent to the driver and passenger.

[0676] Step 7: Provide a user interface

[0677] The terminal displays detailed information such as the reasons for pricing, forecasted demand, and competitor trends on a user interface. Specifically, it provides the user with the necessary information via a dashboard, allowing them to change settings and send feedback. The input is notification data from the server, and the output is the user's operation interface.

[0678] Step 8: Feedback and Model Customization

[0679] Users send feedback to the system, and the server customizes the predictive model based on that feedback. Specifically, the server analyzes the user's feedback and adjusts the parameters of the machine learning model. The input is the user's feedback, and the output is a customized predictive model.

[0680] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0681] The system of the present invention combines an AI-based platform for optimizing hotel pricing and revenue management with an emotion engine that recognizes user emotions. The system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[0682] Program Overview

[0683] The program of the present invention collects market trends, guest behavior, local event information, and user sentiment in real time, and uses this data to forecast demand and calculate optimal room rates. It also evaluates user sentiment and incorporates the results into forecasting models and pricing. The results are then communicated to users, maximizing hotel occupancy and revenue.

[0684] Program processing

[0685] 1. Data Collection

[0686] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[0687] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[0688] 2. Data Preprocessing

[0689] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0690] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0691] 3. Demand forecasting

[0692] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0693] 4. Price optimization

[0694] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0695] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis results. The server also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses displeasure, the server adjusts the rate by reducing it.

[0696] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[0697] 5. Notification of Results

[0698] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0699] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0700] 6. User Interface

[0701] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0702] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[0703] Specific examples

[0704] Responses during periods of increased reservations

[0705] 1. Data Collection:

[0706] Server: Collects information about next week's major music festivals from an external API.

[0707] Server: Uses an emotion engine to collect user emotion data, for example, to ensure that users are sending a lot of positive feedback.

[0708] 2. Data Preprocessing:

[0709] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[0710] 3. Demand forecasting:

[0711] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[0712] 4. Price Optimization:

[0713] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[0714] Server: Based on the demand forecast results, increase the room rate by 30%. Also, consider the positive sentiment of users and add special offers.

[0715] 5. Notification of Results:

[0716] Server: Sends updated pricing information to the PMS and reflects it on the device.

[0717] 6. User Interface:

[0718] Users: See the reason for the price adjustment (increased demand due to music festivals) and its impact in the dashboard, along with feedback from the sentiment engine.

[0719] Off-season response

[0720] 1. Data Collection:

[0721] Server: Checks current reservation status data and whether there are any upcoming major events.

[0722] Server: Use the emotion engine to collect user emotion data. Check for a high number of negative feedbacks.

[0723] 2. Data Preprocessing:

[0724] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[0725] 3. Demand forecasting:

[0726] Server: Predicts a drop in demand based on data from similar periods in the past.

[0727] 4. Price Optimization:

[0728] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[0729] Server: Based on demand forecasts, reduce room rates by 20%, add rewards packages, and consider campaigns to alleviate negative sentiment.

[0730] 5. Notification of Results:

[0731] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[0732] 6. User Interface:

[0733] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed. Feedback from the sentiment engine is also displayed.

[0734] In this way, the system of the present invention uses an emotion engine to evaluate user emotions, collects and analyzes data in real time using AI, and sets optimal prices, thereby maximizing hotel occupancy rates and profits.

[0735] The processing flow will be explained below.

[0736] Step 1:

[0737] Data collection:

[0738] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[0739] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[0740] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[0741] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[0742] Step 2:

[0743] Data preprocessing:

[0744] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[0745] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[0746] Step 3:

[0747] Demand forecast:

[0748] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[0749] Step 4:

[0750] Competitive analysis:

[0751] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[0752] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[0753] Step 5:

[0754] Price Optimization:

[0755] Server: Calculates optimal room rates based on demand forecasts and competitive analysis results, using algorithms aimed at maximizing hotel occupancy and profits.

[0756] Server: The server applies the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.) to the calculated optimal price. It also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses dissatisfaction, the server may adjust the price by lowering it.

[0757] Step 6:

[0758] Notification of results:

[0759] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[0760] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[0761] Step 7:

[0762] User Interface:

[0763] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[0764] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[0765] Example 2

[0766] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0767] Traditional hotel pricing and revenue management systems are primarily based on market trends, competitive analysis, and guest behavior, but do not take into account user sentiment and immediate feedback, which can result in inadequate pricing, customer satisfaction, and maximum revenue.

[0768] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for collecting user emotion data, means for preprocessing the collected data, means for analyzing the preprocessed data and emotion data and forecasting demand, means for collecting and analyzing competitors' price information, means for calculating optimal room rates based on the forecast results, competitive analysis, and emotion data, means for applying pricing rules based on the calculated rates to determine final prices, means for notifying the hotel management system of the final price information, and means for providing a dashboard and displaying pricing settings, reasons for the settings, and emotion feedback. This enables optimal pricing, demand forecasting, and competitive analysis that take user emotions into account, thereby improving customer satisfaction and maximizing profits.

[0769] "Market trend data" refers to information that indicates changes and trends in market supply and demand, and primarily includes economic data and industry trends.

[0770] "Guest Behavior Data" means information including a guest's past booking history, behavioral patterns during their stay, as well as customer preferences and feedback.

[0771] "Local Event Information" is data about events and occasions taking place in a particular area, including festivals, concerts, sporting events, etc.

[0772] "User emotion data" refers to information collected from users' emotions and feedback while using the system, including emotional expressions expressed through facial expressions, voice, and text input.

[0773] "Preprocessing" refers to a series of processes for preparing collected data in an analyzable format, including filling in missing values, standardizing formats, and removing outliers.

[0774] A "machine learning algorithm" is a mathematical or statistical model that learns patterns and rules from data and predicts future data. Examples include time series prediction models and multivariate regression models.

[0775] "Competitive analysis" is a method for evaluating, analyzing, and comparing competitors' pricing and market strategies, and uses web scraping technology and API integration.

[0776] "Pricing rules" are internal regulations and external constraints regarding hotel pricing, including rules such as lowest price guarantees and special discounts.

[0777] "Notification" is a means of sending optimized price information to hotel management systems and terminals in real time to inform relevant parties.

[0778] A "dashboard" is part of the system's user interface and is a screen for visually displaying information such as pricing, demand forecasts, competitive situations, and emotional feedback.

[0779] This invention is a system for optimizing hotel pricing and revenue management, specifically combining an AI-based platform with an emotion engine that recognizes user emotions. This system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[0780] Hardware and software used

[0781] Server: Data collection, preprocessing, predictive model building, price optimization, and notifications. Uses libraries and frameworks such as Python, Scikit-learn, BeautifulSoup, and Selenium.

[0782] Emotion engine: Recognizes emotions by analyzing user feedback, facial expressions, and voice data. Specific examples include models using machine learning and deep learning.

[0783] Terminals: Computers used at front desks or administrative locations receive notifications of new pricing information and display dashboards.

[0784] User Interface: Provides a dashboard displaying pricing, demand forecasts, competitive information, and sentiment feedback.

[0785] Data collection

[0786] The server uses external APIs to collect market trend data, guest behavior data, and local event information. For example, it obtains information from tourist association APIs, social media data, and travel booking sites. This data is updated hourly.

[0787] The server uses an emotion engine to collect emotional data in real time from feedback, facial expressions, and voice data while the user is using the system. For example, data can be obtained through feedback input at the front desk or conversations with a chatbot.

[0788] Data Preprocessing

[0789] The server performs pre-processing on the collected data to remove missing values ​​and outliers. For example, it uses a data cleaning tool to detect, delete, or impute abnormal values.

[0790] The server unifies all data formats, converting different data formats (JSON, CSV, XML, etc.) into a uniform format and integrating them into a single database.

[0791] Demand forecasting

[0792] The server uses the preprocessed data and sentiment data to apply machine learning algorithms (e.g., Scikit-learn time series forecasting models and multivariate regression models) to forecast demand.

[0793] For example, historical data can be used to predict increased demand during specific events.

[0794] Price Optimization

[0795] The server uses web scraping techniques and API integration to obtain pricing information from other hotels to obtain competitor pricing, using tools such as BeautifulSoup and Selenium.

[0796] The system calculates optimal room rates based on demand forecasts and competitive analysis. For example, it raises rates during periods of high demand and lowers rates during periods of low demand. It also adjusts rates by taking into account user feedback.

[0797] The hotel's policies and specific constraints (such as lowest price guarantees and special discounts) are applied to the calculated best price to arrive at the final room price.

[0798] Notification of results

[0799] The server sends the optimized pricing information to the hotel management system, which updates the information in real time using API integration.

[0800] Terminals (front desk or administrator terminals) will receive notifications of the new pricing and will display pop-ups or alerts.

[0801] User Interface

[0802] Users access a dashboard to view optimized pricing and why, demand forecasts, competitor activity, and sentiment feedback. The dashboard is updated in real time, allowing for quick action.

[0803] Users can customize the settings of the predictive model, weighting certain factors, and see feedback from the sentiment engine.

[0804] Specific examples

[0805] Responses during periods of increased reservations

[0806] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[0807] Off-season response

[0808] For example, the server collects current reservation status and event information and uses the sentiment engine to determine that a large amount of negative feedback has been collected. The server then performs data preprocessing and predicts a decline in demand based on data from similar periods in the past. The server then analyzes the prices of competing hotels, reduces room rates by 20%, and adds special offers packages. It also considers campaigns to alleviate negative sentiment. The optimized prices and special offers are sent to the PMS and reflected on the device. Users can use the dashboard to determine the reasons for pricing and customize settings, and also check sentiment feedback.

[0809] Example prompts to input to the generative AI model

[0810] "How can I forecast demand and optimize pricing during festivals?"

[0811] "Please explain how to best adjust prices if demand drops during the off-season."

[0812] "Describe the effectiveness of using user sentiment data to set hotel prices."

[0813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0814] Step 1: Data collection

[0815] The server uses external APIs to collect market trend data, guest behavior data, and local event information, specifically from tourism association APIs, social media data, and travel booking sites.

[0816] Inputs: Market trend data from external APIs, guest behavior data, and local event information.

[0817] Output: Collected market trend data, guest behavior data, and local event information.

[0818] What it does: Executes an API call, retrieves data, and saves it to the database.

[0819] Step 2: Collecting emotion data

[0820] The server uses an emotion engine to collect emotion data from feedback input by the user while using the system, as well as facial expressions and voice data during operation.

[0821] Input: Feedback, facial expression data, and audio data.

[0822] Output: Emotion data.

[0823] How it works: Activates the emotion engine and generates emotion data in real time by analyzing feedback, facial expressions, and voice data.

[0824] Step 3: Data Preprocessing

[0825] The server pre-processes all collected data to remove missing values ​​and outliers, for example, by using Excel's data cleaning tools to detect and remove outliers.

[0826] Inputs: Collected market trend data, guest behavior data, local event information, and sentiment data.

[0827] Output: The preprocessed dataset.

[0828] Operation: Imputes missing values, removes outliers, and standardizes data formats.

[0829] Step 4: Demand forecast

[0830] The server uses the preprocessed data and sentiment data to apply machine learning algorithms to predict future demand. Specifically, it uses Python libraries (e.g., Scikit-learn) to build time series forecasting models and multivariate regression models and executes the forecasting models.

[0831] Input: Preprocessed dataset, sentiment data.

[0832] Output: Demand forecast results.

[0833] How it works: Trains machine learning models and performs forecasting to calculate future demand.

[0834] Step 5: Price optimization

[0835] The server uses web scraping technology and API integration to gather current information on competitors' pricing. Specifically, it uses tools such as BeautifulSoup and Selenium to obtain pricing information.

[0836] Inputs: Competitor pricing information, demand forecast results, sentiment data.

[0837] Output: Optimized room rates.

[0838] Operation: Obtains price information, calculates optimal prices by combining demand forecasts and competitive analysis, and adjusts prices based on user sentiment.

[0839] Step 6: Applying Pricing Rules

[0840] The server applies the hotel's policies and specific constraints (such as best price guarantees or special discounts) to the calculated best price to determine the final room price.

[0841] Input: Optimized room rates, hotel policies and constraints information.

[0842] Output: Final room price.

[0843] How it works: Rules like lowest price guarantees and special discounts are applied to determine the final price.

[0844] Step 7: Notification of results

[0845] The server sends the optimized pricing information to the hotel management system (PMS), which updates the information in real time using API integration.

[0846] Input: Final room rate.

[0847] Output: Fee information notified to PMS.

[0848] Operation: Connects to PMS via API and sends pricing information.

[0849] Step 8: User Interface

[0850] Users access a dashboard to see optimized pricing and why, the latest demand forecast, competitor activity, and sentiment feedback.

[0851] Input: Data on the dashboard.

[0852] Output: The information confirmed by the user.

[0853] What it does: Displays information visually using graphs and charts and allows users to customize settings.

[0854] Specific examples

[0855] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[0856] Example prompts to input to a generative AI model:

[0857] "How can I forecast demand and optimize pricing during festivals?"

[0858] "Please explain how to best adjust prices if demand drops during the off-season."

[0859] "Describe the effectiveness of using user sentiment data to set hotel prices."

[0860] (Application example 2)

[0861] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0862] Conventional pricing systems rely on data based on market trends and competitive analysis, which means they have a problem of not being able to reflect user emotions and behavior. In particular, it is difficult to quickly respond to fluctuations in consumer behavior and the market, which can result in lost sales opportunities and excess inventory. Furthermore, it is difficult to set optimal prices solely through competitor price analysis, so pricing that responds to consumer needs and emotions is required.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting consumer behavior data, means for collecting related event information, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand, means for analyzing the prices of competing companies, means for calculating optimal product prices based on the prediction results and competitive analysis, means for applying pricing rules based on the calculated prices to determine final prices, means for notifying final price information, means for providing a user interface and displaying price settings and the reasons for them, means for acquiring user emotion data using an emotion engine and reflecting this in price settings, means for performing demand forecasting using a machine learning algorithm, and means for adjusting prices based on specific events and feedback. This enables optimal price setting in response to consumer emotions and market trends.

[0864] "Market trend data" refers to information related to overall market trends, such as supply and demand in the market, price fluctuations, and consumer purchasing behavior.

[0865] "Consumer behavior data" refers to information about consumer behavior, such as the actions and trends consumers take when purchasing products, their purchasing history, and their search history.

[0866] "Related event information" is information about specific events, campaigns, sales, festivals, etc. that affect the market and consumption.

[0867] "Preprocessing" is a process that improves the quality of collected data by removing missing values ​​and outliers and standardizing the data format.

[0868] "Demand forecasting" is the process of predicting future demand based on market trend data, consumer behavior data, etc.

[0869] "Competitor price analysis" is the process of collecting competitors' product prices and analyzing that data to use as a reference when setting your own product prices.

[0870] "Pricing rules" are rules or restrictions that apply to set prices, such as lowest price guarantees or special discounts.

[0871] "Notification" is the act of notifying users and systems of the final calculated price information in real time.

[0872] The "user interface" is an interface for providing and displaying optimized pricing, the reasons for it, analysis results, emotion engine feedback, etc. to the user.

[0873] The "emotion engine" is a system that acquires and analyzes emotional data from the user's facial expressions, voice, etc.

[0874] A "machine learning algorithm" is a calculation method or model used to forecast demand and optimize prices based on collected data.

[0875] "Feedback" refers to opinions, impressions, and information about usability collected from system users.

[0876] The present invention is a system for optimizing pricing and revenue management on an online shopping site. This system is realized by components including a server, a terminal, and a user.

[0877] System Configuration

[0878] 1. Server:

[0879] It plays a central role in collecting, preprocessing, and analyzing various types of data.

[0880] Collect market trend data, consumer behavior data, relevant event information, and competitor pricing data.

[0881] The emotion engine collects user emotion data.

[0882] This data is preprocessed and demand forecasts are made using machine learning algorithms.

[0883] Calculate the optimal product price based on the forecast results and competitive analysis, and determine the final price in accordance with pricing rules.

[0884] It has the function of notifying the final price information.

[0885] 2. Terminal:

[0886] It provides a dashboard for users to see pricing and why, the latest demand forecasts, and competitor activity.

[0887] It can be accessed from various devices such as mobile devices and PCs.

[0888] 3. User:

[0889] Provides emotion data collected by the emotion engine.

[0890] Review pricing information provided by the system and provide feedback if necessary.

[0891] Processing Details

[0892] Data collection

[0893] The server uses external APIs to collect market trend data, consumer behavior data, and related event information in real time, and also uses web scraping technology to obtain competitor pricing information.

[0894] The emotion engine uses the camera and microphone on the user's smartphone to collect emotional data from facial expressions and voice.

[0895] Data Preprocessing

[0896] The server performs preprocessing of the collected data, removing missing values ​​and outliers and standardizing the data format to improve data quality.

[0897] Demand forecasting

[0898] The server applies machine learning algorithms (e.g., LSTM models or multivariate regression models) based on the preprocessed data to predict future demand.

[0899] Price Optimization

[0900] The server calculates the optimal product price based on the prediction results and the competitive analysis results, taking into account the user's emotional evaluation results obtained by the emotion engine.

[0901] Pricing rules will be applied to determine the final price.

[0902] Notification of results

[0903] The server notifies the user interface of the optimized pricing information in real time.

[0904] Specific examples

[0905] Seasonal sale pricing

[0906] 1. Data Collection:

[0907] The server collects market trend data for Black Friday.

[0908] The emotion engine confirmed that users frequently displayed excited facial expressions while using the app.

[0909] 2. Data Preprocessing:

[0910] The server preprocesses the collected data and removes missing values ​​and outliers.

[0911] 3. Demand forecasting:

[0912] The server uses historical data from Black Friday to predict a surge in demand.

[0913] 4. Price Optimization:

[0914] The server collects competitor pricing information and offers a 20% discount.

[0915] Consider sentiment data and provide special offers to users.

[0916] 5. Notification of Results:

[0917] The server sends the updated price information to the online shopping site's system.

[0918] 6. User Interface:

[0919] Users can see the reason behind the new price (Black Friday sale) and see the sentiment engine feedback.

[0920] Prompt Sentence Examples

[0921] "Predict demand and set prices for Black Friday"

[0922] "Adjust prices for products with many negative reviews"

[0923] In this way, by utilizing an emotion engine and machine learning algorithms, it is possible to create a system that enables optimal pricing in response to user emotions and market trends.

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1: Data collection

[0926] The server uses external APIs to collect market trend data, consumer behavior data, and related event information. The server retrieves data in JSON format from the external APIs. It also uses web scraping technology to collect pricing information from competitors. Furthermore, the emotion engine uses the smartphone's camera and microphone to collect emotion data in real time from the user's facial expressions and voice. The inputs are market trend data, consumer behavior data, related event information, and emotion data, and the output is an integrated set of these data.

[0927] Step 2: Data Preprocessing

[0928] The server preprocesses the data collected in step 1, specifically removing missing values ​​and outliers and standardizing the data format (e.g., normalizing numerical data and encoding categorical data). The input is the data collected in step 1, and the output is a preprocessed, consistent dataset.

[0929] Step 3: Demand forecast

[0930] The server uses the preprocessed data to apply machine learning algorithms (e.g., LSTM models, time series forecasting models) to predict future demand. The server trains the model based on past data and performs demand forecasts based on new data. The input is the preprocessed data, and the output is the future demand forecast.

[0931] Step 4: Price optimization

[0932] The server calculates the optimal product price based on the demand forecast results and competitive analysis results. It also takes into account the user's emotional data from the emotion engine, adjusting the price if the user expresses displeasure, for example. It applies pricing rules to determine the final price. The inputs are the demand forecast results, competitive analysis results, and emotional data, and the output is the optimized product price.

[0933] Step 5: Notification of results

[0934] The server reflects the optimized price information in the online shopping site's pricing system. Specifically, it updates the price information using an API and notifies users of the price change via in-app notifications or push notifications. The input is the optimized price information, and the output is the updated price information and a notification to the user.

[0935] Step 6: User Interface

[0936] Users can check pricing and its reasons, demand forecast results, and competitive analysis data in real time through the provided dashboard. Users can also check feedback from the sentiment engine and send feedback as needed. The input is the notified price information and analysis data, and the output is the display on the dashboard and feedback from users.

[0937] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0938] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0939] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0940] [Third embodiment]

[0941] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0942] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0943] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0944] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0945] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0946] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0947] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0948] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0949] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0950] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0951] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0952] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0953] The system of the present invention is an AI-based platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component.

[0954] Program Overview

[0955] The program of the present invention collects information on market trends, guest behavior, and local events in real time, and uses this data to forecast demand and calculate optimal room rates. The results are then notified to users, maximizing hotel occupancy rates and revenue.

[0956] Program processing

[0957] 1. Data Collection

[0958] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[0959] 2. Data analysis

[0960] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[0961] Server: Predicts demand from pre-processed data using machine learning models that are trained based on historical data and market trends.

[0962] 3. Price optimization

[0963] Server: Analyze competitor pricing and gather information to compare with your hotel's prices.

[0964] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis, taking into account the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.).

[0965] 4. Notification of Results

[0966] Server: Sends optimized pricing information to the hotel's PMS (Property Management System), and notifies connected reservation systems and front desk terminals.

[0967] 5. User Interface

[0968] Users can view optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model to weight specific factors.

[0969] Specific examples

[0970] Responses during periods of increased reservations

[0971] 1. Data Collection:

[0972] Server: Collects information about next week's major music festivals from an external API.

[0973] 2. Data Analysis:

[0974] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[0975] 3. Price optimization:

[0976] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[0977] Server: Based on the demand forecast results, increase the room rate by 30%.

[0978] 4. Notification of Results:

[0979] Server: Sends updated pricing information to the PMS and reflects it on the device.

[0980] 5. User Interface:

[0981] Users: View the dashboard to see the reason for the price adjustment (increased demand due to a music festival) and its impact.

[0982] Off-season response

[0983] 1. Data Collection:

[0984] Server: Checks current reservation status data and whether there are any upcoming major events.

[0985] 2. Data Analysis:

[0986] Server: Predicts a drop in demand based on data from similar periods in the past.

[0987] 3. Price optimization:

[0988] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[0989] Server: Based on forecasted demand, we will reduce room rates by 20% and add special offers packages.

[0990] 4. Notification of Results:

[0991] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[0992] 5. User Interface:

[0993] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed.

[0994] In this way, the system of the present invention uses AI to collect and analyze data in real time and set optimal prices, thereby maximizing hotel occupancy rates and profits.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] Data collection:

[0998] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[0999] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[1000] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[1001] Step 2:

[1002] Data preprocessing:

[1003] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1004] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1005] Step 3:

[1006] Demand forecast:

[1007] Server: Using the pre-processed data, machine learning algorithms (e.g., time series forecasting models or multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1008] Step 4:

[1009] Competitive analysis:

[1010] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1011] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[1012] Step 5:

[1013] Price Optimization:

[1014] Server: Calculates optimal room rates based on demand forecasts and competitive analysis, using algorithms designed to maximize hotel occupancy and profits.

[1015] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[1016] Step 6:

[1017] Notification of results:

[1018] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1019] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1020] Step 7:

[1021] User Interface:

[1022] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1023] Users: Use the ability to customize the forecast model settings to weight specific factors, which will take effect immediately and affect the next forecast.

[1024] Example 1

[1025] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1026] In the hotel industry, optimizing room rates and maximizing revenue are important challenges. However, current methods often involve manual data collection and analysis, making it difficult to quickly respond to fluctuations in demand or competitor pricing trends. This often results in missed revenue opportunities and makes it difficult to set optimal prices. Furthermore, data preprocessing and machine learning model adjustments require specialized knowledge, making them difficult for average users to use. To solve these issues, a system is needed that can collect and analyze a variety of data in real time and quickly propose prices.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1028] In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for preprocessing the collected data, means for analyzing the preprocessed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal room rates based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated rates and determining final prices, means for notifying final price information, means for providing a user interface and displaying pricing settings and reasons for them, means for forecasting demand using a machine learning model and customizing model parameters, and means for collecting data using an external API. This enables accurate data collection and analysis in real time, enabling prompt and optimal room rate setting.

[1029] "Market trend data" is information that shows overall market movements, such as market trends, price fluctuations, and consumer preferences.

[1030] "Guest behavior data" refers to information that indicates the behavioral patterns of guests, such as their reservation status, cancellation history, frequency of stay, and length of stay.

[1031] "Local event information" is event information related to a particular area, such as concerts, festivals, and sporting events held in that area.

[1032] "Means for preprocessing collected data" refers to techniques for removing missing values ​​and outliers from collected data and standardizing the data format.

[1033] "Means for analyzing preprocessed data and forecasting demand" refers to technology for forecasting future demand using preprocessed data, and employs machine learning models, etc.

[1034] "Means to analyze competitors' prices" refers to the technology of collecting and analyzing the pricing of other hotels in the same market.

[1035] "Means for calculating optimal room rates based on forecast results and competitive analysis" refers to a technology for calculating optimal room rates based on the results of demand forecasts and the results of competitor price analysis.

[1036] "Means for determining the final price by applying pricing rules based on the calculated rate" refers to a technology that applies the hotel's policies and restrictions to the calculated rate to determine the final price.

[1037] The "means for notifying final price information" is a technology for transmitting the determined final price to the hotel's management system or reservation system.

[1038] The "means for providing a user interface and displaying pricing and the reasons therefor" refers to a technique for providing an interface for a user to check pricing and the reasons therefor.

[1039] "Means for forecasting demand using a machine learning model and customizing the model parameters" is a technology that uses a machine learning model to forecast demand and allows users to adjust the parameters of the model.

[1040] "Means of collecting data using external APIs" refers to technology that uses APIs to obtain data from external systems and services.

[1041] The system of the present invention is an AI-powered platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component. The server uses external APIs to collect market trend data, guest behavior data, and local event information. The server preprocesses the collected data and uses a machine learning model to predict demand. Based on this prediction, the server analyzes competitors' prices and calculates the optimal room rate. The server then sends the optimized pricing information to a property management system (PMS), which then notifies the connected reservation system and front desk terminal. Users can view the optimized pricing and the reasons for it, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the predictive model and assign weights to specific factors.

[1042] Hardware and software used

[1043] Server: The server is responsible for a series of processes such as data collection, preprocessing, analysis, price calculation, and notification. It uses Python and its libraries (pandas, scikit-learn, etc.) and uses HTTP requests to communicate with external APIs.

[1044] Terminals: Terminals used at the front desk or reservation system are designed to display optimized pricing information in real time, often with a browser-based interface.

[1045] User Interface: A browser-based dashboard allows users to see pricing and why, with specific graphical representations and numerical details, and often uses a front-end framework such as React or Vue.js.

[1046] Specific examples

[1047] Responses during periods of increased reservations

[1048] 1. The server collects information about large music festivals scheduled for next week from an external API.

[1049] 2. The server uses a machine learning model to predict a surge in demand based on historical data from the festival period.

[1050] 3. The server compares competitors' prices with the hotel's regular rates and increases the room rate by 30% based on the demand forecast results.

[1051] 4. The server sends the updated fee information to the PMS and reflects it on the terminal.

[1052] 5. The user sees the reason for the price adjustment (increased demand due to a music festival) and its impact on the dashboard.

[1053] Off-season response

[1054] 1. The server checks the current reservation status data and checks that there are no upcoming major events.

[1055] 2. The server predicts a drop in demand based on data from similar periods in the past.

[1056] 3. The server analyzes the pricing of competing hotels and compares it with the hotel's regular price.

[1057] 4. The server reduces the room rate by 20% and adds a special offer package based on demand forecasts.

[1058] 5. The server sends the adjusted price and benefit information to the PMS, which then reflects it on the terminal.

[1059] 6. User can check the reason for the pricing (low demand) through the dashboard and customize settings as needed.

[1060] In this way, the system of the present invention maximizes hotel occupancy rates and revenue by utilizing external APIs to collect data in real time and forecasting demand using machine learning models. Furthermore, users can view the system's pricing process and its background through a dashboard, enhancing reliability and transparency.

[1061] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1062] System program processing flow

[1063] Step 1: Data collection

[1064] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information.

[1065] Specific operation: The server calls "MarketDataAPI" or "EventInfoAPI" and periodically obtains the data returned in JSON format.

[1066] Inputs: Market trend data, guest behavior data, local event information

[1067] Output: Raw collected data (JSON format)

[1068] Step 2: Data Preprocessing

[1069] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[1070] Specific operation: The server uses Python's pandas library, removes missing values ​​using DataFrame.dropna(), and unifies the date and time format using pd.to_datetime().

[1071] Input: Raw data collected

[1072] Output: Preprocessed data

[1073] Step 3: Demand forecast

[1074] Server: Uses pre-processed data to predict demand using machine learning models.

[1075] Specific operation: The server uses scikit-learn's LinearRegression model, learns from past data using the fit method, and performs demand forecasting using the predict method.

[1076] Input: Preprocessed data

[1077] Output: Demand forecast results

[1078] Step 4: Price optimization

[1079] Server: Collects competitor pricing information and compares it with the hotel's own rates. Then, based on the demand forecast and competitor pricing analysis results, calculates the optimal room rate taking into account specific constraints.

[1080] Specific operation: The server calls the "CompetitorPriceAPI" to obtain competitor price data in JSON format. It then uses Python to integrate the demand data and competitor prices to calculate the optimal price.

[1081] Input: Demand forecast results, competitor price data

[1082] Output: Calculated optimal room price

[1083] Step 5: Notification of results

[1084] Server: Sends optimized pricing information to the PMS and notifies connected reservation systems and front desk terminals.

[1085] What happens: The server sends the new price information to the PMS API endpoint using an HTTP POST request.

[1086] Input: Calculated best room price

[1087] Output: New price information reflected in PMS and terminal

[1088] Step 6: User Interface

[1089] Users: View optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model.

[1090] What it does: A user logs in and accesses the dashboard via a browser, where they can view data in charts and tables and adjust forecast parameters using sliders.

[1091] Input: Parameter settings entered by the user

[1092] Output: Display of updated forecast results and pricing information

[1093] In this way, the system performs specific data processing and calculations at each step, ultimately providing the user with the optimal pricing and the reasons for it.

[1094] (Application example 1)

[1095] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1096] The challenge is to maximize the operational efficiency of taxi services using autonomous vehicles and optimize the utilization rate and revenue of taxis in operation. To achieve this, it is necessary to accurately predict demand for market trends, traffic conditions, and specific events, which fluctuate in real time, and set appropriate prices. However, current technology does not yet have a system that can efficiently collect and analyze these factors and automatically optimize prices. This makes it difficult to respond to fluctuations in demand and maximize revenue.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1098] In this invention, the server includes means for collecting market trend data, means for collecting traffic condition data, means for collecting specific event information, means for collecting operation condition data, means for pre-processing the collected data, means for analyzing the pre-processed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal fares based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated fares to determine final prices, means for notifying final price information, and means for providing a user interface and displaying pricing settings and reasons for them, thereby optimizing operation management and pricing settings of autonomous taxi services in real time and maximizing profits.

[1099] "Market trend data" is information used to understand market conditions and fluctuations. This includes data on economic indicators, consumer behavior, price fluctuations, etc.

[1100] "Traffic condition data" refers to information related to road congestion and traffic flow, including traffic jams, accidents, and traffic light status.

[1101] "Specific event information" refers to information about events that take place at specific dates, times, and locations. This refers to information about events that affect demand, such as concerts, sporting events, and local festivals.

[1102] "Operation status data" refers to information about the current operating status, location, speed, etc. of an autonomous vehicle. This data is used to understand the real-time status of the vehicle while it is in operation.

[1103] "Preprocessing" is the process of removing missing values ​​and outliers from collected data and preparing the data in a format that is easy to analyze.

[1104] "Demand forecasting" refers to predicting future demand based on past data and current conditions. This is done using machine learning and statistical models.

[1105] "Competitive analysis" refers to researching and comparatively analyzing the pricing and service content of competitors, which can be used to help develop your own pricing strategy.

[1106] "Pricing rules" refer to pre-determined pricing rules and standards that are used to calculate optimal prices based on demand and competitive conditions.

[1107] "User interface" refers to the display and controls that allow a user to interact with a system, including graphical interfaces and dashboards.

[1108] "Notification" refers to the process by which the system communicates calculation results and updated information to relevant parties. This includes push notifications on smartphones and emails.

[1109] The system of the present invention is a technology for optimizing the operation management and pricing of autonomous taxi services. The system is implemented by components including a server, a terminal, and a user.

[1110] server

[1111] The server collects market trend data, traffic data, specific event information, and operational status data in real time using external APIs. This data is updated periodically and pre-processed on the server. This pre-processing includes removing missing values ​​and outliers and standardizing the data format.

[1112] The server then uses a machine learning model to predict demand based on the pre-processed data. This model is trained based on past data and market trends. Based on the results of the demand forecast, the server analyzes competitors' prices and calculates the optimal taxi fare. This takes into account not only the demand forecast results and the results of the competitor analysis, but also specific pricing rules and constraints.

[1113] Terminal

[1114] The terminal refers to the smartphone used by taxi drivers and passengers. The optimal fare calculated by the server is sent to the terminal via push notification or app notification. This allows drivers and passengers to check the latest price in real time. The terminal's user interface also displays detailed information such as the reasons for the price setting, predicted demand, and competitor trends.

[1115] User

[1116] Users include system administrators, taxi drivers, and service users. Through the dashboard, users can check pricing and the reasons for it, the latest demand forecast, and competitor trends. They can also customize the parameters of the forecasting model and assign weights to specific factors. Furthermore, users can send feedback to the server to further customize the forecasting model.

[1117] Specific examples

[1118] Consider the following scenario: If information collected from an external API indicates that a large rock festival will be held in a city next week, the server uses this information to predict a surge in demand. Using data from past similar events, the server increases pricing by 25% over normal rates. This information is sent to drivers' and passengers' smartphones, and the dashboard displays the reason for the price adjustment as "Increased demand due to rock festival."

[1119] Prompt Sentence Examples

[1120] "Please forecast demand during the rock festival based on market trends, traffic conditions, and event information for the next two weeks, and set the optimal taxi fares. Please also take into account past data."

[1121] As described above, the system of the present invention can maximize the utilization rate and revenue of autonomous taxi services by collecting and analyzing data in real time and providing optimal pricing.

[1122] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1123] Step 1: Data collection

[1124] The server uses external APIs to collect market trend data, traffic situation data, specific event information, and operation status data. This data is obtained in real time and updated periodically. Specifically, it makes API calls, standardizes the data format, and saves it in a database. The input is raw data obtained from the API, and the output is standardized data required for preprocessing.

[1125] Step 2: Data Preprocessing

[1126] The server performs preprocessing on the collected data. This preprocessing includes removing missing values ​​and outliers and standardizing the data format. Specifically, it uses a data cleaning algorithm to filter out inappropriate data. The input is the collected raw data, and the output is clean data that can be analyzed.

[1127] Step 3: Demand forecast

[1128] The server uses a machine learning model on the preprocessed data to forecast demand. The model used is a generative AI model trained based on past data and market trends. Specifically, clean data is input into the model to generate forecast results that predict future demand. The input is clean data, and the output is predicted demand data.

[1129] Step 4: Competitive analysis

[1130] The server collects competitors' pricing information and performs price analysis based on the collected information. Specifically, it obtains competitors' pricing data from an external API and compares it with the company's own prediction results. The input is competitors' pricing data, and the output is competitor comparison data.

[1131] Step 5: Price optimization

[1132] The server calculates the optimal fare based on the demand forecast and competitive analysis results. This calculation takes into account not only the demand forecast and competitive analysis results, but also specific pricing rules and constraints. Specifically, it uses a fare calculation algorithm to calculate the optimal price. The inputs are the demand forecast and competitive comparison data, and the output is the optimized fare data.

[1133] Step 6: Price Notification

[1134] The server sends the optimized fare data to the terminal and notifies the driver and passenger through push notifications or app notifications. Specifically, a notification server is used to deliver price information to the driver's and passenger's smartphones in real time. The input is the optimized fare data, and the output is the notification sent to the driver and passenger.

[1135] Step 7: Provide a user interface

[1136] The terminal displays detailed information such as the reasons for pricing, forecasted demand, and competitor trends on a user interface. Specifically, it provides the user with the necessary information via a dashboard, allowing them to change settings and send feedback. The input is notification data from the server, and the output is the user's operation interface.

[1137] Step 8: Feedback and Model Customization

[1138] Users send feedback to the system, and the server customizes the predictive model based on that feedback. Specifically, the server analyzes the user's feedback and adjusts the parameters of the machine learning model. The input is the user's feedback, and the output is a customized predictive model.

[1139] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1140] The system of the present invention combines an AI-based platform for optimizing hotel pricing and revenue management with an emotion engine that recognizes user emotions. The system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[1141] Program Overview

[1142] The program of the present invention collects market trends, guest behavior, local event information, and user sentiment in real time, and uses this data to forecast demand and calculate optimal room rates. It also evaluates user sentiment and incorporates the results into forecasting models and pricing. The results are then communicated to users, maximizing hotel occupancy and revenue.

[1143] Program processing

[1144] 1. Data Collection

[1145] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[1146] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[1147] 2. Data Preprocessing

[1148] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1149] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1150] 3. Demand forecasting

[1151] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1152] 4. Price optimization

[1153] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1154] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis results. The server also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses displeasure, the server adjusts the rate by reducing it.

[1155] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[1156] 5. Notification of Results

[1157] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1158] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1159] 6. User Interface

[1160] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1161] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[1162] Specific examples

[1163] Responses during periods of increased reservations

[1164] 1. Data Collection:

[1165] Server: Collects information about next week's major music festivals from an external API.

[1166] Server: Uses an emotion engine to collect user emotion data, for example, to ensure that users are sending a lot of positive feedback.

[1167] 2. Data Preprocessing:

[1168] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[1169] 3. Demand forecasting:

[1170] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[1171] 4. Price Optimization:

[1172] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[1173] Server: Based on the demand forecast results, increase the room rate by 30%. Also, consider the positive sentiment of users and add special offers.

[1174] 5. Notification of Results:

[1175] Server: Sends updated pricing information to the PMS and reflects it on the device.

[1176] 6. User Interface:

[1177] Users: See the reason for the price adjustment (increased demand due to music festivals) and its impact in the dashboard, along with feedback from the sentiment engine.

[1178] Off-season response

[1179] 1. Data Collection:

[1180] Server: Checks current reservation status data and whether there are any upcoming major events.

[1181] Server: Use the emotion engine to collect user emotion data. Check for a high number of negative feedbacks.

[1182] 2. Data Preprocessing:

[1183] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[1184] 3. Demand forecasting:

[1185] Server: Predicts a drop in demand based on data from similar periods in the past.

[1186] 4. Price Optimization:

[1187] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[1188] Server: Based on demand forecasts, reduce room rates by 20%, add rewards packages, and consider campaigns to alleviate negative sentiment.

[1189] 5. Notification of Results:

[1190] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[1191] 6. User Interface:

[1192] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed. Feedback from the sentiment engine is also displayed.

[1193] In this way, the system of the present invention uses an emotion engine to evaluate user emotions, collects and analyzes data in real time using AI, and sets optimal prices, thereby maximizing hotel occupancy rates and profits.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] Data collection:

[1197] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[1198] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[1199] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[1200] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[1201] Step 2:

[1202] Data preprocessing:

[1203] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1204] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1205] Step 3:

[1206] Demand forecast:

[1207] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1208] Step 4:

[1209] Competitive analysis:

[1210] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1211] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[1212] Step 5:

[1213] Price Optimization:

[1214] Server: Calculates optimal room rates based on demand forecasts and competitive analysis results, using algorithms aimed at maximizing hotel occupancy and profits.

[1215] Server: The server applies the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.) to the calculated optimal price. It also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses dissatisfaction, the server may adjust the price by lowering it.

[1216] Step 6:

[1217] Notification of results:

[1218] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1219] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1220] Step 7:

[1221] User Interface:

[1222] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1223] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[1224] Example 2

[1225] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1226] Traditional hotel pricing and revenue management systems are primarily based on market trends, competitive analysis, and guest behavior, but do not take into account user sentiment and immediate feedback, which can result in inadequate pricing, customer satisfaction, and maximum revenue.

[1227] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for collecting user emotion data, means for preprocessing the collected data, means for analyzing the preprocessed data and emotion data and forecasting demand, means for collecting and analyzing competitors' price information, means for calculating optimal room rates based on the forecast results, competitive analysis, and emotion data, means for applying pricing rules based on the calculated rates to determine final prices, means for notifying the hotel management system of the final price information, and means for providing a dashboard and displaying pricing settings, reasons for the settings, and emotion feedback. This enables optimal pricing, demand forecasting, and competitive analysis that take user emotions into account, thereby improving customer satisfaction and maximizing profits.

[1228] "Market trend data" refers to information that indicates changes and trends in market supply and demand, and primarily includes economic data and industry trends.

[1229] "Guest Behavior Data" means information including a guest's past booking history, behavioral patterns during their stay, as well as customer preferences and feedback.

[1230] "Local Event Information" is data about events and occasions taking place in a particular area, including festivals, concerts, sporting events, etc.

[1231] "User emotion data" refers to information collected from users' emotions and feedback while using the system, including emotional expressions expressed through facial expressions, voice, and text input.

[1232] "Preprocessing" refers to a series of processes for preparing collected data in an analyzable format, including filling in missing values, standardizing formats, and removing outliers.

[1233] A "machine learning algorithm" is a mathematical or statistical model that learns patterns and rules from data and predicts future data. Examples include time series prediction models and multivariate regression models.

[1234] "Competitive analysis" is a method for evaluating, analyzing, and comparing competitors' pricing and market strategies, and uses web scraping technology and API integration.

[1235] "Pricing rules" are internal regulations and external constraints regarding hotel pricing, including rules such as lowest price guarantees and special discounts.

[1236] "Notification" is a means of sending optimized price information to hotel management systems and terminals in real time to inform relevant parties.

[1237] A "dashboard" is part of the system's user interface and is a screen for visually displaying information such as pricing, demand forecasts, competitive situations, and emotional feedback.

[1238] This invention is a system for optimizing hotel pricing and revenue management, specifically combining an AI-based platform with an emotion engine that recognizes user emotions. This system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[1239] Hardware and software used

[1240] Server: Data collection, preprocessing, predictive model building, price optimization, and notifications. Uses libraries and frameworks such as Python, Scikit-learn, BeautifulSoup, and Selenium.

[1241] Emotion engine: Recognizes emotions by analyzing user feedback, facial expressions, and voice data. Specific examples include models using machine learning and deep learning.

[1242] Terminals: Computers used at front desks or administrative locations receive notifications of new pricing information and display dashboards.

[1243] User Interface: Provides a dashboard displaying pricing, demand forecasts, competitive information, and sentiment feedback.

[1244] Data collection

[1245] The server uses external APIs to collect market trend data, guest behavior data, and local event information. For example, it obtains information from tourist association APIs, social media data, and travel booking sites. This data is updated hourly.

[1246] The server uses an emotion engine to collect emotional data in real time from feedback, facial expressions, and voice data while the user is using the system. For example, data can be obtained through feedback input at the front desk or conversations with a chatbot.

[1247] Data Preprocessing

[1248] The server performs pre-processing on the collected data to remove missing values ​​and outliers. For example, it uses a data cleaning tool to detect, delete, or impute abnormal values.

[1249] The server unifies all data formats, converting different data formats (JSON, CSV, XML, etc.) into a uniform format and integrating them into a single database.

[1250] Demand forecasting

[1251] The server uses the preprocessed data and sentiment data to apply machine learning algorithms (e.g., Scikit-learn time series forecasting models and multivariate regression models) to forecast demand.

[1252] For example, historical data can be used to predict increased demand during specific events.

[1253] Price Optimization

[1254] The server uses web scraping techniques and API integration to obtain pricing information from other hotels to obtain competitor pricing, using tools such as BeautifulSoup and Selenium.

[1255] The system calculates optimal room rates based on demand forecasts and competitive analysis. For example, it raises rates during periods of high demand and lowers rates during periods of low demand. It also adjusts rates by taking into account user feedback.

[1256] The hotel's policies and specific constraints (such as lowest price guarantees and special discounts) are applied to the calculated best price to arrive at the final room price.

[1257] Notification of results

[1258] The server sends the optimized pricing information to the hotel management system, which updates the information in real time using API integration.

[1259] Terminals (front desk or administrator terminals) will receive notifications of the new pricing and will display pop-ups or alerts.

[1260] User Interface

[1261] Users access a dashboard to view optimized pricing and why, demand forecasts, competitor activity, and sentiment feedback. The dashboard is updated in real time, allowing for quick action.

[1262] Users can customize the settings of the predictive model, weighting certain factors, and see feedback from the sentiment engine.

[1263] Specific examples

[1264] Responses during periods of increased reservations

[1265] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[1266] Off-season response

[1267] For example, the server collects current reservation status and event information and uses the sentiment engine to determine that a large amount of negative feedback has been collected. The server then performs data preprocessing and predicts a decline in demand based on data from similar periods in the past. The server then analyzes the prices of competing hotels, reduces room rates by 20%, and adds special offers packages. It also considers campaigns to alleviate negative sentiment. The optimized prices and special offers are sent to the PMS and reflected on the device. Users can use the dashboard to determine the reasons for pricing and customize settings, and also check sentiment feedback.

[1268] Example prompts to input to the generative AI model

[1269] "How can I forecast demand and optimize pricing during festivals?"

[1270] "Please explain how to best adjust prices if demand drops during the off-season."

[1271] "Describe the effectiveness of using user sentiment data to set hotel prices."

[1272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1273] Step 1: Data collection

[1274] The server uses external APIs to collect market trend data, guest behavior data, and local event information, specifically from tourism association APIs, social media data, and travel booking sites.

[1275] Inputs: Market trend data from external APIs, guest behavior data, and local event information.

[1276] Output: Collected market trend data, guest behavior data, and local event information.

[1277] What it does: Executes an API call, retrieves data, and saves it to the database.

[1278] Step 2: Collecting emotion data

[1279] The server uses an emotion engine to collect emotion data from feedback input by the user while using the system, as well as facial expressions and voice data during operation.

[1280] Input: Feedback, facial expression data, and audio data.

[1281] Output: Emotion data.

[1282] How it works: Activates the emotion engine and generates emotion data in real time by analyzing feedback, facial expressions, and voice data.

[1283] Step 3: Data Preprocessing

[1284] The server pre-processes all collected data to remove missing values ​​and outliers, for example, by using Excel's data cleaning tools to detect and remove outliers.

[1285] Inputs: Collected market trend data, guest behavior data, local event information, and sentiment data.

[1286] Output: The preprocessed dataset.

[1287] Operation: Imputes missing values, removes outliers, and standardizes data formats.

[1288] Step 4: Demand forecast

[1289] The server uses the preprocessed data and sentiment data to apply machine learning algorithms to predict future demand. Specifically, it uses Python libraries (e.g., Scikit-learn) to build time series forecasting models and multivariate regression models and executes the forecasting models.

[1290] Input: Preprocessed dataset, sentiment data.

[1291] Output: Demand forecast results.

[1292] How it works: Trains machine learning models and performs forecasting to calculate future demand.

[1293] Step 5: Price optimization

[1294] The server uses web scraping technology and API integration to gather current information on competitors' pricing. Specifically, it uses tools such as BeautifulSoup and Selenium to obtain pricing information.

[1295] Inputs: Competitor pricing information, demand forecast results, sentiment data.

[1296] Output: Optimized room rates.

[1297] Operation: Obtains price information, calculates optimal prices by combining demand forecasts and competitive analysis, and adjusts prices based on user sentiment.

[1298] Step 6: Applying Pricing Rules

[1299] The server applies the hotel's policies and specific constraints (such as best price guarantees or special discounts) to the calculated best price to determine the final room price.

[1300] Input: Optimized room rates, hotel policies and constraints information.

[1301] Output: Final room price.

[1302] How it works: Rules like lowest price guarantees and special discounts are applied to determine the final price.

[1303] Step 7: Notification of results

[1304] The server sends the optimized pricing information to the hotel management system (PMS), which updates the information in real time using API integration.

[1305] Input: Final room rate.

[1306] Output: Fee information notified to PMS.

[1307] Operation: Connects to PMS via API and sends pricing information.

[1308] Step 8: User Interface

[1309] Users access a dashboard to see optimized pricing and why, the latest demand forecast, competitor activity, and sentiment feedback.

[1310] Input: Data on the dashboard.

[1311] Output: The information confirmed by the user.

[1312] What it does: Displays information visually using graphs and charts and allows users to customize settings.

[1313] Specific examples

[1314] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[1315] Example prompts to input to a generative AI model:

[1316] "How can I forecast demand and optimize pricing during festivals?"

[1317] "Please explain how to best adjust prices if demand drops during the off-season."

[1318] "Describe the effectiveness of using user sentiment data to set hotel prices."

[1319] (Application example 2)

[1320] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1321] Conventional pricing systems rely on data based on market trends and competitive analysis, which means they have a problem of not being able to reflect user emotions and behavior. In particular, it is difficult to quickly respond to fluctuations in consumer behavior and the market, which can result in lost sales opportunities and excess inventory. Furthermore, it is difficult to set optimal prices solely through competitor price analysis, so pricing that responds to consumer needs and emotions is required.

[1322] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting consumer behavior data, means for collecting related event information, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand, means for analyzing the prices of competing companies, means for calculating optimal product prices based on the prediction results and competitive analysis, means for applying pricing rules based on the calculated prices to determine final prices, means for notifying final price information, means for providing a user interface and displaying price settings and the reasons for them, means for acquiring user emotion data using an emotion engine and reflecting this in price settings, means for performing demand forecasting using a machine learning algorithm, and means for adjusting prices based on specific events and feedback. This enables optimal price setting in response to consumer emotions and market trends.

[1323] "Market trend data" refers to information related to overall market trends, such as supply and demand in the market, price fluctuations, and consumer purchasing behavior.

[1324] "Consumer behavior data" refers to information about consumer behavior, such as the actions and trends consumers take when purchasing products, their purchasing history, and their search history.

[1325] "Related event information" is information about specific events, campaigns, sales, festivals, etc. that affect the market and consumption.

[1326] "Preprocessing" is a process that improves the quality of collected data by removing missing values ​​and outliers and standardizing the data format.

[1327] "Demand forecasting" is the process of predicting future demand based on market trend data, consumer behavior data, etc.

[1328] "Competitor price analysis" is the process of collecting competitors' product prices and analyzing that data to use as a reference when setting your own product prices.

[1329] "Pricing rules" are rules or restrictions that apply to set prices, such as lowest price guarantees or special discounts.

[1330] "Notification" is the act of notifying users and systems of the final calculated price information in real time.

[1331] The "user interface" is an interface for providing and displaying optimized pricing, the reasons for it, analysis results, emotion engine feedback, etc. to the user.

[1332] The "emotion engine" is a system that acquires and analyzes emotional data from the user's facial expressions, voice, etc.

[1333] A "machine learning algorithm" is a calculation method or model used to forecast demand and optimize prices based on collected data.

[1334] "Feedback" refers to opinions, impressions, and information about usability collected from system users.

[1335] The present invention is a system for optimizing pricing and revenue management on an online shopping site. This system is realized by components including a server, a terminal, and a user.

[1336] System Configuration

[1337] 1. Server:

[1338] It plays a central role in collecting, preprocessing, and analyzing various types of data.

[1339] Collect market trend data, consumer behavior data, relevant event information, and competitor pricing data.

[1340] The emotion engine collects user emotion data.

[1341] This data is preprocessed and demand forecasts are made using machine learning algorithms.

[1342] Calculate the optimal product price based on the forecast results and competitive analysis, and determine the final price in accordance with pricing rules.

[1343] It has the function of notifying the final price information.

[1344] 2. Terminal:

[1345] It provides a dashboard for users to see pricing and why, the latest demand forecasts, and competitor activity.

[1346] It can be accessed from various devices such as mobile devices and PCs.

[1347] 3. User:

[1348] Provides emotion data collected by the emotion engine.

[1349] Review pricing information provided by the system and provide feedback if necessary.

[1350] Processing Details

[1351] Data collection

[1352] The server uses external APIs to collect market trend data, consumer behavior data, and related event information in real time, and also uses web scraping technology to obtain competitor pricing information.

[1353] The emotion engine uses the camera and microphone on the user's smartphone to collect emotional data from facial expressions and voice.

[1354] Data Preprocessing

[1355] The server performs preprocessing of the collected data, removing missing values ​​and outliers and standardizing the data format to improve data quality.

[1356] Demand forecasting

[1357] The server applies machine learning algorithms (e.g., LSTM models or multivariate regression models) based on the preprocessed data to predict future demand.

[1358] Price Optimization

[1359] The server calculates the optimal product price based on the prediction results and the competitive analysis results, taking into account the user's emotional evaluation results obtained by the emotion engine.

[1360] Pricing rules will be applied to determine the final price.

[1361] Notification of results

[1362] The server notifies the user interface of the optimized pricing information in real time.

[1363] Specific examples

[1364] Seasonal sale pricing

[1365] 1. Data Collection:

[1366] The server collects market trend data for Black Friday.

[1367] The emotion engine confirmed that users frequently displayed excited facial expressions while using the app.

[1368] 2. Data Preprocessing:

[1369] The server preprocesses the collected data and removes missing values ​​and outliers.

[1370] 3. Demand forecasting:

[1371] The server uses historical data from Black Friday to predict a surge in demand.

[1372] 4. Price Optimization:

[1373] The server collects competitor pricing information and offers a 20% discount.

[1374] Consider sentiment data and provide special offers to users.

[1375] 5. Notification of Results:

[1376] The server sends the updated price information to the online shopping site's system.

[1377] 6. User Interface:

[1378] Users can see the reason behind the new price (Black Friday sale) and see the sentiment engine feedback.

[1379] Prompt Sentence Examples

[1380] "Predict demand and set prices for Black Friday"

[1381] "Adjust prices for products with many negative reviews"

[1382] In this way, by utilizing an emotion engine and machine learning algorithms, it is possible to create a system that enables optimal pricing in response to user emotions and market trends.

[1383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1384] Step 1: Data collection

[1385] The server uses external APIs to collect market trend data, consumer behavior data, and related event information. The server retrieves data in JSON format from the external APIs. It also uses web scraping technology to collect pricing information from competitors. Furthermore, the emotion engine uses the smartphone's camera and microphone to collect emotion data in real time from the user's facial expressions and voice. The inputs are market trend data, consumer behavior data, related event information, and emotion data, and the output is an integrated set of these data.

[1386] Step 2: Data Preprocessing

[1387] The server preprocesses the data collected in step 1, specifically removing missing values ​​and outliers and standardizing the data format (e.g., normalizing numerical data and encoding categorical data). The input is the data collected in step 1, and the output is a preprocessed, consistent dataset.

[1388] Step 3: Demand forecast

[1389] The server uses the preprocessed data to apply machine learning algorithms (e.g., LSTM models, time series forecasting models) to predict future demand. The server trains the model based on past data and performs demand forecasts based on new data. The input is the preprocessed data, and the output is the future demand forecast.

[1390] Step 4: Price optimization

[1391] The server calculates the optimal product price based on the demand forecast results and competitive analysis results. It also takes into account the user's emotional data from the emotion engine, adjusting the price if the user expresses displeasure, for example. It applies pricing rules to determine the final price. The inputs are the demand forecast results, competitive analysis results, and emotional data, and the output is the optimized product price.

[1392] Step 5: Notification of results

[1393] The server reflects the optimized price information in the online shopping site's pricing system. Specifically, it updates the price information using an API and notifies users of the price change via in-app notifications or push notifications. The input is the optimized price information, and the output is the updated price information and a notification to the user.

[1394] Step 6: User Interface

[1395] Users can check pricing and its reasons, demand forecast results, and competitive analysis data in real time through the provided dashboard. Users can also check feedback from the sentiment engine and send feedback as needed. The input is the notified price information and analysis data, and the output is the display on the dashboard and feedback from users.

[1396] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1397] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1398] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1399] [Fourth embodiment]

[1400] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1401] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1402] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1403] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1404] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1406] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1407] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1408] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1409] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1410] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1411] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1412] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1413] The system of the present invention is an AI-based platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component.

[1414] Program Overview

[1415] The program of the present invention collects information on market trends, guest behavior, and local events in real time, and uses this data to forecast demand and calculate optimal room rates. The results are then notified to users, maximizing hotel occupancy rates and revenue.

[1416] Program processing

[1417] 1. Data Collection

[1418] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[1419] 2. Data analysis

[1420] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[1421] Server: Predicts demand from pre-processed data using machine learning models that are trained based on historical data and market trends.

[1422] 3. Price optimization

[1423] Server: Analyze competitor pricing and gather information to compare with your hotel's prices.

[1424] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis, taking into account the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.).

[1425] 4. Notification of Results

[1426] Server: Sends optimized pricing information to the hotel's PMS (Property Management System), and notifies connected reservation systems and front desk terminals.

[1427] 5. User Interface

[1428] Users can view optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model to weight specific factors.

[1429] Specific examples

[1430] Responses during periods of increased reservations

[1431] 1. Data Collection:

[1432] Server: Collects information about next week's major music festivals from an external API.

[1433] 2. Data Analysis:

[1434] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[1435] 3. Price optimization:

[1436] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[1437] Server: Based on the demand forecast results, increase the room rate by 30%.

[1438] 4. Notification of Results:

[1439] Server: Sends updated pricing information to the PMS and reflects it on the device.

[1440] 5. User Interface:

[1441] Users: View the dashboard to see the reason for the price adjustment (increased demand due to a music festival) and its impact.

[1442] Off-season response

[1443] 1. Data Collection:

[1444] Server: Checks current reservation status data and whether there are any upcoming major events.

[1445] 2. Data Analysis:

[1446] Server: Predicts a drop in demand based on data from similar periods in the past.

[1447] 3. Price optimization:

[1448] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[1449] Server: Based on forecasted demand, we will reduce room rates by 20% and add special offers packages.

[1450] 4. Notification of Results:

[1451] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[1452] 5. User Interface:

[1453] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed.

[1454] In this way, the system of the present invention uses AI to collect and analyze data in real time and set optimal prices, thereby maximizing hotel occupancy rates and profits.

[1455] The processing flow will be explained below.

[1456] Step 1:

[1457] Data collection:

[1458] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[1459] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[1460] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[1461] Step 2:

[1462] Data preprocessing:

[1463] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1464] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1465] Step 3:

[1466] Demand forecast:

[1467] Server: Using the pre-processed data, machine learning algorithms (e.g., time series forecasting models or multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1468] Step 4:

[1469] Competitive analysis:

[1470] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1471] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[1472] Step 5:

[1473] Price Optimization:

[1474] Server: Calculates optimal room rates based on demand forecasts and competitive analysis, using algorithms designed to maximize hotel occupancy and profits.

[1475] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[1476] Step 6:

[1477] Notification of results:

[1478] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1479] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1480] Step 7:

[1481] User Interface:

[1482] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1483] Users: Use the ability to customize the forecast model settings to weight specific factors, which will take effect immediately and affect the next forecast.

[1484] Example 1

[1485] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1486] In the hotel industry, optimizing room rates and maximizing revenue are important challenges. However, current methods often involve manual data collection and analysis, making it difficult to quickly respond to fluctuations in demand or competitor pricing trends. This often results in missed revenue opportunities and makes it difficult to set optimal prices. Furthermore, data preprocessing and machine learning model adjustments require specialized knowledge, making them difficult for average users to use. To solve these issues, a system is needed that can collect and analyze a variety of data in real time and quickly propose prices.

[1487] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1488] In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for preprocessing the collected data, means for analyzing the preprocessed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal room rates based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated rates and determining final prices, means for notifying final price information, means for providing a user interface and displaying pricing settings and reasons for them, means for forecasting demand using a machine learning model and customizing model parameters, and means for collecting data using an external API. This enables accurate data collection and analysis in real time, enabling prompt and optimal room rate setting.

[1489] "Market trend data" is information that shows overall market movements, such as market trends, price fluctuations, and consumer preferences.

[1490] "Guest behavior data" refers to information that indicates the behavioral patterns of guests, such as their reservation status, cancellation history, frequency of stay, and length of stay.

[1491] "Local event information" is event information related to a particular area, such as concerts, festivals, and sporting events held in that area.

[1492] "Means for preprocessing collected data" refers to techniques for removing missing values ​​and outliers from collected data and standardizing the data format.

[1493] "Means for analyzing preprocessed data and forecasting demand" refers to technology for forecasting future demand using preprocessed data, and employs machine learning models, etc.

[1494] "Means to analyze competitors' prices" refers to the technology of collecting and analyzing the pricing of other hotels in the same market.

[1495] "Means for calculating optimal room rates based on forecast results and competitive analysis" refers to a technology for calculating optimal room rates based on the results of demand forecasts and the results of competitor price analysis.

[1496] "Means for determining the final price by applying pricing rules based on the calculated rate" refers to a technology that applies the hotel's policies and restrictions to the calculated rate to determine the final price.

[1497] The "means for notifying final price information" is a technology for transmitting the determined final price to the hotel's management system or reservation system.

[1498] The "means for providing a user interface and displaying pricing and the reasons therefor" refers to a technique for providing an interface for a user to check pricing and the reasons therefor.

[1499] "Means for forecasting demand using a machine learning model and customizing the model parameters" is a technology that uses a machine learning model to forecast demand and allows users to adjust the parameters of the model.

[1500] "Means of collecting data using external APIs" refers to technology that uses APIs to obtain data from external systems and services.

[1501] The system of the present invention is an AI-powered platform for optimizing hotel pricing and revenue management. The system is implemented by a server, a terminal, and a user component. The server uses external APIs to collect market trend data, guest behavior data, and local event information. The server preprocesses the collected data and uses a machine learning model to predict demand. Based on this prediction, the server analyzes competitors' prices and calculates the optimal room rate. The server then sends the optimized pricing information to a property management system (PMS), which then notifies the connected reservation system and front desk terminal. Users can view the optimized pricing and the reasons for it, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the predictive model and assign weights to specific factors.

[1502] Hardware and software used

[1503] Server: The server is responsible for a series of processes such as data collection, preprocessing, analysis, price calculation, and notification. It uses Python and its libraries (pandas, scikit-learn, etc.) and uses HTTP requests to communicate with external APIs.

[1504] Terminals: Terminals used at the front desk or reservation system are designed to display optimized pricing information in real time, often with a browser-based interface.

[1505] User Interface: A browser-based dashboard allows users to see pricing and why, with specific graphical representations and numerical details, and often uses a front-end framework such as React or Vue.js.

[1506] Specific examples

[1507] Responses during periods of increased reservations

[1508] 1. The server collects information about large music festivals scheduled for next week from an external API.

[1509] 2. The server uses a machine learning model to predict a surge in demand based on historical data from the festival period.

[1510] 3. The server compares competitors' prices with the hotel's regular rates and increases the room rate by 30% based on the demand forecast results.

[1511] 4. The server sends the updated fee information to the PMS and reflects it on the terminal.

[1512] 5. The user sees the reason for the price adjustment (increased demand due to a music festival) and its impact on the dashboard.

[1513] Off-season response

[1514] 1. The server checks the current reservation status data and checks that there are no upcoming major events.

[1515] 2. The server predicts a drop in demand based on data from similar periods in the past.

[1516] 3. The server analyzes the pricing of competing hotels and compares it with the hotel's regular price.

[1517] 4. The server reduces the room rate by 20% and adds a special offer package based on demand forecasts.

[1518] 5. The server sends the adjusted price and benefit information to the PMS, which then reflects it on the terminal.

[1519] 6. User can check the reason for the pricing (low demand) through the dashboard and customize settings as needed.

[1520] In this way, the system of the present invention maximizes hotel occupancy rates and revenue by utilizing external APIs to collect data in real time and forecasting demand using machine learning models. Furthermore, users can view the system's pricing process and its background through a dashboard, enhancing reliability and transparency.

[1521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1522] System program processing flow

[1523] Step 1: Data collection

[1524] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information.

[1525] Specific operation: The server calls "MarketDataAPI" or "EventInfoAPI" and periodically obtains the data returned in JSON format.

[1526] Inputs: Market trend data, guest behavior data, local event information

[1527] Output: Raw collected data (JSON format)

[1528] Step 2: Data Preprocessing

[1529] Server: Preprocesses the collected data, removes missing values ​​and outliers, and standardizes the data format.

[1530] Specific operation: The server uses Python's pandas library, removes missing values ​​using DataFrame.dropna(), and unifies the date and time format using pd.to_datetime().

[1531] Input: Raw data collected

[1532] Output: Preprocessed data

[1533] Step 3: Demand forecast

[1534] Server: Uses pre-processed data to predict demand using machine learning models.

[1535] Specific operation: The server uses scikit-learn's LinearRegression model, learns from past data using the fit method, and performs demand forecasting using the predict method.

[1536] Input: Preprocessed data

[1537] Output: Demand forecast results

[1538] Step 4: Price optimization

[1539] Server: Collects competitor pricing information and compares it with the hotel's own rates. Then, based on the demand forecast and competitor pricing analysis results, calculates the optimal room rate taking into account specific constraints.

[1540] Specific operation: The server calls the "CompetitorPriceAPI" to obtain competitor price data in JSON format. It then uses Python to integrate the demand data and competitor prices to calculate the optimal price.

[1541] Input: Demand forecast results, competitor price data

[1542] Output: Calculated optimal room price

[1543] Step 5: Notification of results

[1544] Server: Sends optimized pricing information to the PMS and notifies connected reservation systems and front desk terminals.

[1545] What happens: The server sends the new price information to the PMS API endpoint using an HTTP POST request.

[1546] Input: Calculated best room price

[1547] Output: New price information reflected in PMS and terminal

[1548] Step 6: User Interface

[1549] Users: View optimized pricing and why, the latest demand forecast, and competitor trends through a dashboard. Users can also customize the parameters of the forecasting model.

[1550] What it does: A user logs in and accesses the dashboard via a browser, where they can view data in charts and tables and adjust forecast parameters using sliders.

[1551] Input: Parameter settings entered by the user

[1552] Output: Display of updated forecast results and pricing information

[1553] In this way, the system performs specific data processing and calculations at each step, ultimately providing the user with the optimal pricing and the reasons for it.

[1554] (Application example 1)

[1555] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1556] The challenge is to maximize the operational efficiency of taxi services using autonomous vehicles and optimize the utilization rate and revenue of taxis in operation. To achieve this, it is necessary to accurately predict demand for market trends, traffic conditions, and specific events, which fluctuate in real time, and set appropriate prices. However, current technology does not yet have a system that can efficiently collect and analyze these factors and automatically optimize prices. This makes it difficult to respond to fluctuations in demand and maximize revenue.

[1557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1558] In this invention, the server includes means for collecting market trend data, means for collecting traffic condition data, means for collecting specific event information, means for collecting operation condition data, means for pre-processing the collected data, means for analyzing the pre-processed data and forecasting demand, means for analyzing competitors' prices, means for calculating optimal fares based on the forecast results and competitive analysis, means for applying pricing rules based on the calculated fares to determine final prices, means for notifying final price information, and means for providing a user interface and displaying pricing settings and reasons for them, thereby optimizing operation management and pricing settings of autonomous taxi services in real time and maximizing profits.

[1559] "Market trend data" is information used to understand market conditions and fluctuations. This includes data on economic indicators, consumer behavior, price fluctuations, etc.

[1560] "Traffic condition data" refers to information related to road congestion and traffic flow, including traffic jams, accidents, and traffic light status.

[1561] "Specific event information" refers to information about events that take place at specific dates, times, and locations. This refers to information about events that affect demand, such as concerts, sporting events, and local festivals.

[1562] "Operation status data" refers to information about the current operating status, location, speed, etc. of an autonomous vehicle. This data is used to understand the real-time status of the vehicle while it is in operation.

[1563] "Preprocessing" is the process of removing missing values ​​and outliers from collected data and preparing the data in a format that is easy to analyze.

[1564] "Demand forecasting" refers to predicting future demand based on past data and current conditions. This is done using machine learning and statistical models.

[1565] "Competitive analysis" refers to researching and comparatively analyzing the pricing and service content of competitors, which can be used to help develop your own pricing strategy.

[1566] "Pricing rules" refer to pre-determined pricing rules and standards that are used to calculate optimal prices based on demand and competitive conditions.

[1567] "User interface" refers to the display and controls that allow a user to interact with a system, including graphical interfaces and dashboards.

[1568] "Notification" refers to the process by which the system communicates calculation results and updated information to relevant parties. This includes push notifications on smartphones and emails.

[1569] The system of the present invention is a technology for optimizing the operation management and pricing of autonomous taxi services. The system is implemented by components including a server, a terminal, and a user.

[1570] server

[1571] The server collects market trend data, traffic data, specific event information, and operational status data in real time using external APIs. This data is updated periodically and pre-processed on the server. This pre-processing includes removing missing values ​​and outliers and standardizing the data format.

[1572] The server then uses a machine learning model to predict demand based on the pre-processed data. This model is trained based on past data and market trends. Based on the results of the demand forecast, the server analyzes competitors' prices and calculates the optimal taxi fare. This takes into account not only the demand forecast results and the results of the competitor analysis, but also specific pricing rules and constraints.

[1573] Terminal

[1574] The terminal refers to the smartphone used by taxi drivers and passengers. The optimal fare calculated by the server is sent to the terminal via push notification or app notification. This allows drivers and passengers to check the latest price in real time. The terminal's user interface also displays detailed information such as the reasons for the price setting, predicted demand, and competitor trends.

[1575] User

[1576] Users include system administrators, taxi drivers, and service users. Through the dashboard, users can check pricing and the reasons for it, the latest demand forecast, and competitor trends. They can also customize the parameters of the forecasting model and assign weights to specific factors. Furthermore, users can send feedback to the server to further customize the forecasting model.

[1577] Specific examples

[1578] Consider the following scenario: If information collected from an external API indicates that a large rock festival will be held in a city next week, the server uses this information to predict a surge in demand. Using data from past similar events, the server increases pricing by 25% over normal rates. This information is sent to drivers' and passengers' smartphones, and the dashboard displays the reason for the price adjustment as "Increased demand due to rock festival."

[1579] Prompt Sentence Examples

[1580] "Please forecast demand during the rock festival based on market trends, traffic conditions, and event information for the next two weeks, and set the optimal taxi fares. Please also take into account past data."

[1581] As described above, the system of the present invention can maximize the utilization rate and revenue of autonomous taxi services by collecting and analyzing data in real time and providing optimal pricing.

[1582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1583] Step 1: Data collection

[1584] The server uses external APIs to collect market trend data, traffic situation data, specific event information, and operation status data. This data is obtained in real time and updated periodically. Specifically, it makes API calls, standardizes the data format, and saves it in a database. The input is raw data obtained from the API, and the output is standardized data required for preprocessing.

[1585] Step 2: Data Preprocessing

[1586] The server performs preprocessing on the collected data. This preprocessing includes removing missing values ​​and outliers and standardizing the data format. Specifically, it uses a data cleaning algorithm to filter out inappropriate data. The input is the collected raw data, and the output is clean data that can be analyzed.

[1587] Step 3: Demand forecast

[1588] The server uses a machine learning model on the preprocessed data to forecast demand. The model used is a generative AI model trained based on past data and market trends. Specifically, clean data is input into the model to generate forecast results that predict future demand. The input is clean data, and the output is predicted demand data.

[1589] Step 4: Competitive analysis

[1590] The server collects competitors' pricing information and performs price analysis based on the collected information. Specifically, it obtains competitors' pricing data from an external API and compares it with the company's own prediction results. The input is competitors' pricing data, and the output is competitor comparison data.

[1591] Step 5: Price optimization

[1592] The server calculates the optimal fare based on the demand forecast and competitive analysis results. This calculation takes into account not only the demand forecast and competitive analysis results, but also specific pricing rules and constraints. Specifically, it uses a fare calculation algorithm to calculate the optimal price. The inputs are the demand forecast and competitive comparison data, and the output is the optimized fare data.

[1593] Step 6: Price Notification

[1594] The server sends the optimized fare data to the terminal and notifies the driver and passenger through push notifications or app notifications. Specifically, a notification server is used to deliver price information to the driver's and passenger's smartphones in real time. The input is the optimized fare data, and the output is the notification sent to the driver and passenger.

[1595] Step 7: Provide a user interface

[1596] The terminal displays detailed information such as the reasons for pricing, forecasted demand, and competitor trends on a user interface. Specifically, it provides the user with the necessary information via a dashboard, allowing them to change settings and send feedback. The input is notification data from the server, and the output is the user's operation interface.

[1597] Step 8: Feedback and Model Customization

[1598] Users send feedback to the system, and the server customizes the predictive model based on that feedback. Specifically, the server analyzes the user's feedback and adjusts the parameters of the machine learning model. The input is the user's feedback, and the output is a customized predictive model.

[1599] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1600] The system of the present invention combines an AI-based platform for optimizing hotel pricing and revenue management with an emotion engine that recognizes user emotions. The system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[1601] Program Overview

[1602] The program of the present invention collects market trends, guest behavior, local event information, and user sentiment in real time, and uses this data to forecast demand and calculate optimal room rates. It also evaluates user sentiment and incorporates the results into forecasting models and pricing. The results are then communicated to users, maximizing hotel occupancy and revenue.

[1603] Program processing

[1604] 1. Data Collection

[1605] Server: Uses external APIs to collect market trend data, guest behavior data, and local event information, which is updated periodically.

[1606] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[1607] 2. Data Preprocessing

[1608] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1609] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1610] 3. Demand forecasting

[1611] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1612] 4. Price optimization

[1613] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1614] Server: Calculates the optimal room rate based on the demand forecast and competitive analysis results. The server also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses displeasure, the server adjusts the rate by reducing it.

[1615] Server: Apply the hotel's policies and specific constraints (e.g., best price guarantees, special discounts, etc.) to the calculated best price, which determines the final room price.

[1616] 5. Notification of Results

[1617] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1618] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1619] 6. User Interface

[1620] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1621] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[1622] Specific examples

[1623] Responses during periods of increased reservations

[1624] 1. Data Collection:

[1625] Server: Collects information about next week's major music festivals from an external API.

[1626] Server: Uses an emotion engine to collect user emotion data, for example, to ensure that users are sending a lot of positive feedback.

[1627] 2. Data Preprocessing:

[1628] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[1629] 3. Demand forecasting:

[1630] Server: Using historical demand data from the festival, machine learning models predict spikes in demand.

[1631] 4. Price Optimization:

[1632] Server: Analyze competitors' prices and compare them with your hotel's regular rates.

[1633] Server: Based on the demand forecast results, increase the room rate by 30%. Also, consider the positive sentiment of users and add special offers.

[1634] 5. Notification of Results:

[1635] Server: Sends updated pricing information to the PMS and reflects it on the device.

[1636] 6. User Interface:

[1637] Users: See the reason for the price adjustment (increased demand due to music festivals) and its impact in the dashboard, along with feedback from the sentiment engine.

[1638] Off-season response

[1639] 1. Data Collection:

[1640] Server: Checks current reservation status data and whether there are any upcoming major events.

[1641] Server: Use the emotion engine to collect user emotion data. Check for a high number of negative feedbacks.

[1642] 2. Data Preprocessing:

[1643] Server: Preprocesses the collected data and removes missing values ​​and outliers.

[1644] 3. Demand forecasting:

[1645] Server: Predicts a drop in demand based on data from similar periods in the past.

[1646] 4. Price Optimization:

[1647] Server: Analyze the pricing of competing hotels and compare it to your regular prices.

[1648] Server: Based on demand forecasts, reduce room rates by 20%, add rewards packages, and consider campaigns to alleviate negative sentiment.

[1649] 5. Notification of Results:

[1650] Server: Sends the adjusted price and benefit information to the PMS and reflects it on the device.

[1651] 6. User Interface:

[1652] Users: View pricing reasons (low demand) through the dashboard and customize settings as needed. Feedback from the sentiment engine is also displayed.

[1653] In this way, the system of the present invention uses an emotion engine to evaluate user emotions, collects and analyzes data in real time using AI, and sets optimal prices, thereby maximizing hotel occupancy rates and profits.

[1654] The processing flow will be explained below.

[1655] Step 1:

[1656] Data collection:

[1657] Server: Calls external APIs to gather market trend data, such as average room rates, booking rates, and seasonal trends for the hotel's market. This data is updated every few hours.

[1658] Server: Connects to the PMS (Property Management System) to retrieve guest behavior data, such as past booking data, cancellation rates, demographic information, etc. This data is updated at the end of the day.

[1659] Server: Retrieves information about upcoming local events from APIs of local governments and event organizers. This data is also updated regularly.

[1660] Server: Using the emotion engine, emotional data is collected from feedback entered by the user while using the system, facial expressions while operating the system, and voice data.

[1661] Step 2:

[1662] Data preprocessing:

[1663] Server: All collected data is pre-processed to remove missing values ​​and outliers, improving data quality and preventing incorrect predictions.

[1664] Server: Standardize all data formats to ensure consistency in subsequent analysis steps.

[1665] Step 3:

[1666] Demand forecast:

[1667] Server: Using the pre-processed data and sentiment data, machine learning algorithms (e.g., time series forecasting models and multivariate regression models) are applied to predict future demand. The models are trained from historical data, taking into account market trends, guest behavior, and local event data.

[1668] Step 4:

[1669] Competitive analysis:

[1670] Server: Use web scraping technology and API integration to gather current information to obtain competitor pricing.

[1671] Server: Analyzes the collected competitor pricing data and compares it with your hotel's prices.

[1672] Step 5:

[1673] Price Optimization:

[1674] Server: Calculates optimal room rates based on demand forecasts and competitive analysis results, using algorithms aimed at maximizing hotel occupancy and profits.

[1675] Server: The server applies the hotel's policies and specific constraints (e.g., lowest price guarantees, special discounts, etc.) to the calculated optimal price. It also takes into account the user's emotional evaluation results from the emotion engine. For example, if the user expresses dissatisfaction, the server may adjust the price by lowering it.

[1676] Step 6:

[1677] Notification of results:

[1678] Server: Sends optimized pricing information to the hotel's PMS using API integration, with real-time updates.

[1679] Terminals: Front desk and administrative terminals receive new pricing as notifications and, in some cases, alerts to highlight important changes.

[1680] Step 7:

[1681] User Interface:

[1682] Users: Access the dashboard to see optimized pricing and why, the latest demand forecasts, and competitor trends. The dashboard updates in real time, allowing users to act quickly.

[1683] Users: Enjoy the ability to customize the settings of the predictive model, weighting specific factors, and see feedback from the sentiment engine.

[1684] Example 2

[1685] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1686] Traditional hotel pricing and revenue management systems are primarily based on market trends, competitive analysis, and guest behavior, but do not take into account user sentiment and immediate feedback, which can result in inadequate pricing, customer satisfaction, and maximum revenue.

[1687] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting guest behavior data, means for collecting local event information, means for collecting user emotion data, means for preprocessing the collected data, means for analyzing the preprocessed data and emotion data and forecasting demand, means for collecting and analyzing competitors' price information, means for calculating optimal room rates based on the forecast results, competitive analysis, and emotion data, means for applying pricing rules based on the calculated rates to determine final prices, means for notifying the hotel management system of the final price information, and means for providing a dashboard and displaying pricing settings, reasons for the settings, and emotion feedback. This enables optimal pricing, demand forecasting, and competitive analysis that take user emotions into account, thereby improving customer satisfaction and maximizing profits.

[1688] "Market trend data" refers to information that indicates changes and trends in market supply and demand, and primarily includes economic data and industry trends.

[1689] "Guest Behavior Data" means information including a guest's past booking history, behavioral patterns during their stay, as well as customer preferences and feedback.

[1690] "Local Event Information" is data about events and occasions taking place in a particular area, including festivals, concerts, sporting events, etc.

[1691] "User emotion data" refers to information collected from users' emotions and feedback while using the system, including emotional expressions expressed through facial expressions, voice, and text input.

[1692] "Preprocessing" refers to a series of processes for preparing collected data in an analyzable format, including filling in missing values, standardizing formats, and removing outliers.

[1693] A "machine learning algorithm" is a mathematical or statistical model that learns patterns and rules from data and predicts future data. Examples include time series prediction models and multivariate regression models.

[1694] "Competitive analysis" is a method for evaluating, analyzing, and comparing competitors' pricing and market strategies, and uses web scraping technology and API integration.

[1695] "Pricing rules" are internal regulations and external constraints regarding hotel pricing, including rules such as lowest price guarantees and special discounts.

[1696] "Notification" is a means of sending optimized price information to hotel management systems and terminals in real time to inform relevant parties.

[1697] A "dashboard" is part of the system's user interface and is a screen for visually displaying information such as pricing, demand forecasts, competitive situations, and emotional feedback.

[1698] This invention is a system for optimizing hotel pricing and revenue management, specifically combining an AI-based platform with an emotion engine that recognizes user emotions. This system is implemented by the following components: a server, a terminal, a user, and an emotion engine.

[1699] Hardware and software used

[1700] Server: Data collection, preprocessing, predictive model building, price optimization, and notifications. Uses libraries and frameworks such as Python, Scikit-learn, BeautifulSoup, and Selenium.

[1701] Emotion engine: Recognizes emotions by analyzing user feedback, facial expressions, and voice data. Specific examples include models using machine learning and deep learning.

[1702] Terminals: Computers used at front desks or administrative locations receive notifications of new pricing information and display dashboards.

[1703] User Interface: Provides a dashboard displaying pricing, demand forecasts, competitive information, and sentiment feedback.

[1704] Data collection

[1705] The server uses external APIs to collect market trend data, guest behavior data, and local event information. For example, it obtains information from tourist association APIs, social media data, and travel booking sites. This data is updated hourly.

[1706] The server uses an emotion engine to collect emotional data in real time from feedback, facial expressions, and voice data while the user is using the system. For example, data can be obtained through feedback input at the front desk or conversations with a chatbot.

[1707] Data Preprocessing

[1708] The server performs pre-processing on the collected data to remove missing values ​​and outliers. For example, it uses a data cleaning tool to detect, delete, or impute abnormal values.

[1709] The server unifies all data formats, converting different data formats (JSON, CSV, XML, etc.) into a uniform format and integrating them into a single database.

[1710] Demand forecasting

[1711] The server uses the preprocessed data and sentiment data to apply machine learning algorithms (e.g., Scikit-learn time series forecasting models and multivariate regression models) to forecast demand.

[1712] For example, historical data can be used to predict increased demand during specific events.

[1713] Price Optimization

[1714] The server uses web scraping techniques and API integration to obtain pricing information from other hotels to obtain competitor pricing, using tools such as BeautifulSoup and Selenium.

[1715] The system calculates optimal room rates based on demand forecasts and competitive analysis. For example, it raises rates during periods of high demand and lowers rates during periods of low demand. It also adjusts rates by taking into account user feedback.

[1716] The hotel's policies and specific constraints (such as lowest price guarantees and special discounts) are applied to the calculated best price to arrive at the final room price.

[1717] Notification of results

[1718] The server sends the optimized pricing information to the hotel management system, which updates the information in real time using API integration.

[1719] Terminals (front desk or administrator terminals) will receive notifications of the new pricing and will display pop-ups or alerts.

[1720] User Interface

[1721] Users access a dashboard to view optimized pricing and why, demand forecasts, competitor activity, and sentiment feedback. The dashboard is updated in real time, allowing for quick action.

[1722] Users can customize the settings of the predictive model, weighting certain factors, and see feedback from the sentiment engine.

[1723] Specific examples

[1724] Responses during periods of increased reservations

[1725] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[1726] Off-season response

[1727] For example, the server collects current reservation status and event information and uses the sentiment engine to determine that a large amount of negative feedback has been collected. The server then performs data preprocessing and predicts a decline in demand based on data from similar periods in the past. The server then analyzes the prices of competing hotels, reduces room rates by 20%, and adds special offers packages. It also considers campaigns to alleviate negative sentiment. The optimized prices and special offers are sent to the PMS and reflected on the device. Users can use the dashboard to determine the reasons for pricing and customize settings, and also check sentiment feedback.

[1728] Example prompts to input to the generative AI model

[1729] "How can I forecast demand and optimize pricing during festivals?"

[1730] "Please explain how to best adjust prices if demand drops during the off-season."

[1731] "Describe the effectiveness of using user sentiment data to set hotel prices."

[1732] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1733] Step 1: Data collection

[1734] The server uses external APIs to collect market trend data, guest behavior data, and local event information, specifically from tourism association APIs, social media data, and travel booking sites.

[1735] Inputs: Market trend data from external APIs, guest behavior data, and local event information.

[1736] Output: Collected market trend data, guest behavior data, and local event information.

[1737] What it does: Executes an API call, retrieves data, and saves it to the database.

[1738] Step 2: Collecting emotion data

[1739] The server uses an emotion engine to collect emotion data from feedback input by the user while using the system, as well as facial expressions and voice data during operation.

[1740] Input: Feedback, facial expression data, and audio data.

[1741] Output: Emotion data.

[1742] How it works: Activates the emotion engine and generates emotion data in real time by analyzing feedback, facial expressions, and voice data.

[1743] Step 3: Data Preprocessing

[1744] The server pre-processes all collected data to remove missing values ​​and outliers, for example, by using Excel's data cleaning tools to detect and remove outliers.

[1745] Inputs: Collected market trend data, guest behavior data, local event information, and sentiment data.

[1746] Output: The preprocessed dataset.

[1747] Operation: Imputes missing values, removes outliers, and standardizes data formats.

[1748] Step 4: Demand forecast

[1749] The server uses the preprocessed data and sentiment data to apply machine learning algorithms to predict future demand. Specifically, it uses Python libraries (e.g., Scikit-learn) to build time series forecasting models and multivariate regression models and executes the forecasting models.

[1750] Input: Preprocessed dataset, sentiment data.

[1751] Output: Demand forecast results.

[1752] How it works: Trains machine learning models and performs forecasting to calculate future demand.

[1753] Step 5: Price optimization

[1754] The server uses web scraping technology and API integration to gather current information on competitors' pricing. Specifically, it uses tools such as BeautifulSoup and Selenium to obtain pricing information.

[1755] Inputs: Competitor pricing information, demand forecast results, sentiment data.

[1756] Output: Optimized room rates.

[1757] Operation: Obtains price information, calculates optimal prices by combining demand forecasts and competitive analysis, and adjusts prices based on user sentiment.

[1758] Step 6: Applying Pricing Rules

[1759] The server applies the hotel's policies and specific constraints (such as best price guarantees or special discounts) to the calculated best price to determine the final room price.

[1760] Input: Optimized room rates, hotel policies and constraints information.

[1761] Output: Final room price.

[1762] How it works: Rules like lowest price guarantees and special discounts are applied to determine the final price.

[1763] Step 7: Notification of results

[1764] The server sends the optimized pricing information to the hotel management system (PMS), which updates the information in real time using API integration.

[1765] Input: Final room rate.

[1766] Output: Fee information notified to PMS.

[1767] Operation: Connects to PMS via API and sends pricing information.

[1768] Step 8: User Interface

[1769] Users access a dashboard to see optimized pricing and why, the latest demand forecast, competitor activity, and sentiment feedback.

[1770] Input: Data on the dashboard.

[1771] Output: The information confirmed by the user.

[1772] What it does: Displays information visually using graphs and charts and allows users to customize settings.

[1773] Specific examples

[1774] For example, the server collects information about next week's large-scale music festival from an external API and uses an emotion engine to gather positive user feedback. The server preprocesses the collected data, interpolates outliers with the median value, and then predicts a surge in demand using historical data from the festival period. The server then analyzes competitors' prices, increases the hotel's room rates by 30%, and adds special offers. The optimized price information is sent to the PMS, and a pop-up notification is displayed on the device. Users can view the reasons and impact of the price adjustment on the dashboard, and their emotional feedback is also displayed.

[1775] Example prompts to input to a generative AI model:

[1776] "How can I forecast demand and optimize pricing during festivals?"

[1777] "Please explain how to best adjust prices if demand drops during the off-season."

[1778] "Describe the effectiveness of using user sentiment data to set hotel prices."

[1779] (Application example 2)

[1780] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1781] Conventional pricing systems rely on data based on market trends and competitive analysis, which means they have a problem of not being able to reflect user emotions and behavior. In particular, it is difficult to quickly respond to fluctuations in consumer behavior and the market, which can result in lost sales opportunities and excess inventory. Furthermore, it is difficult to set optimal prices solely through competitor price analysis, so pricing that responds to consumer needs and emotions is required.

[1782] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting market trend data, means for collecting consumer behavior data, means for collecting related event information, means for preprocessing the collected data, means for analyzing the preprocessed data and predicting demand, means for analyzing the prices of competing companies, means for calculating optimal product prices based on the prediction results and competitive analysis, means for applying pricing rules based on the calculated prices to determine final prices, means for notifying final price information, means for providing a user interface and displaying price settings and the reasons for them, means for acquiring user emotion data using an emotion engine and reflecting this in price settings, means for performing demand forecasting using a machine learning algorithm, and means for adjusting prices based on specific events and feedback. This enables optimal price setting in response to consumer emotions and market trends.

[1783] "Market trend data" refers to information related to overall market trends, such as supply and demand in the market, price fluctuations, and consumer purchasing behavior.

[1784] "Consumer behavior data" refers to information about consumer behavior, such as the actions and trends consumers take when purchasing products, their purchasing history, and their search history.

[1785] "Related event information" is information about specific events, campaigns, sales, festivals, etc. that affect the market and consumption.

[1786] "Preprocessing" is a process that improves the quality of collected data by removing missing values ​​and outliers and standardizing the data format.

[1787] "Demand forecasting" is the process of predicting future demand based on market trend data, consumer behavior data, etc.

[1788] "Competitor price analysis" is the process of collecting competitors' product prices and analyzing that data to use as a reference when setting your own product prices.

[1789] "Pricing rules" are rules or restrictions that apply to set prices, such as lowest price guarantees or special discounts.

[1790] "Notification" is the act of notifying users and systems of the final calculated price information in real time.

[1791] The "user interface" is an interface for providing and displaying optimized pricing, the reasons for it, analysis results, emotion engine feedback, etc. to the user.

[1792] The "emotion engine" is a system that acquires and analyzes emotional data from the user's facial expressions, voice, etc.

[1793] A "machine learning algorithm" is a calculation method or model used to forecast demand and optimize prices based on collected data.

[1794] "Feedback" refers to opinions, impressions, and information about usability collected from system users.

[1795] The present invention is a system for optimizing pricing and revenue management on an online shopping site. This system is realized by components including a server, a terminal, and a user.

[1796] System Configuration

[1797] 1. Server:

[1798] It plays a central role in collecting, preprocessing, and analyzing various types of data.

[1799] Collect market trend data, consumer behavior data, relevant event information, and competitor pricing data.

[1800] The emotion engine collects user emotion data.

[1801] This data is preprocessed and demand forecasts are made using machine learning algorithms.

[1802] Calculate the optimal product price based on the forecast results and competitive analysis, and determine the final price in accordance with pricing rules.

[1803] It has the function of notifying the final price information.

[1804] 2. Terminal:

[1805] It provides a dashboard for users to see pricing and why, the latest demand forecasts, and competitor activity.

[1806] It can be accessed from various devices such as mobile devices and PCs.

[1807] 3. User:

[1808] Provides emotion data collected by the emotion engine.

[1809] Review pricing information provided by the system and provide feedback if necessary.

[1810] Processing Details

[1811] Data collection

[1812] The server uses external APIs to collect market trend data, consumer behavior data, and related event information in real time, and also uses web scraping technology to obtain competitor pricing information.

[1813] The emotion engine uses the camera and microphone on the user's smartphone to collect emotional data from facial expressions and voice.

[1814] Data Preprocessing

[1815] The server performs preprocessing of the collected data, removing missing values ​​and outliers and standardizing the data format to improve data quality.

[1816] Demand forecasting

[1817] The server applies machine learning algorithms (e.g., LSTM models or multivariate regression models) based on the preprocessed data to predict future demand.

[1818] Price Optimization

[1819] The server calculates the optimal product price based on the prediction results and the competitive analysis results, taking into account the user's emotional evaluation results obtained by the emotion engine.

[1820] Pricing rules will be applied to determine the final price.

[1821] Notification of results

[1822] The server notifies the user interface of the optimized pricing information in real time.

[1823] Specific examples

[1824] Seasonal sale pricing

[1825] 1. Data Collection:

[1826] The server collects market trend data for Black Friday.

[1827] The emotion engine confirmed that users frequently displayed excited facial expressions while using the app.

[1828] 2. Data Preprocessing:

[1829] The server preprocesses the collected data and removes missing values ​​and outliers.

[1830] 3. Demand forecasting:

[1831] The server uses historical data from Black Friday to predict a surge in demand.

[1832] 4. Price Optimization:

[1833] The server collects competitor pricing information and offers a 20% discount.

[1834] Consider sentiment data and provide special offers to users.

[1835] 5. Notification of Results:

[1836] The server sends the updated price information to the online shopping site's system.

[1837] 6. User Interface:

[1838] Users can see the reason behind the new price (Black Friday sale) and see the sentiment engine feedback.

[1839] Prompt Sentence Examples

[1840] "Predict demand and set prices for Black Friday"

[1841] "Adjust prices for products with many negative reviews"

[1842] In this way, by utilizing an emotion engine and machine learning algorithms, it is possible to create a system that enables optimal pricing in response to user emotions and market trends.

[1843] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1844] Step 1: Data collection

[1845] The server uses external APIs to collect market trend data, consumer behavior data, and related event information. The server retrieves data in JSON format from the external APIs. It also uses web scraping technology to collect pricing information from competitors. Furthermore, the emotion engine uses the smartphone's camera and microphone to collect emotion data in real time from the user's facial expressions and voice. The inputs are market trend data, consumer behavior data, related event information, and emotion data, and the output is an integrated set of these data.

[1846] Step 2: Data Preprocessing

[1847] The server preprocesses the data collected in step 1, specifically removing missing values ​​and outliers and standardizing the data format (e.g., normalizing numerical data and encoding categorical data). The input is the data collected in step 1, and the output is a preprocessed, consistent dataset.

[1848] Step 3: Demand forecast

[1849] The server uses the preprocessed data to apply machine learning algorithms (e.g., LSTM models, time series forecasting models) to predict future demand. The server trains the model based on past data and performs demand forecasts based on new data. The input is the preprocessed data, and the output is the future demand forecast.

[1850] Step 4: Price optimization

[1851] The server calculates the optimal product price based on the demand forecast results and competitive analysis results. It also takes into account the user's emotional data from the emotion engine, adjusting the price if the user expresses displeasure, for example. It applies pricing rules to determine the final price. The inputs are the demand forecast results, competitive analysis results, and emotional data, and the output is the optimized product price.

[1852] Step 5: Notification of results

[1853] The server reflects the optimized price information in the online shopping site's pricing system. Specifically, it updates the price information using an API and notifies users of the price change via in-app notifications or push notifications. The input is the optimized price information, and the output is the updated price information and a notification to the user.

[1854] Step 6: User Interface

[1855] Users can check pricing and its reasons, demand forecast results, and competitive analysis data in real time through the provided dashboard. Users can also check feedback from the sentiment engine and send feedback as needed. The input is the notified price information and analysis data, and the output is the display on the dashboard and feedback from users.

[1856] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1857] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1858] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1859] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1860] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1861] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1862] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1863] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1864] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1865] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1866] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1867] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1868] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1869] 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.

[1870] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1871] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1872] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1873] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1874] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1875] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1876] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1877] The following is further disclosed regarding the above embodiment.

[1878] (Claim 1)

[1879] a means of collecting market trend data;

[1880] A means of collecting guest behavior data;

[1881] A means of gathering information about local events,

[1882] a means for pre-processing the collected data;

[1883] a means for analyzing the pre-processed data and forecasting demand;

[1884] A means of analyzing competitor prices;

[1885] A means to calculate optimal room rates based on forecast results and competitive analysis;

[1886] A means for applying pricing rules based on the calculated fees to determine the final price; and

[1887] a means of communicating final pricing information;

[1888] A system that provides a user interface and includes a means for displaying pricing and the reasons for it.

[1889] (Claim 2)

[1890] 10. The system of claim 1, wherein at least large-scale event information is collected.

[1891] (Claim 3)

[1892] 10. The system of claim 1, further comprising at least means for receiving feedback and customizing the predictive model.

[1893] "Example 1"

[1894] (Claim 1)

[1895] a means of collecting market trend data;

[1896] A means of collecting guest behavior data;

[1897] A means of gathering information about local events,

[1898] a means for pre-processing the collected data;

[1899] a means for analyzing the pre-processed data and forecasting demand;

[1900] A means of analyzing competitor prices;

[1901] A means to calculate optimal room rates based on forecast results and competitive analysis;

[1902] A means for applying pricing rules based on the calculated fees to determine the final price; and

[1903] a means of communicating final pricing information;

[1904] means for providing a user interface and displaying pricing and reasons for pricing;

[1905] A means to use machine learning models to forecast demand and customize the parameters of the models;

[1906] A system that includes a means of collecting data using external APIs.

[1907] (Claim 2)

[1908] 10. The system of claim 1, wherein at least large-scale event information is collected.

[1909] (Claim 3)

[1910] 10. The system of claim 1, further comprising at least means for receiving feedback and customizing the predictive model.

[1911] "Application Example 1"

[1912] (Claim 1)

[1913] a means of collecting market trend data;

[1914] a means for collecting traffic condition data;

[1915] a means for collecting specific event information;

[1916] a means for collecting operational status data;

[1917] a means for pre-processing the collected data;

[1918] a means for analyzing the pre-processed data and forecasting demand;

[1919] A means of analyzing competitor prices;

[1920] A means of calculating optimal fares based on forecast results and competitive analysis;

[1921] A means for applying pricing rules based on the calculated fees to determine the final price; and

[1922] a means of communicating final pricing information;

[1923] A system that provides a user interface and includes a means for displaying pricing and the reasons for it.

[1924] (Claim 2)

[1925] 10. The system of claim 1, wherein at least large-scale event information is collected.

[1926] (Claim 3)

[1927] 10. The system of claim 1, further comprising at least means for receiving feedback and customizing the predictive model.

[1928] "Example 2: Combining Emotion Engines"

[1929] (Claim 1)

[1930] a means of collecting market trend data;

[1931] A means of collecting guest behavior data;

[1932] A means of gathering information about local events,

[1933] means for collecting user emotion data;

[1934] a means for pre-processing the collected data;

[1935] a means for analyzing the pre-processed data and sentiment data to forecast demand;

[1936] A means of collecting and analyzing competitor pricing information;

[1937] A means to calculate optimal room rates based on forecast results, competitive analysis, and sentiment data;

[1938] A means for applying pricing rules based on the calculated fees to determine the final price; and

[1939] a means for communicating the final pricing information to the hotel management system;

[1940] A system that provides a dashboard and includes a means to display pricing and why, as well as sentiment feedback.

[1941] (Claim 2)

[1942] 10. The system of claim 1, wherein at least large-scale event information is collected.

[1943] (Claim 3)

[1944] 10. The system of claim 1, further comprising means for receiving at least user feedback and customizing the forecasting model and pricing.

[1945] "Application example 2 when combining emotion engines"

[1946] (Claim 1)

[1947] a means of collecting market trend data;

[1948] means of collecting consumer behavior data;

[1949] a means for collecting relevant event information;

[1950] a means for pre-processing the collected data;

[1951] a means for analyzing the pre-processed data and forecasting demand;

[1952] A means of analyzing competitor prices;

[1953] a means for calculating optimal product prices based on the forecast results and competitive analysis;

[1954] A means for determining the final price by applying pricing rules based on the calculated price;

[1955] a means of communicating final pricing informa...

Claims

1. a means of collecting market trend data; A means of collecting guest behavior data; A means of gathering information about local events, a means for pre-processing the collected data; a means for analyzing the pre-processed data and forecasting demand; A means of analyzing competitor prices; A means to calculate optimal room rates based on forecast results and competitive analysis; A means for applying pricing rules based on the calculated fees to determine the final price; and a means of communicating final pricing information; A system that provides a user interface and includes a means for displaying pricing and the reasons for it.

2. The system of claim 1 , wherein at least large-scale event information is collected.

3. The system of claim 1 , further comprising at least means for receiving feedback and customizing the predictive model.

Images